IJCSIS Volumes by Annapurna Patil
The International Journal of Computer Science and Information Security is a monthly periodical on... more The International Journal of Computer Science and Information Security is a monthly periodical on research in general computer science and information security.
Target Audience: IT academics, university IT faculties; industry IT departments; government departments; the mobile industry and the computing industry.
Coverage includes: security infrastructures, network security: Internet security, content protection, cryptography, steganography and formal methods in information security; multimedia systems, software, information systems, intelligent systems, web services, data mining, wireless communication, networking and technologies, innovation technology and management.
https://sites.google.com/site/ijcsis/Home
Papers by Annapurna Patil
Multi-label classification (MLC) can be defined as the objective of learning a classification mod... more Multi-label classification (MLC) can be defined as the objective of learning a classification model which has the capability to infer the accurate labels of new, previously unseen, objects where it is a likely situation that each object of the dataset may rightfully belong to multiple class labels. While single-label classification problems have been thoroughly researched, the same cannot be said for MLC. A gradually increasing number of problems are now being tackled as multi-label, allowing for richer and more accurate knowledge mining in real-world domains, such as medical diagnoses, social media, text classification, etc. Currently, there are two ways of solving MLC problems; Problem Transformation Approach and Algorithm Adaptation Method. Of the two, the former has in its domain Classifier Chains (CC) which is the most effective and popular method of solving MLC problems because of its simplicity in implementation. Unfortunately, CC is not favoured due to 2 drawbacks, [1] ordering of the labels for classification are randomly decided without a fixed logic or algorithm to it which results in varying accuracy, [2] all the labels, even those which may be redundant for a particular dataset are put into the chain despite the probability that some may be carrying irrelevant details. Through the research conducted for the purpose of this study, both challenges are tackled along with others detailed further on simultaneously using Genetic Algorithms (GA) over a Partial CC (PartCC) model, which is a modification over CC. A toxic comments dataset is used since its classification is a multi-label text classification problem with a highly imbalanced dataset. This paper aims to create a prototype model that is capable of detecting various types of toxicity like neutral, toxic, severe toxic, threats, obscenity, insults and identity hate. With the explosion of social media in the modern world and the resulting increasing phenomenon of social media hatred and bullying, there is a need for an advanced prototype model to predict the toxicity of each class of comments.
Automation is a process of developing a tool or a product to perform on its own, in order to achi... more Automation is a process of developing a tool or a product to perform on its own, in order to achieve all the functionalities required of a complex system, without human intervention. The current Certification Process of the J2EE product in IBM is consuming unnecessary time even for the valid products. In order to reduce this processing overhead, the process of automation was proposed by the technologist to save time so as to accomplish the task early. The need for automating the tool of Certification arose due to unwanted utilization of man-hour and manpower. The existing system halts after the tool finishes the comparison of the listings (which contain details of the build, its environment and the list of files present within the build), until the administrator logs-in. Administrator checks each transaction ID individually for intimating the clients about the status of their products. The proposed system aims at sending the intimation to the clients as soon as the comparison is done successfully, without the intervention of administrator i.e., an automated notification will be sent after successful comparison of the listings. The tool will also provide an option to generate chart/graph whenever the managerial team needs it at just one click. The work carried out here is aimed at automating the process of certifying the Java products or assets developed by IBM Software Product Groups. It also aims at generating graphs at real-time for the number of products certified till date. The certification process is for IBM JRE/SDK used by IBM Software Product Groups. It will be done by comparing the listings submitted by the IBM Software Product Groups and the reference listings present in the Certification server. JRE/SDK should adhere to the constraints as per the Oracle license. The IBM product or asset is certified after the Certification Team sends the "Java Compatibility Logo". Here Javapath, listpath, build listing, product details for automation and start-and-end dates for graph generation act as inputs in Product Certification Process. After submitting the request, a transaction ID is generated which keeps track of certification status. The process ends with sending a notification about successful submission of the request. The report is generated as bar-graph with x-axis showing the duration in months, quarters or years and y-axis showing the number of products/builds certified. After the implementation and the testing process, it is noticed that the time-consumption and manpower required for Certification Process is reduced.
International Journal of Grid and High Performance Computing, Mar 22, 2023
Earlier detection and classification of squamous cell carcinoma (OSCC) is a widespread issue for ... more Earlier detection and classification of squamous cell carcinoma (OSCC) is a widespread issue for efficient treatment, enhancing survival rate, and reducing the death rate. Thus, it becomes necessary to design effective diagnosis models for assisting pathologists in the OSCC examination process. In recent times, deep learning (DL) models have exhibited considerable improvement in the design of effective computer-aided diagnosis models for OSCC using histopathological images. In this view, this paper develops a novel duck pack optimization with deep transfer learning enabled oral squamous cell carcinoma classification (DPODTL-OSC3) model using histopathological images. The goal of the DPODTL-OSC3 model is to improve the classifier outcomes of OSCC using histopathological images into normal and cancerous class labels. Finally, the variational autoencoder (VAE) model is utilized for the detection and classification of OSCC. The performance validation and comparative result analysis for the DPODTL-OSC3 model are tested using a histopathological imaging database.
