Tajinder Kumar
@jmit.ac.in
Assistant Professor Computer Science and Engineering
Kurukshetra University
RESEARCH INTERESTS
Cloud computing, Machine learning, Biometrics
Scopus Publications
Scopus Publications
Tajinder Kumar, Purushottam Sharma, Jaswinder Tanwar, Hisham Alsghier, Shashi Bhushan, Hesham Alhumyani, Vivek Sharma, and Ahmed I. Alutaibi
Institution of Engineering and Technology (IET)
AbstractCloud computing has drastically changed the delivery and consumption of live streaming content. The designs, challenges, and possible uses of cloud computing for live streaming are studied. A comprehensive overview of the technical and business issues surrounding cloud‐based live streaming is provided, including the benefits of cloud computing, the various live streaming architectures, and the challenges that live streaming service providers face in delivering high‐quality, real‐time services. The different techniques used to improve the performance of video streaming, such as adaptive bit‐rate streaming, multicast distribution, and edge computing are discussed and the necessity of low‐latency and high‐quality video transmission in cloud‐based live streaming is underlined. Issues such as improving user experience and live streaming service performance using cutting‐edge technology, like artificial intelligence and machine learning are discussed. In addition, the legal and regulatory implications of cloud‐based live streaming, including issues with network neutrality, data privacy, and content moderation are addressed. The future of cloud computing for live streaming is examined in the section that follows, and it looks at the most likely new developments in terms of trends and technology. For technology vendors, live streaming service providers, and regulators, the findings have major policy‐relevant implications. Suggestions on how stakeholders should address these concerns and take advantage of the potential presented by this rapidly evolving sector, as well as insights into the key challenges and opportunities associated with cloud‐based live streaming are provided.
Ramesh Kait, Sarbjit Kaur, Purushottam Sharma, Chhikara Ankita, Tajinder Kumar, and Xiaochun Cheng
Wiley
AbstractDue to the characteristics of vehicular ad hoc networks, the increased mobility of nodes and the inconsistency of wireless communication connections pose significant challenges for routing. As a result, researchers find it to be a fascinating topic to study. Furthermore, since these networks are vulnerable to various assaults, providing an authentication method between the source and destination nodes is crucial. How to route in such networks more efficiently, taking into account node mobility characteristics and accompanying massive historical data, is still a matter of discussion. Fuzzy logic‐based Trusted Routing Protocol for vehicular cloud networks (FTRP) is proposed in this study that determines the secure path for data dissemination. Fuzzy Logic determines the node candidacy value and selects or rejects a path accordingly. The cloud assigns a confidence score to each vehicle based on the data it collects from nodes after each interaction. Our study identifies the secure path on the basis of trust along with factors such as speed, closeness to other nodes, signal strength and distance from the neighbouring nodes. Simulations of the novel protocol demonstrate that it can keep the packet delivery ratio high with little overhead and low delay. FTRP has significant implications for deploying Vehicular Cloud Networks using electric vehicle technologies in smart cities. The routing data is collected with the help of Internet of Technology (IOT) sensors. The information is transmitted between vehicles using IOT gateways.
Vishal Garg, Bikrampal Kaur, and Tajinder Kumar
AIP Publishing
Vishal Garg, Bikrampal Kaur, Tajinder Kumar, Purushottam Sharma, Majed Alowaidi, and Sunil Kumar Sharma
World Scientific Pub Co Pte Ltd
This paper uses the chaotic fuzzy encryption (CFE) technique and a greedy chemical reaction optimization algorithm based on mobile cloud computing to protect data from any assault. Mobile users who use protected mobile cloud computing (Mobi-Cloud) must trust the cloud service provider to keep the data sent from their mobile devices safe when mobile users express strong reservations about storing personal information in the public cloud. The Greedy Chemical Reaction Optimization (G-CRO) algorithm reduces critical limitations by determining the offloading end with motion at run time, i.e. the task’s operating time, CPU usage, memory utilization, and energy usage. The experimental results show that the proposed method performs better in terms of file uploading time, file downloading time, memory usage in file uploading, memory usage in file downloading, encryption time, decryption time, memory usage on file encryption, memory usage on file decryption, security levels, and key generation time. Compared to the Proxy Re-Encryption (PRE) algorithm, the suggested method consumes less time for key creation (26.04).
