Dr Rajat Bhardwaj
@jainuniversity.ac.in
Associate Professor/ CSE
Jain University
RESEARCH INTERESTS
Manets, IoT, AIML, Blockchain, Networks, Healthcare, etc
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Rajat Bhardwaj, Priyanka Jaroli, Ruchi Kawatra, Naveen Kumar, and Rajesh Kumar Kaushal
AIP Publishing
Mahesh T.R., Vinoth Kumar V., Rajat Bhardwaj, Surbhi B. Khan, Nora A. Alkhaldi, Nancy Victor, and Amit Verma
Elsevier BV
Raj Gaurang Tiwari, Abeer A. Aljohani, Rajat Bhardwaj, and Ambuj Kumar Agarwal
De Gruyter
Mahesh Thyluru Ramakrishna, Vinoth Kumar Venkatesan, Rajat Bhardwaj, Surbhi Bhatia, Mohammad Khalid Imam Rahmani, Saima Anwar Lashari, and Aliaa M. Alabdali
MDPI AG
Today, people frequently communicate through interactions and exchange knowledge over the social web in various formats. Social connections have been substantially improved by the emergence of social media platforms. Massive volumes of data have been generated by the expansion of social networks, and many people use them daily. Therefore, one of the current problems is to make it easier to find the appropriate friends for a particular user. Despite collaborative filtering’s huge success, accuracy and sparsity remain significant obstacles, particularly in the social networking sector, which has experienced astounding growth and has a large number of users. Social connections have been substantially improved by the emergence of social media platforms. In this work, a social and semantic-based collaborative filtering methodology is proposed for personalized recommendations in the context of social networking. A new hybrid collaborative filtering (HCoF) approach amalgamates the social and semantic suggestions. Two classification strategies are employed to enhance the performance of the recommendation to a high rate. Initially, the incremental K-means algorithm is applied to all users, and then the KNN algorithm for new users. The mean precision of 0.503 obtained by HCoF recommendation with semantic and social information results in an effective collaborative filtering enhancement strategy for friend recommendations in social networks. The evaluation’s findings showed that the proposed approach enhances recommendation accuracy while also resolving the sparsity and cold start issues.
Md. Mehedi Hassan, Sadika Zaman, Swarnali Mollick, Md. Mahedi Hassan, M. Raihan, Chetna Kaushal, and Rajat Bhardwaj
Springer Science and Business Media LLC
Ankit Kumar, Surbhi Bhatia, Rajat Bhardwaj, Kamred Udham Singh, Neeraj varshney, and Linesh Raja
Springer Science and Business Media LLC
Shailaja Salagrama, Rajat Bhardwaj, J. Logeshwaran, and Rishi Prakash Shukla
IEEE
This study aims to evaluate the usage of three-dimensional (3D) magnetic resonance imaging (MRI) for determining the composition of athermanous plaques gift in the arterial partitions of sufferers. Atherosclerosis is a continual and innovative disease characterized by the build-up of lipid-wealthy plaques inside the arteries. It is the main reason for coronary artery disease and stroke. These plaques can rupture, mainly to a thrombus that could result in addition to damage to the arteries' partitions. The usage of 3D MRI for the assessment of extreme, huge plaques is high-quality in imparting critical data on the composition and, therefore, the stability of the plaque. This approach shows promise in assisting the choice-making system by imparting valuable statistics on plaques' dimensions, morphology, and traits. Furthermore, it can predict the development of arterial thrombosis and the want for open surgical tactics.
J. Logeshwaran, Rajat Bhardwaj, Shailaja Salagrama, and Abhijit Das
IEEE
the paper discusses a way of growing the capability of severe deep learning machines (ELM) for biomedical informatics programs. This technique involves varying the dimensions of the training set, the variety of neurons in the hidden layer, the kind of activation function used, the range of different sorts of neurons used and the regularization techniques used.so that it will maximize the ability of ELM fashions for biomedical informatics applications, the authors advocate using a stepwise seek technique to determine the fine combination of parameters. This technique entails first defining a baseline or initial configuration of ELM parameters and then iteratively enhancing that configuration via deep learning from the empirical effects of each optimization step. distinctive regularization strategies are carried out at every optimization step which could involve pruning hidden neurons as a way to reduce the complexity of the model. The authors verified their technique on publicly to be had datasets consisting of the Michigan Imputation of missing Values (MIMV) dataset and on a dataset of clinical records from the branch of Anesthesiology, branch of health and Human services.
V. Aravinda Rajan, T. Marimuthu, Rajat Bhardwaj, and Rishi Prakash Shukla
IEEE
An enhanced active reinforcement learning technique has been proposed to enable autonomous robots to operate and execute tasks in industrial automation. This approach combine hierarchical reinforcement learning and Bayesian optimization, to acquire knowledge from complex real-world environments and acquire optimal policies which can enable autonomous robots to perform collaborative tasks efficiently. The main advantage of this enhanced active reinforcement learning approach is the capability of the autonomous robot to autonomously adapt its movements and decision-making strategies when new tasks are required. It allows for the robot to explore its environment and learn how to complete tasks optimally while reducing the burden of manual intervention. Moreover, the proposed approach can generalize its knowledge to establish rewarding collaborative behaviors between robots and humans, thus allowing for collaborative human-robot interactions. This will be beneficial in performing industrial automation with robot cooperative tasks and optimize the efficiency of the industrial automation system..
