Airport Runway Obstacle Detection and Analysis from UAV Imagery: A Review Using the Stanford Drone Dataset
Maintaining obstacle-free runways is an essential part of airport operations and aviation safety. The growing availability of high-resolution imagery from UAVs, especially from publicly available datasets like the Stanford Drone Dataset (SDD), presents new challenges and opportunities for innovative obstacle detection systems. This paper provides a systematic methodological overview of airport runway obstacle detection from UAV imagery with emphasis on methods transferable to the SDD. This methodology examines cutting-edge computer vision methods, among them object recognition models like YOLO, Faster R-CNN, and Vision Transformers, and their theoretical potential for recognizing common runway hazards like cars, people, and foreign object debris (FOD). The review also contains a thorough analysis of the SDD's architecture, objects, resolution, and limitations relative to runway conditions. We also introduce a conceptual pipeline for real-time obstacle detection and discuss its possible incorporation into airport safety management systems. Lastly, this review determines the main research gaps and presents future research directions for enhancing obstacle detection accuracy, real-time performance, and adaptability to varied airport environments. This work intends to provide a basis for future experimental studies and system development utilizing UAV-based imagery for airport runway safety.
Published by: Joseph Chakravarthi Chavali, D. Abraham Chandy
Author: Joseph Chakravarthi Chavali
Paper ID: V11I4-1205
Paper Status: published
Published: August 7, 2025
Neonatal Alloimmune Thrombocytopenia (NAIT): A Comprehensive Review
Neonatal Alloimmune Thrombocytopenia (NAIT) is a rare but potentially life-threatening condition in which maternal alloantibodies target fetal platelet antigens, leading to severe thrombocytopenia, bleeding complications, and, in some cases, intracranial hemorrhage (ICH) or fetal demise. This review provides a comprehensive exploration of NAIT’s pathophysiology, immunologic mechanisms, genetic predispositions, clinical manifestations, diagnostic approaches, and evolving prevention and treatment strategies. Special emphasis is placed on the immunogenetic triggers, particularly Human Platelet Antigen (HPA) incompatibilities, and their population-specific prevalence. Diagnostic techniques such as MAIPA and HPA genotyping are highlighted alongside current antenatal interventions, including intravenous immunoglobulin (IVIG), corticosteroids, and antigen-negative platelet transfusions. Advances in population-based screening, noninvasive fetal genotyping, and consensus guidelines have significantly improved outcomes, reducing ICH rates and enhancing survival. Despite these advances, long-term neurodevelopmental sequelae remain a concern, even in nonhemorrhagic cases. This review integrates recent epidemiologic and clinical findings from 2023 to 2025, emphasizing the growing importance of early recognition, targeted management, and international consensus in improving care for NAIT-affected neonates and future pregnancies.
Published by: Aadya Gaur
Author: Aadya Gaur
Paper ID: V11I4-1206
Paper Status: published
Published: August 7, 2025
A Network Security Monitoring System using Deep Learning
In an era of evolving and increasingly complex cyber threats, the importance of robust network security is paramount. This paper presents a novel method of strengthening network defenses by building a highly flexible and durable Network Security Monitoring System (NSMS). By utilizing deep learning, more especially self-taught learning (STL), we set out to reinvent network security. In this study, we apply STL to the well-known NSL-KDD dataset, which is a commonly used network security monitoring system benchmark. We thoroughly analyze our NSMS solution's performance utilizing a range of important metrics, such as accuracy, precision, recall, and F-measure, to determine its overall effectiveness. Impressively, this method produced a 92.84% accuracy on the training set. As we use both the training and testing datasets in our work, our research expands on this basis and provides a distinct advantage for comparison, allowing a straight comparison to this earlier work. This study's main importance comes from its ability to prevent intentional attacks and to proactively identify unanticipated and unforeseeable security breaches. This research represents a milestone in the development of NSMS technology in the dynamic cybersecurity landscape, enabling enterprises to strengthen their security posture and protect their assets in a world that is becoming more interconnected.
