Dr. C.L.P. Gupta

Scopus Publications

A Review Paper on Intelligent Heuristic-based Deep Learning Structure for the Observation of Breast Cancer
Manish Kumar Soni, C. S. Raghuvansi, and C. L. P. Gupta
AIP Publishing

Comparative Analysis of Deep Learning Techniques for Prediction of Protein Structure
Sunit Kumar Mishra, Sudhakar Tripathi, and C. L. P. Gupta
Springer Nature Switzerland

Deep Learning Application in PQRS Segment Detection in ECG Data
Amit Kumar Pandey and C. L. P. Gupta
IEEE
The electrocardiogram is a vital piece of information about a person's health that provides measurements of changes in the cardiovascular system. When using complex software modules to diagnose diseases, the clinical ECG signal is always tainted by power line interference and electromagnetic fields, leading to inaccurate results.Therefore, it's critical to reduce these ECG data acquisition recording inaccuracies in order to perform precise clinical analysis. We are working on an algorithm that will split the data array of three successive ECG signals into three equivalents. The Empirical Mode After decomposing the data matrix and running it through the Independent Component Generation algorithm, we will identify and remove any noisy components using deep learning scheme. To obtain an error-free result of ECG data, we will then apply reverse ICA and EMD features for deep learning.

Integrity Evaluation Model for Object Oriented Software: A Developer Perspective
Vivek Gupta and C L P Gupta
IEEE
Software integrity stands as a paramount element in software development. Evaluating integrity through design properties proves more fitting, and its validation underscores the genuine impact of structural and functional aspects in object-oriented design software. Integrity serves as a crucial quality indicator, and gauging it opens avenues for streamlining and enhancing the maintenance process. Software integrity offers valuable insights throughout the phases of design, coding, testing, and quality assurance. Both researchers and practitioners emphasize the desirability and significance of the integrity aspect in developing secure and robust software. Despite its vital role in the software development process, integrity is often inadequately managed. This paper underscores the necessity and significance of integrity during the design phase and endeavors to establish a substantial correlation between integrity and design properties. In light of this, a model is proposed for evaluating integrity in object-oriented design through the establishment of multiple linear regressions. Ultimately, the proposed model undergoes validation through experimental trials.

Quantification of Reliability in Object-Oriented Software: Functionality Perspective
Anuj Kumar Yadav and C L P Gupta
IEEE
Object-oriented design and development are now commonly used in software development environments. Important design concepts including inheritance, coupling, cohesion, and encapsulation are supported by this method. The work in progress aims at offering a functionally-based, robust estimating technique for object-oriented design. Functionality plays a critical part in producing high-quality products within predetermined time and cost limits. This paper introduces an approach for quantifying functionality and reliability, acknowledging the paramount importance of functionality during the design phase. Statistical analyses affirm functionality as a significant factor influencing software reliability. Building on the proposed mapping of object-oriented design features to functionality, a multiple regression equation has been constructed to calculate the functionality of design hierarchies. It is clear that usefulness has a favourable effect on object-oriented systems’ dependability. In order to determine dependability based on functionality, an additional multiple regression equation is created. Lastly, experimental trials are used to validate the suggested model.

Detection of COVID-19 Disease Using Federated Learning
Saurabh Dixit and C. L. P. Gupta
Springer Nature Switzerland

Futuristic trends in vehicle communication based on iot and cloud computing
Chhote Lal Prasad Gupta and Shashank Gaur
Chapman and Hall/CRC

Machine Learning Based Flexibility Evaluation Model: An Empirical Validation
Abdullah and C.L.P. Gupta
IEEE
Programming engineers and maintainers need to peruse and comprehend source programs and other programming relics. The expansion in size and intricacy of programming impressively influences a few quality credits, exceptionally flexibility and viability. Bogus investigation frequently prompts misconception, ambiguities and subsequently to broken advancement results. In spite of the way that product flexibility is vital and one of the main element of the product improvement lifecycle, it is inadequately made due. This is principally because of the absence of its appropriate administration and control. The paper features the meaning of flexibility overall and as a central point of programming viability. In this paper a work has been completed to lay out a relationship amongst object situated plan possessions and flexibility as a first influence. A flexibility assessment model has been proposed for object oriented software by laying out various design metrices. All in all the flexibility assessment model has been validated utilizing experimental tryout.