Tajinder Kumar, Ramesh Kait, Ankita, and Sunita Rani
IEEE
The area of continuous learning, which addresses the difficulty of learning and adapting in changing contexts, has attracted much interest lately. Although continual learning approaches have seen significant theoretical breakthroughs, applying them in the real world is still difficult. This essay tries to close the knowledge gap between theory and practice by thoroughly analyzing continual learning's practical implications. The authors give case studies and real-world examples from various fields, such as computer vision, natural language processing, robotics, and online learning. We highlight the advantages, constraints, and lessons discovered while implementing continuous learning in real-world situations by looking at these applications. The authors covered the technical issues, like managing limited resources and dealing with concept drift and catastrophic forgetfulness. The authors also look at the organizational and moral repercussions of implementing continual learning systems in real-world contexts. This paper is an invaluable resource for scholars, practitioners, and decision-makers interested in learning more about the opportunities and difficulties of using continual learning techniques to address real-world issues and support systems for lifelong learning.
Tajinder Kumar, Ramesh Kait, Ankita, and Sunita Rani
IEEE
For its potential use in healthcare, Generative Pre-trained Transformers (GPT) and comparable models have attracted a lot of attention. These models present opportunities for therapeutic decision assistance, effective recordkeeping, natural language interactions, and patient education. Their application in healthcare, however, also has some drawbacks and difficulties that need to be properly handled.. The applications of GPT models in healthcare are incredibly broad. Through natural language interactions, they can produce patient education materials, offer decision help to healthcare professionals, and enhance user experience. GPT models offer the potential to improve tele-medicine projects, healthcare process optimization, and patient engagement. They can also help in literature reviews, information retrieval, and medical research, which enable researchers and healthcare practitioners to stay current with evidence-based practices. When applying GPT models in healthcare, a number of issues must be taken into account. These include the limitations of medical knowledge, ethical issues, potential biases and informational errors, legal and regulatory compliance, and the difficulty of having limited contextual awareness. GPT models should be used to support human decision-making rather than to replace medical experts. Critical issues that must be taken into account include patient confidentiality, data security, and the ethical usage of GPT models. To establish credibility and validate the GPT models' outputs in healthcare contexts, improvements to their interpretability and explain ability are required. To guarantee the application and efficacy of GPT models in healthcare, domain-specific adaption and clinical validation are crucial research fields. To properly handle the opportunities and drawbacks of GPT models, collaboration between researchers, healthcare professionals, and policymakers is crucial. The potential for revolutionizing healthcare delivery is enormous with pre-trained Transformers. But the difficulties and potential traps they pose must be carefully considered. GPT models can be ethically implemented and help to improve healthcare outcomes by resolving ethical issues, guaranteeing data privacy and security, and proving their efficacy in clinical situations. For GPT models to be used in healthcare to their fullest potential and to reduce the hazards involved, further research and collaboration are required.
Vikram Verma, Alankrita Aggarwal, and Tajinder Kumar
IEEE
Brain tumor classification and detection utilizing machine learning and deep learning are increasingly becoming the focus of medical image analysis research. Thanks to the advancement of modern imaging technology and machine learning algorithms, it is now possible to accurately and efficiently classify and diagnose brain tumors using a range of methodologies. Machine learning and deep learning algorithms are currently utilized to assess medical images and categorize tumors based on traits such as shape, size, and texture. Convolutional neural networks (CNNs), a popular deep learning technique, are utilized to identify brain tumors in medical pictures precisely. These models were created using large datasets of brain MRI scans and are incredibly accurate in spotting the presence of cancer. These models have been tested and trained using a variety of freely available datasets, such as the Brain Tumour Segmentation (BraTS) dataset and the LGG/GBM dataset. Researchers have developed several methods for preprocessing the data, increasing the dataset, and fine-tuning the models to improve the models' accuracy further. Overall, categorizing and identifying brain tumors using machine learning and deep learning is a rapidly growing field promising to enhance patient outcomes. By accurately and successfully identifying brain tumors, these techniques can lead to earlier detection and more tailored treatments, ultimately improving patient outcomes. The categorization and detection of brain tumors have been enhanced thanks to machine learning and deep learning on various datasets.
