Journal of Biomedical Engineering and Medical Imaging, 2015
In this paper we have presented results for classification of electroencephalograph (EEG) signals... more In this paper we have presented results for classification of electroencephalograph (EEG) signals produced by the random visual exposure of primary colours i.e. red, green and blue to the subject while sitting in a dark room. Event-related spectral perturbations (ERSP) are used as features for support vector machine (SVM). Our objective was to classify the EEG signals as Red, Green and Blue classes and we have successfully classified the three visual conditions having accuracy of 84%, 89% and 98% with linear, polynomial and radial basis function kernels respectively with in all the groups of data among all the subjects.
Proceedings of the 2019 International Conference on Artificial Intelligence, Robotics and Control, 2019
This paper aims to evaluate EEG as an application predictor of Holland test with career interest.... more This paper aims to evaluate EEG as an application predictor of Holland test with career interest. Consequently, it is essential to develop and analyze the brain wave of clinical changes of the EEG signals during Holland answering questions. The experimental test begins by answering Holland test with 34 participants of staff members at KAU (College of Computing and Information Technology and College of Engineering). Accordingly, the test is applied twice, one without using EEG and the second with EEG recording. The proposed solution uses 34 answering of participants of Holland career test dataset after getting the content data from the answering of Holland using the EEG and initial career assessment. Consequently, the Holland answering test (without EEG) is analyzed along with EEG analysis of the Holland answering in different frequency bands such as delta, theta, alpha and beta. Therefore, we aim to provide researchers, a methodology, if we could identify career interest using EEG s...
DIY (Do It Yourself) approaches have led the way for learning things in a new and smart way. One ... more DIY (Do It Yourself) approaches have led the way for learning things in a new and smart way. One way to learn things practically is to play computer or smartphone games. Gaming for learning has several uses, you master your skills in a fun way. Since the children most of the time these days are busy with playing games on smartphones, therefore, in this research we focus on how to use the modern 3D mobile games for teaching ethics and Islamic values. We have built two mobile apps for this purpose, Akhlaqee-1 and Akhlaqee-2, using the Unity 3D gaming engine. Akhlaqee-1 has been built with virtual reality applications i.e. Oculus Touch where the player can wear the Oculus headset and using an oculus rift can play the game. The other application Akhlaqee-2 has been built to be a heavy graphics-based computer virtual reality game. Additionally, the students used an olfactory display and a new mechanism for walking in virtual reality environments to increase the realism of the virtual env...
This book covers multidisciplinary domains. If you are working with colors and electroencephalogr... more This book covers multidisciplinary domains. If you are working with colors and electroencephalographic signals, specially from human brain perception point of view then this book is right for you. We hope that this book will provide you help in designing experimental protocols and related laboratory setup to analyze human brain's response in electroencephalographic signals against colored visual stimuli. This book presents not only the requirements for experimental setups but also covers comprehensive background and introductory information related to human brain, EEG signal processing, suitable tool for pattern recognition along with mathematical models and Brain-Computer Interface applications. We also hope that after reading this book you would be able to recognize colors in EEG signals and will gain the skills in order to utilize colors as visual stimuli in applications for Brain-Computer Interfaces. Please note that this book is resulted as a part of PhD Thesis at Universit...
Many business applications rely on their historical data to predict their business future. The ma... more Many business applications rely on their historical data to predict their business future. The marketing products process is one of the core processes for the business. Customer needs give a useful piece of information that helps to market the appropriate products at the appropriate time. Moreover, services are considered recently as products. The development of education and health services is depending on historical data. For the more, reducing online social media networks problems and crimes need a significant source of information. Data analysts need to use an efficient classification algorithm to predict the future of such businesses. However, dealing with a huge quantity of data requires great time to process. Data mining involves many useful techniques that are used to predict statistical data in a variety of business applications. The classification technique is one of the most widely used with a variety of algorithms. In this paper, various classification algorithms are rev...
