Sentiment Analysis of Product Reviews Using LSTM - A Comparative Evaluation with Machine Learning Algorithms Employing BOW and TF-IDF Techniques Karthiga S, Sutha K, Pavithra V, Sakthivel S, Sowmya V, Sasidevi J Journal of Machine and Computing, 2025 Sentiment analysis has become an invaluable tool in understanding consumer opinions in large datasets. This study explores sentiment analysis of the product review dataset applying different machine learning classification algorithms, specifically focusing on two primary feature extraction methods: (TF-IDF) and (BOW) A thorough comparison was conducted to assess the effectiveness of each method alone, as well as a novel hybrid technique that merges both TF-IDF and BOW. And compared with deep learning approach, our findings demonstrate that feature extraction technique significantly enhances classification performance. Among the tested algorithms, logistic regression with tfidf, bow exhibited even greater accuracy. Obtaining the most accurate results possible from the sentiment analysis is the primary objective of this endeavor. The first step in the process of analyzing and classifying the data is going to be the preprocessing of the data, followed by the extraction of features, then the categorization of sentiments via the use of machine learning algorithms, and lastly the assessment of the algorithms. The end findings indicate that the SVM classifier obtained an accuracy of 93%, the Naive Bayes classifier achieved an accuracy of 91%, the Logistic regression classifier got an accuracy of 94%, and the LSTM classifier earned an accuracy which was 93.58%. In future work may explore the integration of additional feature extraction methods with deep learning to refine and improve sentiment analysis models.
Machine Learning-based Anomaly Detection in IOT Sensing Devices for Optimal Security S. Karthiga, P. Ravisankar, R. Vijayarajeswari, N. Pushpa, T. Vino, Dinesh Dobhal 2nd IEEE International Conference on Data Science and Information System Icdsis 2024, 2024 The Internet of Things (IoT) is well-known as a new detecting paradigm for interacting with the real world in Industry 4.0. With IoT, major security concern arises in data communication between remote location and the data server. Data obtained from the different sensor devices have to be transmitted securely. Implementing Machine Learning algorithms increases the security as well as the efficiency of the IoT devices. In this research work, MQTT protocol is implemented for data transmission services in Internet of Things enabled devices. The research utilized historical information from a smart manufacturing plant’s tracking sensor, control devices, and IoT cameras. The findings of this research work 5rimproved plant efficacy and security, resulting in quicker and more efficient reactions to uncommon incidents. Outcomes indicate a considerable influence on intelligent manufacturing plant effectiveness and security. Advanced detection of anomalies led to quicker and more efficient reactions to odd events, reducing significant occurrences and enhancing safety. Moreover, technique improvement and IoT infrastructure enhanced productivity by minimizing downtime and maximizing resource use. The suggested study compares machine learning-based protection measures to past studies on IoT protection and identifying anomalies in industrial settings, demonstrating their usefulness. Researchers saw a rise of 14% in the detection of anomalies and a 2% drop in false positives after training machine learning models.
Security based Approach of SHA 384 and SHA 512 Algorithms in Cloud Environment Thambusamy Velmurugan, Sivakumar Karthiga Journal of Computer Science, 2020 Cloud computing is going to be the next big thing in the era of internet world. As the world moves ahead towards enhancement of the cloud features we also have to take a serious consideration of the enhancing cloud securities to protect the end-user’s data. The major usage of this cloud feature are widely applied in the cloud based IT sector for operation advancement, Data storage; on-demand software delivery and many more operations which also requires the scrutiny of the data that is being shared. This research work is carried out to enhance the security of the end-users using secured hashing algorithm. In this, the principles of hash utility are applied that makes the intruders difficult to decode the encrypted password of the user. Even if the intruder or even the administrator of the server tries to decode the encryption for multiple attempts to decode the password the hash codes of the server keeps on changing for multiple attempts. This research work gives a new solution for the concern that is getting raised on the data privacy. The usage of the secured hashing algorithm helps to develop platform that ensure data security for the end-user in the cloud environment. For that the Secure Hashing Algorithm (SHA) 384& SHA 512 is taken and implemented by a practical approach in cloud. For the implementation of these two algorithms, the major attacks faced by end user namely Brute force attack, Man in Middle attack and Rainbow attack are experimented under cloud platform. From the experimental results, it is identified that the best algorithm to protect the data.
