AI-Based Deepfake Detection: A Review Of Spatial Artifact, Temporal Consistency And Biological Signal Approaches For Real-Time Media Verification
Authors: Gadge Anuja Harishchandra, Prof. N. G. Rokade, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Deepfakes, realistic manipulations of faces, voices and videos produced with generative adversarial networks and diffusion models, threaten digital media integrity, personal privacy and public security. Traditional verification by visual inspection or simple forensic tools struggles against these sophisticated alterations. This paper reviews AI-based deepfake detection with emphasis on approaches suited to a real-time framework. It explains how deepfakes are generated and then surveys three families of detection cues: spatial artifacts within individual frames, such as warping, blending boundaries and texture inconsistencies captured by convolutional networks; temporal inconsistencies across frames, including unnatural blinking and lip motion detected with recurrent and spatio-temporal models; and biological signals such as subtle colour changes caused by blood flow that synthetic faces fail to reproduce. Benchmark datasets including FaceForensics++, Celeb-DF and the DeepFake Detection Challenge are discussed. A five-layer real-time detection architecture covering media ingestion, face processing, multi-cue analysis, decision fusion and reporting is proposed, together with research gaps, objectives, a comparison of methods and challenges such as generalization to unseen generators, compression and adversarial attacks. The review concludes that fusing complementary cues offers the most reliable automated defence.
DOI: https://doi.org/10.5281/zenodo.24030535
Privacy-Preserving Technologies For Secure Data Management In Digital Systems: A Review Of Encryption, Anonymization, Differential Privacy, Federated Learning And Secure Computation
Authors: Gawade Aditi Dattatray, Prof. C. A. Kolse, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Digital platforms, cloud services, online transactions and data-driven applications collect and process large volumes of personal and confidential information every day, increasing the risk of data breaches, unauthorized access, identity theft and misuse. Protecting privacy while still allowing data to be used for legitimate purposes has therefore become a core requirement of modern systems. This paper reviews the principal privacy-preserving technologies and how they can be combined for secure data management. It covers data encryption at rest and in transit, anonymization models such as k-anonymity and l-diversity together with the risk of re-identification, differential privacy, which adds calibrated noise to protect individuals, federated learning, which trains models without centralizing raw data, homomorphic encryption, which allows computation on encrypted data, secure multi-party computation and trusted execution environments. Attacks such as membership inference that motivate these defences are discussed. A layered architecture for privacy-aware data management is proposed, with a research gap analysis, objectives and a comparison of techniques by protection level, performance cost and maturity. Regulatory drivers, including India's Digital Personal Data Protection Act 2023 and the GDPR, are considered. The review concludes that no single technique is sufficient and that layered combinations matched to the threat model provide the best balance of privacy, utility and performance.
DOI: https://doi.org/10.5281/zenodo.24032829
Edge AI For Real-Time Prediction in Autonomous Vehicles: A Review of Trajectory Forecasting Models and Onboard Optimization
Authors: Bhalerao Onkar Rohidas, Prof. M. A. Auti, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Autonomous vehicles must predict how nearby vehicles, cyclists and pedestrians will move within the next few seconds in order to plan safe actions. Sending raw sensor data to the cloud for this prediction introduces latency and dependence on network connectivity that can jeopardize safety. This paper reviews Edge AI approaches that perform perception and motion prediction on onboard embedded hardware. It surveys trajectory forecasting models, from social pooling of recurrent networks and generative adversarial prediction to graph-based models that encode high-definition maps and agent interactions, and multi-modal predictors that output several likely futures. Large-scale motion forecasting datasets are discussed. The review then examines techniques for running these models within strict latency and power budgets, including pruning, quantization to integer arithmetic, knowledge distillation and hardware–software co-design on automotive accelerators. A five-layer onboard architecture covering sensing, perception, edge prediction, planning and vehicle control is proposed, with research gaps, objectives and a comparison of prediction models. The review concludes that compact, quantized multi-modal predictors running at the edge can deliver the low-latency, reliable forecasts that safe autonomous driving requires.