The suspension of tiny solid particles inside the energy transport liquids could enhance their th... more The suspension of tiny solid particles inside the energy transport liquids could enhance their thermal conductivity as well as provide an efficient and inventive approach to significantly improve their properties of heat transport. Therefore, our aim is to explore the radiative two-dimensional unsteady flow of a viscous nanofluid about an aligned magnetic field that includes the joint effect of suction, velocity slip, and heat source across a porous convective stretching/shrinking surface. Initially, using non-dimensional variables, the nonlinear governing partial differential equations (PDEs) were transformed into ordinary differential equations (ODEs) which were subsequently solved with the help of bvp4c built-in package in MATLAB. The results declare that escalating the values of the unsteadiness parameter escalates the friction drag whereas it reduces with the escalation of the slip parameter. Furthermore, the heat transfer rate escalates with the escalation of radiation and con...
Transactions on Machine Learning and Artificial Intelligence
In this work, we propose an image processing-based hybrid technique that provides assistance in d... more In this work, we propose an image processing-based hybrid technique that provides assistance in detecting certain patterns in traffic infractions committed by drivers on the roads. The proposed technique is based on the speed estimation using video data in conjunction with tracking methods. Our hybrid proposal comprises two parts. First, we propose a method to detect the road lanes using Hough transform. Second, we detect the vehicles in the video datasets using Haar Cascade methodology and then track those vehicles for their speed estimation and for monitoring the driving patterns. In addition, the types of infractions that a driver can commit while driving are also detailed. The most significant cases in which the infractions are determined is when the driver makes a rapid and continuous change of lanes, parking at inappropriate places and prohibited U-turns. The results are provided in terms of vehicle detection and speed estimation. Our results and analysis reveal that the propo...
Sign languages are used by the deaf and mute community of the world. These are gesture based lang... more Sign languages are used by the deaf and mute community of the world. These are gesture based languages where the subjects use hands and facial expressions to perform different gestures. There are hundreds of different sign languages in the world. Furthermore, like natural languages, there exist different dialects for many sign languages. In order to facilitate the deaf community several different repositories of video gestures are available for many sign languages of the world. These video based repositories do not support the development of an automated language translation systems. This research aims to investigate the idea of engaging the deaf community for the development and validation of a parallel corpus for a sign language and its dialects. As a principal contribution, this research presents a framework for building a parallel corpus for sign languages by harnessing the powers of crowdsourcing with editorial manager, thus it engages a diversified set of stakeholders for building and validating a repository in a quality controlled manner. It further presents processes to develop a word-level parallel corpus for different dialects of a sign language; and a process to develop sentence-level translation corpus comprising of source and translated sentences. The proposed framework has been successfully implemented and involved different stakeholders to build corpus. As a result, a word-level parallel corpus comprising of the gestures of almost 700 words of Pakistan Sign Language (PSL) has been developed. While, a sentence-level translation corpus comprising of more than 8000 sentences for different tenses has also been developed for PSL. This sentence-level corpus can be used in developing and evaluating machine translation models for natural to sign language translation and vice-versa. While the machine-readable word level parallel corpus will help in generating avatar based videos for the translated sentences in different dialects of a sign language.
The International Journal of Integrated Engineering
This article presents, a load management system is designed and implemented to integrate renewabl... more This article presents, a load management system is designed and implemented to integrate renewable energy resources (RES) (solar and wind), which manage the load according to the supply/demand and the user's priorities. The system is implemented on a hybrid system integrating wind energy, solar energy, utility supply, and battery energy storage system. Load management is carried out via switching of the loads. The sources can also be turned ON and OFF. During excess power, the battery module works as an energy storage unit or backup energy supply unit during demand. Loads can be turned ON and OFF wirelessly via GSM. The grid operator can switch the loads by simply sending a command via a short service message (SMS). In the end, the system is tested, and the results are presented. The hybrid system is simulated in MATLAB/Simulink first and then hardware implementation is carried out, which involves integrating renewable resources via converters and load management by switching us...