Raja Praveen K N and Rajat
IEEE
In the era of cloud networking, database protection is a problem that is becoming more and more crucial, and blockchain technology is emerging as a potent remedy. Blockchain is a digital ledger technology that uses an immutable, distributed, and decentralized record of transactions to build a secure, transparent, and auditable data protection system. The integrity of data saved in the cloud is further ensured by using blockchain technology. By using cryptographic hashes, data stored on the blockchain can be verified for accuracy and authenticity. This means that any changes or modifications to the data will be detected and addressed. Furthermore, blockchain technology provides a permanent and immutable record of transactions, making it difficult for data to be tampered with or corrupted. In addition to its security benefits, blockchain technology also offers scalability, efficiency, and cost savings. Blockchain-based databases are much more efficient than traditional databases, as they require fewer resources and are able to process a larger volume of transactions. Furthermore, since blockchain technology is decentralized, it can work across multiple devices and networks, allowing for a more efficient and cost-effective solution.
Rajat, Priyanka Jaroli, Chaitanya Singla, Vivek Bhardwaj, and Srikanta K Mohapatra
IEEE
Nowadays each and every person connected through the digital platform. The digital market take place the physical market. People purchase everything not going physically on market and buy everything. In the e-commerce platform initially, people purchase any product firstly read the review regarding the product as well as organization provided by the previous customer. The paper illustrates a sentiment analysis on the huge amazon customer review data from the e-commerce website. Initially the dataset in the json format and preprocessing on the data set and convert the dataset into CSV file. Secondly, load the dataset and break the collective information into the training and testing information. Using the method inverse document frequency and term frequency and get features of the information dataset. At last, the deep learning model is use and evaluate the reviews of the customer. The result final outcomes result shows the model precision, recall, f-measure, accuracy and time of the developed model on the real text data.
V Vivek and Rajat
IEEE
Since the computer’s invention, every subject of knowledge has been digitalized, allowing computer users to view all available information. Because of this, data in every industry is growing exponentially. This article explains why researchers study agriculture. We projected three new classification approaches to overawe these restrictions: Hybrid KNN classification methods produce and choose prototypes from an initial training set. These methods include training set reduction KNN, which uses prototype selection to reduce training sets, training set reduction, which creates training set prototypes utilizing either the Elbow or Silhouette technique, and hybrid classification approaches, which use both prototype generation & selection mechanisms. If any of these strategies are to succeed, the KNN classifier must finish its classification work faster and use less space. Utilizing a soil fitness card agricultural dataset, we tested our unique classification algorithms and found that they solve our concerns.
Hamnah Rao, Meenu Gupta, Parul Agarwal, Surbhi Bhatia, and Rajat Bhardwaj
Springer Science and Business Media LLC
Rajesh Kumar Kaushal, Rajat Bhardwaj, Naveen Kumar, Abeer A. Aljohani, Shashi Kant Gupta, Prabhdeep Singh, and Nitin Purohit
Hindawi Limited
Mobile computing and technology are becoming more common in many parts of private life and public services, and they are playing an increasingly important role in healthcare, not just for sensory devices but also for communication, recording, and display. They are used for more than only sensory devices but also for communications, recording, and display. Numerous medical indications and postoperative days must be monitored carefully. As a result, the most recent development in Internet of Things- (IoT-) based healthcare communication has been embraced. The Internet of Things (IoT), which is employed in a wide range of applications, is a catalyst for the healthcare industry. Healthcare data is complicated, making it difficult to handle and evaluate in order to derive useful information for decision-making. On the other hand, data security is a vital requirement in a healthcare data systems. Determining the need for a smart and secure IoT platform for healthcare applications, we create one in this study. Here, a cutting-edge encryption algorithm is used to protect the health data. Normalization is first used to preprocess the data and remove any irrelevant information. Using principal component analysis and logistic regression, the data’s features are extracted (LR-PCA). To choose the pertinent features, a feature selection process based on genetic algorithms is used. We have put out a brand-new kernel homomorphism. To increase the security of the IoT network, use the two-fish Encryption algorithm (KHTEA). EBSMO (exponential Boolean spider monkey optimization) is used to further boost the encryption process’ effectiveness. Utilizing the MATLAB simulation tool, the proposed system is assessed, and the metrics are contrasted with the accepted practices. Our suggested solution has been shown to be effective in protecting medical healthcare data. The effectiveness of the proposed and existing approaches is assessed using metrics for encryption time, execution time, and security level. The security precautions we suggested for healthcare data worked well.