DOI: https://doi.org/10.5281/zenodo.24032970
Ai-Powered Drones For Disaster Search And Rescue: A Review Of Human Detection, Autonomous Navigation And Emergency Communication
Authors: Pabale Sakshi Fakir, Prof. J. M. Patade, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Earthquakes, floods, landslides and building collapses cause serious damage and loss of life, and locating trapped or stranded people quickly is one of the most critical tasks for rescue teams. Ground searches are slow and often dangerous in unstable or inaccessible areas. AI-powered drones offer a faster and safer alternative by combining aerial mobility with onboard cameras, thermal sensors, GPS and computer vision. This paper reviews the design of AI drones for disaster rescue. It examines aerial datasets and deep object detectors for recognizing people, vehicles and damaged structures from above, thermal imaging for finding victims at night or under light cover, coverage path planning for searching large areas systematically, simultaneous localization and mapping for operation where GPS is unreliable, and drone networks that relay communication when ground infrastructure fails. Practical constraints of battery life, payload, onboard computing and regulation are discussed. A five-layer architecture comprising sensing, onboard edge AI, navigation and control, communication and a ground control station is proposed, followed by a research gap analysis, objectives, comparison of detection models and a discussion of challenges. The review concludes that AI drones can cover large areas quickly, reach inaccessible locations and reduce risk to rescuers, making disaster response faster, safer and more effective.
DOI: https://doi.org/10.5281/zenodo.24033116
Generative And Deep Learning In Bioinformatics: A Review Of Protein Structure Prediction, Sequence Representation Learning And Ai-Assisted Drug Discovery
Authors: Tirandaj Fatima Khalid, Prof. S. S. Bhor, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Artificial intelligence, and generative modelling in particular, is creating new opportunities in bioinformatics. Conventional computational biology relied on physics-based simulation, sequence alignment and manual feature engineering, each limited by computational cost and the need for expert interpretation. This paper reviews how deep learning and generative models are used in bioinformatics research. It first examines protein structure prediction, where deep learning achieved a step change in accuracy and extended to complexes of biomolecules, and discusses what such predictions can and cannot tell researchers. It then reviews representation learning on biological sequences, in which transformer models trained on large public sequence databases learn representations that capture structural and evolutionary signal and support downstream tasks such as property and variant-effect prediction. The paper surveys the families of generative models used in the field, including variational autoencoders, graph neural networks, diffusion models and transformers, at the level of their modelling assumptions, and reviews published applications in computational drug discovery such as virtual screening and candidate prioritization. It discusses data resources, evaluation practice, the central role of experimental validation, and the governance of research, including responsible-use and biosecurity frameworks. Research gaps, objectives, a comparison of model families and challenges are presented. The review concludes that these methods are decision-support tools for researchers and do not replace laboratory experimentation or institutional oversight.
DOI: https://doi.org/10.5281/zenodo.24033350
Edge Ai: Intelligent Computing At The Edge For Real-Time Applications — A Review Of Architectures, Model Optimization And Deployment
Authors: Bhor Darshan Vasant, Prof. M. A. Auti, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Edge Artificial Intelligence (Edge AI) combines machine learning with edge computing so that data are processed on or near the devices that produce them, such as sensors, cameras, smartphones, IoT nodes and embedded systems, rather than entirely in remote cloud servers. This brings decisions closer to the data source, reducing latency, bandwidth use and dependence on connectivity while improving privacy. This paper reviews the foundations and practice of Edge AI for real-time applications. It examines the edge computing paradigm and edge intelligence levels, the partitioning of neural networks between device, edge server and cloud, efficient architectures such as depthwise-separable networks, early-exit inference, and compression by pruning, quantization and knowledge distillation. Tiny machine learning on microcontrollers and standard benchmarks for measuring edge inference are discussed. Applications in smart surveillance, industrial monitoring, healthcare wearables, autonomous robots and smart cities are summarized. A layered device–edge–cloud architecture is proposed, together with research gaps, objectives, a comparison of deployment tiers and an analysis of challenges including limited resources, heterogeneity, security and model updates. The review concludes that Edge AI is essential for low-latency, private and reliable intelligent systems.
DOI: https://doi.org/10.5281/zenodo.24034625
Multimodal Ai Integrating Text, Images, Audio And Video For Intelligent Healthcare Diagnosis: A Review Of Fusion Methods And Foundation Models
Authors: Khot Shruti Rahul, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Clinical diagnosis rarely relies on one source of information: doctors combine medical images, symptoms described by patients, clinical reports, laboratory results, electronic health records, and sometimes audio or video such as heart sounds or gait recordings. Multimodal Artificial Intelligence integrates such heterogeneous data to improve the accuracy, efficiency and reliability of diagnosis. This paper reviews multimodal AI for intelligent healthcare diagnosis assistance. It introduces the taxonomy of multimodal machine learning, covering representation, alignment and fusion, and compares early, intermediate and late fusion strategies. Applications are reviewed in disease detection, image interpretation with reports, personalized treatment and patient monitoring, together with vision–language models that learn from paired images and text and generalist medical foundation models that accept many input types. Public multimodal datasets are discussed. A five-layer architecture comprising multimodal data acquisition, modality-specific encoders, fusion, diagnostic reasoning and clinician-facing explanation is proposed, with research gaps, objectives, a comparison of fusion strategies and challenges including missing modalities, data alignment, privacy, interpretability and validation. The review concludes that multimodal AI can provide more comprehensive patient analysis and faster decisions when it is rigorously validated and clinically supervised.
