Pooja Yadav
@mjpru.ac.in
Assistant Professor ,Department of CSIT
MJP Rohilkhand University
EDUCATION
Ph.D. (Pursuing), M.Tech, B.Tech
RESEARCH INTERESTS
ML , IoT, NLP, DL, Data Mining
Scopus Publications
Scopus Publications
Pooja Yadav, S. C. Sharma, Rajesh Mahadeva, and Shashikant P. Patole
Institute of Electrical and Electronics Engineers (IEEE)
Non-communicable disease, especially chronic disease, is the most common factor of complication of deteriorating physical health and the state of one’s mind. It is also a prominent cause of illness and mortality around the world. Primarily chronic disease is preventable at a particular stage though its occurrence is critical. To make clinical decisions, these illness prediction models were created to assist clinicians and patients. A chronic disease prediction model takes into account many risk variables to determine an individual’s illness risk. Machine learning approaches have made it possible to predict chronic disease early by collecting Electronic Health Record (EHR) data. This paper focuses on the diabetes dataset extracted from Kaggle and two unseen real datasets. In this paper, we have implemented Synthetic Minority Over-Sampling Technique (SMOTE) algorithm to balance the dataset. We have also explored Boruta as the feature selection method. To tune hyper-parameters of different algorithms, we have proposed an improved technique by combining the Grid Search method with the Grey Wolf Optimization algorithm. The Grid Search method requires extensive searching, while the Grey Wolf Optimization algorithm is easily linked, rapid to seek, and extremely exact. Nine conventional classification techniques have been evaluated in this paper. This research concentrates on the Stacking Classifier to assess the performance of the prediction model that produces the best results. The Proposed Model gave the highest F1-Score 98.84% on PIMA dataset, 98% after validation on the Synthetic dataset, 97.3% on ADRC dataset, 96.20% on FHD dataset. To the best of our knowledge, no previous work has focused on such a sort of technique and these two datasets. The outcomes of the comparison experiment on the PIMA dataset reveals that the proposed strategy performs better. This study also provides the interpretation of the proposed model. It conducts an ethical assessment of what explainability means for the use of Machine Learning models in clinical practice.
Pooja Yadav, Nitin Arora, and Subhash Chander Sharma
IEEE
Chronic Diseases have spread speedily over the last one and a half decades; these life-threatening chronic diseases have a significantly higher rate of morbidity and fatality. Illness diagnosis using machine learning methods helps to decrease the percentage of fatality. On the other hand, Optimization algorithms address a broad range of problems while being flexible and adaptive. Such nature-inspired optimization algorithms are Genetic Algorithms (GA), Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Artificial Bee Colonies (ABC), and many more. These methods have been employed in the early prediction of many illnesses. This article investigates the effectiveness of several nature-inspired optimization strategies in diagnosing chronic illness. Compared to ACO, GA, and ABC algorithms, PSO has been widely used in an illness diagnosis. Furthermore, combining optimization approaches yields better results than using them separately.
Nitin Arora, Pooja Yadav, Kuldeep Tripathi, and Subhash Sharma
IEEE
Image classification is one of the computer vision problems. It is a supervised learning technique, in this, images are classified according to their different characteristics (features). There are various facial image datasets of different persons with different facial expressions. Classification based on different facial expressions is always a challenging task for researchers because a person can have different facial expressions like smiling, sad, normal, with or without goggles, etc., depending upon the mood of the person. Deep learning technique like Convolutional neural networks (CNN) is an indemand technique to classify images based on their features. This paper demonstrates the performance of CNN using a different number of images with different numbers of expressions per person and keeping all the other parameters the same. For performance measurement of CNN, the faces94 dataset of is used. Based on the evaluated results, some important points are highlighted.
Pooja Yadav and S. C. Sharma
Springer Science and Business Media LLC
Vandana Srivastava, Tripti Mahara, and Pooja Yadav
Elsevier BV
Er. Pooja Yadav, Er. Ankur Mittal, and Hemant Yadav
IEEE
Internet of Things is the Connections of embedded technologies that containedphysical objects and is used to communicate and intellect or interact with the inner states or the external surroundings.Rather than people to people communication, IoT emphasis on machine to machine communication. This paper familiarises the status of IoT growth In India, and also contains security issues challenges.Finally, this paper reviews the Risk factor, security issues and challenges in Indian perspective.
Pooja Yadav, Nishchol Mishra, and Sanjeev Sharma
IEEE
Need of hiding information from intruders has been around since ancient times. Nowadays Digital media is getting advanced like text, image, audio, video etc. To maintain the secrecy of information, different methods of hiding have been evolved. One of them is Steganography, which means hiding information under some other information without noticeable change in cover information. Recently Video Steganography has become a boon for providing large amount of data to be transferred secretly. Video is simply a sequence of images, hence much space is available in between for hiding information. In proposed scheme video steganography is used to hide a secret video stream in cover video stream. Each frame of secret video will be broken into individual components then converted into 8-bit binary values, and encrypted using XOR with secret key and encrypted frames will be hidden in the least significant bit of each frames using sequential encoding of Cover video. To enhance more security each bit of secret frames will be stored in cover frames following a pattern BGRRGBGR.
S.S. Bedi, H. Yadav, and P. Yadav
IEEE
Clustering techniques have been used by many intelligent software agents in order to retrieve, filter, and categorize documents available on the World Wide Web. Clustering is also useful in extracting salient features of related web documents to automatically formulate queries and search for other similar documents on the Web. Traditional clustering algorithms either use a priori knowledge of document structures to define a distance or similarity among these documents, or use probabilistic techniques such as Bayesian classification. Many of these traditional algorithms, however, falter when the dimensionality of the feature space becomes high relative to the size of the document space. In this paper, we introduce two new clustering algorithms that can effectively cluster documents, even in the presence of a very high dimensional feature space. These clustering techniques which are based on generalizations of graph partitioning, do not require pre-specified ad hoc distance functions, and are capable of automatically discovering document similarities or associations. We conduct several experiments on real Web data using various feature selection heuristics, and compare our clustering schemes to standard distance-based techniques, such as hierarchical agglomeration clustering, and Bayesian classification methods, AutoClass.