B. Priya Kamath

This study investigates the critical task of assessing water potability using supervised machine-learning techniques. The problem statement involves accurately predicting water potability based on chemical and physical parameters, which are crucial for public health and environmental sustainability. Exploratory Data Analysis (EDA) highlighted significant insights into feature distributions and correlations, guiding preprocessing steps and model selection. The Synthetic Minority Oversampling Technique (SMOTE) was applied to mitigate class imbalance, ensuring robust model training. Three classification algorithms, namely Logistic Regression (LR), K-Nearest Neighbors (KNN), and Random Forest (RF), were evaluated, with RF exhibiting superior performance after Optuna hyperparameter tuning, achieving an accuracy of 68%. Based on the performance of RF and KNN, a weighted voting-based ensemble technique achieved an accuracy of 71%. This study emphasizes the importance of leveraging machine learning to support water quality assessment, offering reliable tools for decision-making in public health and environmental management.

Sentiment Analysis (SA) is a well-known and emerging research field in the area of Natural Language Processing (NLP) and text classification. Feature engineering is considered to be one of the major steps in the Machine Learning (ML) pipeline with effective feature extraction playing a vital role in improving the performance of the SA tasks. Choosing an appropriate feature from the text is considered to be the most challenging task in text classification. This study examines the implementation of different traditional feature extraction models such as Bag of Words (BoW), Term Frequency-Inverse Document Frequency (TF-IDF), N-grams, and word embeddings like Word2Vec and Bidirectional Encoder Representations from Transformers (BERT) on an Amazon review dataset. Furthermore, the hyperparameters of the BERT model were fine-tuned, optimizing its performance on the SA task. Additionally, this research explores the effectiveness of combining the word vectors generated using TF-IDF and BERT for SA. The proposed hybrid model implements an effective negation handling approach and combines TF-IDF with BERT to improve performance for Amazon product review classification.The hybrid model was evaluated using several performance metrics, including accuracy, recall, precision, and F1-score. The proposed hybrid model shows promising results achieving an accuracy of 88%. The integration of BERT and TF-IDF not only enhances the model’s ability to understand and interpret text but also demonstrates the potential of combining advanced and traditional NLP techniques.

Intelligent classification models for food products basis on morphological, colour and texture features