Dr.Inderpreet Kaur
Verified @gmail.com
RESEARCH, TEACHING, or OTHER INTERESTS
Health Information Management, Computer Networks and Communications, Computer Engineering, Computer Science Applications
FUTURE PROJECTS
An efficient Remote Patient Monitoring: The merge of Blockchain and Artificial Intelligence"
In recent years, the healthcare landscape has undergone a significant evolution, with a pronounced shift towards remote patient monitoring (RPM). This transition is fueled by technological advancements and the increasing demand for accessible and effective healthcare solutions. Central to this evolution are blockchain and artificial intelligence (AI), two cutting-edge technologies converging to redefine RPM systems. This paper investigates the fusion of blockchain and AI in RPM, presenting a pioneering approach that enhances patient care, data security, and operational efficiency.
Applications Invited
collaborators
Scopus Publications
Scopus Publications
Inderpreet Kaur, Yashica Chauhan, Utsav Gupta, and Sagar Malik
IEEE
CryptoBot is a groundbreaking automated cryptocurrency trading system that answers the issues faced by traders in an environment where market dynamics change swiftly. Hence, CryptoBot employs a holistic approach of data gathering, preprocessing, predictive modelling, and real-time decision-making, thus it keeps analyzing real-time market data. The system then uses state of the art machine learning algorithms to make accurate predictions about price movements and determine when to enter and exit trades. This program also shows very promising results indicating a significant improvement in trading performance compared to traditional human-based strategies. CryptoBot therefore becomes an instrument of innovation for both experienced and non-experienced cryptocurrency investors. Thus, with its flexibility, precision, and smart automation users become more competitive reshaping how the investor interacts with the volatile but lucrative world of cryptocurrencies. As digital assets continue to reshape finance, CryptoBot stands at the forefront, exemplifying the future of intelligent trading.
Gagandeep Kaur, Ruchika Bindal, Veerpal Kaur, Inderpreet Kaur, and Sunil Gupta
AIP Publishing
Renu Mishra, Inderpreet Kaur, Santosh Sahu, Sandeep Saxena, Nitima Malsa, and Mamta Narwaria
Elsevier BV
Inderpreet Kaur, Renu Mishra, Mamta Narwaria, and Sandeep Saxena
IGI Global
With the progressive growth in the adaptability of the Blockchain technology with flexible solutions, various industries, academicians and researchers are paying attentions in such area to explore Nobel opportunities. Due to its qualities like decentralization, immutability, and encryption, block chain has the potential to shift the hierarchy of healthcare also. This area has observed many benefits of Blockchain technology, but still people have hesitations to adapt it due to lack of standardization, high cost, lack of awareness, and lack of technical knowledge to implement it. This chapter aimed to showcase the potential for block chain technology in the tale care system.Various BC based models and frameworks are discussed to cover various stages of secured data transfer for patient empowerment. This covers all technological issues in storing medical records in the various application areas where block chains will provide secured and authenticated transfers of patient personal data.
Jyoti Verma, Vidhu Baggan, Inderpreet Kaur, Monika Sethi, Manish Snehi, and Shilpi Harnal
IEEE
Due to the increased reliance on technology in modern times, the likelihood of cyberattacks has increased. With the advent of remote working and internet business, the threat landscape has grown, making it harder for enterprises to defend their data and systems. As a result, robust cybersecurity measures, such as footprinting techniques, are more important than ever before. Footprinting can assist businesses in recognizing possible vulnerabilities in their networks and systems, enabling them to take preventative steps to bolster their security posture. Also, it can assist companies in identifying possible dangers and preventing attacks before they materialize. Footprinting is a crucial component of the pre-attack stage of a cyber-attack, as it helps attackers discover the most vulnerable locations in a network or computer system. This work explores the artificial intelligence for Footprinting and evaluates two widely-used classifiers, Decision Tree and Naive bayes, employing precision and recall parameters. The DT classifier has a higher success rate in recognising certain sorts of attacks, whereas the Naive-Bayesian classifiers has a greater rate of accuracy in detecting a wide variety of fraudulent activity. During the first stage of the research, both classifiers obtain outstanding recall and accuracy rates, with the DT classifiers achieving a recall and precision of 99% and the Naive-Bayesian method earning an average recall and precision of 98%. The results indicate that the efficacy of these classifier depends on the particular qualities of the data and the classification task's objectives. The study emphasises the footprinting potential of machine learning.
