Feature selection is a critical pre-processing step in machine learning. For supervised problems, class labels are used to identify important features. However, the tagging of the data is labor intensive and hence costly. Consequently, there is an abundance of unlabeled data and limited labeled data. Hence, semi-supervised learning is very pertinent. The problem of feature selection is equally relevant for semi-supervised learning. In this research work, a fresh semi-supervised method of feature selection is proposed. In the first step, gradient boosting classifier is used for labeling the unlabeled portion of the data and augment the training set. Repeated sampling is done from the unlabeled portion, to generate multiple augmented training sets. Top-k features are selected based on mutual information from each augmented training set. While selecting the features, it is ensured that the features are not redundant using a correlation coefficient. A voting-based approach is used to combine these multiple feature sets. The proposed method is compared with a) Supervised Feature Selection on the full dataset (Benchmark) and b) Supervised Feature Selection on the labeled portion. On comparing these three methods across 18 datasets, it was found that semisupervised feature selection outperforms the supervised model based on F1 scores by 2.78% and 2.63% in two different configurations. Also, the model outperforms the benchmark by 0.36% and 1.12%.

Today, the most feasible and easy form of Human-Computer Interaction (HCI) is the use of mobile applications. Mobile applications have become an integral part of our day-to-day lives reaching out to each corner of society and caters to the problems. The applications available are customized, but the incorporation of intelligence especially for the disabled to assist their lives is absent. This motivates the research work specified in this paper is non-commercial application development for society. Designing applications that are highly scalable and intelligent to minimize problems faced by differently-abled , is explicitly covered here. The proposed system makes use of Speech-To-Text and Text-To-Speech conversion techniques for back end and provides enhanced scalability by allowing users to regulate the functionality of the application, customized based on their preferred region, topic and time stamps. Applications and devices meant for the differently-abled do exist, however, most of them have unidirectional and singular functionality with minimum customizability. In most cases, very complicated hardware systems are associated with the proposed work which in turn makes it expensive to maintain. The proposed application aims to offer voice-based functionality automation, remote health monitoring, and pattern recognition for recommendation systems, explicitly for the visually impaired and the solitary elderly The reading of remote health monitoring is close to the actual value with a standard deviation of 1.45% or 0.76 on the average.