Deep Insight of HR Management On Work From Home SC

See discussions, stats, and author profiles for this publication at: https://www.researchgate.
net/publication/370738402
Deep insight of HR management on work from home scenario during Covid

pandemic situation using intelligent: analysis on IT sectors in Tamil Nadu
Article in International Journal of Systems Assurance Engineering and Management · May 2023
DOI: 10.1007/s13198-023-01880-w
CITATION READS
1 41
2 authors, including:
Martin Selvakumar
GREAT LAKES INSTITUTE OF MANAGEMENT CHENNAI
3 PUBLICATIONS 18 CITATIONS
SEE PROFILE
All content following this page was uploaded by Martin Selvakumar on 20 June 2023.
The user has requested enhancement of the downloaded file.

Int J Syst Assur Eng Manag
https://doi.org/10.1007/s13198-023-01880-w
ORIGINAL ARTICLE
Deep insight of HR management on work from home scenario

during Covid pandemic situation using intelligent: analysis on IT
sectors in Tamil Nadu
Martin Selvakumar Mohanan1,3 · Vijayakumar Rajarathinam2
Received: 9 November 2021 / Revised: 19 January 2022 / Accepted: 20 February 2023

© The Author(s) under exclusive licence to The Society for Reliability Engineering, Quality and Operations Management (SREQOM), India and
The Division of Operation and Maintenance, Lulea University of Technology, Sweden 2023
Abstract The unexpected Coronavirus Disease 2019 These responses are given to the prediction phase that is
(COVID-19) pandemic has heavily hit on global busi- performed using the proposed Deep Neural Network (DNN).
ness, causing major disruptions in Human Resource Man- DNN is used to obtain the result more quickly. Features are
agement (HRM) across a wide range of industries. Since automatically deduced and optimally tuned for desired out-
work and family are the major essential aspects of every- comes. The same neural network based approach can be
one’s lives, work-life balance is a major factor impacting applied to many different applications and data types. Here,
happiness. Changes brought on by the novel coronavirus the weight of DNN is optimized by the Oppositional Ran-
COVID-19 have had far-reaching consequences for busi- dom Searched Tunicate Swarm Algorithm (ORS-TSA) for
nesses all around the world, and had a significant impact enhancing the performance through RMSE minimization.
on human resource management. HRM had to cope with ORS-TSA has strong global optimization ability, robust-
the layoffs and staff reductions brought on by the pandemic ness and fast convergence speed. It gives the optimal results
lockdown. Work-life balance is a constant challenge for most when comparing the other traditional algorithms. Finally, the
of the employees. The work-from-home scenario shifted outcomes are compared with different methods using error
the balance between job and personal life. Most of the prior measures to describe the superiority of the proposed method.
studies have looked at the nature of work-life balance, but
only a few have covered the effects of a pandemic on the Keywords Human resouce management · Work from
workplace. The goal of this research is to conduct a thor- home scenario · Covid pandemic situation · IT sectors in
ough examination of HRM in IT firms in Tamil Nadu under Tamil Nadu · Proposed deep neural network · Oppositional
a work-from-home scenario in the event of a COVID pan- random searched tunicate swarm algorithm
demic. Here, the analysis is conducted on the basis of nine
categories such as “employee wellbeing, flexible workplace,
remote work, job loss, human capital, human resource devel- 1 Introduction
opment, leadership, performance, and communication”. A
questionnaire is prepared to address the challenges facing COVID-19 revealed several flaws and challenges that have
in the above mentioned drives. Next, the responses are col- been present in business for a lengthy duration, includ-
lected from different IT HR professionals in Tamil Nadu. ing how to perform everyday tasks from the standpoint of
physical to virtual contacts. Companies may now deter-
mine which positions require face-to-face interaction and
* Martin Selvakumar Mohanan to what degree under the current operating model (Madero
martinselvakumar.m@greatlakes.edu.in Gomez et al. 2020). This is an essential procedure because
1
OB & HR, Great Lakes Institute of Management, Chennai, the workplace will undoubtedly grow from fundamental on-
India site to remote, face-to-face, or a mixture of these on the
2
Management, Texila American University, Lusaka, Zambia basis of how it is structured (Yoosefi Lebni et al. 2021a).
3
Department of Business Administration, Turiba University, For example, in hybrid or remote scenarios, like partially
Riga, Latvia on location and partially remote, there arise advantages in
13
Vol.:(0123456789)
the manner the workplace is intended for both the employees processing and ANN algorithms are used for this purpose.
and the company, as it can permit them to work from their Mainly two ANN approaches are used. This method is fur-
office, home or even a devoted remote office near to their ther applied for different cancer detection (Nautiyal et al.
homes, with lesser geographical conditions than entering 2019).
the major headquarters office (Yoosefi Lebni et al. 2021b). Every company works to meet its objectives through its
As a result, people will live where they choose, which may personnel. Employers and workers must be able to have the
be at a reduced cost of living or closer to loved ones, making ability to adapt to varying business demands in this chal-
the workplace a more appealing location to work. Attribut- lenging market. Employees face several challenges as a
ing jobs to various workplace types can aid in determining result of culture, technology, and varying work environments
who can work physically and who can work overseas (Risley (Adam et al. 2021). To accomplish corporate goals, keep
2020). This may be beneficial to both employers and work- traditional workers, and recruit new workers, it’s critical to
ers, as it allows people to feel more at ease in their occupa- put the entire employees’ abilities and expertise to use. Due
tions and workspaces, as well as to be more inspired, leading to the fact that employees are now working from home, firms
to increased return for employers (Maqsood et al. 2021c) are requiring greater levels of effectiveness from them. As
(NeJhaddadgar et al. 2020). employees must manage their job and family commitments,
Human resource managers are seeking creative, innova- most times one among them will take priority over the other,
tive and efficient solutions to fix employee conflicts, sus- resulting in an unbalance between home work and life in the
tain their health (Radic et al. 2020), and assistance them current working environment (Albitar et al. 2020). Work-life
by constructing a dependable management scheme (Shuja balance is represented in the organization’s effectiveness and
et al. 2020). They are in responsible for hiring people, han- performance. Scholars have agreed that in the face of mas-
dling their effectiveness, benefits, and salaries as well as sive health catastrophes, companies must be more alert and
constructing and revamping employee categorizations. Con- robust. The effect of the COVID-19 outbreak has elevated
sidering the extraordinary and unpredictable conditions and this problem to new heights, not just in China’s economy
shifting economic landscape, the historical issue of COVID- but also globally (Arora and Suri 2020). COVID-19 has
19 necessitates profound thought and adaptability in order to been spreading for more than a year, and its impact on HR
adequately handle human resources (Cooke et al. 2020). San challenges will persist for a long time. The major problem
Matthew Libraries’ whole personnel was able to contact con- that organisations face today is not a singular incident, but
sumers via phone in even less than two months as a result of a new reality that provides a variety of study opportunities
this crisis, and top teams were formed to find solutions and for organisational researchers and practitioners. In the cur-
give services to the public in an entirely different and adapt- rent situation, where often stated difficulties have been com-
able setting. They are also attempted to adapt to specific pounded by the emergence of COVID-19 and accompanied
events inside the business by developing insightful inquiries by an economic crisis, modern HR challenges can be rather
and improving staff competencies (Su et al. 2021). Different diversified. Performance modification and staff well-being
environmental, political, and economic or health crises, such are examples of such issues (Bajrami and Demirovi et al.
as COVID-19, should be utilized to examine and enhance 2020); Employees cannot function as successfully as they
the capacities of individuals and organizations (Fonseca could prior COVID-19, thus organisations are struggling to
and Azevedo 2020). Successful businesses all across the provide the same payment to them; trouble inspiring trust
world, like Amazon, Facebook, and Google, have discovered in employees (Bierema 2020); and heightened external and
that fast change provides incredible chances and benefits. internal disputes amid an unforeseen vast-scale public crisis
COVID-19 motivates the researchers to undergo the deep (Cai et al. 2020). What a broad spectrum of growing HR
learning process to detect the COVID- 19 patient rapidly. challenges, as well as the significant effects of the epidemic,
The existing method has classified the X-rays images into would certainly necessitate more attention and debate.
COVID- 19 and normal by using multi-model classification After reviewing the literature works with many heuristic
process (Verma et al. 2022). This multi-model classification algorithms, it is observed that many limitations still need to
incorporates Support Vector Machine (SVM) in the last layer be solved with an HRM on work from home scenario.
of VGG16 Convolution network. For synchronization among Q1. What are the aspects extracted from reviews?
VGG16 and SVM, they have added one more layer of con- Q2. What are the practical implications available for
volution, pool, and dense between VGG16 and SVM. This HRM on work from home scenario?
study motivates us to find early stages tumors to increase Q3. Which meta-heuristic algorithm can enhanced for
the survival rate of the patient. This CAD system is efficient improve the performance for the HRM on work from home
because it takes minimum time to detect whether the patient scenario?
has cancer or not. This paper presents a system for finding Q4. Why there is a need for optimizing the weight of
the suspected reign for lung cancer using CT images. Image DNN?
13
Q5. How to evaluate a HRM on work from home scenario has revolutionised the way organisations and workers work
using different performance metrics under evaluation? and will remain to do so, necessitating ongoing innova-
The paper contribution is. tion of how they function and creating unprecedented
actions, resulting in significant variations in the workplace.
• To conduct a thorough examination of HRD in IT firms As a result, the workplace concept would never be what
in Tamil Nadu under a work-from-home scenario in the was envisaged prior to COVID-19, where work technol-
event of a COVID pandemic by gathering the responses ogy, reinvention and safety were major elements in the
of questionnaire from the HR in different IT companies transformation.
of Tamil Nadu. In 2021, Reza et al. (2021) have recognised unforeseen
• To develop a proposed DNN for the prediction process of problems, tactics, and uncommon decisions connected to
responses, where the weight is optimized with the con- human resource management in the COVID-19 pandemic
sideration of RMSE minimization. other than clinical organizations. To mitigate COVID-19’s
• To propose a novel form of optimization algorithm called effects, the research used a textual assessment technique
ORS-DNN for enhancing the prediction process and to primarily on the basis of businesses’ human resource man-
compare it with different methods for revealing its supe- agement practices. It used electronic databases such as
riority in the HRM on work from home scenario due to PubMed,Web of Science, Scopus, LISTA, and PsycINFO
the COVID pandemic situation. to search for academic research. From November 2021 to
• To validate the efficient performance for the HRM on the initial quarter of 2021, 1281 articles were extracted from
work from home scenario by comparing it with the con- the databases discussed. On the basis of the exclusion and
ventional techniques by considering their performance inclusion criteria, this research evaluated chosen publica-
measures. tions, identified 15 relevant articles, and deleted duplicates.
Furthermore, on the basis of the results of the literature,
The paper organization is: Section 1 provides the intro- the study built a conceptual framework for human resource
