Authors: Lende Vedika Vijay, Prof. R. V. Varhade, Prof. M. C. Kolse, Prof. S. K. Said

Abstract: Artificial Intelligence is transforming how science is done by helping researchers analyse complex data, uncover hidden patterns, generate hypotheses and accelerate discovery across disciplines. This review examines the role of AI in scientific discovery, covering methods, applications, benefits, challenges and future possibilities. Machine learning, deep learning, physics-informed neural networks, equation discovery, natural language processing of scientific literature, reinforcement learning and generative AI are explained in terms of how they support data-driven investigation. Landmark applications are reviewed across structural biology, drug and antibiotic discovery, chemistry, materials science, physics, fusion-energy control, mathematics, astronomy and weather and climate forecasting. The emergence of autonomous laboratories and language-model agents that plan and execute experiments is discussed. A five-layer framework for AI-assisted discovery comprising data, representation, modelling, hypothesis generation and experimental validation is proposed, with research gaps, objectives, a comparison of AI roles and challenges including data quality, interpretability, reproducibility, physical consistency and the risk of over-reliance. The review concludes that AI is most powerful as a partner to scientists, accelerating the cycle of hypothesis, experiment and understanding while human judgement guides what is meaningful.

DOI: https://doi.org/10.5281/zenodo.24126531

Published by: vikaspatanker

Authors: Dr. Devendar Veeramalla, Dr.P.Srinivas, Dr.D.Rajkumar, Dr.K.Ramesh

Abstract: Freshwater swamps stand as complex transitional environments where stagnant or sluggish hydrological regimes create unique ecological niches. Functioning well beyond simple geographic boundaries, they govern critical biogeochemical pathways, regulate catchment-scale water budgets, buffer downstream communities against peak flood pulses, and trap massive subterranean carbon stocks. In recent decades, however, continuous agricultural conversion, rapid industrial infrastructure growth, and unmitigated runoff have systematically disrupted swamp functionality. These pressures are further compounded by climatically driven droughts, extreme deluge cycles, and marine saltwater encroachment. A chronic gap in targeted environmental legislation and public appreciation leaves these vital wetlands structurally unprotected. This paper explores the core ecological and socioeconomic services supplied by freshwater swamps, examines the compounding mechanics driving their decline, and puts forward an actionable framework that combines watershed-scale spatial planning, hydrological re-wetting, institutional oversight, and community stewardship.

DOI: https://doi.org/10.5281/zenodo.24102509

Published by: vikaspatanker

Authors: Gunjan and Rishita Vohra, Mr.Ritiesh Kumar Chandel, Dr. Akhilesh Das

Abstract: Food spoilage and the premature disposal of edible food are persistent problems for public health, the economy and the environment. Fixed best-before and expiry dates are set under controlled conditions and ignore the temperature fluctuations and handling that food experiences between farm and fridge. This paper reviews recent artificial intelligence (AI) approaches to freshness detection and shelf-life prediction, covering convolutional neural network (CNN) image classifiers and low-cost gas-sensor systems with machine-learning models, and compares their reported performance. Building on the gaps identified, we formulate the problem mathematically and propose a four-layer vision–sensor fusion framework that combines a transfer-learned CNN with a regression model to estimate remaining shelf life, together with a confidence-aware decision rule that sends uncertain items to manual inspection. We also describe an edge-deployment architecture, a planned experimental protocol and the main risks. Reported accuracies in the reviewed sensor-based studies range from 91.9% to 97.05%. The framework is conceptual; experimental validation on a multi-product dataset is identified as future work.

Published by: vikaspatanker

Authors: Alfiya Mehboob Kazi, Prof. S. K. Said, Prof. M. C. Kolse

Abstract: Artificial Intelligence (AI) is reshaping healthcare by accelerating diagnosis, shortening parts of the drug-development cycle and making treatment decisions more individual. This review consolidates evidence from four connected areas: medical imaging, drug discovery, personalized medicine, and the ethical and regulatory conditions under which these tools can be trusted. Imaging is the most mature domain, where deep convolutional networks now detect abnormalities, triage urgent studies and improve reconstruction, while pathology, cardiology and neurology are rapidly following. In drug discovery, learning-based models help identify targets, generate candidate molecules and select trial participants, although gains are concentrated in early pipeline stages. Personalized medicine uses electronic health records and multi-omics data to estimate individual treatment response. Alongside these benefits, the paper analyses risks concerning patient privacy, dataset bias, opacity and accountability, and maps them to the Indian context of the Ayushman Bharat Digital Mission, the Digital Personal Data Protection Act 2023 and national AI strategy documents. A layered reference architecture for responsible clinical AI is proposed, together with a research gap analysis and objectives. The review concludes that healthcare AI should be judged by measurable improvement in patient outcomes, supported by prospective validation, secure data practice, fairness auditing and human oversight.