Indonesian Journal of Electrical Engineering and Computer Science
For all industrial and distribution sites, the lagging power factor of electrical loads is a comm... more For all industrial and distribution sites, the lagging power factor of electrical loads is a common problem. In the early days, it was corrected manually by adding the capacitor banks of certain values in parallel. Automatic power factor correction (APFC) using a capacitor bank helps to make a power factor that is close to unity. It consists of a microcontroller that processes the value of the power factor to enable the system and monitor the power factor if it falls below (0.77) from the specified level. This paper presents the automatic correction of the power factor by adding the capacitors banks automatically of the desired value in a three-phase system in the form of binary coding (0-7). The main purpose of this system is to maintain the power factor as close as to unity, for the experimental case, it is set to (0.93) which helps to decreases the losses and ultimately increase the efficiency of the system.
Internet of things (IoT) is a promising technology which provides efficient and reliable solution... more Internet of things (IoT) is a promising technology which provides efficient and reliable solutions towards the modernization of several domains. IoT based solutions are being developed to automatically maintain and monitor agricultural farms with minimal human involvement. The article presents many aspects of technologies involved in the domain of IoT in agriculture. It explains the major components of IoT based smart farming. A rigorous discussion on network technologies used in IoT based agriculture has been presented, that involves network architecture and layers, network topologies used, and protocols. Furthermore, the connection of IoT based agriculture systems with relevant technologies including cloud computing, big data storage and analytics has also been presented. In addition, security issues in IoT agriculture have been highlighted. A list of smart phone based and sensor based applications developed for different aspects of farm management has also been presented. Lastly, the regulations and policies made by several countries to standardize IoT based agriculture have been presented along with few available success stories. In the end, some open research issues and challenges in IoT agriculture field have been presented.
Recently, the impact of colors on the brain signals has become one of the leading researches in B... more Recently, the impact of colors on the brain signals has become one of the leading researches in BCI systems. These researches are based on studying the brain behavior after color stimulus, and finding a way to classify its signals offline without considering the real time. Moving to the next step, we present a real time classification model (online) for EEG signals evoked by RGB colors stimuli, which is not presented in previous studies. In this research, EEG signals were recorded from 7 subjects through BCI2000 toolbox. The Empirical Mode Decomposition (EMD) technique was used at the signal analysis stage. Various feature extraction methods were investigated to find the best and reliable set, including Event-related spectral perturbations (ERSP), Target mean with Feast Fourier Transform (FFT), Wavelet Packet Decomposition (WPD), Auto Regressive model (AR) and EMD residual. A new feature selection method was created based on the peak's time of EEG signal when red and blue colors...
This review article provides a deep insight into the Brain–Computer Interface (BCI) and the appli... more This review article provides a deep insight into the Brain–Computer Interface (BCI) and the application of Machine Learning (ML) technology in BCIs. It investigates the various types of research undertaken in this realm and discusses the role played by ML in performing different BCI tasks. It also reviews the ML methods used for mental state detection, mental task categorization, emotion classification, electroencephalogram (EEG) signal classification, event-related potential (ERP) signal classification, motor imagery categorization, and limb movement classification. This work explores the various methods employed in BCI mechanisms for feature extraction, selection, and classification and provides a comparative study of reviewed methods. This paper assists the readers to gain information regarding the developments made in BCI and ML domains and future improvements needed for improving and designing better BCI applications.
There has been significant development in the facial recognition technology during past few decad... more There has been significant development in the facial recognition technology during past few decades. This technology has been widely used by different organizations and governments for defense, security, and surveillance projects. Furthermore, it has now been incorporated into our daily usages, such as consumer applications, personal data protection, or cyber-security, particularly while using smartphones. Most of these systems work very efficient, however, there are some challenges related to the accuracy of results of facial recognition systems when tested on images of people with dark skin. As a matter of fact, various studies demonstrate higher accuracy when tested on data set with white skin personnel, while exhibit a much lesser accuracy when the same algorithms are tested on dataset of people with dark skin. This article highlights the variation in accuracy of existing facial recognition algorithms when applied to dark-skinned people. Furthermore, as a principal contribution it presents a hybrid algorithm based on Gaussian and Explicit rule model that improves the accuracy for face-detection for dark skinned people. Thorough experimental evaluation has been conducted with a data set of black faces by first identifying skin and non-skin regions and then applying skin segmentation. The results have been compared with existing face detection algorithms with a clear improvement in the accuracy of 89% for dark skin.