Deep Learning Based Object Oriented Software Estimation: A Case Of Reusability
Abdullah and C.L.P. Gupta
IEEE
The software development stages supported by deep learning techniques in view of the collection of software engineering promises, it is essential to see the current software engineering requirements helped through deep learning, by seeing it various supports experts find the feasible to use deep learning information to deliver commercial software by considering functional and nonfunctional requirements. A Reusability assessment model for object oriented design particularly for design phase of development life cycle has been developed in this research paper with the help of deep learning technique. The developed system relates the Reusability orientated diagram qualities with software maintenance requirements and also connects feasibility with Reusability. No such model has been currently available in the literature review that measures Reusability of OO diagram through bringing practicality into consideration utilizing deep learning. The proposed model overcomes any barrier among object orientated outline qualities, practicality and Reusability. Proposed efforts works in order to improve the overall software design quality by considering the quality key attributes especially reusability of software design at initial stage of development life cycle. Finally in view of the above truth proposed model has been developed and validated with the help of class diagrams.

Malicious Traffic Classification in WSN using Deep Learning Approaches
Chhote Lal Prasad Gupta, Dinesh Rajassekharan, Dilip Kumar Sharma, Mohanraj Elangovan, Varatharaj Myilsamy, and Kamal Upreti
IEEE
Classifying malicious traffic in Wireless Sensor Networks (WSNs) is crucial for maintaining the network's security and dependability. Traditional security techniques are challenging to deploy in WSNs because they comprise tiny, resourceconstrained components with limited processing and energy capabilities. On the other hand, machine learning-based techniques, such as Deep Learning (DL) models like LSTMs, may be used to detect and categorize fraudulent traffic accurately. The classification of malicious traffic in WSNs is crucial because of security. To protect the network's integrity, data, and performance and ensure the system functions properly and securely for its intended use, hostile traffic categorization in WSNs is essential. Classifying malicious communication in a WSN using a Long Short-Term Memory (LSTM) is efficient. WSNs are susceptible to several security risks, such as malicious nodes or traffic that can impair network performance or endanger data integrity. In sequential data processing, LSTM is a Recurrent Neural Network (RNN) appropriate for identifying patterns in network traffic data.

Compressed Deep Learning and Transfer Learning Model for Detecting Brain Tumour
Saurabh Dixit and C.L.P. Gupta
IEEE
The accurate detection of brain tumors is of paramount importance in medical imaging for early diagnosis and effective treatment planning. In this study, we explore the application of deep learning and transfer learning techniques to detect brain tumors using medical images. Our proposed model incorporates VGG16, VGG19, and EfficientNetB3, with EfficientNetB3 utilized as the transfer learning base. Remarkably, our model achieves an impressive accuracy of 92% for brain tumor detection. In this article a genetic algorithm-based compression approach is used to reduce model size and computational demands, while ensuring accuracy is preserved. The outcomes demonstrate substantial reductions in storage space and improved inference time. Our literature review underscores the efficacy of deep learning and transfer learning in brain tumor detection, indicating promising applications in healthcare. Overall, this research contributes to the advancement of medical imaging and brain tumor diagnosis, presenting a valuable tool for medical professionals in their endeavors to combat this life-threatening disease.

Comparative Result Analysis of Optimization Techniques in Convolutional Neural Network for Prediction and Diagnosis of Monkey Pox
Madhukar Dwivedi, C.L.P Gupta, and Raj Gaurang Tiwari
IEEE
Today the entire world has to face virus attacks from various sources. The carrier sources of these viruses comprise animals, insects, and birds. As the world just came out from a disastrous pandemic of the century. The human race might have to face another threat of virus attack in the form of monkeypox. This virus can be turned into a pandemic if society fails to take preventive measures beforehand. These preventive measures include early detection, timely medication, and prevention to spread among the masses. A pandemic could soon be proclaimed because of the widespread infection that has been detected in more than 1/3 nations worldwide. Because of a trait that makes it difficult to distinguish between chickenpox, measles, and monkeypox. In this paper, it is suggested that deep learning methods be used to distinguish monkeypox from others through image data. The accuracy of prediction is improved by using boosting approach with the Convolutional Neural Network model. The data set was gathered from multiple sources through web scraping. This study offers a comparison of the prediction accuracy both before and after boosting.