duction of HRM on work from home scenario. The literature management techniques to combat the COVID-19 pandemic.
works are in Sect. 2. The proposed model of HRM on work In 2020, Thilagaraj (2020) have looked into a variety of
from home scenario is given in Sect. 3. The employee well- issues that affected work-life balance when workers were
being category is explained in Sect. 4. Section 5 describes required to work from home. The report’s goal was to inves-
the flexible workplace category. Section 6 elaborates on the tigate the present state of work-life balance, and it discovered
remote work category. The job loss is discussed in Sect. 7. that work-life obligations had an influence on employees’
Section 8 describes the human capital category. The human personal lives. During the epidemic, the researchers gathered
resource development category is shown in Sect. 9. Sec- data from 60 individuals who worked from home. The data
tion 10 elaborates the leadership category. Section 11 was investigated, and it was discovered that the employees’
explains the performance category. The communication work-life balance was negatively impacted. As a result, the
category is described in Sect. 12. Section 13 reveals the employees, who decide the company’s success, should be
deep learning impact on HRM on work from home scenario provided with the ideal atmosphere in order to improve their
during COVID pandemic situation. The results and discus- job happiness.
sions are provided in Sect. 14. The conclusion is in Sect. 15. In 2020, Gigauri (2020) has delivered a study that was
dependent on qualitative expert conducting interviews.
It highlighted the issues that HRM has faced in Georgia,
2 Literature survey as well as the repercussions of the catastrophe on human
resources, the solutions that organizations have imple-
2.1 Related works mented, and advice for dealing with the situation from an
HRM perspective. According to the conclusions of the
In 2021, Lucas et al. (2021) have looked at the existing state expert interviews, organisations, in collaboration with HR
and future development of the workplace in the light of the managers, should build crisis management strategies and
COVID-19 pandemic. Documents, articles, and question- new rules for hybrid and remote working systems as a reac-
naires from a variety of sources were reviewed to learn tion to present and future problems.
more regarding the individuals’ and organisations’ expe- In 2021, Zhong et al. (2021a) have undertaken a thor-
riences with remote working, as well as the benefits and ough literature study on developing research in the world of
drawbacks of being able to get to work in the epidemic. The business and management to determine what the develop-
data analysis enabled the discovery of trends in the existing ing human resource difficulties were during the COVID-
literature describing what had occurred and, in particular, 19 pandemic and offered relevant methods to address these
its impact on the workplace. COVID-19’s transformation concerns. Based on a review of the literature, nine major
13
human resource concerns were identified across 13 sec- This might help to accelerate further use of teleworking
tors. COVID-19 has a huge influence on traditional human methods even after the disaster, with a variety of conse-
resource management, according to the result of this article, quences and unknown net impact on growth and various
which necessitated researchers’ empirical and theoretical measures. S social partner cooperation and public policies
attention. The proposals suggested relevant human resource were critical in ensuring that novel; welfare-improving and
methods for dealing with developing human resource diffi- efficient working techniques created during the recession
culties, as well as a number of research locations for future were preserved and established once the physical separation
studies in this topic. had ended. To enhance the welfare and productivity benefits
In 2020, Caligiuri et al. (2020) have demonstrated the use of various widespread telework, governments should encour-
of existing International Business (IB) research, with a focus age investments in the managerial and physical capacity of
on International HRM (IHRM), in addressing COVID-19 workers and firms to telework, as well as label potential
pandemic concerns. Multinational corporations’ decision- anxieties about worker well-being and long-term innova-
makers have adopted a variety of measures to mitigate the tion, particularly associated with excessive workspace down-
pandemic’s effects. Many of these efforts, whether at the scaling. How should public policy facilitate efficiency gains
macro or corporate level, have something to do with control- from teleworking in the post-COVID-19 era?
ling distance and redefining limits. As the IB field was estab- In 2020, Kaushik et al. (2020) have focused on the impact
lished as a valid area of academic investigation, managing of COVID-19 virus pandemic on working life of employees.
distance as well as rethinking borders has been a fundamen- This research paper has also emphasized that how employers
tal concern of most of the IB research. Greater cross-border as well as HR managers were required to think out of the box
distance difficulties (e.g., as a consequence of travel prohibi- and bring forth best practices as well as redefining HR roles
tions and limited international mobility) have resulted from during any adversity. It has also given light on few impor-
the pandemic, as well as new intra-firm distancing concerns tant issues such as People-Connect, adoption of a system of
for formerly co-located staff. Distance poses challenges Skilling, re-skilling, Up-skilling and multi-skilling people
with respect to staff selection, support, training, health and about technology, design thinking, storytelling, analytics,
safety, virtual collaboration, and leadership according to Artificial intelligence to prepare our workforce to become
previous IHRM study. Most of this thought might be used more competent and talented by enhancing their skill set.
to overcoming distance problems caused by pandemics. In 2021, Zito et al. (2021) have estimated a Structural
The current, exceptional examples of required physical dis- Equations Model (SEM) for revealing that organizational
tance really shouldn’t appear to suggest equivalent rises in communication was positively associated with self-efficacy
psychological distance, and also provided firms with just and negatively with technostress and psycho-physical disor-
some knowledge into the unexpected advantages of a virtual ders. As mediators, technostress was positively associated
workforce – a form of workforce that, indeed very possibly, with psycho-physical disorders, whereas self-efficacy was
will impact the post-COVID world’s ’new normal.’ Existing negatively associated. As regards mediated effects, results
IHRM research did provide useful information for present, have showed negative associations between organizational
but there were still significant knowledge gaps. In terms of communication and psycho-physical disorders through both
future IHRM research, three aspects were suggested: han- technostress and self-efficacy. This study has contributed
dling uncertainty, promoting global and international work, to literature underlying the role of communication in the
and rethinking organisational performance. current crisis and consequent reorganization of the working
In 2021, Butterick and Charlwood (2021b) have revealed processes.
that the COVID-19 epidemic profounded labour market In 2021, Ayedee et al. (2021) have discussed various
inequities. HRM ideas and practices that supported and problems faced by human resource managers during the
legitimised the commercialization of labour were partly COVID-19 pandemic. The authors have seen a solution of
at fault for these inequities. During the epidemic, workers the same in the application of emotional intelligence. The
whose employment have been commercialised have harmed strategic human resource management approach can help
significantly. While HRM was not solely to blame for the HR managers in applying emotional intelligence. Strategic
misery, it was critical for those of us interested in studying, Human Resource Management (SHRM) was a proactive
teaching, and practicing HRM to consider how our work approach in comparison to traditional human resource man-
has exacerbated a poor situation in order to improve in the agement and it can help in formulating the policies effec-
future. tively. The researchers have conducted online interviews to
In 2020, Kahn et al. (2020) have begun to utilize telework check the opinions of HR managers about the applicability
(working from home) on a big scale due to the continuous of emotional intelligence.
economic and health problems caused by the COVID-19
pandemic and the mandatory physical distancing procedures.
13
2.2 Review Azizi 2021) is not used in any subjects and also enhances the
employee health, welfare, adaptation to change, motivation,
In all companies, the proliferation of COVID-19 causes dis- productivity, and satisfaction in the workplace. Still, further
ruption, uncertainty, complexity, and ambiguity. Any organi- study is needed via questionnaires and interviews. WLB fac-
zation’s most valuable asset is its people, who help it realise tor (Thilagaraj 2020) strengthens the communication of the
its objectives. As a result, the organizational strategy review organizations policies and also returns proper balance for
is an acceptable response for managing human resources spending the time with family. Yet, employees feel stressed
sustainably. Work-life balance is a constant challenge for all regarding the overtime working. Qualitative expert interview
employees. The work-from-home scenario shifted the bal- research method (Gigauri 2020) does important achievement
ance between job and personal life. Many prior studies have through the introduction of training employees and online
looked at the nature of work-life balance, but only a few HR processes and also achieves the outcomes through the
have covered the effects of a pandemic on the workplace. adaptation to the new reality. But, the questionnaire is not
Table 1 shows some of the features and challenges of exist- modeled for the future quantitative survey. Emerging stud-
ing impacts of work from home methods. Grounded theory ies (Zhong et al. 2021a) solve the emerging HR issues for
(Antonio 2021) is flexible for employee care, family concili- the enhancement of HRM research and also generate new
ation, and working and also paves the way for the feasibility problems by the novel HR practices. Still, the developed
of the variation of the organizations. But, it returns less time- theories are not tested completely. Extant IB (Caligiuri et al.
line selection. Narrative review approach (Mohammad Reza 2020) contains several features such as methodologically
Table 1 Features and challenges of existing impacts of work from home methods
Author [citation] Methodology Features Challenges
Lucas et al. (2021) Grounded theory It paves the way for the feasibility of It returns less timeline selection
the variation of the organizations
It is flexible for the employee care,
family conciliation, and working
Reza et al. (2021) Narrative review approach It enhances the employee health, wel- It needs further study via questionnaires
fare, adaptation to change, motiva- and interviews
tion, productivity, and satisfaction in
the workplace
This concept is not used in any
subjects
Thilagaraj (2020) WLB factor Proper balance is returned for spend- Employees feel stressed regarding the
ing the time with family overtime working
It strengthens the communication of
the organizations policies
Gigauri (2020) Qualitative expert inter- The outcomes are achieved through It does not model the questionnaire for
view research method the adaptation to the new reality the future quantitative survey
Important achievement is done
through the introduction of training
employees and online HR processes
Zhong et al. (2021a) Emerging studies New problems generated by the novel It does not permit to test the developed
HR practices are recognized theories completely
The emerging HR issues are solved for
the enhancement of HRM research
Caligiuri et al. (2020) Extant IB It supports and informs the manage- It is impossible to answer the ‘big ques-
ment practice tions’ without the knowledge sharing
It contains several features such as
methodologically pluralist, multi-
level, multi-stakeholder oriented,
and multidisciplinary in nature
Butterick and Charlwood (2021b) HRM It reflects the paths for a better future It does not make the case for regula-
Ethical and moral beings are con- tion and policy for enhancing the job
trolled using a degree of agency quality
Kahn et al. (2020) Telework It offers bilateral tax agreements It leads to hidden overtime
It adapts the regulatory and legal
system
13
pluralist, multilevel, multi-stakeholder oriented, and mul- Three Phases

