Saroj Mohan Institute of Technology

The rapid advancement of autonomous vehicle (AV) technology necessitates innovative approaches to recruiting talent capable of ensuring safety in AV systems. This study explores the application of advanced predictive modeling for identifying ideal candidates in autonomous vehicle safety development. Utilizing a deep learning-based natural language processing (NLP) approach, specifically BERT (Bidirectional Encoder Representations from Transformers), we analyze candidate profiles, resumes, and technical assessments to predict role suitability. The implementation of this model is achieved through TensorFlow, an open-source deep learning framework. By leveraging BERT's contextual understanding of language and TensorFlow's scalable architecture, the proposed solution evaluates candidates not only on technical proficiency but also on contextual experience and domain-specific knowledge. The results demonstrate significant improvements in recruitment efficiency and accuracy, providing a transformative approach to building high-caliber teams for AV safety.

The graph theory has numerous applications in the problems of operations research, economics, systems analysis, and transportation systems. However, real applications of a graph theory are full of linguistic vagueness, i.e., uncertainty. For example, the vehicle travel time or number of vehicles on a road network may not be known precisely. The fuzzy graph model can be used to model the complex, not clearly explained uncertain real life applications, in which conventional graph may fail to model properly. In a fuzzy graph, it is very important to identify the nature (strength) of nodes and no such analysis on nodes is available in the literature. In this paper, we introduce a method to find out the strength of the node in a fuzzy graph. The degree of the node and maximum membership value of the adjacent edges of that node are used to compute the strength of the node. The strength of a fuzzy node itself is a fuzzy set. Depending upon the strength of the nodes, we classify the nodes of a fuzzy graph into six types namely α strong fuzzy node, β strong fuzzy node, regular fuzzy node, α weak fuzzy node, β weak fuzzy node and balance fuzzy node.

Electrical discharge machining (EDM) is a nontraditional machining process used for machining hard conductive materials by employing an electrically conductive tool and dielectric. In present days, biodielectric fluids are being used as substitutes with some exceptional attributes in EDM. In that context, the objective of the current work is to study the effectiveness of vegetable oil as dielectric fluid in EDM. In this article, experiment has been conducted using Jatropha biodiesel (Jatropha BD), Rice bran biodiesel (Rice bran BD) and EDM oil as dielectric fluid. The experimental results have reported that the material removal rate (MRR) patterns of Jatropha BD and Rice bran BD oil are almost similar to those of EDM oil, whereas in most of the cases, Jatropha BD displays better surface quality than the Rice bran BD oil. However, both the vegetable oils show superior surface quality compared to EDM oil. Evolvements of unhygienic and toxic gases and generation of nonbiodegradable wastes are few of the critical issues for inferior sustainability and biodegradability of dielectrics. Based on the test results of dissolved gas analysis, transesterified Jatropha oil and Rice Bran oil have been introduced as sustainable and biodegradable dielectrics in EDM.

Topological index is a numerical value associated with a chemical constitution for correlation of chemical structure with various physical properties, chemical reactivity or biological activity. In this work, some new indices based on neighborhood degree sum of nodes are proposed. To make the computation of the novel indices convenient, an algorithm is designed. Quantitative structure property relationship (QSPR) study is a good statistical method for investigating drug activity or binding mode for different receptors. QSPR analysis of the newly introduced indices is studied here which reveals their predicting power. A comparative study of the novel indices with some well-known and mostly used indices in structure-property modelling and isomer discrimination is performed. Some mathematical properties of these indices are also discussed here.

In the current decade, chaos based image encryption has distinctly captured a remarkable position in multimedia data security. In this paper, a hybrid chaos based image encryption scheme has been developed. A two-dimensional ecological chaotic map, namely Beddington, Free and Lawton (BFL) map has been combined with logistic map and Chebyshev map to generate a pseudo-random keystream for image encryption. In addition, an image substitution technique based on logistic map has been proposed. The random nature of keystream has been successfully tested by employing DIEHARD and NIST randomness test suites. Furthermore, the scheme has also been verified by histogram, correlation, global entropy, local entropy, key sensitivity and differential attack analyses. The proposed scheme achieves average 41.6% and 8.5% improvement in correlation value of cipher image and plaintext sensitivity, respectively, compared to Sheela et al.’s scheme.