Papers by Meena Kowshalya
Computer Systems Science and Engineering
Sentiment analysis is the process of determining the intention or emotion behind an article. The ... more Sentiment analysis is the process of determining the intention or emotion behind an article. The subjective information from the context is analyzed by the sentimental analysis of the people's opinion. The data that is analyzed quantifies the reactions or sentiments and reveals the information's contextual polarity. In social behavior, sentiment can be thought of as a latent variable. Measuring and comprehending this behavior could help us to better understand the social issues. Because sentiments are domain specific, sentimental analysis in a specific context is critical in any real-world scenario. Textual sentiment analysis is done in sentence, document level and feature levels. This work introduces a new Information Gain based Feature Selection (IGbFS) algorithm for selecting highly correlated features eliminating irrelevant and redundant ones. Extensive textual sentiment analysis on sentence, document and feature levels are performed by exploiting the proposed Information Gain based Feature Selection algorithm. The analysis is done based on the datasets from Cornell and Kaggle repositories. When compared to existing baseline classifiers, the suggested Information Gain based classifier resulted in an increased accuracy of 96% for document, 97.4% for sentence and 98.5% for feature levels respectively. Also, the proposed method is tested with IMDB, Yelp 2013 and Yelp 2014 datasets. Experimental results for these high dimensional datasets give increased accuracy of 95%, 96% and 98% for the proposed Information Gain based classifier for document, sentence and feature levels respectively compared to existing baseline classifiers.
International journal of software computing and testing, Jun 23, 2020
International Journal of Scientific Research in Science, Engineering and Technology, 2020
Data privacy and security are incredibly important in the healthcare industry. Federated learning... more Data privacy and security are incredibly important in the healthcare industry. Federated learning is a new way of training a machine learning algorithm using distributed data which is not hosted in a centralized server. Numerous centralized machine learning models exists in literature but none offers privacy to users’ data. This paper proposes a federated learning approach for early detection of Type-2 Diabetes among patients. A simple federated architecture is exploited for early detection of Type-2 diabetes. We compare the proposed federated learning model against our centralised approach. Experimental results prove that the federated learning model ensures significant privacy over centralised learning model whereas compromising accuracy for a subtle extend.
International journal of scientific research in science, engineering and technology, 2020
Frauds in Credit cards have become more usual in today's generation and many cases have been repo... more Frauds in Credit cards have become more usual in today's generation and many cases have been reported in the past with the increase in cybercrimes. Though there exist numerous techniques to detect online credit card fraudulence, deep-learning and federated learning techniques can efficiently detect accurate fraudulence. This paper exploits two unsupervised learning algorithms namely Auto encoder and Restricted Boltzmann Machine (RBM) implemented over a federated learning framework to predict number of credit card fraudulent users.time European credit card dataset with 284,807 transactions are used to find the number of fraudulent users. The decentralized federated learning framework is compared against centralized approach. The average accuracy using federated learning for Auto encoder and RBM is 88% and 94% respectively and 99% and 92% using centralized deep learning approach. Federated Learning ensured high differential privacy compromising accuracy.
Social Internet of Things (SIoT) is defined as social network of intelligent and smarter objects.... more Social Internet of Things (SIoT) is defined as social network of intelligent and smarter objects. The social objects namely smartphones, tablets, etc., have become part of our lives and have made life simpler and smarter. Smart objects on the other side have also made mankind lazy resulting in a sedentary lifestyle. Research in human physical activity recognition is not new and has attracted many new avenues in the recent past. In this paper, we have proposed a simple application that classifies human physical activities like sitting, standing, walking, jogging, climbing upstairs and downstairs using smartphones without the need of an external server or a personal computer. For the first time in literature, a smartphone is able to identify and classify the physical activities of the owner and notify the percentage of activeness and passiveness at regular time intervals. The triaxial accelerometer in the smartphone was used for data collection with the phone being carried in the subj...
Istrazivanja i projektovanja za privredu, 2017
Internet of Things, the one paradigm many vision idea is ruling the world. By 2025 over trillions... more Internet of Things, the one paradigm many vision idea is ruling the world. By 2025 over trillions and trillions of objects will be connected to the internet. Social networking concepts are revolutions beyond IoT. One of the many visions of IoT is to make objects not only smarter but also socially conscious. A new paradigm named Social Internet of Things evolved which integrated two technologies namely Internet of Things and Social Networking. A SIoT comprises of socially aware smart objects that can autonomously establish and enable collaboration with other smart objects that are friends. In this paper we study the role, characteristics of social objects and their relationships. Five kinds of relationships are identified. These relationship and characteristics helps in revealing the level of trust between objects. Experiments were conducted for 85 social objects in an office environment and the types of objects, their relationships, interest, activities etc were discovered.
Wireless Personal Communications, 2019
Curse of dimensionality problem needs to be addressed carefully when designing a classifier. Give... more Curse of dimensionality problem needs to be addressed carefully when designing a classifier. Given a huge dimensional dataset, one interesting problem is the choice of optimal selection of features for classification. Feature selection is an interesting and most optimal solution to the curse of dimensionality problem. Numerous feature selection algorithms have been proposed in the recent past to solve the curse of dimensionality problem but no one stop solution prevails. This paper proposes two novel algorithms for feature selection namely Reverse Piece-wise Correlation Based Feature Selection (RPwCBFS) and Shuffled Piece-wise Correlation Based Feature Selection (SPwCBFS) that divides the feature space into pieces and computes the similarity of feature subsets in reverse order and in random shuffled manner respectively. The proposed algorithms are compared with Fast Correlation Based Feature selection (FCBF), Fast Correlation Based Feature selection # (FCBF#) and Fast Correlation Based Feature selection In Piece (FCBFiP). Standard medium and huge dimensional datasets are used for experimentation purpose. Experimental results prove that the Reverse Piece-wise Correlation Based Feature Selection algorithm (RPwCBFS) and Shuffled Piece-wise Correlation Based Feature Selection algorithm (SPwCBFS) are prominent solution for feature selection when the underlying dataset is medium sized. For huge dimensional datasets, Shuffled Piece-wise Correlation Based Feature Selection algorithm (SPwCBFS) proves to be an optimal choice.