Nine categories
tidisciplinary in nature and also supports and informs the
management practice. Yet, it is impossible to answer the ‘big Employee Wellbeing Initial Phase
questions’ without the knowledge sharing. HRM (Butterick Flexible workplace

Questionnaire preparation
et al. 2021b) controls the ethical and moral beings with the
help of a degree of agency and also reflects the paths for a Remote work Second Phase
better future. But, the case is not made for regulation and Collection of response from
Job loss
policy for enhancing the job quality. Telework (Kahn and different IT HR professionals
in Tamil Nadu
Wiczer 2020) adapts the regulatory and legal system and Human Capital
also offers bilateral tax agreements. Still, it leads to hid-
den overtime. These challenges are lead to develop a novel Human resource Development
Third Phase
method using the deep learning methods for controlling the Leadership Performs the prediction
issues generated in the work from home by the HRM. analysis using deep
Performance learning
Proposed
Communication DNN
3 Proposed model of HRM on work from home
scenario during COVID pandemic situation ORS-TSA
3.1 Architectural representation
The goal of this study is to determine how COVID-19 affects Fig. 1 Developed Architecture of HRM on work from home scenario
the workplace and to investigate the presence of potential during COVID pandemic situation
drivers that will allow for the analysis, study and monitoring
of what the workplace of the future will be. How workplace
transformation might occur in organisations in pandemic • In the first step, a questionnaire is created to address the
contexts like COVID-19 is of great relevance. At first, it issues that the above-mentioned drivers. The data col-
appears that family reconciliation, remote work and flexible lected for the questionnaire should be based on Tamil
working schedules are deciding the workplace’s longevity Nadu’s IT HR viewpoint.
during the pandemic timespan; nevertheless, certain vari- • The second step entails gathering responses from various
ables like passion at work, engagement and mindfulness IT HR specialists in Tamil Nadu. As a result, the indus-
may also be pertinent in this procedure, together with the trial authorities are being pressured to provide as much
COVID-19 (Soham 2021; Samajpaty 2021) context. The exact information as possible.
purpose of this study is to make a systematic analysis on • In the third step, prediction (Gupta et al. 2019) analysis is
HR in IT industries in Tamil Nadu during the work from done using deep learning. Furthermore, combining deep
home scenario in COVID pandemic situation. The analysis learning with a meta-heuristic method aids in the long-
is conducted based on 9 different categories. term analysis.
• Employee Wellbeing
• Flexible workplace 4 Employee wellbeing of HR management
• Remote work on work from home scenario during Covid
• Job loss pandemic situation
• Human Capital
• Human resource Development This part describes the employee wellbeing of HR manage-
• Leadership ment on work from home scenario in the course of COVID
• Performance pandemic situation. From Fig. 2a, the negative character-
• Communication istics from the employees during the work from home is
depicted as high demands by 9.5% of the HR, needs vast
The architectural description of the introduced model of effort by 23.8% of HR, some consultation on variation by
HRM on work from home scenario during COVID pandemic 33.3% of HR, role conflict by 23.8% of HR, and issues with
situation is shown in Fig. 1. remaining staff members by 9.5% of HR. On considering
This study concentrates on three distinct phases. Fig. 2b, the employees with the positive characteristics in
their job is shown as control over how you do or what you
do it by 14.3% of HR, colleague support by 23.8% of HR,
13
Fig. 2 Employee wellbeing of HR management on work from home scenario during COVID pandemic situation
manager support by 42.9% of HR, and appropriate rewards work from home is shown as open by 14.3% of the HR, con-
by 19% of HR. In Fig. 2c, the employees handling the scientious by 33.3% of HR, extravert by 14.3% of HR, agree-
problems in positive manner during this work from home able by 33.3% of HR, and stable by 25% of HR. On consid-
is described as concentrating on the problem and trying to ering Fig. 2f, the employees description during work from
handle it by 30% of HR, attaining social support by 35% of home in this pandemic situation is given as helping by 20%
HR, and none by 30% of HR. while considering Fig. 2d, the of HR, courteous by 30% of HR, and good sport by 50% of
problem handling with the employees in a passive manner HR. In Fig. 2g, the employees present in the organization are
during work from home in this pandemic situation is shown comfortable during this work from home owing to the pan-
as avoiding them by 42.9% of HR, wishful thinking usage demic situation is depicted as high job satisfaction by 23.8%
by 23.8% of HR, and blame yourself by 33.3% of HR. from of HR, inspired employee who does not want to leave by
Fig. 2e, the employees showing positive personality during 23.8% of HR, and none by 52.4% of HR. While considering
13
Fig. 2h, the personal contract maintenance by the employees 5 Flexible workplace of HR management on work
during this work from home situation is shown as maintain- from home scenario during Covid pandemic
ing promises by 28.6% of HR, treated fairly by 33.3% of HR, situation
and high commitment by 38.1% of HR. From Fig. 2i, the
employees having a high level of wellbeing satisfaction dur- This part shows the flexible workplace of HRM on work
ing this pandemic situation because of the work from home from home scenario during COVID pandemic situation.
is shown as highly satisfied by 33.3% of HR, positive mood From Fig. 3a, maximum of the employees satisfied with
by 38.1% of HR, and happiness by 28.6% of HR. the work from home option than the office during this
pandemic situation is shown as strongly agree by 42.9%
of HR, disagree by 28.6% of HR, neither agree nor disa-
gree by 14.3% of HR, agree by 9.5% of HR and strongly
disagree by 6% of HR. On considering Fig. 3b, employees
requested for a variation in the work arrangements with
Fig. 3 Flexible workplace of HR management on work from home scenario during COVID pandemic situation
13
respect to flexibility like workplace position, change in working options to the employees during this work from
the core days or hours, and count of hours is given as yes home is shown as strongly agree by 23.8% of HR, disagree
by 28.6% of HR, no by 28.6% of HR, and prefers not to by 33.3% of HR, neither agree nor disagree by 23.8% of
answer by 42.9% of HR. In Fig. 3c, the employees being HR, agree by 14.3% of HR, and strongly disagree by 6%
loyal to the organization during this pandemic situation of HR. In Fig. 3g, the employees supporting in covering
because of the work from home is shown as more by 14.3% maximum turnover during this work from home condition
of HR, less by 42.9% of HR, and no change by 42.9% of is given as strongly agree by 14.3% of HR, disagree by
HR. While considering Fig. 3d, the employees looking 23.8% of HR, neither agree nor disagree by 33.3% of HR,
for a job with another organization during this work from agree by 23.8% of HR, and strongly disagree by 6% of HR.
home owing to the inconvenient faced in this organiza-
tion is given as yes by 28.6% of HR, no change by 38.1%
of HR, and not sure by 33.3% of HR. From Fig. 3e, the
employees intended on working for this company during
this work from home is shown as yes by 28.6% of HR, no
change by 38.1% of HR, and not sure by 33.3% of HR.
On considering Fig. 3f, the company offering flexible
Fig. 4 Remote work of HR management on work from home scenario during COVID pandemic situation
13
6 Remote work of HR management on work not to say by 71.4% of HR. In Fig. 5c, the employees ready
from home scenario during Covid pandemic for working in the company in the future amidst the work
situation from home is shown as yes by 33.3% of HR, no by 28.6% of
HR, and prefer not to say by 38.1% of HR. While consider-
This portion explains the remote work of HRM on work ing Fig. 5d, the employees preferring training for avoiding
from home scenario during COVID pandemic situation. the loss of job in the future due to this work from home is
From Fig. 4a, the employees satisfied with the home-based shown as yes by 19% of HR, no by 23.8% of HR, and prefer
workplace during this work from home is shown as yes by not to say by 57.1% of HR. From Fig. 5e, the employees
23.8% of HR, no by 14.3% of HR, rarely by 14.3% of HR, working in a usual manner to avoid the loss of job during this
often by 33.3% of HR, and prefer not to say by 14.3% of work from home is given as others else with pay by 19% of
HR. On considering Fig. 4b, the employees working with HR, others without pay by 6% of HR, family gain by 23.8%
more effectiveness during this work from home is shown as of HR, cooperative member by 42.9% of HR, and other by
getting an opportunity to perform some other work by 19% 9.5% of HR. On considering Fig. 5f, the major obstacle in
of HR, not spending long duration in meetings by 28.6% getting a job for the employees during this work from home
of HR, and getting time to concentrate on their work by is shown as no education by 14.3% of HR, inappropriate
52.4% of HR. In Fig. 4c, the controlling of employees on general education by 28.6% of HR, inappropriate vocational
their working days during this work from home is given as education by 28.6% of HR, in accurate training opportu-
yes by 9.5% of HR, no by 23.8% of HR, rarely by 23.8% of nities by 23.8% of HR, and improper work experience by
HR, often by 14.3% of HR, and prefer not to say by 28.6% of 6% of HR. In Fig. 5g, the employees resent and actively
HR. While considering Fig. 4d, the flexibility for performing viewing for work before getting this current job during this
interviews with the remote people during this work from pandemic situation is given as less than a week by 9.5% of
home is shown as yes by 14.3% of HR, no by 19% of HR, HR, 1–4 weeks by 28.6% of HR, 1–2 months by 33.3% of
rarely by 28.6% f HR, often by 28.6% of HR, and prefer not HR, 3–6 months by 19% of HR, and 6 months–1 year by
to say by 9.5% of HR. From Fig. 4e, the missing of signifi- 9.5% of HR.
cant work tools with the employees during this work from
home is shown as requires physical equipment by 19% of
HR, requires documents and data by 38.9% of HR, and work 8 Human capital of HR management on work
tasks that cannot be done from home by 42.1% of HR. On from home scenario during Covid pandemic
considering Fig. 4f, the elaborate discussion of the meetings situation
with the employees during this work from home is given as
yes by 14.3% of HR, no by 9.5% of HR, rarely by 9.5% of This section explains the human capital of HR management
HR, often by 38.1% of HR, and prefers not to say by 28.6% on work from home scenario during COVID pandemic situ-
of HR. In Fig. 4g, remote work for the employees considered ation. From Fig. 6a, the data presently gathered from the
better than working from office is shown as strongly agree employees for assessing the leadership and management
by 19% of HR, disagree by 19% of HR, neither agree nor capability during this work from home is shown as employee
disagree by 23.8% of HR, agree by 19% of HR, and strongly demographics by 14.3% of HR, management ability by
disagree by 19% of HR. 14.3% of HR, development and training quality by 47.6%
of HR, absence by 19% of HR, and recruitment by 5% of
HR. On considering Fig. 6b, the link among organizational
7 Job loss of HR management on work from home performance and employee metrics during this work from
scenario during Covid pandemic situation home is given as yes by 14.3% of HR, no by 38.1% of HR,
and never by 47.6% of HR. In Fig. 6c, the key employee
This part explains the job loss of HRM on work from home indicator incorporation into the monitoring of entire per-
scenario during COVID pandemic situation. From Fig. 5a, formance of the organization during this work from home
the reasons for not working or looking for work with the is shown as balanced scorecard by 23.8% of HR, manage-
