https://dspace.iiti.ac.in:8080/jspui/handle/123456789/9539 Mon, 27 Jul 2026 08:01:48 GMT 2026-07-27T08:01:48Z https://dspace.iiti.ac.in:8080/jspui/handle/123456789/18826 Title: Vision-based biometric identification of cattle using lightweight models [RESTRICTED THESIS-01 Year] Authors: Pathak, Prashant Digambar Abstract: [Abstract is restricted for 01 Year, due to IPR related issue] Tue, 23 Jun 2026 00:00:00 GMT https://dspace.iiti.ac.in:8080/jspui/handle/123456789/18826 2026-06-23T00:00:00Z https://dspace.iiti.ac.in:8080/jspui/handle/123456789/18825 Title: Strategies for optimized deployment of wireless sensor networks in complex terrestrial and underwater environments Authors: Tyagi, Shekhar Abstract: Wireless Sensor Networks(WSNs) play a vital role in real time monitoring and data collection in complex environments, where direct human intervention is not possible. WSNs are effective in monitoring forest fires, landslides, floods, earthquakes, marine biology, underwater surveillance, and various other terrestrial and underwater applications. However, an optimal or effective deployment and resilience of these networks remain significantly challenging due to signal or path loss issues because of terrain irregularities, such as elevation and vegetation variations in terrestrial and depth variations in underwater scenarios, various other environmental constraints. This thesis presents a series of techniques, aiming to optimize sensor deployment in such complex environments, followed by a scheme for assessing network resilience in obstacle-clad terrestrial terrains. In the first work, a novel deployment technique is proposed for Wireless Sensor Networks operating over irregular-obstructed terrains, with obstacles such as vegetation, rocks and uneven elevations. The approach comprises extraction of satellite images of the Region of Interest (RoI) from Google Earth and generating a KML file (Keyhole Markup File) for the RoI containing the latitude, longitude, and elevation values of each and every point in the RoI. These points are used to generate a contour map of the RoI containing detailed terrain morphology. Mon, 22 Jun 2026 00:00:00 GMT https://dspace.iiti.ac.in:8080/jspui/handle/123456789/18825 2026-06-22T00:00:00Z https://dspace.iiti.ac.in:8080/jspui/handle/123456789/18762 Title: Towards efficient and accurate deep learning models for medical image segmentation [RESTRICTED THESIS-01 Year] Authors: Uppal, Dolly Abstract: [Abstract is restricted for 01 Year, due to IPR related issue] Tue, 16 Jun 2026 00:00:00 GMT https://dspace.iiti.ac.in:8080/jspui/handle/123456789/18762 2026-06-16T00:00:00Z https://dspace.iiti.ac.in:8080/jspui/handle/123456789/18753 Title: Towards social safety in digital platforms: multimodal hostile content detection and explanation Authors: Mohammad Zia Ur Rehman Abstract: The exponential rise of user-generated content on social media has fostered connectivity but also facilitated the proliferation of hostile narratives, ranging from explicit abuse to subtle, implicit forms of hate speech and dark humor. While automated detection systems have advanced, significant gaps remain in addressing low-resource languages, multimodal complexity, and the interpretability of model decisions. This thesis proposes a comprehensive suite of frameworks to detect and understand hostile content across three modalities: text, memes, and video. In the textual domain, the thesis addresses the problem in low-resource Indic languages. First, it introduces a user-aware framework for abusive content detection in multilingual and code-mixed environments. By integrating social context features, such as user history and post affinity, with cross-lingual textual embeddings, the proposed method significantly enhances detection performance in low-resource settings. Second, to bridge the gap between black-box predictions and human reasoning, the thesis presents X-MuTeST, an explainable framework for hate speech detection in Hindi, Telugu, and English. This work contributes benchmark datasets with token-level human rationales and employs a novel training strategy that combines Large Language Model (LLM) consultation with N-gram-based explainability to improve both plausibility and faithfulness. Fri, 12 Jun 2026 00:00:00 GMT https://dspace.iiti.ac.in:8080/jspui/handle/123456789/18753 2026-06-12T00:00:00Z