DOI: https://doi.org/10.5281/zenodo.24034883
AI Phishing Email Detector: A Review Of Transformer-Based NLP, Sender And Url Analysis, And Defence Against AI-Generated Phishing
Authors: Kurhade Suyash Rajaram, Prof. R. V. Varhade, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Phishing emails deceive individuals into revealing credentials and personal data, and attackers can now use large language models to write fluent, personalized phishing messages at scale that slip past rule-based filters. This paper reviews AI techniques for an adaptive phishing email detector that analyses message text, sender information and embedded URLs in real time. It traces detection from structural and feature-based approaches through natural-language analysis of intent and urgency to transformer models such as BERT and RoBERTa fine-tuned for phishing classification. URL analysis with deep character models, sender-authentication checks and behavioural signals are reviewed. Particular attention is given to the new threat of AI-generated phishing, including studies showing that language models can craft convincing spear-phishing emails and that the same models can help detect them. A five-layer architecture comprising email ingestion, multi-view feature extraction, transformer-based and URL classifiers, risk fusion with explanation, and user interaction with feedback is proposed. Research gaps, objectives, a comparison of models and challenges including adversarial adaptation, false positives, privacy and multilingual phishing are discussed. The review concludes that adaptive, explainable, multi-view detection is necessary as phishing becomes AI-assisted.
DOI: https://doi.org/10.5281/zenodo.24035093
AI Guardian for Aircraft Safety and Rescue: A Review of Predictive Health Monitoring, Collision Avoidance and Autonomous Emergency Response
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
AI-Powered Smart Helmet For Two-Wheeler Rider Safety: A Review Of Accident Detection, Rider-State Monitoring And Emergency Response Systems
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
Cryptographic Hashing In Cyber Security: A Review Of Hash Algorithms, Collision Attacks And Forensic File Integrity Verification
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
Generative Ai For Smart City Management: A Review Of Large Language Models, Synthetic Data, Scenario Simulation And Urban Digital Twins
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
Mitigating Hallucinations In Large Language Models Using Retrieval-Augmented Generation And Knowledge Graphs: A Review
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
How Recommendation Systems Work At Netflix And Youtube: A Review Of Candidate Generation, Ranking, Multitask Objectives And Responsible Personalization
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
Artificial Intelligence In Healthcare: A Review Of Diagnostic Imaging, Drug Discovery, Personalized Medicine And Responsible Adoption In India
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
Artificial Intelligence For Scientific Discovery: A Review Of Methods, Landmark Applications And The Emergence Of Autonomous Research
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
Explainable AI: Making Machine Learning Decisions Transparent And Interpretable — A Review Of Methods, Evaluation And Human-Centred Explanation
Authors: Padir Aditi Vinod, Prof. J. M. Patade, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Machine learning models increasingly influence decisions in healthcare, finance, hiring and public services, yet many of the most accurate models are complex black boxes whose reasoning cannot be inspected. Explainable Artificial Intelligence (XAI) aims to make these decisions transparent and interpretable so that users can understand, trust, debug and contest them. This paper reviews XAI as a general discipline rather than for a single domain. It clarifies concepts of interpretability, explainability, transparency and faithfulness, and organizes methods into inherently interpretable models, global explanations such as partial dependence and accumulated local effects, local feature attribution with LIME, SHAP and integrated gradients, visual explanations for deep networks, concept-based explanations and counterfactuals. Evaluation of explanations, including sanity checks that reveal misleading saliency maps, and insights from social science on what makes a good explanation are discussed. A five-layer explainable ML pipeline comprising data, model, explanation engine, evaluation and audience-specific presentation is proposed, with research gaps, objectives, a comparison of methods and challenges such as the accuracy–interpretability trade-off, unstable explanations and regulation. The review concludes that explanations should be faithful, evaluated and designed for the people who use them.
DOI: https://doi.org/10.5281/zenodo.24126787
Traffic Light Green-Time Prediction Using Machine Learning: A Review Of Adaptive Signal Control From Fixed Timing To Learning-Based Intersections
Authors: Nalawade Tanvi Dnyaneshwar, Prof. J. M. Patade, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Traffic congestion is a major urban problem, worsened by conventional traffic lights that operate on fixed time intervals without considering how many vehicles are waiting on each approach. This paper reviews approaches to adaptive traffic signal control and focuses on using machine learning to predict suitable green-light durations for each lane of an intersection based on traffic demand. It traces the field from classical signal timing formulas through adaptive systems that adjust timings from detector data, to data-driven prediction of traffic flow and reinforcement learning controllers that learn signal policies through simulation. Input parameters such as lane-wise vehicle counts from cameras, traffic density, queue length, waiting time and time of day are discussed, along with traffic simulators used for safe training and evaluation. A five-layer prototype architecture is proposed in which vehicle detection feeds feature construction, a regression model predicts green times, a safety and constraint layer enforces minimum and maximum phases and pedestrian crossing times, and a controller updates the signal. Research gaps, objectives, a comparison of control approaches and challenges such as sensor reliability, mixed Indian traffic and coordination across intersections are discussed.