employees during this work from home is shown as preg- ment board reports by 28.6% of HR, and others by 47.6%
nancy, injury, own illness by 19% of HR, personal family of HR. While considering Fig. 6d, single or very small key
responsibilities by 33.3% of HR, training or education leave employee indicator count in this pandemic situation is given
by 33.3% of HR, beginning to work later by 9.5% of HR, and as yes by 19% of HR, no by 28.6% of HR, and often by
no reason specified by 4% of HR. On considering Fig. 5b, 52.4% of HR. From Fig. 6e, the data containing highest sig-
the employees leaving the job due to the work pressure dur- nificance for understanding the employee-performance link
ing this work from home because of the pandemic situation in this pandemic situation due to the work from home is
is given as yes by 9.5% of HR, No by 19% of HR, and prefer given as recruitment by 14.3% of HR, retention by 28.6%
13
Fig. 5 Job Loss of HR management on work from home scenario during COVID pandemic situation
of HR, talent management by 42.9% of HR, and reward by 9 Human resource development of HR
14.3% of HR. On considering Fig. 6f, the employee man- management on work from home scenario
agement metrics being gathered in a routine manner in this during Covid pandemic situation
pandemic situation is shown as leadership ability by 19% of
HR, development and training investment by 19% of HR, This part explains the human resource development of HRM
engagement/staff motivation by 33.3% of HR, retention by on work from home scenario during COVID pandemic situa-
19% of HR, and performance by 9.5% of HR. In Fig. 6g, the tion. From Fig. 7a, the HR having complete aware of the busi-
different metrics for gathering the data from the employees ness strategies and requirements in this pandemic situation is
during this work from home is given as human investment shown as fully agree by 23.8% of HR, agree by 14.3% of HR,
ratio by 19% of HR, total employment costs by 9.5% of HR, neither agree nor disagree by 23.8% of HR, partially disagree
resignations by 33.3% of HR, commitment index by 23.8% by 23.8% of HR, and fully disagree by 14.3% of HR. On con-
of HR, and remuneration by 14.3% of HR. sidering Fig. 7b, the efforts considered for creating awareness
13
Fig. 6 Human Capital of HR management on work from home scenario during COVID pandemic situation
within the employees regarding the customer requirements, institutes by 14.3% of HR, and employee referrals by 14.3%
financial position, cost, quality of service/product of the organ- of HR. While considering Fig. 7d, the employee contract type
ization during this work from home is shown as fully agree preferred by the organization during this work from home is
by 28.6% of HR, agree by 14.3% of HR, neither agree nor given as permanent by 9.5% of HR, contractual by 33.3% of
disagree by 28.6% of HR, partially disagree by 14.3% of HR, HR, temporary by 33.3% of HR, and part time by 23.8% of
and fully disagree by 14.3% of HR. In Fig. 7c, the emphasis HR. From Fig. 7e, the significance to several issues that are
of the organization on each of the below recruitment sources associated with organizational workflows during this work
in this COVID pandemic is shown as printing advertisements from home with the employees is given as efficiency by 19%
by 28.6% of HR, career/Internet sites by 14.3% of HR, con- of HR, creativity and innovation by 19% of HR, flexibility by
sultants/placement agencies by 28.6% of HR, educational 23.8% of HR, wide job classes by 23.8% of HR, and detailed
work planning by 14.3% of HR. On considering Fig. 7f, the
degree of usage with consideration of selecting the employ-
ees in this COVID pandemic is shown as psychological tests
13
Fig. 7 Human Resource Development of HR management on work from home scenario during COVID pandemic situation
by 14.3% of HR, performance tests by 19% of HR, realistic 10 Leadership of HR management on work
job previews by 23.8% of HR, trainability by 28.6% of HR, from home scenario during Covid pandemic
and team-oriented selection by 14.3% of HR. In Fig. 7g, the situation
organization having a broad network of computerized human
resource information system along with the latest software in This part describes the leadership of HRM on work from
this work from home is given as fully agree by 23.8% of HR, home scenario during COVID pandemic situation. From
agree by 19% of HR, neither agree nor disagree by 28.6% of Fig. 8a, the maintenance of leadership perfectly during
HR, partially disagree by 23.8% of HR, and fully disagree by this work from home is given as not true by 19% of HR,
4% of HR. seldom true by 28.6% of HR, occasionally true by 19% of
HR, somewhat true by 23.8% of HR, and very true by 9.5%
of HR. On considering Fig. 8b, allocating and obtaining
resources seems to be a challenging aspect of leadership
job during this pandemic situation is given as not true by
13
Fig. 8 Leadership of HR management on work from home scenario during COVID pandemic situation
9.5% of HR, seldom true by 23.8% of HR, occasionally be considered as a portion of the decision making process
true by 33.3% of HR, somewhat true by 23.8% of HR, in this work from home is given as strongly disagree by
and very true by 9.5% of HR. In Fig. 8c, the successful 23.8% of HR, disagree by 14.3% of HR, neutral by 28.6%
conflict resolution is the leadership opponent respect in of HR, agree by 19% of HR, and strongly agree by 14.3%
this work from home scenario is shown as not true by 6% of HR. On considering Fig. 8f, the leadership needs stay-
of HR, seldom true by 28.6% of HR, occasionally true by ing apart from the employees as they perform their work
38.1% of HR, somewhat true by 14.3% of HR, and very in this pandemic situation is given as fully agree by 14.3%
true by 14.3% of HR. While considering Fig. 8d, flexible of HR, agree by 19% of HR, neither agree nor disagree by
leadership that makes variations in the organization in this 38.1% of HR, partially disagree by 14.3% of HR, and fully
pandemic situation is given as fully agree by 23.8% of disagree by 14.3% of HR. In Fig. 8g, the leaders offering
HR, agree by 14.6% of HR, neither agree nor disagree by employees total freedom for handling problems on their
28.6% of HR, partially disagree by 19% of HR, and fully self in this work from home condition is shown as strongly
disagree by 14.3% of HR. From Fig. 8e, the employees to disagree by 14.3% of HR, disagree by 19% of HR, neutral
13
Fig. 9 Performance of HR management on work from home scenario during COVID pandemic situation
by 28.6% of HR, agree by 23.8% of HR, and strongly agree from the employees during this work from home is given
by 14.3% of HR. as yes by 42.9% of HR, no by 19% of HR, and prefer not to
say by 38.1% of HR. On considering Fig. 9b, the employee
performance greater on the job during this pandemic situa-
11 Performance of HR management on work tion is shown as all of the time by 19% of HR, most of the
from home scenario during Covid pandemic time by 23.8% of HR, some of the time by 33.3% of HR,
situation a little of the time by 14.3% of HR, and none of the time
by 9.5% of HR. In Fig. 9c, the employees not focusing on
This section describes the performance of HRM on work their job during this COVID situation is given as all of
from home scenario during COVID pandemic situation. the time by 14.3% of HR, most of the time by 28.6% of
From Fig. 9a, the special achievement or work success HR, some of the time by 19% of HR, a little of the time by
13
33.3% of HR, and none of the time by 5% of HR. While employees suffering from the listening problems in this
considering Fig. 9d, the health problems lessening the work from home situation is shown as unfamiliar with the
amount or kind of work the employees perform because foreigner’s pronunciation and accents by 19% of HR, not
of the COVID breakthrough is shown as all of the time able to catch the conversations or words by 23.8% of HR,
by 14.3% of HR, most of the time by 19% of HR, some not able to get the technical terms by 19% of HR, not able
of the time by 33.3% of HR, a little of the time by 19% of to remember the complete information by 23.8% of HR,
HR, and none of the time by 14.3% of HR. From Fig. 9e, and others by 14.3% of HR. On considering Fig. 10f, the
the normal job performance rating of the employees over company improving the English communication skills of
these two years because of the work from home due to the the employees during this work from home situation is
COVID pandemic is shown as zero by 19% of HR, two by shown as using English during work by 9.5% of HR, con-
19% of HR, five by 19% of HR, seven by 23.8% of HR, and sidering English courses at a language institute by 42.9%
ten by 19% of HR. On considering Fig. 9f, the comparison of HR, training abroad by 19% of HR, in-house training
of the entire job performance of one employee with the by 23.8% of HR, and others by 5% of HR. In Fig. 10g, the
performance of various employers having a similar form communication affecting the employees in the organiza-
of job in this COVID pandemic is shown as much better tion during this pandemic situation because of the work
by 9.5% of HR, somewhat better by 19% of HR, average from home is given as to some extent by 14.3% of HR, to
by 19% of HR, somewhat worse by 33.3% of HR, and lot vast extent by 38.1% of HR, never by 23.8% of HR, and
worse by 19% of HR. In Fig. 9g, the employees consider- prefers not to say by 23.8% of HR.
ing challenging tasks for improving their performance dur-
ing this work from home situation is given as yes by 19%
of HR, no by 38.1% of HR, and often by 42.9% of HR. 13 Deep learning impact on HRM on work
from home scenario during COVID pandemic
situation
12 Communication of HR management on work 13.1 Deep learning for HRM on work from home
from home scenario during Covid pandemic scenario
situation
Here, nine categories are described for analyzing the
This part explains the communication of HRM on work HRM on work from home scenario during COVID pan-
from home scenario during COVID pandemic situation. demic situation. Every category is composed of more than
From Fig. 10a, communication with the employees goes seven questions. The DNN network is assessed for every
better during this COVID pandemic is shown as never by category, thus a total of 9 DNN networks are assessed.
28.6% of HR, not often by 28.6% of HR, sometimes by Every question contains responses that are designed in
19% of HR, often by 14.3% of HR, and always by 9.5% the format of multiple responses. The responses are gath-
of HR. On considering Fig. 10b, effective communica- ered from the HR IT professionals of Tamil Nadu. The
tion attained easier by considering turns talking with the response changes on the basis of every preference of the
employees during this work from home is given as never HR. From the collected responses, assigning score for
by 14.3% of HR, not often by 33.3% of HR, sometimes by every response takes place. The possibilities associated
23.8% of HR, often by 19% of HR, and always by 9.5% with the score of each response are defined. These pos-
of HR. In Fig. 10c, the employees making perfect com- sibilities are subjected to the proposed DNN for the future
munication during the meetings in this work from home response prediction. The training and the testing process
scenario is shown as yes by 9.5% of HR, no by 14.3% of occur in the proposed DNN. In the training process,
HR, rarely by 14.3% of HR, very often by 52.4% of HR, the possibilities are subjected as input to the proposed
and often by 9.5% of HR. While considering Fig. 10d, the DNN, and the target is considered fixed that is the mean
communication of employees with the organization during (scores). During the testing phase, the same possibilities
this work from home is given as very good by 9.5% of HR, are provided as input to the proposed DNN and the out-
good by 9.5% of HR, fair by 28.6% of HR, poor by 28.6% put obtained is the predicted (score), which is associated
of HR, and very poor by 23.8% of HR. From Fig. 10e, the to the future responses. Here, the weight of the DNN is
13
Fig. 10 Communication of HR management on work from home scenario during COVID pandemic situation
13
constraints, where the range is decided based on the optimal