K. Babu, K Subramani, Ahmad Hussein Alawady, Ahila R, Inderpreet Kaur, and B. Gunapriya
IEEE
With the rapid improvement of market economy and modern logistics technique, the logistics distribution link is receiving more and more attention, and the logistics distribution path question in distribution has become the core question in logistics distribution. Study the optimization of logistics distribution path. Logistics distribution path optimization needs to find an optimal distribution route with less distribution vehicles and the shortest total length of the path, and has the rapidity of distribution. The traditional algorithm takes a long time to search the optimal route, which makes it difficult to find the optimal distribution route, resulting in high logistics distribution costs. In order to quickly find the optimal distribution route and improve the quality of logistics service, a logistics model based on particle swarm optimization algorithm is proposed. The group is composed of several non-intelligent individuals or groups of individuals. Each individual's behavior follows certain simple rules and has no intelligence; Individuals or groups of individuals can cooperate to solve questions through certain principles of message exchange, thus showing the behavioral characteristics of collective intelligence. After research, the algorithm in this paper is effective and suitable for wide application in practice.
Gagandeep Kaur, Inderpreet Kaur, Shilpi Harnal, and Swati Malik
Wiley
Sanjay Kumar, Sanjeev Kumar Singh, Naresh Kumar, Kuldeep Singh Kaswan, Inderpreet Kaur, and Gourav Mitawa
CRC Press
Surya Pratap Singh, Siddharth Kumar, Shivani Verma, and Inderpreet Kaur
IEEE
Even though emotions don’t have much to do with the content of the speech, it has a major impact on human communication by providing much more positive feedback. Therefore, Speech emotion recognition (SER) and multimodal emotion recognition systems have been a hot area of research owing to their range of applications in several domains, such as social robots, virtual reality, and human-machine interaction applications. This paper compares two models by choosing multi-dimension CNN models and features for SER on the RAVDESS dataset.
Vanshit Gupta, Vansh Verma, Supreet Kaur, and Inderpreet Kaur
IEEE
As technology advances, massive amounts of data in many different formats are produced everywhere. The industries that have fueled the growth of data, including retail, media, finance, healthcare, and education, have produced a tremendously large and complicated collection of data that is known as "big data." On the other hand, a virtual service called cloud computing is utilised for processing, data storage, and data mining in order to maximise flexibility and cut costs. It is assisting society in addressing upcoming issues, including large data management, cyber security, and quality control. Additionally, cutting-edge technologies like distributed ledger technology, artificial intelligence, and many other capabilities are becoming accessible as services thanks to cloud computing. The two most important techniques in the field of information technology. These two IT efforts have the potential to transform every aspect of the company and have an impact on how we analyse data. It’s become popular in research to use the cloud environment for large data analysis. This work attempts to comprehend the Cloud Computing technology in Big Data so as to obtain efficient and quick results. Furthermore, the paper sheds light on the challenges faced in the domain and concludes with the future scope of these technologies.
Inderpreet Kaur and Arvinder Kaur
Springer Singapore
Inderpreet Kaur and Arvinder Kaur
Springer Science and Business Media LLC
Inderpreet Kaur, Vibha Tripathi, and Nidhi
CRC Press
Inderpreet Kaur, Parth Pulastiya, and Vivek Anil Pandey
Springer Singapore
Inderpreet Kaur and Arvinder Kaur
Institute of Electrical and Electronics Engineers (IEEE)
Purpose: Code smells are residuals of technical debt induced by the developers. They hinder evolution, adaptability and maintenance of the software. Meanwhile, they are very beneficial in indicating the loopholes of problems and bugs in the software. Machine learning has been extensively used to predict Code Smells in research. The current study aims to optimise the prediction using Ensemble Learning and Feature Selection techniques on three open-source Java data sets. Design and Results: The work Compares four varied approaches to detect code smells using four performance measures Accuracy(P1), G-mean1 (P2), G-mean2 (P3), and F-measure (P4). The study found out that values of the performance measures did not degrade it instead of either remained same or increased with feature selection and Ensemble Learning. Random Forest turns out to be the best classifier while Correlation-based Feature selection(BFS) is best amongst Feature Selection techniques. Ensemble Learning aggregators, i.e. ET5C2 (BFS intersection Relief with classifier Random Forest), ET6C2 (BFS union Relief with classifier Random Forest), and ET5C1 (BFS intersection Relief with Bagging) and Majority Voting give best results from all the aggregation combinations studied. Conclusion: Though the results are good, but using Ensemble learning techniques needs a lot of validation for a variety of data sets before it can be standardised. The Ensemble Learning techniques also pose a challenge concerning diversity and reliability and hence needs exhaustive studies.