DOI: https://doi.org/10.5281/zenodo.24037844

Published by: vikaspatanker

Authors: Tambe Siddhi Mahesh, Prof. S. S. Bhor, Prof. M. C. Kolse, Prof. S. K. Said

Abstract: Streaming platforms such as Netflix and YouTube offer catalogues far larger than any user can browse, and most of what people watch is chosen from personalized recommendations. This paper explains how these industrial recommendation systems work, based on published research from the platforms and the wider community. It traces the evolution from the Netflix Prize and matrix factorization to deep learning, and describes the typical two-stage pipeline: candidate generation, which retrieves a few hundred relevant items from millions using embeddings learned from watch histories, and ranking, which scores candidates with richer features to predict clicks, watch time and satisfaction. It reviews multitask ranking that balances engagement and satisfaction objectives and corrects position bias, sampling-bias correction in two-tower retrieval models, reinforcement learning that optimizes long-term user value, and the personalization of rows, artwork and the home page at Netflix. Evaluation through offline metrics and online A/B testing is discussed, as are concerns about filter bubbles, calibration of recommendations to user interests and audits of problematic content pathways. A five-layer architecture is presented with research gaps, objectives, a comparison of techniques and challenges. The review concludes that modern recommenders are complex, multi-objective systems in which responsible design is as important as accuracy.

DOI: https://doi.org/10.5281/zenodo.24037654

Published by: vikaspatanker

Authors: Bankar Akshada Santosh, Prof. S. K. Said, Prof. M. C. Kolse

Abstract: Large Language Models (LLMs) can produce fluent but factually incorrect statements, known as hallucinations, which limits their reliability in healthcare, law, education and other critical domains. This paper reviews methods that reduce hallucination by grounding generation in external knowledge. Retrieval-Augmented Generation (RAG) retrieves relevant passages at query time and conditions the model on them, while Knowledge Graphs (KGs) provide structured, verifiable facts and explicit relations that support multi-hop reasoning. The review explains dense passage retrieval, retrieval-augmented pre-training, graph-based RAG that summarizes communities of related entities, and reasoning that walks over knowledge-graph paths. It also covers evaluation, including truthfulness benchmarks and metrics for faithfulness, context relevance and answer relevance. A hybrid architecture is proposed that combines vector retrieval with knowledge-graph lookup, assembles grounded context, generates answers with citations and verifies claims before responding. Research gaps, objectives, a comparison of grounding strategies and challenges such as retrieval errors, outdated knowledge, graph construction cost and latency are discussed. The review concludes that combining unstructured retrieval with structured knowledge offers a practical route to more accurate and transparent LLM applications.

DOI: https://doi.org/10.5281/zenodo.24037457

Published by: vikaspatanker

Authors: Kashid Sagar Shivaji, Prof. M. C. Kolse, Prof. S. K. Said

Abstract: Rapid urbanization places pressure on traffic, energy, water, waste, environment and public services, and traditional city management often struggles with congestion, pollution and inefficient use of resources. Generative Artificial Intelligence (GenAI), comprising models that create text, images, time series and simulations, offers new tools for city administrators, planners and citizens. This paper reviews the application of GenAI to smart city management. It examines foundation models and large language models that provide conversational access to city data and assist with reports and citizen services; generative models that synthesize realistic sensor data and future scenarios; graph-based spatio-temporal models for traffic forecasting that feed generative planning; and urban digital twins in which generated scenarios can be tested before decisions are made. Applications in traffic, energy, environmental monitoring, waste management, public safety and urban planning are discussed. A five-layer architecture integrating IoT data, a city data platform, predictive and generative AI, a digital twin and stakeholder interfaces is proposed, with research gaps, objectives, a comparison of AI roles and challenges including hallucination, bias, data governance, privacy and accountability. The review concludes that GenAI can make city management more efficient and participatory when grounded in reliable data and human oversight.