Weight solutions attained in the training phase. The total node count
optimization
by ORS-TSA
is determined as in Eq. (1) when the hidden layer is taken into
Assign score for
Responses
every answer
Possibilities
consideration.
√
nw = aw + bw + cw (1)
Proposed DNN
Training
The input layer node count is supplied by aw, the output
Input Target
Mean (Score)
layer node count is supplied by bw , the hidden layer node
Possibilities Proposed DNN
count is supplied by nw, and a constant value is supplied by
cw. In the case of hidden layer, non-linear fitness capacity is
Input
Testing
Output
used as an activation function. The sigmoid is utilized as an
Possibilities Proposed DNN Predicted (Score) activation function, as demonstrated in Eq. (2).
1
SW = (2)
1 + e−resw
Fig. 11 Architectural model of the deep learning effect on HRM for
work from home scenario Here, Eq. (3) provides the input data resw, and the mapping
function MWfw is used to activate it.
( )
MWfw = sigm 𝜔iw resw + 𝛽iw (3)
optimized by the suggested ORS-TSA, thus known as pro-
posed DNN. The overall response is predicted by this pro- The bias is denoted by 𝛽 , whereas the weight matrix is
posed DNN, which is described as the predicted response denoted by 𝜔.
that is called as the output. The architectural model of the The DNN provides advantages such as well for vari-
deep learning effect on HRM on work from home during ous applications, sophisticated capabilities, ultimate plat-
COVID pandemic situation is displayed in Fig. 11. This, form adaptability, and so on. However, it is URL-dependent,
in turn provides a clear depiction on distinct HRM for requires a large amount of data, and increases the cost to con-
work from home scenario. sumers, and so on. To address these flaws, the weight of DNN
is optimized, resulting in proposed DNN. This proposed DNN
13.2 Proposed DNN has advantages such as improved security, ease of usage, and
dependability. The weight of DNN has a boundary range of
The DNN is considered as the learning algorithm for analyz- 5–255. As a result, the objective is shown in Eq. (4).
ing the HRM on work from home scenario during COVID
pandemic situation. The three major components of DNN Obj = arg min (RMSE)
{WTDNN } (4)
(Ramesh et al. 2019a) are the "input layer," "output layer," and
"hidden layers." It contains two hidden layers that aid in the The objective is defined by Obj and the weight of pro-
mapping of "output and input data." Due to the rising number posed DNN is specified by WTDNN accordingly. "RMSE is
of training iterations, it is still difficult to satisfy the decision a commonly used measure of the discrepancies between
limit. "Training speed and classification accuracy" is improved values predicted by a model or an estimate and the values
by constructing two hidden layers. Cross entropy is used as observed," according to Eq. (5).
the loss function of DNN as the preparation for training and �
testing. The use of cross-entropy losses greatly improved the � ng � �2
� ∑
� fgeg2 − ageg1
performance of the sigmoid and soft max output models. The �
� eg=1 (5)
optimization of DNN is to improve the performance of the RMSE =
ng
network. It can be used to achieve the best performance by
reducing the errors. The optimization of significant param- The computed value for each fitted point is represented by
eters in each technique is performed through the optimiza- eg, the actual value by ag, the fitted point count by ng, and
tion algorithm for getting the optimal solutions. Here, the trial the forecast value by fg in the above equation, respectively.
and error method is used for assigning the range for particular
13
13.3 Proposed ORS‑TSA ⃗ − rd ⋅ T⃗t (b)||

⃗ = ||F W
PH
| | (10)
The proposed ORS-TSA for the HRM on work from home The random number is represented by rd , the tunicate posi-
scenario during the COVID pandemic situation enhances tion is represented by T⃗t (b), the food source position is repre-
the prediction phase through the optimization of the weight sented by F W ⃗ , the current iteration is represented by b, and
of the DNN with the consideration of RMSE minimization. the distance between the search agent and the food source is
TSA (SatnamKaur et al. 2020) mimics the behaviours of represented by PH ⃗.
"jet propulsion and tunicate swarm." It’s a solution approach As in Eq. (11), the search agent maintains his place in the
for "non-linear constrained issues." Tunicate swarm activ- route of the best search agent.
ity triggers it for living in the deep ocean. To statistically
{
simulate jet propulsion behaviour, a tunicate must meet three ( �) FW ⃗ +E ⃗ ⋅ PH
⃗ if rd ≥ 0.5
criteria: avoid conflicts among search agents, go along the T⃗t b = (11)
FW ⃗ −E ⃗ ⋅ PH
⃗ if rd < 0.5
path of the best search agent’s position, and stay close to the
optimum search agent. Swarm activity will keep a number of ( )
Clearly, the term T⃗t b′ describes the updated tunicate posi-
different search agents informed on the optimum response. tion with reference to the food supply F W ⃗ . The top two opti-
To mathematically model the jet propulsion behaviour, a mal best solutions are kept, and other search agent locations are
tunicate should satisfied three conditions namely avoid the adjusted on the basis of the best search representative position,
conflicts between search agents, movement towards the posi- to statistically mimic tunicate’s swarm behaviour. The tunicate
tion of best search agent, and remains close to the best search swarm behaviour is characterized by the formula below, which
agent. The efficiency of this algorithm is further compared is similar to Eq. (12).
with several well-regarded met heuristic approaches based ( )
on the generated optimal solutions. The simulation results ( ) T⃗t (b) + Tt b⃗ + 1
demonstrate that TSA generates better optimal solutions in Tt b⃗ + 1 = (12)
comparison to other competitive algorithms and is capable 2 + g1
of solving real case studies having unknown search spaces.
The TSA has various advantages, like improved convergence,
Conflicts within the search agents are avoided by comput-
global optimum solutions, reduced vulnerability, increased
ing fresh search agent placement with the help of a vector
⃗ , as detailed below. scalability and sensitivity, and the capability to apply it to real-
E
world case scenarios. Unfortunately, it is incapable of solving
⃗ "binary or multi-objective optimization problems." As a result,
⃗=K
E (6) worst position is also considered through the random search to
⃗
Q improve performance, resulting in the algorithm known as ORS-
TSA. This ORS-TSA reduces computing time and simplifies the
⃗ = g2 + g3 − J⃗
K (7) solution of "binary and multi-objective optimization problems."
In the traditional TSA, the random number g2 lies in the
range of [0,1]. But, in the proposed ORS-TSA, the term g2 is
J⃗ = 2 ⋅ g1 (8)
computed with the help of oppositional random search-based
The social pressures inside the search agents are repre- concept as below in Eq. (13).
sented by Q⃗ , random numbers by g1, g2, and g3, water flow
Objworst − Objbest
advection is represented by K⃗ , and gravitational force is rep- g2 = ⃗
∗Q (13)
Objmean
resented by J in the aforementioned equations. The vector J⃗ is
⃗
computed using Eq. (9). Here, the worst fitness is given by Objworst , best fit-
ness is given by Objbest , and the mean fitness is given
⃗ = ⌊Tmin + g1 ⋅ Tmax − Tmin ⌋
Q (9) by Objmean respectively. The pseudo code of ORS-TSA
The starting speed is equal to Tmin and the subordinate is shown in Algorithm 1 and its flowchart is given in
speed is equal to Tmax in this situation. As in Eq. (10), the Fig. 12.
search agents are then relocated in the direction of the best
neighbour.
13
Algorithm 1: Proposed ORS-TSA

Begin
Population initialization
Parameter initialization
Fitness computation
For b 1 to bmax
Update g 2 using the oppositional random search equation as in Eq. (13)
If rd 0.5 then
Converge the search agents in the location of the best search agent route through the first
portion of Eq. (11)
else
Converge the search agents in the location of the best search agent route through the
second portion of Eq. (11)
End if
End for
Fitness update
Return best search agent
Stop
Start 14 Results and discussions
Population and 14.1 Experimental setup

parameter initialization
The proposed model of HRM on work from home sce-
Fitness calculation nario during COVID pandemic situation was implemented
in MATLAB 2020a and the outcomes were analyzed. The
for b 1 to bmax population size and the iteration count were 10 and 25. Here,
the proposed ORS-TSA-DNN was compared with various
Update g2 by ORS heuristic-based algorithms like PSO-DNN (Humam et al.
equation
2019b), GWO-DNN (Bansal and Singh 2021), WOA-DNN
(Dinakara et al. 2017), and TSA-DNN (SatnamKaur et al.
No if Yes 2020) as well as classifier algorithms like NN (Huang et al.
rd<=0.5 2001), KNN (Anushya et al. 2019), SVM (Wang et al.
2009), and DNN (Ramesh et al. 2019a) in terms of several
Converge search agents in Converge search agents in
error measures to describe the superiority of the proposed
the best search agent location the best search agent location
through second portion through first portion method. The hidden neuron count for the proposed approach
can be listed below, for category 1 is [70,255], category 2 is
[100,212], category 3 is [40,167], category 4 is [133,216],
Fitness update category 5 is [70, 30], category 6 is [141,254], category 7
is [158,160], category 8 is [227, 99], category 9 is [139,
Stop 80]. The hidden neuron count for the neural network is 10.
Finally, the hidden neuron count for DNN is (Adam et al.
Fig. 12 Flowchart of proposed ORS-TSA 2021; Adam et al. 2021). The whole dataset has been divided
13
Fig. 13 RMSE analysis of

different heuristic-based
algorithms for the HRM on
work from home scenario
with respect to, a Employee
Wellbeing, b Flexible work-
place, c Remote Work, d Job
loss, e Human capital, f Human
resource development, g Lead-
ership, h Performance, and i
Communication
13

different classifier algorithms
for the HRM on work from
home scenario with respect to, a
Employee wellbeing, b Flexible
workplace, c Remote work, d
Job loss, e Human capital, f
Human resource development, g
Leadership, h Performance, and
i Communication”
13
Table 2 Overall prediction analysis of different heuristic-based algorithms for the HRM on work from home scenario
Employee wellbeing
Error measures PSO-DNN (Humam GWO-DNN (Bansal and WOA-DNN (Dinakara TSA-DNN (Satnam- ORS-TSA-DNN
et al. 2019b) Singh 2021) et al.2017) Kaur et al. 2020)
“MEP” 57.796 55.499 56.281 57.046 54.653