Protein classification using machine learning and statistical techniques
Chhote L. P. Gupta, Anand Bihari, and Sudhakar Tripathi
Bentham Science Publishers Ltd.
Background: In the recent era, the prediction of enzyme class from an unknown protein is one of the challenging tasks in bioinformatics. Day-to-day, the number of proteins increases which causes difficulties in clinical verification and classification; as a result, the prediction of enzyme class gives a new opportunity to bioinformatics scholars. The machine learning classification technique helps in protein classification and predictions. But it is imperative to know which classification technique is more suited for protein classification. This study used human proteins data that is extracted from the UniProtKB databank. A total of 4368 protein data with 45 identified features were used for experimental analysis. Objective: The prime objective of this article is to find an appropriate classification technique to classify the reviewed as well as un-reviewed human enzyme class of protein data. Also, find the significance of different features in protein classification and prediction. Methods: In this article, the ten most significant classification techniques such as CRT, QUEST, CHAID, C5.0, ANN, SVM, Bayesian, Random Forest, XgBoost, and CatBoost have been used to classify the data and discover the importance of features. To validate the result of different classification techniques, accuracy, precision, recall, F-measures, sensitivity, specificity, MCC, ROC, and AUROC were used. All experiments were done with the help of SPSS Clementine and Python. Results: Above discussed classification techniques give different results and found that the data are imbalanced for class C4, C5, and C6. As a result, all of the classification techniques give acceptable accuracy above 60% for these classes of data, but their precision value is very less or negligible. The experimental results highlight that the Random forest gives the highest accuracy as well as AUROC among all, i.e., 96.84% and 0.945, respectively, and also has high precision and recall value. Conclusion: The experiment conducted and analyzed in this article highlights that the Random Forest classification technique can be used for protein of human enzyme classification and predictions.

Rat protein’s enzyme class classification using machine learning
Chhote Lal Prasad Gupta, , Anand Bihari, Sudhakar Tripathi, , and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
In the current era, bioinformatics has been an emerging research area in the context of protein enzyme classification from the unknown protein data. In bioinformatics, the prime goal is to manipulate the protein data and develop a computational technique to classify and predict the appropriate features for function predictions. In this context, several machine learning and statistical technique have been designed for classification of data. The classification of protein data is one the challenging task and generally the classification of protein data has been done on human protein data. In this article, we have considered rat enzyme class for classification and predictions. Here we have used like CRT, CHAID, C5.0, NEURAL, SVM, and Bayesian for classification of protein data and to measure the performance of the model, the accuracy, specificity, sensitivity, precision, recall, f-measures and MCC have been used. The experimental result highlights that the some of the protein data are imbalance that affects the performance. In this experiment, the Lyases, Isomerases and Ligases class of data are imbalanced and affect the performance of the models. The experimental results highlight that the C5.0 gives 91.5% accuracy and takes only 4 second for computation and can be used for protein classification and prediction of protein data.

Human protein sequence classification using machine learning and statistical classification techniques
ChhoteLal Prasad Gupta, , Anand Bihari, Sudhakar Tripathi, , and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
In the field of computational biology, to gauge the meaningful and accurate feature for protein function predications, either the profile-based protein data or sequence-based data has been used. As we know that the prediction of enzyme class from an unknown protein is most interacted research in the current era. In this context, machine learning and statistical classification technique has been used. In this article, we have use six different machine learning and statistical classification technique such as CRT, QUEST, CHAID, C5.0, ANN and SVM for classification of 4314 number of human protein sequence data. These data are extracted form UniprotKB databank with the help of PROFEAT server. The extracted data are categorized in seven different classes. To manipulate the high dimensional protein sequence data with some missing value, the SPSS has been used for classification and estimation of the performance of classification technique. The experimental results highlight that the class C4, C5, C6 and C7 data are imbalanced that affect the overall performance of classification technique. This article provides an extensive comparative analysis of different classification technique on sequence-based protein data. The experimental analysis highlights that the SVM and C5.0 classification technique gives better result than others and can be used for protein classification and predictions.

Dr. C.L.P. Gupta

EDUCATION

RESEARCH, TEACHING, or OTHER INTERESTS

Scopus Publications