Journal of Biomedical Engineering and Medical Imaging, 2015
In this paper we have presented results for classification of electroencephalograph (EEG) signals... more In this paper we have presented results for classification of electroencephalograph (EEG) signals produced by the random visual exposure of primary colours i.e. red, green and blue to the subject while sitting in a dark room. Event-related spectral perturbations (ERSP) are used as features for support vector machine (SVM). Our objective was to classify the EEG signals as Red, Green and Blue classes and we have successfully classified the three visual conditions having accuracy of 84%, 89% and 98% with linear, polynomial and radial basis function kernels respectively with in all the groups of data among all the subjects.
Proceedings of the 2019 International Conference on Artificial Intelligence, Robotics and Control, 2019
This paper aims to evaluate EEG as an application predictor of Holland test with career interest.... more This paper aims to evaluate EEG as an application predictor of Holland test with career interest. Consequently, it is essential to develop and analyze the brain wave of clinical changes of the EEG signals during Holland answering questions. The experimental test begins by answering Holland test with 34 participants of staff members at KAU (College of Computing and Information Technology and College of Engineering). Accordingly, the test is applied twice, one without using EEG and the second with EEG recording. The proposed solution uses 34 answering of participants of Holland career test dataset after getting the content data from the answering of Holland using the EEG and initial career assessment. Consequently, the Holland answering test (without EEG) is analyzed along with EEG analysis of the Holland answering in different frequency bands such as delta, theta, alpha and beta. Therefore, we aim to provide researchers, a methodology, if we could identify career interest using EEG s...
DIY (Do It Yourself) approaches have led the way for learning things in a new and smart way. One ... more DIY (Do It Yourself) approaches have led the way for learning things in a new and smart way. One way to learn things practically is to play computer or smartphone games. Gaming for learning has several uses, you master your skills in a fun way. Since the children most of the time these days are busy with playing games on smartphones, therefore, in this research we focus on how to use the modern 3D mobile games for teaching ethics and Islamic values. We have built two mobile apps for this purpose, Akhlaqee-1 and Akhlaqee-2, using the Unity 3D gaming engine. Akhlaqee-1 has been built with virtual reality applications i.e. Oculus Touch where the player can wear the Oculus headset and using an oculus rift can play the game. The other application Akhlaqee-2 has been built to be a heavy graphics-based computer virtual reality game. Additionally, the students used an olfactory display and a new mechanism for walking in virtual reality environments to increase the realism of the virtual env...
This book covers multidisciplinary domains. If you are working with colors and electroencephalogr... more This book covers multidisciplinary domains. If you are working with colors and electroencephalographic signals, specially from human brain perception point of view then this book is right for you. We hope that this book will provide you help in designing experimental protocols and related laboratory setup to analyze human brain's response in electroencephalographic signals against colored visual stimuli. This book presents not only the requirements for experimental setups but also covers comprehensive background and introductory information related to human brain, EEG signal processing, suitable tool for pattern recognition along with mathematical models and Brain-Computer Interface applications. We also hope that after reading this book you would be able to recognize colors in EEG signals and will gain the skills in order to utilize colors as visual stimuli in applications for Brain-Computer Interfaces. Please note that this book is resulted as a part of PhD Thesis at Universit...
Many business applications rely on their historical data to predict their business future. The ma... more Many business applications rely on their historical data to predict their business future. The marketing products process is one of the core processes for the business. Customer needs give a useful piece of information that helps to market the appropriate products at the appropriate time. Moreover, services are considered recently as products. The development of education and health services is depending on historical data. For the more, reducing online social media networks problems and crimes need a significant source of information. Data analysts need to use an efficient classification algorithm to predict the future of such businesses. However, dealing with a huge quantity of data requires great time to process. Data mining involves many useful techniques that are used to predict statistical data in a variety of business applications. The classification technique is one of the most widely used with a variety of algorithms. In this paper, various classification algorithms are rev...