“SMAPE” 0.86555 0.82042 0.83568 0.8508 0.80422
“MASE” 2.5207 2.3637 2.4149 2.4667 2.308
“MAE” 0.31413 0.30167 0.3059 0.31007 0.29709
“RMSE” 0.33924 0.32789 0.33173 0.33559 0.32375
“L1 Norm” 5146.7 4942.6 5011.9 5080.1 4867.5
“L2 Norm” 43.423 41.969 42.462 42.956 41.44
“L Infinity Norm” 0.74434 0.74434 0.74434 0.74434 0.74434
Flexible workplace
“MEP” 57.718 55.382 56.172 56.971 54.539
“SMAPE” 0.86376 0.81827 0.83349 0.84901 0.80214
“MASE” 2.5531 2.3854 2.4437 2.5002 2.33
“MAE” 0.31423 0.30151 0.30583 0.31017 0.29692
“RMSE” 0.3377 0.32625 0.33013 0.33401 0.3221
“L1 Norm” 5148.3 4940 5010.7 5081.8 4864.7
“L2 Norm” 43.225 41.761 42.257 42.754 41.229
“L Infinity Norm” 0.73148 0.73148 0.73148 0.73148 0.70435
Remote work
“MEP” 57.756 55.43 56.213 56.991 54.594
“SMAPE” 0.86504 0.81967 0.83483 0.8501 0.80357
“MASE” 2.5254 2.3631 2.4168 2.4681 2.3088
“MAE” 0.31448 0.30183 0.30609 0.31034 0.29725
“RMSE” 0.33841 0.32709 0.3309 0.33474 0.32293
“L1 Norm” 5152.5 4945.2 5015 5084.6 4870.1
“L2 Norm” 43.317 41.868 42.355 42.846 41.335
“L Infinity Norm” 0.75447 0.75447 0.75447 0.75447 0.75447
Job loss
“MEP” 57.668 55.382 56.162 56.922 54.53
“SMAPE” 0.86399 0.81887 0.83409 0.8491 0.80267
“MASE” 2.494 2.3537 2.3998 2.4482 2.2923
“MAE” 0.31387 0.30141 0.30568 0.30979 0.29678
“RMSE” 0.33789 0.32644 0.33036 0.33413 0.32232
“L1 Norm” 5142.4 4938.3 5008.3 5075.7 4862.5
“L2 Norm” 43.25 41.784 42.286 42.769 41.257
“L Infinity Norm” 0.71797 0.71797 0.71797 0.71797 0.71797
Human capital
“MEP” 57.689 55.37 56.16 56.932 54.539
“SMAPE” 0.86423 0.81889 0.83416 0.84934 0.80281
“MASE” 2.5 2.3423 2.3993 2.4484 2.288
“MAE” 0.31388 0.30126 0.30556 0.30977 0.29672
“RMSE” 0.33774 0.32631 0.33019 0.33404 0.32215
“L1 Norm” 5142.7 4935.8 5006.3 5075.3 4861.4
“L2 Norm” 43.231 41.767 42.264 42.757 41.236
“L Infinity Norm” 0.76362 0.76362 0.76362 0.76362 0.76362
Human resource development
“MEP” 57.692 55.391 56.178 56.953 54.54
“SMAPE” 0.86402 0.81899 0.83429 0.84943 0.8027
13
Table 2 (continued)
Employee wellbeing
Error measures PSO-DNN (Humam GWO-DNN (Bansal and WOA-DNN (Dinakara TSA-DNN (Satnam- ORS-TSA-DNN
et al. 2019b) Singh 2021) et al.2017) Kaur et al. 2020)
“MASE” 2.5072 2.3497 2.4026 2.455 2.295

“MAE” 0.3139 0.30134 0.30563 0.30986 0.29671
“RMSE” 0.33758 0.32624 0.33015 0.33396 0.32206
“L1 Norm” 5142.9 4937.2 5007.5 5076.8 4861.2
“L2 Norm” 43.211 41.759 42.26 42.747 41.224
“L Infinity Norm” 0.71302 0.71302 0.71302 0.71302 0.7122
Leadership
“MEP” 57.757 55.467 56.24 57.008 54.636
“SMAPE” 0.86464 0.81978 0.83484 0.84995 0.80379
“MASE” 2.5444 2.3795 2.4315 2.4857 2.3222
“MAE” 0.31424 0.30177 0.30599 0.31017 0.29719
“RMSE” 0.33751 0.32623 0.33009 0.33391 0.32208
“L1 Norm” 5148.5 4944.2 5013.3 5081.8 4869.2
“L2 Norm” 43.201 41.757 42.251 42.74 41.226
“L Infinity Norm” 0.70931 0.70931 0.70931 0.70931 0.70931
Performance
“MEP” 57.762 55.417 56.208 57.008 54.559
“SMAPE” 0.86511 0.81944 0.83486 0.8503 0.80306
“MASE” 2.5612 2.3913 2.4447 2.5023 2.3308
“MAE” 0.31473 0.30198 0.30631 0.31063 0.2973
“RMSE” 0.3385 0.32709 0.33104 0.33482 0.32289
“L1 Norm” 5156.5 4947.7 5018.5 5089.4 4871
“L2 Norm” 43.328 41.867 42.373 42.857 41.33
“L Infinity Norm” 0.76304 0.76304 0.76304 0.76304 0.76304
Communication
“MEP” 57.704 55.363 56.16 56.939 54.528
“SMAPE” 0.86458 0.81906 0.83436 0.84962 0.80296
“MASE” 2.5243 2.3661 2.4193 2.4702 2.311
“MAE” 0.31426 0.30157 0.30589 0.31014 0.29702
“RMSE” 0.33823 0.32692 0.33074 0.33459 0.3228
“L1 Norm” 5148.8 4940.8 5011.8 5081.4 4866.4
“L2 Norm” 43.294 41.846 42.335 42.827 41.319
“L Infinity Norm” 0.71351 0.71351 0.71351 0.71351 0.71351
into two parts, where 70% of data have been used for train- 14.3 RMSE analysis in heuristic basis
ing and 30% of data have been used for testing. Thus, all
the data have been trained and tested efficiently to show the The RMSE analysis of different categories of the proposed
performance of the proposed model. HRM on work from home during COVID pandemic situ-
ation is given in Fig. 13. From Fig. 13d, for job loss, the
14.2 Error metrics RMSE of ORS-TSA-DNN at 65% learning percentage is
10.34%, 7.14%, 3.70%, and 13.33% higher than TSA-DNN,
The different error metrics are described below (Chicco et al. WOA-DNN, GWO-DNN, and PSO-DNN respectively.
2021d). On considering Fig. 13e, for human capital, the RMSE of
13
Table 3 Overall prediction Employee wellbeing

analysis of different classifier-
based algorithms for the HRM Error measures NN (Huang KNN ( Anushya SVM ( Wang DNN ( Ramesh ORS-TSA-DNN
on work from home scenario et al. 2001) et al. 2019) et al. 2009) et al. 2019a)
“MEP” 58.627 59.408 60.233 61.097 54.653

“SMAPE” 0.88214 0.89806 0.91482 0.93229 0.80422
“MASE” 2.5811 2.6336 2.6953 2.7768 2.308
“MAE” 0.31863 0.32286 0.32734 0.33208 0.29709
“RMSE” 0.3433 0.34719 0.35123 0.35552 0.32375
“L1 Norm” 5220.4 5289.8 5363.1 5440.9 4867.5
“L2 Norm” 43.943 44.44 44.958 45.507 41.44
“L Infinity Norm” 0.74434 0.74434 0.74434 0.74434 0.74434
Flexible workplace
“MEP” 58.573 59.368 60.201 61.047 54.539
“SMAPE” 0.88053 0.89658 0.91335 0.93061 0.80214
“MASE” 2.6243 2.6816 2.7467 2.8165 2.33
“MAE” 0.31887 0.32322 0.32773 0.33236 0.29692
“RMSE” 0.3418 0.34579 0.34983 0.35401 0.3221
“L1 Norm” 5224.4 5295.7 5369.6 5445.3 4864.7
“L2 Norm” 43.75 44.261 44.778 45.314 41.229
“L Infinity Norm” 0.73148 0.73148 0.7505 0.7505 0.70435
Remote work
“MEP” 58.597 59.383 60.21 61.059 54.594
“SMAPE” 0.88166 0.89762 0.91449 0.93172 0.80357
“MASE” 2.5917 2.6406 2.6965 2.77 2.3088
“MAE” 0.31906 0.32333 0.32782 0.33246 0.29725
“RMSE” 0.34249 0.34639 0.35046 0.35464 0.32293
“L1 Norm” 5227.5 5297.5 5370.9 5447.1 4870.1
“L2 Norm” 43.839 44.338 44.858 45.393 41.335
“L Infinity Norm” 0.75447 0.75447 0.75447 0.75447 0.75447
Job loss
“MEP” 58.491 59.283 60.125 60.966 54.53
“SMAPE” 0.88043 0.89636 0.91323 0.93038 0.80267
“MASE” 2.5502 2.6118 2.6797 2.7524 2.2923
“MAE” 0.31837 0.3227 0.32727 0.33186 0.29678
“RMSE” 0.34201 0.34592 0.34999 0.35412 0.32232
“L1 Norm” 5216.2 5287.2 5361.9 5437.2 4862.5
“L2 Norm” 43.777 44.278 44.798 45.327 41.257
“L Infinity Norm” 0.71797 0.71797 0.71797 0.73203 0.71797
Human capital
“MEP” 58.522 59.335 60.205 61.09 54.539
“SMAPE” 0.88087 0.89701 0.91429 0.93188 0.80281
“MASE” 2.5535 2.6205 2.6961 2.7824 2.288
“MAE” 0.31843 0.32288 0.32759 0.33241 0.29672
“RMSE” 0.34188 0.34583 0.34995 0.35412 0.32215
“L1 Norm” 5217.1 5290.1 5367.2 5446.2 4861.4
“L2 Norm” 43.76 44.266 44.794 45.328 41.236
“L Infinity Norm” 0.76362 0.76362 0.76362 0.76362 0.76362
Human resource development
“MEP” 58.52 59.325 60.149 60.972 54.54
“SMAPE” 0.88051 0.89656 0.91321 0.9301 0.8027
“MASE” 2.5626 2.6235 2.6947 2.7595 2.295
“MAE” 0.3184 0.32277 0.32726 0.33176 0.29671
13
Table 3 (continued) Employee wellbeing