Published by: Pramodh Puthota, MR. G.Sivannarayana, Pasupuleti Bhavana Pradeepa Rani, Siriki Sravya, Vaddeswarapu Rahul
Author: Pramodh Puthota
Paper ID: V11I4-1201
Paper Status: published
Published: August 4, 2025
Exploration of Biosurfactant Producing Microorganism from Garage Soil: Production, Characterization, and its Application
Biosurfactants are bioactive surface molecules produced by microorganisms, gaining notoriety for their environmentally friendly and biodegradable characteristics. This research emphasizes the extraction, production, and analysis of biosurfactants from hydrocarbon-polluted soils collected from a garage and truck terminal in the Yeshwanthpur industrial region. The samples were enriched using Mineral Salt Medium (MSM), and bacterial strains were isolated through serial dilution and pour plate methods. The identification of biosurfactant-producing bacteria was performed utilizing drop collapse, oil displacement, and emulsification assays. Among the isolates, isolate 2 exhibited the most promising results and was chosen for further research. Gram staining, endospore staining, and biochemical tests revealed the organism to be Bacillus cereus. Optimization of biosurfactant production was achieved by adjusting pH, temperature, incubation duration, inoculum volume, and nutrient sources. The maximum biosurfactant yield was attained with 250 µl of inoculum and with optimum physical parameters of pH 6 and temperature 35°C at a 24-hour incubation period, with glucose and peptone as carbon and nitrogen sources, respectively. The biosurfactants were extracted through acid precipitation followed by solvent extraction using chloroform and methanol. The characterization of the crude biosurfactant was performed. The antimicrobial properties against selected bacterial and fungal strains were assessed using the agar diffusion method, and bioremediation potential was evaluated. Distinct zones of inhibition confirmed the antimicrobial efficacy of the biosurfactant. These results imply that Bacillus cereus isolated from garage soil contains effective biosurfactant-producing potential and can be used in environmental bioremediation and antimicrobial property, offering a sustainable substitute for synthetic surfactants.
Published by: Namitha K, Bindu P, Mohammed Faizal, Anuroopa N
Author: Namitha K
Paper ID: V11I4-1200
Paper Status: published
Published: August 4, 2025
MediNav: An AI-Driven Specialist Referral Tool to Reduce Wait Times in Indian Public Hospitals
Public hospitals in India face significant challenges with long patient wait times, particularly due to disorganized referral systems. Many patients approaching these hospitals come from underserved backgrounds or have limited health literacy and often struggle to identify the appropriate type of doctor for their specific health issues. As many public hospitals in India lack a structured first point of contact or General Practitioner (GP) system, this confusion contributes to unnecessary delays and increased wait times. To address this issue, the study introduces MediNav, an AI-powered tool designed to evaluate patient symptoms and guide them to the right type of doctor for consultation. By doing so, MediNav enhances patient flow and minimizes unnecessary delays, particularly benefiting those who may not know how to navigate the healthcare system. The AI model, developed using XGBoost on symptom–specialty data, achieved an overall accuracy of 85.58% in live primary healthcare (PHC) settings. Through a comparative assessment of wait times, MediNav has the potential to reduce patient waiting time stemming from misreferrals or department transfers by an average of 39.4 minutes per individual in public Indian hospitals. In the absence of a GP or structured referral layer, such inefficiencies are common in India’s public hospitals. With typical patient volumes of 500 or more per day, this translates to over 328 clinical hours saved daily. This significant reduction can enhance clinical efficiency within strained public health systems, ultimately improving access to care for all patients, especially those with limited understanding of the healthcare process.
Published by: Akshita Mangal
Author: Akshita Mangal
Paper ID: V11I4-1191
Paper Status: published
Published: August 1, 2025
Empowering Indian Educators through AI: Transforming Faculty Development and Pedagogical Practices in Higher Education
The rapid integration of Artificial Intelligence (AI) into education systems is redefining teaching and learning paradigms across the globe. In India, with the rollout of the National Education Policy (NEP) 2020 and the push for digital transformation, AI holds the potential to completely change faculty development and pedagogical practices in higher education. This research investigates the impact of AI-based tools on Indian educators, focusing on personalized teaching, adaptive learning systems, and data-driven decision-making. The study examines how AI technologies empower faculty through continuous upskilling and reskilling, enabling them to adapt to evolving learning environments. Using AI-driven Learning Management Systems (LMS), teachers can now access real-time analytics, automate assessments, and personalize student feedback. However, the adoption of these technologies depends on institutional readiness, faculty digital literacy, and infrastructure availability. A structured questionnaire was distributed to 100 faculty members across Indian universities. The data was analyzed using SPSS tools, including percentage analysis, multiple regression, and chi-square analysis. The study identifies eight key factors influencing faculty empowerment: digital literacy, institutional support, training programs, AI integration in LMS, perceived usefulness, ease of use, policy awareness, and resistance to change. Results reveal a strong correlation between AI adoption and enhanced teaching effectiveness. Faculty members exposed to AI tools demonstrated increased engagement, better course customization, and improved student performance metrics. However, challenges such as lack of AI training, fear of redundancy, and inadequate infrastructure remain. The study emphasizes the need to implement structured AI competency programs and clear policy directives under NEP 2020. This research contributes to ongoing discourse by offering a faculty-centric perspective on AI adoption in Indian higher education. It offers concrete recommendations for policymakers, academic leaders, and EdTech developers to collaboratively design future-ready academic ecosystems.
Published by: Dr.V.Victor Solomon
Author: Dr.V.Victor Solomon
Paper ID: V11I4-1188
Paper Status: published
Published: July 30, 2025