Wireless Personal Communications, 2018
Social Internet of Things (SIoT) is a young paradigm that integrates Internet of Things and Socia... more Social Internet of Things (SIoT) is a young paradigm that integrates Internet of Things and Social Networks. Social Internet of Things is defined as a social network of intelligent objects. SIoT has led to autonomous decision making and communication between object peers. SIoT has created and opened many research avenues in the recent years and it is vital to understand the impact of SIoT in the real world. In this paper, we have mined twitter to evaluate the user awareness and impact of SIoT among the public. We use R for mining twitter and perform extensive sentiment analysis using supervised and semi supervised algorithms to evaluate the user's perception about SIoT. Experimental results show that the proposed Fragment Vector model, a semi supervised classification algorithm is better when compared to supervised classification algorithms namely Improved Polarity Classifier (IPC) and SentiWordNet Classifier (SWNC). We also evaluate the combined performance of IPC and SWNC and propose a hybrid classifier (IPC ? SWNC). Our analysis was challenged by limited number of tweets with respect to our study. Experimental results using R has produced evidences of its social influences.
Sādhanā, 2018
The world has faced three Information and Communication Technology (ICT) revolutions and the thir... more The world has faced three Information and Communication Technology (ICT) revolutions and the third ICT wave led to Internet of Things, the notion of anything, everything, anytime and everywhere. Out of the many visions of IoT, one revolutionary concept is to make IoT sociable i.e., incorporating social networking within Internet of Things. This revolution has led to the notion of Social Internet of Things (SIoT). Establishing a SIoT network or community is not so simple and requires integration of heterogeneous technology and communication solutions. This paper focuses on establishing a secure and reliable communication over nodes in SIoT by computing trust dynamically among neighboring nodes. Trust Management is an important area that has attracted numerous researchers over the past few years. The proposed DTrustInfer computes trust based on first hand observation, second hand observation, centrality and dependability factor of a node. Properties of trust such as honesty, cooperativeness, community interest and energy of a node are considered for computing trust. Also, this paper ensures secure communication among SIoT nodes through simple secret codes. Experimental results show that the proposed DTrustInfer outperforms the existing trust models significantly.
IET Networks, 2017
The Internet is populated with billions of electronic gadgets that have become a part of our fabr... more The Internet is populated with billions of electronic gadgets that have become a part of our fabric. Internet of Things is gaining popularity in at most all applications from smart buildings, intelligent transportation, healthcare and defence. IoT is a many vision one paradigm technology. One of the many visions of IoT is to make 'Things' social. Social Internet of Things (SIoT) is a young paradigm that integrates IoT and Social networking principles where Things are not only autonomous and smarter but also socially conscious. The authors propose a trust management scheme to facilitate trustworthy automatic decision making based on behaviour of objects. The authors use SIoT Trust metrics namely direct trust, centrality, community interest, Cooperativeness, Service Score to compute Trustworthiness among objects. The Expected trust and periodic trust updates evidently identify the presence of 'on off' selective forwarding attacks. The authors demonstrate the advantages of the proposed scheme with other existing trust management schemes in the literature.
Studies in Informatics and Control, 2016
Internet of Thingo (IoT) io one paradigm many vioiono technology. One of the many vioiono of Inte... more Internet of Thingo (IoT) io one paradigm many vioiono technology. One of the many vioiono of Internet of Things io to make Things oociable. Thio io achieved by integrating IoT and Social networking which may lead to a new paradigm called Social Internet of Thingo (SIoT). SIoT io defined ao collection of intelligent objecto that can autonomouoly interact with ito peero via ownero. In a SIoT ocenario, detecting and characterizing a network otructure io very important. In thio paper, we propooe a new community detection algorithm that detecto communitieo in SIoT uoing three metrico namely oocial oimilarity, preference oimilarity and movement oimilarity. To the beot of our knowledge thio io the firot work that detecto communitieo in large ocale Social Internet of Thingo uoing oocial, preference and movement oimilarity. The experimental reoulto ohow that the propooed community detection ocheme achieveo higher quality reoulto in termo of detection rate and execution time when compared to exioting methodo.
Istrazivanja i projektovanja za privredu, 2016
International Journal of Ad hoc, Sensor & Ubiquitous Computing, 2011
Wireless sensor networks (WSN) are emerging in various fields like disaster management, battle fi... more Wireless sensor networks (WSN) are emerging in various fields like disaster management, battle field surveillance and border security surveillance. A large number of sensors in these applications are unattended and work autonomously. Clustering is a key technique to improve the network lifetime, reduce the energy consumption and increase the scalability of the sensor network. In this paper, we study the impact of heterogeneity of the nodes to the performance of WSN. This paper surveys the different clustering algorithm for heterogeneous WSN.
SSRN Electronic Journal, 2022
Wireless Personal Communications
Uploads
Papers by Meena Kowshalya