Jaswinder Tanwar, Tajinder Kumar, Ahmed A. Mohamed, Purushottam Sharma, Sachin Lalar, Ismail Keshta, and Vishal Garg
MDPI AG
This paper explains the project’s objectives, identifies the key stakeholders, defines the project manager’s authority and provides a preliminary breakdown of roles and responsibilities. For the project’s future, it acts as a source of authority. This paper’s objective is to record the justifications for starting the project, its goals, limitations, solution instructions and the names of the principal stakeholders. This manuscript is meant to be used as a “Project Management Plan Light” for small and medium-sized projects when it would be uneconomical to prepare an entire collection of documents that make up a project management plan. A global media cloud will be provided and managed by the ABC cloud company inside of a consumer’s current premises. In this paper, the authors explain the end-to-end delivery of cloud and compute services. The article mainly focuses on the delivery of virtual machines (VMs), graphics processing unit (GPUs), cloud storage, transcoding, packaging, 24/7 customer support and billing modules for the services used by end customers. The process starts with customer requirements gathering to initiate the feasibility check for the services desired or required by the clients. Pre-sale solution engineers capture all the customer requirements in the solution design document to review with the engineering and delivery team for the implementation. Based on the solution design document, the solution engineer needs to raise the system’s feasibility for the local loops, cross connects, VMs, GPUs, storage, transcoders and packagers required to meet the end customer expectations on the service delivery. The solution engineer must sign-off on the solution design document agreed with end customer from the engineering and technical team. The program manager and technical team review the solution design document and confirm the order ID requirement in the system for the sales team to share with the order entry team to log the orders for a signed customer order form (COF). The program manager will initiate the service delivery for these order IDs logged in to the system for these services. Once services are ready for customer delivery, a technical team will share the customer portal with the end customer and provide training to the teams at the customer end use the required resources for cloud, compute and storage uses. Along with the services mentioned above, customers can access the usage and billing information in the customer portal. Moreover, the program manager is to share the project closure document, including the information about the services, reference IDs to log the trouble ticket with the supplier’s 24/7 support team and billing start date for customer acceptance.
Tajinder Kumar, Shashi Bhushan, and Surender Jangra
Elsevier BV
Tajinder Kumar, Shashi Bhushan, and Surender Jangra
The Science and Information Organization
In the field of wireless multimedia authentication unimodal biometric model is commonly used but it suffers from spoofing and limited accuracy. The present work pro-poses the fusion of features of face and fingerprint recognition system as an Improved Biometric Fusion System (IBFS) leads to improvement in performance. Integrating multiple biometric traits recognition performance is improved and thereby reducing fraudulent access.The paper introduces an IBFS comprising of authentication systems that are Improved Fingerprint Recogni-tion System (IFPRS) and Improved Face Recognition System (IFRS) are introduced. Whale optimization algorithm is used with minutiae feature for IFPRS and Maximally Stable External Regions (MSER) for IFRS. To train the designed IBFS, Pattern net model is used as a classification algorithm. Pattern net works based on processed data set along with SVM to train the IBFS model to achieve better classification accuracy. It is observed that the proposed fusion system exhibited average true positive rate and accuracy of 99.8 percentage and 99.6 percentage, respectively.
Tajinder Kumar, , Dr. Shashi Bhushan, Dr.Surendrer Jangra, , and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
This research presents an improved biometric fusion system (IBFS) that integrates fingerprint and face as a subsystem. Two authentication systems, namely, Improved Fingerprint Recognition System (IFPRS) and Improved Face Recognition System (IFRS), are introduced respectively. For both, Atmospheric Light Adjustment (ALA) algorithm is used as an image quality enhancement technique for the improvement in visualization of acquired fingerprint and face data. Genetic Algorithm (GA) is used as an optimization algorithm with minutiae feature for IFPRS and Speed Up Robust Feature (SURF) for IFRS. Artificial Neural Network (ANN) is used as a classifier for IBFS. For the demonstration of the results, quality based parameters are computed, and in the end, a comparison is drawn to depict the efficiency of the work.The optimization techniques such as Particle Swarm Optimization (PSO) and BFO (Bacterial Foraging Optimization) has been considered to determine the effectiveness of the proposed model.The experimental results consider different parameters such as False Acceptance Rate (FAR), False Rejection Ratio (FRR), Accuracy and Execution time which shows that performance of the proposed model better than the other optimization models. In addition, to enhance robustness of the proposed structure, the results further compared with conventional technique which shows that accuracy has been improved by 2%.
Tajinder Kumar, Shashi Bhushan, and Surender Jangra
Springer Singapore
Lalita Chaudhary, Vikas Deep, Vishakha Puniyani, Vikram Verma, and Tajinder Kumar
Springer India