Error measures NN (Huang KNN ( Anushya SVM ( Wang DNN ( Ramesh ORS-TSA-DNN
et al. 2001) et al. 2019) et al. 2009) et al. 2019a)
“RMSE” 0.34165 0.34555 0.34956 0.35363 0.32206

“L1 Norm” 5216.7 5288.3 5361.8 5435.5 4861.2
“L2 Norm” 43.732 44.23 44.743 45.265 41.224
“L Infinity Norm” 0.71302 0.7254 0.7254 0.74048 0.7122
Leadership
“MEP” 58.566 59.362 60.209 61.059 54.636
“SMAPE” 0.88094 0.89684 0.91378 0.93111 0.80379
“MASE” 2.6007 2.657 2.7273 2.7997 2.3222
“MAE” 0.31861 0.3229 0.32754 0.33218 0.29719
“RMSE” 0.34154 0.34535 0.34948 0.35369 0.32208
“L1 Norm” 5220.2 5290.4 5366.4 5442.4 4869.2
“L2 Norm” 43.717 44.205 44.734 45.273 41.226
“L Infinity Norm” 0.70931 0.70931 0.71218 0.73405 0.70931
Performance
“MEP” 58.598 59.395 60.217 61.048 54.559
“SMAPE” 0.88172 0.89771 0.91442 0.93145 0.80306
“MASE” 2.6185 2.6828 2.7524 2.8172 2.3308
“MAE” 0.31926 0.32362 0.32809 0.33261 0.2973
“RMSE” 0.34257 0.34653 0.35057 0.3547 0.32289
“L1 Norm” 5230.8 5302.2 5375.4 5449.4 4871
“L2 Norm” 43.849 44.356 44.873 45.401 41.33
“L Infinity Norm” 0.76304 0.76304 0.76304 0.76304 0.76304
Communication
“MEP” 58.544 59.334 60.161 61.011 54.528
“SMAPE” 0.88108 0.89695 0.91371 0.93104 0.80296
“MASE” 2.5939 2.6515 2.7163 2.7888 2.311
“MAE” 0.31882 0.32312 0.32763 0.33227 0.29702
“RMSE” 0.34229 0.34619 0.35027 0.35444 0.3228
“L1 Norm” 5223.6 5294 5367.9 5443.9 4866.4
“L2 Norm” 43.813 44.312 44.834 45.368 41.319
“L Infinity Norm” 0.71351 0.71351 0.72416 0.72799 0.71351
ORS-TSA-DNN at 35% learning percentage is 42.86, 33.33, ORS-TSA-DNN at 45% learning percentage is 33.33, 30,
20, and 50% surpassed than TSA-DNN, WOA-DNN, GWO- 26.32, and 22.22% more than DNN, SVM, KNN, and NN
DNN, and PSO-DNN respectively. In Fig. 13f, for human respectively. On considering Fig. 14b, for flexible work-
resource development, the RMSE of ORS-TSA-DNN at place, the RMSE of ORS-TSA-DNN at 75% learning per-
45% learning percentage is 17.65, 12.5, 6.67, and 22.22% centage is 11.11, 8.57, 5.88, and 3.03% superior to DNN,
improved than TSA-DNN, WOA-DNN, GWO-DNN, and SVM, KNN, and NN respectively. In Fig. 14c, for remote
PSO-DNN respectively. Thus, the RMSE analysis is bet- work, the RMSE of ORS-TSA-DNN at 55% learning per-
ter with the ORS-TSA-DNN than the other heuristic-based centage is 21.43, 18.52, 15.38, and 8.33% progressed than
algorithms for the HRM on work from home scenarios due DNN, SVM, KNN, and NN respectively. Thus, the clas-
to the COVID pandemic situation. sifier analysis holds better outcomes with the ORS-TSA-
DNN than the other algorithms for the HRM on work from
14.4 RMSE analysis in classifier basis home scenario method.
The RMSE analysis of different classifier algorithms for

the HRM on work from home scenario is shown in Fig. 14.
From Fig. 14a, for employee wellbeing, the RMSE of
13

different heuristic algorithms
for the HRM on work from
home scenario with respect to, a
Employee Wellbeing, b Flexible
workplace, c Remote Work, d
Job Loss, e Human Capital, f
Human Resource Development,
g Leadership, h Performance,
and i Communication
13

different classifiers for the
HRM on work from home
scenario with respect to, a
and i Communication
13