2022 IEEE 19th India Council International Conference (INDICON), Nov 24, 2022
Biomedical Signal Processing and Control, Mar 1, 2023
Springer eBooks, Sep 1, 2022
2021 IEEE 18th India Council International Conference (INDICON), Dec 19, 2021
Blockchain is said to be one of the most prominent inventions since the advent of the internet. C... more Blockchain is said to be one of the most prominent inventions since the advent of the internet. Cryptocurrency is one of the most well-known blockchain applications and has shown tremendous growth in recent times. Most cryptocurrency platforms currently utilize Proof of Work as the consensus mechanism. However, this includes a high energy cost in the form of repeated hash computations to keep the blockchain tamper-proof. The proposed work combines the idea of Useful Work and Proof of Stake, where blockchain nodes train machine learning models submitted by users and earn Work Stake Tokens on successful completion, which can be used as stake in the Proof of Stake algorithm. Proof of Solution efficiently utilizes the vast computational resources of miners to perform useful work. The combined approach reduces redundant model training via multiple nodes by half, improving on the drawback of Proof of Useful Work.
International Journal of Ambient Computing and Intelligence, Apr 8, 2022
Cloud Computing is one of the most popular platforms in recent times and has many services to off... more Cloud Computing is one of the most popular platforms in recent times and has many services to offer. The resources are deployed on the Cloud and are made available to cloud users over high-speed internet connectivity. Many enterprises think of migrating the data or application hosted from one Cloud to another based on the requirements. Migration from one Cloud to another Cloud requires security as it is vital for any data. This article presents a novel secure framework called ‘InterCloudFramework,’ considering well-established criteria to migrate various services across clouds with minimal supervision and interruption. Security is the primary concern to migrate the data among inter-clouds. The study incorporates the Elliptical-Curve Diffie-Hellman algorithm to encrypt the data and Merkle Hash Trees to check the integrity of the data. In addition to security during migration, the framework reduces the migration time of data or applications.
Recognizing Activities from raw video streams has been one of the most challenging problems in th... more Recognizing Activities from raw video streams has been one of the most challenging problems in the domain of computer vision since past three decades. In this paper we propose a method of combining unsupervised and supervised methods to develop a scalable solution which can have real world applications in surveillance, video indexing, security and could help us have an efficient way of tackling large scale surveillance with minimal human intervention. With our unsupervised reconstruction CNN we can cluster different videos based on their dense frame representations and then train a separate classifier for each of the clusters. This methods allows us to easily add new activities to the system without training the entire system from scratch. For activity recognition among the clusters we use LSTM based Recurrent neural networks with different hyperparameter for each clusters' classifier.
This paper explores the health care scenario of elder citizens. It compares the health care scena... more This paper explores the health care scenario of elder citizens. It compares the health care scenarios in first world and India and proposes technological solutions that can be implemented incorporating technologies like Internet of Things (IoT), data analytics and Cloud Computing.
2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Jul 8, 2022
With the current advances in networking and the usage of computer networks in different sectors o... more With the current advances in networking and the usage of computer networks in different sectors of technology, network security plays a prime role in enabling the proper functioning of networks by detecting and preventing attacks. In this paper, we propose an architecture using the Snort IDS/IPS and machine learning to build an Intelligent Network Intrusion Detection and Prevention System with dynamic rule updation creating robust and secure system with reduced resource consumption which can be used in Domestic Networks. The objective of JARVIS, the proposed system, is to detect malicious patterns in real-time traffic data and take action by dynamically updating Snort rules. By deploying a machine learning model (Random Forest) in parallel and dynamically enabling rules, resource consumption of Snort can be reduced and optimized. The model detects any attacks and suggests rules that can be deployed on Snort to prevent the attack. The false-positive rate of the model was reduced by looking at DNS queries to analyze the intent behind the traffic data. JARVIS also provides a web interface where the User can view Network Traffic Data, Detected Attacks as well as take the necessary actions. The machine learning model successfully detected incoming attacks with considerable accuracy and suggested rules in the web interface which allowed the user to deploy them and prevent the attack from causing further damage.
2022 IEEE North Karnataka Subsection Flagship International Conference (NKCon)
2023 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE)
2022 4th International Conference on Circuits, Control, Communication and Computing (I4C)
Lecture notes in networks and systems, Sep 1, 2022
2021 IEEE 18th India Council International Conference (INDICON), 2021
Over the last few years, the world has been moving towards digital healthcare, where harnessing m... more Over the last few years, the world has been moving towards digital healthcare, where harnessing medical data distributed across multiple healthcare providers is essential to achieving personalized treatments. Though the efficiency and speed of the diagnosis process have increased due to the digitalization of healthcare data, it is at constant risk of cyberattacks. Medical images, in particular, seem to have become a regular victim of hackers, due to which there is a need to find a feasible solution for storing them securely. This work proposes a blockchain-based framework that leverages the InterPlanetary File system (IPFS) to provide decentralized storage for medical images. Our proposed blockchain storage model is implemented in the IPFS distributed file-sharing system, where each image is stored on IPFS, and its corresponding unique content-addressed hash is stored in the blockchain. The proposed model ensures the security of the medical images without any third-party dependency and eliminates the obstacles that arise due to centralized storage.
Uploads
IJCSIS Volumes by Annapurna Patil
Target Audience: IT academics, university IT faculties; industry IT departments; government departments; the mobile industry and the computing industry.
Coverage includes: security infrastructures, network security: Internet security, content protection, cryptography, steganography and formal methods in information security; multimedia systems, software, information systems, intelligent systems, web services, data mining, wireless communication, networking and technologies, innovation technology and management.
https://sites.google.com/site/ijcsis/Home
Papers by Annapurna Patil
Target Audience: IT academics, university IT faculties; industry IT departments; government departments; the mobile industry and the computing industry.
Coverage includes: security infrastructures, network security: Internet security, content protection, cryptography, steganography and formal methods in information security; multimedia systems, software, information systems, intelligent systems, web services, data mining, wireless communication, networking and technologies, innovation technology and management.
https://sites.google.com/site/ijcsis/Home