Sanjay Kumar, Naresh Kumar, Rishabh, Inderpreet Kaur, and Vivek Keshari
Radiance Research Academy
Introduction: Brain tumours are the most known and aggressive disorder, leading to a poor lifetime at the highest level. Treatment is one of the main benefits of development that saves a life. Imagery is used to analyse the tumour in brain, lung, liver, bosom, neck, etc, through tomography, appealing reverb imagery (MRI) and ultrasound imaging. And that's it. Objective: In this study, in particular, the tumour of the mind is examined through enticing reverse imagery. The enormous amount of knowledge produced by the MRI scanner, however, at any one time obstructs the manual tumour against non-tumour order. Result: The process has had several challenges, as computations for several images are reliable. An unambiguous necessity is to increase the survival rate of the programmed order. The scheduling of the mind tumour is an incredibly problematic task in the exceptional spatial and basic fluctuation that accompanies the local brain tumour. Conclusion: In this research, a programmed exploration of mind tumours is proposed using the characterization of convolution neural networks (CNNs). The most important type of composition is the completion of the use of small pits. CNN's paper has less predictability and 97.5 accuracies.
Paridhi Baliyan, Prakhar Chandra, Sukriti Srivastava, and Inderpreet Kaur
IEEE
Cryptography is the methodology in which the information is cast into a form that forestalls the abuse of it. In this advanced time of the wireless, it is imperative to guarantee the safe conveyance of the pertinent information which are otherwise exposed to disgusting goals. The procedure of transformation of plaintext to encode text is known as encryption and its converse is known as decryption. The three kinds of cryptography methods, viz., Asymmetric key, Symmetric-key, and Hash Functions. A huge segment of this contemporary method is the key; which is a specific component of extreme significance, as this is what is utilized while scrambling or descrambling the desired information. In this paper, we have compared the two techniques. Incipiently, Particle Swarm Optimization, a strategy of delivering keys to design a stream figure for text encryption. The tale methodology named Particle Swarm Optimization Key Generation Algorithm (PKGA) uses a character code table for encoding the keys. The essential ideal situation of this procedure is that it diminishes the quantity of keys to be fused and coursed. On the other hand is Ant Colony Optimization Techniques to produce keys for the encryption of the information. This entire philosophy depends on the conduct of the ants in their characteristic inquiry of food. The drawback of using Ant Colony Optimization is to downscale the number of keys to be utilized during encipherment when contrasted with different strategies of cryptography in presence. ACO would warrant the generation of such keys with utmost proficiency.
Dr. Inderpreet Kaur
Institute of Advanced Scientific Research
Inderpreet Kaur, Lakshay Rohilla, Alisha Nagpal, Bishwajeet Pandey, and Sanchit Sharma
Springer Singapore
Arvinder Kaur and Inderpreet Kaur
Elsevier BV
Inderpreet Kaur and Arvinder Kaur
ACM
Software Quality is an important nonfunctional requirement which is not satisfied by many software products. Prediction models using object oriented metrics can be used to identify the faulty classes. In this paper, we will empirically study the relationship between object oriented metrics and fault proneness of an open source project Emma. Twelve machine Learning classifiers have been used. Univariate and Multivariate analysis of Emma shows that Random Forest provides optimum values for accuracy, precision, sensitivity and specificity.