DOI: https://doi.org/10.5281/zenodo.24127044
AI-Powered Intelligent Tutoring Systems: A Review Of Learner Modelling, Adaptive Instruction And Conversational Tutors
Authors: Mule Isha Bhagvant, Prof. R. V. Varhade, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Intelligent Tutoring Systems (ITS) aim to give every student the benefits of one-to-one tutoring by using Artificial Intelligence to understand individual needs, abilities and progress. This paper reviews AI-powered ITS. It explains the classic architecture of domain, learner, pedagogical and interface models, and surveys learner modelling through knowledge tracing with Bayesian and deep recurrent approaches, adaptive selection of content and practice, automated feedback and hints, and conversational tutors from early dialogue systems to tutors built on large language models. Evidence on effectiveness is examined, including meta-analyses comparing ITS with human tutoring and classroom instruction, and recent studies of language-model-generated hints. A five-layer AI tutoring architecture is proposed, comprising a content and domain layer, a learner model, an adaptive engine, an AI chatbot tutor and a teacher and parent dashboard with progress reports, quizzes and practice tests. Research gaps, objectives, a comparison of tutoring approaches and challenges including accuracy of generated explanations, over-reliance, privacy, equity of access and multilingual support are discussed. The review concludes that AI tutors can deliver personalized, interactive and effective learning when designed with sound pedagogy and teacher involvement.
DOI: https://doi.org/10.5281/zenodo.24127437
Deepfake Detection Using AI: A Review Of Audio, Visual And Audio–Visual Methods For Digital Forensics
Authors: Kokane Sanika Santosh, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Deepfakes are realistic manipulated images, videos and audio created with deep learning and generative models that can imitate a person's face, voice, expressions or movements. Although useful in entertainment and education, they are misused for misinformation, fake identities, fraud and reputational harm. This paper reviews AI-based deepfake detection across both visual and audio modalities. It explains generation methods, then examines visual detection from facial texture, lighting, eye and lip movement and inter-frame differences using convolutional and attention-based networks; generalizable detectors for fully synthetic images; audio detection from spectral and prosodic voice characteristics using anti-spoofing models; and audio–visual methods that detect mismatches between speech and lip motion. Benchmarks including FaceForensics++, ASVspoof and FakeAVCeleb are discussed. The detection process of collecting and preprocessing media, extracting features and applying machine learning or deep learning models is formalized in a five-layer architecture. Research gaps, objectives, a comparison of modalities and challenges such as generalization, compression, adversarial evasion and explainability for forensic use are presented. The review concludes that combining audio and visual evidence gives the most reliable detection for social media, journalism, banking, law enforcement and digital forensics.
DOI: https://doi.org/10.5281/zenodo.24127827
Real-Time Driver Drowsiness And Fatigue Detection Using Facial Landmarks And Deep Learning: A Review And Webcam-Based System Design
Authors: Dhobale Kartik Rajendra, Prof. N. G. Rokade, Prof. M. C. Kolse, Prof. S. K. Said
Abstract: Driver fatigue is one of the most common and preventable causes of road accidents. Long hours, monotonous highways and lack of rest reduce alertness, often without the driver noticing. Many existing solutions depend on wearable physiological sensors or expensive vehicle hardware that most drivers do not have. This paper reviews driver drowsiness detection approaches and presents the design of a real-time system that needs only an ordinary webcam. Behavioural, physiological and vehicle-based methods are compared, and vision-based techniques are examined in detail, including face detection, dense facial landmark extraction with MediaPipe Face Mesh, eye aspect ratio and mouth aspect ratio measures, PERCLOS and convolutional neural networks that verify eye closure and yawning. Public datasets for drowsiness and yawning are discussed. In the proposed design, OpenCV captures video, Face Mesh locates 468 landmarks, ratios are computed in every frame, and a CNN confirms closed eyes and yawns to reduce false alarms; if signs persist across consecutive frames, an audible alarm is raised. Research gaps, objectives, a comparison of methods and challenges such as night-time lighting, spectacles, head pose and individual variation are discussed.
DOI: https://doi.org/10.5281/zenodo.24127999