recent heuristic algorithms for
the HRM on work from home
scenario with respect to, a
and i Communication
13
14.5 Overall prediction analysis 14.8 Discussion
The overall prediction analysis of different heuristic-based The existing algorithms and classifiers contain certain
and classifier algorithms for the proposed HRM method on demerits like, PSO takes a long time to deploy and gets low
work from home scenario during COVID pandemic situa- accuracy and the GWO, WOA, and TSA algorithms increase
tion is given in Tables 2 and 3 respectively. From Table 2, the error rate and provide a low exploitation phase and it
for leadership category, the RMSE of ORS-TSA-DNN is does not support getting an optimal solution. The challenges
3.54, 2.43, 1.27, and 4.57% higher than TSA-DNN, WOA- of the different classifiers like SVM are data loss, high sen-
DNN, GWO-DNN, and PSO-DNN respectively. Similarly, sitivity, time constraints, and low accuracy, respectively,
for category performance, the RMSE of ORS-TSA-DNN is which also increase the error rate. For KNN, DNN, and NN
3.56, 2.46, 1.28, and 4.61% superior to TSA-DNN, WOA- the accuracy depends on the quality of data, complex sen-
DNN, GWO-DNN, and PSO-DNN respectively. In Table 3, sor data and also it required high memory to store all the
for communication category, the RMSE of ORS-TSA-DNN training data. HRM, Tele Work, and Extant IB provides bet-
is 8.93, 7.84, 6.76, and 5.69% better than DNN, SVM, KNN, ter accomplishment to solve the optimization problems, in
and NN respectively. Thus, the overall prediction analysis certain scenarios, it cannot be successful to get the optimum
is better with the ORS-TSA-DNN than the other methods achievements because of the lower consistency, premature
for the HRM on work from home during COVID pandemic convergence, and local optimum points trapping. The pro-
situation. posed ORS-TSA-DNN model is more efficient than other
conventional heuristic algorithms. This is due to the ability
of ORS-TSA-DNN to produce the resultant outcomes with
14.6 Evaluation of fivefold analysis fewer errors and also contains fault tolerance capacity. It has
a good exploitation capability, it obtained maximum accu-
The evaluation of the different classifier and heuristic algo- racy, and the error rate is low. For these advantages, ORS-
rithms based on fivefold analysis for the HRM on work from TSA-DNN holds better output than the other conventional
home scenario is shown in Figs. 15 and 16. From Fig. 15a, algorithms and classifiers.
for employee wellbeing, the RMSE of ORS-TSA-DNN by
varying onefold values is obtained as 96.84, 94.54, 96, and
62.5% better than TSA-DNN, WOA-DNN, GWO-DNN, and 15 Conclusion
PSO-DNN, respectively. Accordingly, Fig. 16c, for Remote
Work, the RMSE of ORS-TSA-DNN by varying onefold The purpose of this study was to look into HRD in IT busi-
values is secured 57.77, 65.45, 68.33, and 70.76% higher nesses in Tamil Nadu in the case of a COVID pandemic,
than DNN, SVM, KNN, and NN respectively. Therefore, it using a work-from-home scenario. "Employee wellbeing,
is proved that the evaluation of fivefold analyses attains bet- flexible workplace, remote work, job loss, human capital,
ter results with the ORS-TSA-DNN than the other different human resource development, leadership, performance, and
classifiers and heuristic algorithms for the HRM on work communication" were among the nine areas examined here.
from home scenario method. A questionnaire was being prepared to address the issues
that arise during the above-mentioned drives. The responses
14.7 Comparitive analysis of the recent heuristic were then gathered from a variety of IT HR specialists in
algorithms Tamil Nadu. These replies were used in the prediction phase,
which was carried out with the proposed DNN that has been
The comparative analysis of the recent heuristic algorithms suggested. The ORS-TSA was used to optimize the weight of
for the HRM on work from home scenario is shown in DNN in order to improve performance by reducing RMSE.
Fig. 17. From Fig. 17a, for employee wellbeing, the RMSE From the analysis, the RMSE of ORS-TSA-DNN was 3.56,
of ORS-TSA-DNN at learning percentage 75 is attained as 2.46, 1.28, and 4.61% superior to TSA-DNN, WOA-DNN,
3.22, 12.90, and 6.45% lower than HRM, Tele Work, and GWO-DNN, and PSO-DNN respectively. Similarly, the
Extant IB respectively. Accordingly, Fig. 16c, for Remote RMSE of ORS-TSA-DNN was 8.93, 7.84, 6.76, and 5.69%
Work, the RMSE of ORS-TSA-DNN at learning percent- better than DNN, SVM, KNN, and NN respectively. Thus,
age 45 is obtained 6.66, 20, and 13.33% minimized than the overall prediction analysis is better with the ORS-TSA-
HRM, Tele Work, and Extant IB respectively. Therefore, DNN than the other methods for the HRM on work from
it is proved that the ORS-TSA-DNN is enhanced than the home scenario during the COVID pandemic breakthrough.
recent heuristic algorithms for the HRM on work from home The practical implications for the HRM on work from home
scenario method. scenario are, AI technologies and tools play a key role in
every aspect of the COVID-19. Deep learning models can
13
help for real-time applications to predict old and new drugs Bansal JC, Singh S (2021) A better exploration strategy in grey wolf
or treatments that might treat COVID-19. The limitations of optimizer. J Ambient Intell Humaniz Comput 12:1099–1118
Bierema LL (2020) HRD research and practice after ‘the great
the research work is, to better investigate the role of com- COVID-19 pause’: the time is now for bold, critical, research.
munication with respect to different tasks and to the level Human Resour Dev Int 23(4):347–360
of the related techno stress, it could be helpful to conduct a Butterick M, Charlwood A (2021b) HRM and the COVID-19 pan-
longitudinal study, in particular to understand the construc- demic: how can we stop making a bad situation worse? Human
Resour Manag J 31(4):847–856
tion related to well-being that could depend on the particular Cai M, Tindal S, Tartanoglu Bennett S, Velu J (2021) ‘It’s like a war
experience of job or of the situation. Longitudinal analyses zone’: jay’s liminal experience of normal and extreme work
can be helpful in the understanding of the relation between in a UK supermarket during the COVID-19 pandemic. Work,
communication and psycho-physical disorders, also observ- Employ Soc 35(2):386–395
Caligiuri P, De Cieri H, Minbaeva D, Verbeke A, Zimmermann A
ing stress fluctuations on a daily basis. Moreover, in order to (2020) International HRM insights for navigating the COVID-
better understand the active role of employees and to develop 19 pandemic: implications for future research and practice. J Int
also positive and protective practices, future studies should Bus Stud 51:697–713
consider the role of the individual self-efficacy related to Chicco D, Warrens MJ, Jurman G (2021d) The coefficient of deter-
mination R-squared is more informative than SMAPE, MAE,
the use of technology, which might impact on techno stress. MAPE, MSE and RMSE in regression analysis evaluation. PeerJ
Comput Sci 7:e623
Cooke FL, Dickmann M, Parry E (2020) IJHRM after 30 years: tak-
Funding This research did not receive any specific funding. ing stock in times of COVID-19 and looking towards the future
of HR research. Int J Hum Resour Manag 1:1–23
Declarations de Lucas A, Ancill MT, del Val Núñez, SorinGavrilaGavrila, (2021)
Workplace change within the COVID-19 context: a grounded
theory approach. Econ Res-Ekon Istraž 34(1):2297–2316
Conflict of interest The authors declare that they have no conflict Fonseca LM, Azevedo AL (2020) COVID-19: outcomes for global
of interest. supply chains. Manag Market 15:424–438
Gigauri I (2020) Influence of Covid-19 crisis on human resource
Ethical approval This paper does not contain any studies with management and companies’ response: the expert study. Int J
human participants or animals performed by any of the authors. Manag Sci Bus Admi 6(6):15–24
Gupta S, Bharti V, Kumar A (2019) A survey on various machine
learning algorithms for disease prediction. Int J Recent Technol
7(6):84–87
Huang LC, Wu P, Kuo RJ, Huang HC (2001) A neural network mod-
References elling on human resource talent selection. Int J Human Resour
Dev Manag 1(2–4):206–219
Adam JP, Khazaka M, Charikhi F, Clervil M, Huot DD, Jebailey Humam M, Somantri O, Abdillah MB, Romadhon SA, Khambali M,
J, Langevin MC (2021) Management of human resources Rahim R (2019b) The application of particle swarm optimiza-
of a pharmacy department during the COVID-19 pan- tion using neural network to optimize classification of employee
demic: take-aways from the first wave. Res Soc Adm Pharm performance assessment. In: Journal of Physics: Conference
17(1):1990–1996 Series, IOP Publishing, 1175(1): 012067
Albitar K, Ali MG, Kikhia H, Hussainey K (2020) Auditing in times Kaur S, Awasthi LK, Sangal AL, Dhiman G (2020) Tunicate swarm
of social distancing: the effect of COVID-19 on auditing quality. algorithm: a new bio-inspired based metaheuristic paradigm for
Int J Account Inf Manag 29:169–178 global optimization. Eng Appl Artif Intell 90:103541
Anushya P, Jothilakshimi P, Pavithra S, Revathi B (2019) New Kaushik M, Guleria N (2020) The impact of pandemic COVID-19
approach from k-nearest neighbor data classification. SSRG Int in workplace. Eur J Bus Manag 12(15):1–10
J Comput Sci Eng (SSRG–IJCSE)–Special Issue ICTER K Lange and Wiczer (2020) Productivity gains from teleworking
Arora P, Suri D (2020) Redefining, relooking, redesigning, and rein- in the post COVID-19 era: How can public policies make it
corporating HRD in the post Covid 19 context and thereafter. happen?. OECD
Hum Resour Dev Int 23:438–451 Madero Gómez S, Ortiz Mendoza OE, Ramírez J, Olivas-Luján MR
Ayedee D, Kumar M, Buttan D, Shaikh D, Ara A (2021) Role of (2020) Stress and myths related to the COVID-19 pandemic’s
emotional intelligence and strategic human resource manage- effects on remote work. Manag Res J Iberoam Acad Manag
ment during COVID-19 pandemic. Academy of Strategic Man- 18(4):401–420
agement Journal Maqsood A, Abbas J, Rehman G, Mubeen R (2021c) The paradigm
Azizi MR, Atlasi R, Ziapour A, Abbas J, Naemi R (2021) Innovative shift for educational system continuance in the advent of COVID-
human resource management strategies during the COVID-19 19 pandemic: mental health challenges and reflections. Curr Res
pandemic: a systematic narrative review approach. Heliyon Behav Sci 2:100011
7(6):e07233 Nautiyal R, Dahiya P, Dahiya A (2019) Different approaches of ANN
Bajrami DD, Terzić A, Petrović MD, Radovanović M, Tretiakova for detection of cancer. Int J Recent Technol Eng 7(6c):88–93
TN, Hadoud A (2021) Will we have the same employees in hos- N NeJhaddadgar, A Ziapour, G Zakkipour, J Abbas, M Abolfathi,
pitality after all? the impact of COVID-19 on employees’ work M Shabani (2020) Effectiveness of telephone-based screening
attitudes and turnover intentions. Int J Hosp Manag 94:102754 and triage during COVID-19 outbreak in the promoted primary
13
healthcare system: a case study in Ardabil province. Iran, J. Public Wang Q, Li B, and Hu J (2009) Human resource selection based on per-
Health, pp 1–6 formance classification using weighted support vector machine.
A Radic, M Luck, A Ariza-Montes, H Han (2020) Fear and trembling DBLP
of cruise ship employees: psychological effects of the COVID-19 Yoosefi Lebni J, Irandoost S, Mehedi N, Sedighi S, Ziapour A (2021a)
pandemic. Int J Environ Res Publ Health 17(18) The role of celebrities during the COVID-19 pandemic in Iran:
Ramesh S, Vydeki D (2019a) Recognition and classification of paddy opportunity or threat?. Disaster Med Public Health Prep pp 1–2
leaf diseases using optimized deep neural network with Jaya algo- YoosefiLebni J, Abbas J, Moradi F, Salahshoor MR, Chaboksavar F,
rithm. Inf Process Agric 7:249–260 Irandoost SF, Ziapour A (2021b) How the COVID-19 pandemic
Reddy PDP, Reddy VV, Manohar TG (2017) Whale optimization effected economic, social, political, and cultural factors: a lesson
algorithm for optimal sizing of renewable resources for loss from Iran. Int J Soc Psychiatr 67(3):298–300
reduction in distribution systems. Renewables: wind, water, and Zhong Y, Li Y, Ding J, Liao Y (2021a) Risk management: exploring
solar 4:1-13. emerging human resource issues during the COVID-19 pandemic.
Risley C (2020) Maintaining performance and employee engagement J Risk Financ Manag 14(5):228
during the COVID- 19 pandemic. J Libr Adm 60(6):653–659 Zito M, Ingusci E, Cortese CG, Giancaspro ML, Manuti A, Molino
Samajpaty S (2021) Review of enzyme hemagglutanin esterase. J M, Russo V (2021) Does the end justify the means? the role of
Emerg Technol Innov Res 8(3):1967–1971 organizational communication among work-from-home employ-
Shuja KH, Aqeel M, Khan EA, Abbas J (2020) Letter to highlight the ees during the COVID-19 pandemic. Int J Environ Res Public
effects of isolation on elderly during COVID-19 outbreak. Int J Health 18(8):3933
Geriatr Psychiatr 35(12):1477–1478
S Soham (2021) A comparative study of COVID19 vaccine technol- Publisher’s Note Springer Nature remains neutral with regard to
ogy. 2(59):164–167 jurisdictional claims in published maps and institutional affiliations.
Su Z, McDonnell D, Cheshmehzangi A, Abbas J, Li X, Cai Y (2021)
The promise and perils of Unit 731 data to advance COVID-19 Springer Nature or its licensor (e.g. a society or other partner) holds
research. BMJ Glob Health 6(5):e004772 exclusive rights to this article under a publishing agreement with the
Thilagaraj A (2020) A study on impact of covid in work life balance of author(s) or other rightsholder(s); author self-archiving of the accepted
employees in Chennai. J Anc Hist Archeol manuscript version of this article is solely governed by the terms of
Verma SS, Prasad A, Kumar A (2022) CovXmlc: high performance such publishing agreement and applicable law.
COVID-19 detection on X-ray images using multi-model clas-
sification. Biomed Signal Process Control 71:103272
13
View publication stats

Deep Insight of HR Management On Work From Home SC

Uploaded by

Copyright:

Available Formats

Deep Insight of HR Management On Work From Home SC

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Deep Insight of HR Management On Work From Home SC

Uploaded by

Copyright:

Available Formats

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

Deep insight of HR management on work from home scenario during Covid

The user has requested enhancement of the downloaded file.

Deep insight of HR management on work from home scenario

Received: 9 November 2021 / Revised: 19 January 2022 / Accepted: 20 February 2023

pluralist, multilevel, multi-stakeholder oriented, and mul- Three Phases

questions’ without the knowledge sharing. HRM (Butterick Flexible workplace

constraints, where the range is decided based on the optimal

13.3 Proposed ORS‑TSA ⃗ − rd ⋅ T⃗t (b)||

Algorithm 1: Proposed ORS-TSA

Start 14 Results and discussions

Population and 14.1 Experimental setup

Fig. 13 RMSE analysis of

Fig. 14 RMSE analysis of

“MEP” 57.796 55.499 56.281 57.046 54.653

“MASE” 2.5072 2.3497 2.4026 2.455 2.295

Table 3 Overall prediction Employee wellbeing

“MEP” 58.627 59.408 60.233 61.097 54.653

Table 3 (continued) Employee wellbeing

“RMSE” 0.34165 0.34555 0.34956 0.35363 0.32206

The RMSE analysis of different classifier algorithms for

Fig. 15 RMSE analysis of

Fig. 16 RMSE analysis of

Fig. 17 RMSE analysis of

14.5 Overall prediction analysis 14.8 Discussion

View publication stats

You might also like

13.3 Proposed ORS‑TSA ⃗ − rd ⋅ T⃗t (b)||

Start 14 Results and discussions

Population and 14.1 Experimental setup

14.5 Overall prediction analysis 14.8 Discussion