Abeer A. Aljohani, Priyanka Jaroli, and Rajat Chitkara
IEEE
In the modern era each and every thing is digital. E- commerce takes the place of the physical market. People buy anything not going physically anywhere and they are used the E-commerce platform. When The people buy, initially read the reviews provided by the previous customer regarding the product and decide they buy or not. So, the reviews are most essential part of the customer as well as for the customer. This paper delineates the sentiment analysis (SEAN) of the cell amazon real data values initially, use the NLTK, Porter Stemmer and various processing for pre-process the data and get the clean and desired data. Secondly, use the term frequency inverse document frequency (TFIDF) method for extracting the feature and divide the data using the train and test split and last apply the K-nearest neighbor method to train the machine. The artificial model predicts the positive and negative reviews. The experiment outcome result shows the model accuracy, precision, recall of the novel developed algorithm on the real text set.
Sumeet Gupta, M. K. Sharma, Rupinder Singh, Hashem Ali Almashaqbeh, Rajat, and Durgaprasad Gangodkar
IEEE
Due to the proliferation of smart devices in the Internet of Things (IoT) connections, significant security concerns for device-to-device connectivity have been raised. Blockchain is a decentralized and shareable technology that may be used to overcome security challenges in 5 g networking and Internet of Things networks, among other things. This research provides a multi-layer Blockchain Security model that may be used to protect IoT networks while also making their implementation simpler. The grouping idea is used to ease the multi-layer design. Inside this IoT network, the K-unknown groups are formed utilizing methodologies that use hybrid Adaptive Computational Algorithms as well as Evolutionary Techniques & Genetic Algorithms. The group leaders selected are in charge of regional identification & permission. Communications among-st group chiefs & appropriate core networks are facilitated by privately run blockchain implementations. A blockchain of this kind improves reputation verification & confidentiality while also serving as a networking identification method. For the suggested concept construction, the accessible Hyperledger Fabric Blockchain technology is used. Ground stations use a worldwide blockchain architecture to seamlessly interact with one another.
R. Shashikala, Bhaskar Pratap Singh, Mohammed Azam, C R Magesh, Rajat, and Devesh Pratap Singh
IEEE
As we all know that internet of things has now become a vital part of our generation and it has a rapid growth in the field many people see this as the next big thing but they are very much unaware of its norms and benefits it has been estimated that by the end of 2022 to there may be about 50to 60 billion internets of things are going to be installed in our rapidly growing world there are numerous benefits of the internet of things in today's fast-growing and running world but there are numerous backward points are too which make the internet of things that should be handled with care in the right hands basically what are internet of things or the thing we call as IOT so these are the touchable objects which are attached in with sensors, processing abilities, software and other technologies that connect and exchange and process data. automation in manufacturing, farming techniques, surveillance equipment, traceability, decision - making process, and prediction have the potential to transform agricultural production and the food business. Nanotechnology leads to more efficient pesticide use and more advanced agricultural production processes. More efficient, sustainable, and precise agricultural operations, as well as enhanced food processing, will result in increased output and profitability while using less raw and non-renewable resources.
Isha Kansal, Renu Popli, Jyoti Verma, Vivek Bhardwaj, and Rajat Bhardwaj
IEEE
Health care and well-being are concerned with the upkeep or maintenance of humans through preventative medicine, diagnosis, therapies, regeneration, or prevention of disease, ailment, injury, and other health-related conditions in people. Healthcare is unique in comparison to other industries. It is an elevated segment, and people expect the best possible care and services at all costs. Through continuous integration and resource optimization, the use of IoT technology in health applications enables the health care industry to improve care quality while lowering costs. The IoT in diagnostic imaging enables real-time identification and correction of imaging apparatus parameters due to the ease with which imaging apparatus parameters can be auto-analyzed. This paper discusses the impact of online image processing methods in IoT-based health care, which can be beneficial in the health sector for predicting some major human diseases. Due to individuality, image complex nature, extensive variation between interpreters, and fatigue, human experts' ability to interpret images is quite limited. We focus on the role of Digital Image Processing in disease detection, Image Dataset Preparation for Machine and Deep Learning, the role of Digital Image Processing in IOT based applications of health care, a case study of IoT-based healthcare application of disease classification.
Rajat Rajat, Priyanka Jaroli, Naveen Kumar, and Rajesh Kumar Kaushal
IEEE
Nowadays everything is digitalized in the world. In the digitalization world E-commerce take a unique place for people. People are not going anywhere and buy all the thing at home using this E-commerce platform. For selecting the platform generally used the reviews of the people which are already buy from there. The paper proposes a sentiment analysis of the large amazon real dataset based on the counter vectorizer (CV) and term frequency inverse document frequency (TF-IDF) and logistic regressor. Firstly, take the dataset from the amazon E-commerce into JSON format and load the dataset and split the dataset into train test model. Secondly, take out the features using the counter vectorizer and term frequency inverse document frequency (TF-IDF). Finally, logistic regressor (LR) is used and measure the positive and negative sentiment of the review. simulation result represents the model accuracy score, precision, recall, confusion matrix of the implemented approach.