Vivekanand Education Society's Institute of Technology

Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by dopaminergic neuron loss and abnormal protein aggregation. While current treatments offer symptomatic relief, they do not alter the course of disease progression. In recent years, the study of cross-species models has gained traction in uncovering novel therapeutic insights. This paper explores the genetic underpinnings of PD, focusing on key mutations in genes such as SNCA, LRRK2, PINK1, PRKN, and DJ-1, and the associated molecular dysfunctions that lead to neuronal degeneration. It further examines the biological advantages of zebrafish (Danio rerio) and naked mole-rats (Heterocephalus glaber), two organisms with unique regenerative or neuroprotective traits, and evaluates their relevance as alternative models for PD research. By comparing these species and their mechanisms of resilience, the paper discusses the translational potential of genetic, stem cell, and AI-integrated approaches in advancing future therapies. The findings highlight the value of interdisciplinary, cross-species research in addressing current limitations and guiding innovative strategies for neurodegenerative disease intervention.

Indoor navigation systems have become highly important in the case of large buildings and complexes; yet, existing solutions are inclined to be based on specialized hardware infrastructure like WiFi and Bluetooth Low Energy (BLE). This paper presents a new approach to indoor navigation without the requirement of additional hardware through the use of computer vision and augmented reality technology. The system presented makes use of COLMAP - Structure from Motion (SfM) for visualizing the indoor area from video footage. Users simply upload an initial view image to estimate their initial pose through COLMAP-based estimation of camera parameters, achieving localization errors of less than 0.3 m in controlled experiments. Waypoints between the starting and destination coordinates, calculated over the dense point cloud using A* search on a 3D graph, align with ground-truth paths with an average spatial error of less than 0.25 m . Transformation of these waypoints to ARCore space reveals spatial misalignment and jitter, which makes in-situ testing unreliable. Our vision-based pipeline, unlike BLE-based systems (which typically exhibit 1–2 m errors), performs well in the initial stages but requires improvements to be reliable for AR visualization. Key constraints include AR marker stability under dynamic lighting and occlusion, which we identify as important areas for future work.

Text sentiment analysis of the social media text faces challenges posed by unstructured data and labori- ous human labeling for intent-driven, hierarchical classification. This work compares conventional ML models (SVM, Naïve Bayes, Logistic Regression) with contextual DL models (DistilBERT) in terms of their performance on Sentiment140 dataset (1.6 million tweets) where a balanced 300,000 tweets were selected (200,000 training, 50,000 validation and 50,000 test). As a solution to the bottleneck of human labeling for detailed topic classification, a zero-shot classification pipeline that uses Natural Language Inference (NLI) for classification of 1,000 tweets into a two-layer taxonomy of 30 parent topics and 330 subtopics has been created without any human-labeled samples. SVM is able to achieve 81.52% accuracy, while DistilBERT scores 84.44% on 50,000 tweet test set and 83.0% on a small 1,000 tweets sample.

Tuberculosis (TB) remains one of the most persistent infectious diseases worldwide, particularly in resource-limited and densely populated regions. While community-based TB strategies are central to early detection, treatment success, and transmission interruption, their implementation often raises complex ethical and legal concerns. This paper examines the tension between public health imperatives and the protection of individual rights within community TB control programs. Determine a legal principles, human rights frameworks, and on-the-ground practice, we explore how interventions such as active screening, contact tracing, and Directly Observed Treatment (DOT) may unintentionally compromise autonomy, confidentiality, and freedom of movement when not carefully designed. Through case studies in India, South Africa, and Thailand, we illustrate that voluntary, patient-centered approaches outperform coercive systems in sustaining treatment engagement, reducing stigma, and strengthening community trust. Quantitative outputs—including improved treatment initiation and completion rates, decreased stigma, and enhanced participation highlight the practical value of rights-based models. The paper argues that equitable TB control requires balancing collective responsibility with respect for individual dignity. Policies anchored in informed consent, data protection, transparent communication, and social support are essential to achieving this balance.