Browse papers

5 papers

Evidence-Driven Multi-Sensor Monitoring for Railway Track Safety

Danush M · Aug 15, 2026

Abstract : Railway safety systems operate in an environment where a missed obstacle can have severe consequences, while excessive false alarms can reduce the usefulness of an alerting system. Vision systems provide rich semantic information but can degrade under poor lighting or adverse weather. Radar offers complementary distance and motion information and is less dependent on visible illumination, while other short-range sensors can provide inexpensive confirmation signals. This paper proposes an evidence-driven framework, called Virtual Dome, for combining heterogeneous sensors into a layered railway track-monitoring system. The central idea is not to treat any single sensor or machine-learning model as an authority. Instead, the framework separates sensing, feature extraction, evidence fusion, confidence estimation, and alert generation. A track event is escalated when multiple independent signals support the same interpretation or when a high-risk signal persists beyond a defined temporal window. The paper also proposes a practical evaluation protocol covering detection performance, false alarms, latency, environmental robustness, sensor disagreement, and computational cost. Particular attention is given to data scarcity and the difficulty of representing mixed human, animal, object, and infrastructure events in a single dataset. The resulting framework is intended as a research and prototyping architecture rather than a claim of deployment readiness.

Cyber-Physical SystemsSensor FusionComputer VisionRailway SafetyArtificial Intelligence

SQS: A Multi-Dimensional Framework for Evaluating Software Specifications in AI-Assisted Development

Abhavya Anekverna · Aug 15, 2026

Abstract If AI coding agents need to make a lot of inferences, they are more likely to create incorrect code, but if they have less work to do, theoretically it should be more accurate. In an AI coding agent with little to no human interaction, a specification that doesn't specify a behavior can be interpreted as a decision on implementation, with the agent continuing to work without asking for clarification. If a decision on such a behavior, constraint, interface, or acceptance condition is made, it is called a specification-induced assumption, and it is therefore an implementation decision, distinct from an ordinary implementation decision the specification leaves open (e.g., what front-end framework to use). We hypothesize that the quality of a specification impacts the correctness of implementation in the downstream, as follows: Lower quality specification = fewer assumptions an agent may have to make = less deviation from what the specification actually specifies. Current requirements-quality research has been geared towards human-centred requirements processes, and the studies of ambiguity, completeness and consistency have concentrated on them separately. This paper introduces the Specification Quality Score (SQS), a rubric-anchored, operational measure based on five dimensions of specification quality (Completeness, Unambiguity, Internal Consistency, Intent Traceability, Machine-Actionability) with clear criteria for each band of each dimension. We provide worked examples of the framework and a clear explanation of the meaning of the total score. This is a conceptual paper – it is not an empirical validation study, and does not imply that SQS predicts code generation results. This correlational statement, and the controlled experiment necessary to test it, is explicitly suggested as the next step. Keywords: requirements engineering, specification quality, large language models, AI coding agents, specification-driven development

Requirements EngineeringSoftware EngineeringNatural Language ProcessingArtificial IntelligenceComputer Science

FuelGuard AI:An AI-Driven Unified Framework for Intelligent Fuel and LPG Allocation During Emergencies and Supply Shortages

Akshay N, Akshay Guptha L, Akshatha H M, Aishwarya S · Aug 15, 2026

Abstract. Fuel and LPG are essential resources for transportation, households, healthcare, agriculture, and other critical services. During emergencies, supply shortages, and sudden demand fluctuations, conventional distribution systems may face challenges in forecasting demand, managing limited resources, and ensuring fair and secure access. This paper presents FuelGuard AI, an intelligent digital framework developed to support fuel and LPG allocation through centralized monitoring, quota management, priority-based allocation, demand analysis, and secure transaction verification. The implemented prototype integrates citizen and station-operator interfaces with a secure QR-based authentication mechanism using short-lived cryptographic tokens, enabling authorized operators to verify allocation requests before dispensing fuel. The system also maintains transaction records and supports server-side quota deduction to improve traceability and prevent unauthorized or duplicate allocations. In addition, the framework provides a foundation for AI-assisted demand forecasting, shortage detection, and adaptive allocation during critical situations. The proposed system aims to improve transparency, security, resource utilization, and fairness while complementing existing fuel and LPG distribution infrastructure.

Energy ManagementCybersecurityResource AllocationArtificial IntelligenceFuel Management

UrbanNexus: A Digital Twin-Enabled Framework for Multi-Objective Evaluation of Sustainable Urban Interventions

Yashika Rajput · Aug 15, 2026

Abstract Rapid urbanization has intensified interconnected challenges such as air pollution, urban heat, inadequate green cover, and increasing pressure on urban infrastructure. Although artificial intelligence and geospatial technologies have enabled effective prediction and monitoring of individual urban phenomena, existing approaches often address these problems independently and provide limited support for comparing alternative interventions before their real-world implementation. This creates a need for decision-support systems capable of evaluating environmental, health, economic, and implementation trade-offs within a unified framework. This paper proposes UrbanNexus, a Digital Twin-enabled urban decision intelligence framework for the multi-objective evaluation of sustainable urban interventions. The framework integrates heterogeneous environmental, geospatial, demographic, and infrastructure data with machine learning-based urban-state prediction and a simulation-oriented Digital Twin. Alternative interventions, such as tree plantation, green infrastructure, electric public transportation, and hybrid strategies, are represented as scenarios and evaluated according to their potential environmental benefits, health impacts, implementation costs, feasibility, and deployment requirements. A multi-objective decision layer identifies trade-offs among competing strategies, while an explainable decision layer provides interpretable justification for scenario rankings and recommendations. A supporting agentic layer is proposed to coordinate the interpretation of outputs from environmental, health, economic, optimization, and explanation components. The primary contribution of UrbanNexus is a unified framework for cross-domain, multi-objective evaluation and explainable ranking of heterogeneous urban interventions before deployment. The proposed framework establishes the architecture, mathematical decision formulation, and experimental protocol required for future empirical validation. Keywords: Urban AI, Digital Twin, Decision Intelligence, Sustainable Urban Planning, Multi-Objective Optimization, Scenario Simulation, Explainable AI, Multi-Agent Systems

Digital TwinsMulti-Objective OptimizationSustainable CitiesArtificial IntelligenceUrban Planning

Skin Cancer Detection Using Preprocessed Vision Transformers: An Interpretability-Driven Approach

Ananya Atri · Aug 15, 2026

Abstract : Skin cancer is an issue affecting health all over the world, and proper diagnosis of the issue would lead to better patient outcomes. Deep Learning, in particular Convolutional Neural Networks (CNNs), has brought more objective and fast screening techniques. This paper assesses the diagnostic capability of Vision Transformers (ViT) with Explainable AI (XAI) on HAM10000 data (10,015 pigmented skin lesion images). The researchers used a critically important preprocessing pipeline comprising of morphology transformations to remove hair, image segmentation to identify regions of interest and data augmentation to overcome imbalanced classes. Five XAI techniques were used, namely, Grad-CAM, LIME, SHAP, Integrated Gradients and Saliency Maps to improve diagnostic transparency. The experiment outcomes revealed that ViT + Grad-CAM architecture was the best performer with a total accuracy of 96.6%. The model achieved 0.92 precision, 0.90 recall and 0.92 F1-score. Grad-CAM was especially useful in a clinical setting as it is fast to run and localizes classes accurately.

Skin CancerMedicineComputer VisionArtificial IntelligenceVision Transformer