The suspension of tiny solid particles inside the energy transport liquids could enhance their th... more The suspension of tiny solid particles inside the energy transport liquids could enhance their thermal conductivity as well as provide an efficient and inventive approach to significantly improve their properties of heat transport. Therefore, our aim is to explore the radiative two-dimensional unsteady flow of a viscous nanofluid about an aligned magnetic field that includes the joint effect of suction, velocity slip, and heat source across a porous convective stretching/shrinking surface. Initially, using non-dimensional variables, the nonlinear governing partial differential equations (PDEs) were transformed into ordinary differential equations (ODEs) which were subsequently solved with the help of bvp4c built-in package in MATLAB. The results declare that escalating the values of the unsteadiness parameter escalates the friction drag whereas it reduces with the escalation of the slip parameter. Furthermore, the heat transfer rate escalates with the escalation of radiation and con...
Transactions on Machine Learning and Artificial Intelligence
In this work, we propose an image processing-based hybrid technique that provides assistance in d... more In this work, we propose an image processing-based hybrid technique that provides assistance in detecting certain patterns in traffic infractions committed by drivers on the roads. The proposed technique is based on the speed estimation using video data in conjunction with tracking methods. Our hybrid proposal comprises two parts. First, we propose a method to detect the road lanes using Hough transform. Second, we detect the vehicles in the video datasets using Haar Cascade methodology and then track those vehicles for their speed estimation and for monitoring the driving patterns. In addition, the types of infractions that a driver can commit while driving are also detailed. The most significant cases in which the infractions are determined is when the driver makes a rapid and continuous change of lanes, parking at inappropriate places and prohibited U-turns. The results are provided in terms of vehicle detection and speed estimation. Our results and analysis reveal that the propo...
Sign languages are used by the deaf and mute community of the world. These are gesture based lang... more Sign languages are used by the deaf and mute community of the world. These are gesture based languages where the subjects use hands and facial expressions to perform different gestures. There are hundreds of different sign languages in the world. Furthermore, like natural languages, there exist different dialects for many sign languages. In order to facilitate the deaf community several different repositories of video gestures are available for many sign languages of the world. These video based repositories do not support the development of an automated language translation systems. This research aims to investigate the idea of engaging the deaf community for the development and validation of a parallel corpus for a sign language and its dialects. As a principal contribution, this research presents a framework for building a parallel corpus for sign languages by harnessing the powers of crowdsourcing with editorial manager, thus it engages a diversified set of stakeholders for building and validating a repository in a quality controlled manner. It further presents processes to develop a word-level parallel corpus for different dialects of a sign language; and a process to develop sentence-level translation corpus comprising of source and translated sentences. The proposed framework has been successfully implemented and involved different stakeholders to build corpus. As a result, a word-level parallel corpus comprising of the gestures of almost 700 words of Pakistan Sign Language (PSL) has been developed. While, a sentence-level translation corpus comprising of more than 8000 sentences for different tenses has also been developed for PSL. This sentence-level corpus can be used in developing and evaluating machine translation models for natural to sign language translation and vice-versa. While the machine-readable word level parallel corpus will help in generating avatar based videos for the translated sentences in different dialects of a sign language.
The International Journal of Integrated Engineering
This article presents, a load management system is designed and implemented to integrate renewabl... more This article presents, a load management system is designed and implemented to integrate renewable energy resources (RES) (solar and wind), which manage the load according to the supply/demand and the user's priorities. The system is implemented on a hybrid system integrating wind energy, solar energy, utility supply, and battery energy storage system. Load management is carried out via switching of the loads. The sources can also be turned ON and OFF. During excess power, the battery module works as an energy storage unit or backup energy supply unit during demand. Loads can be turned ON and OFF wirelessly via GSM. The grid operator can switch the loads by simply sending a command via a short service message (SMS). In the end, the system is tested, and the results are presented. The hybrid system is simulated in MATLAB/Simulink first and then hardware implementation is carried out, which involves integrating renewable resources via converters and load management by switching us...