DOI: https://doi.org/10.5281/zenodo.24037159

Published by: vikaspatanker

Authors: Shete Priti Rahul, Prof. S. R. Borhade, Prof. M. C. Kolse, Prof. S. K. Said

Abstract: Cryptographic hash functions are a basic building block of cyber security, used to verify that files remain accurate, authentic and unaltered during storage, transmission and sharing. This paper reviews cryptographic hashing with emphasis on file integrity verification and digital forensics. It explains the properties of hash functions, namely fixed-length output, determinism, the avalanche effect, and preimage, second-preimage and collision resistance, and analyses the principal algorithms MD5, SHA-1, SHA-256, SHA-512 and SHA-3, including the Merkle–Damgård and sponge constructions. The history of practical attacks is traced, from collisions on MD5 to identical-prefix and chosen-prefix collisions on SHA-1, explaining why these algorithms must no longer be used for security. The verification process of hashing a file, storing the reference value securely, recomputing and comparing is described, together with applications in malware identification using known-file hash sets, preservation of digital evidence according to forensic guidelines, similarity hashing for detecting near-identical files, and secure software distribution. A five-layer file integrity verification architecture is proposed, along with research gaps, objectives, a comparison of algorithms and challenges such as protecting stored hashes, performance on large data and migration from legacy algorithms. The review concludes that SHA-256, SHA-512 and SHA-3, combined with protected reference values, provide reliable integrity assurance.

DOI: https://doi.org/10.5281/zenodo.24036869

Published by: vikaspatanker

Authors: Aware Uday Navanath, Prof. S. K. Said, Prof. M. C. Kolse

Abstract: Two-wheeler riders account for a large share of road fatalities in India, and many deaths occur not at the moment of impact but during the delay before help arrives. A conventional helmet offers passive head protection but cannot recognize a crash, assess whether the rider is fit to ride or summon assistance. This paper reviews the design of AI-powered smart helmets that integrate Internet of Things (IoT) sensing, embedded intelligence and wireless communication to close this gap. The review covers alcohol detection with gas sensors, drowsiness detection from eye-blink and physiological signals, helmet-wear verification, and crash detection using inertial and impact sensors. It examines how threshold rules, classical machine learning and lightweight neural networks are used to separate real accidents from everyday shocks such as potholes or dropping the helmet, and how GPS and GSM or smartphone links deliver location-tagged alerts to emergency contacts. A layered architecture covering sensing, edge processing, connectivity, cloud services and user applications is proposed, followed by a research gap analysis, objectives, a comparison of detection approaches and a discussion of power, false-alarm, privacy and cost constraints. The review concludes that a low-cost helmet combining preventive monitoring with reliable post-crash alerting can measurably shorten emergency response times for two-wheeler riders.

DOI: https://doi.org/10.5281/zenodo.24036670

Published by: vikaspatanker

Authors: Aher Siddhi Prabhakar, Prof. S. K. Said, Prof. M. C. Kolse

Abstract: Severe weather, mid-flight system failures and hazardous terrain continue to challenge aviation safety, and traditional safeguards depend heavily on pilot intervention and ground communication that may be limited during sudden emergencies. This paper reviews the concept of an AI Guardian, an intelligent framework that supports flight safety before, during and after an incident. Three capability areas are examined. First, predictive health monitoring uses deep learning on engine and flight-data telemetry to estimate remaining useful life and detect anomalies before they become failures. Second, decision support for collision avoidance and emergency handling draws on airborne collision-avoidance logic, neural-network policy compression and formal verification of safety-critical networks. Third, post-incident rescue support coordinates drones with computer vision to locate crash sites, deliver medical kits and relay location data to rescue teams. A five-layer architecture that integrates onboard sensing, edge analytics, pilot advisory, air–ground communication and rescue coordination is proposed. Research gaps, objectives, a comparison of techniques and the certification challenges set out in the EASA AI roadmap are discussed. The review concludes that AI can reduce human error and response time if it remains verifiable, explainable and subordinate to pilot authority.

DOI: https://doi.org/10.5281/zenodo.24036425

Published by: vikaspatanker