Indonesian Journal of Electrical Engineering and Computer Science
For all industrial and distribution sites, the lagging power factor of electrical loads is a comm... more For all industrial and distribution sites, the lagging power factor of electrical loads is a common problem. In the early days, it was corrected manually by adding the capacitor banks of certain values in parallel. Automatic power factor correction (APFC) using a capacitor bank helps to make a power factor that is close to unity. It consists of a microcontroller that processes the value of the power factor to enable the system and monitor the power factor if it falls below (0.77) from the specified level. This paper presents the automatic correction of the power factor by adding the capacitors banks automatically of the desired value in a three-phase system in the form of binary coding (0-7). The main purpose of this system is to maintain the power factor as close as to unity, for the experimental case, it is set to (0.93) which helps to decreases the losses and ultimately increase the efficiency of the system.
Internet of things (IoT) is a promising technology which provides efficient and reliable solution... more Internet of things (IoT) is a promising technology which provides efficient and reliable solutions towards the modernization of several domains. IoT based solutions are being developed to automatically maintain and monitor agricultural farms with minimal human involvement. The article presents many aspects of technologies involved in the domain of IoT in agriculture. It explains the major components of IoT based smart farming. A rigorous discussion on network technologies used in IoT based agriculture has been presented, that involves network architecture and layers, network topologies used, and protocols. Furthermore, the connection of IoT based agriculture systems with relevant technologies including cloud computing, big data storage and analytics has also been presented. In addition, security issues in IoT agriculture have been highlighted. A list of smart phone based and sensor based applications developed for different aspects of farm management has also been presented. Lastly, the regulations and policies made by several countries to standardize IoT based agriculture have been presented along with few available success stories. In the end, some open research issues and challenges in IoT agriculture field have been presented.
Recently, the impact of colors on the brain signals has become one of the leading researches in B... more Recently, the impact of colors on the brain signals has become one of the leading researches in BCI systems. These researches are based on studying the brain behavior after color stimulus, and finding a way to classify its signals offline without considering the real time. Moving to the next step, we present a real time classification model (online) for EEG signals evoked by RGB colors stimuli, which is not presented in previous studies. In this research, EEG signals were recorded from 7 subjects through BCI2000 toolbox. The Empirical Mode Decomposition (EMD) technique was used at the signal analysis stage. Various feature extraction methods were investigated to find the best and reliable set, including Event-related spectral perturbations (ERSP), Target mean with Feast Fourier Transform (FFT), Wavelet Packet Decomposition (WPD), Auto Regressive model (AR) and EMD residual. A new feature selection method was created based on the peak's time of EEG signal when red and blue colors...
This review article provides a deep insight into the Brain–Computer Interface (BCI) and the appli... more This review article provides a deep insight into the Brain–Computer Interface (BCI) and the application of Machine Learning (ML) technology in BCIs. It investigates the various types of research undertaken in this realm and discusses the role played by ML in performing different BCI tasks. It also reviews the ML methods used for mental state detection, mental task categorization, emotion classification, electroencephalogram (EEG) signal classification, event-related potential (ERP) signal classification, motor imagery categorization, and limb movement classification. This work explores the various methods employed in BCI mechanisms for feature extraction, selection, and classification and provides a comparative study of reviewed methods. This paper assists the readers to gain information regarding the developments made in BCI and ML domains and future improvements needed for improving and designing better BCI applications.
There has been significant development in the facial recognition technology during past few decad... more There has been significant development in the facial recognition technology during past few decades. This technology has been widely used by different organizations and governments for defense, security, and surveillance projects. Furthermore, it has now been incorporated into our daily usages, such as consumer applications, personal data protection, or cyber-security, particularly while using smartphones. Most of these systems work very efficient, however, there are some challenges related to the accuracy of results of facial recognition systems when tested on images of people with dark skin. As a matter of fact, various studies demonstrate higher accuracy when tested on data set with white skin personnel, while exhibit a much lesser accuracy when the same algorithms are tested on dataset of people with dark skin. This article highlights the variation in accuracy of existing facial recognition algorithms when applied to dark-skinned people. Furthermore, as a principal contribution it presents a hybrid algorithm based on Gaussian and Explicit rule model that improves the accuracy for face-detection for dark skinned people. Thorough experimental evaluation has been conducted with a data set of black faces by first identifying skin and non-skin regions and then applying skin segmentation. The results have been compared with existing face detection algorithms with a clear improvement in the accuracy of 89% for dark skin.
Uploads
Papers by Saim Rasheed