Daily Archives: November 2, 2026

Authors: Dnyaneshwari Babasaheb Niwdunge, Rasika Jijabhau Gunjal, Priti Vilas Hadawale, Dr. V. M. Dhede, Prof. M. S. Nalawade

Abstract: Many personal safety devices depend on the user pressing a panic button or unlocking a smartphone, yet in a fall, a sudden medical event, an assault or harassment the person may be unable to do either. A wearable that recognises such situations by itself and calls for help silently can close this gap. This review examines the technologies needed for such a device and organises them around SilentSOS, a multimodal context-aware wearable concept. It surveys physiological sensing of heart rate and blood oxygen saturation by photoplethysmography, motion sensing and fall detection with inertial sensors, skin and ambient temperature monitoring, acoustic analysis of surrounding sounds, satellite positioning and cellular alerting. It then reviews how machine learning combines these signals so that the decision does not rest on a single sensor, which reduces both missed events and false alarms. A layered architecture is presented in which an ESP32 microcontroller acquires data from MAX30102, MPU6050, temperature and microphone sensors, extracts features, classifies the situation as normal, suspicious or high-risk, and sends an SMS with location and readings through a GSM module, with a discreet gesture available for manual activation. Design trade-offs including battery life, privacy, on-device inference and validation are discussed, together with future extensions such as ECG and blood-pressure estimation.

DOI: https://doi.org/10.5281/zenodo.23863454

Published by: vikaspatanker

Authors: Kapadi Lalita Arvind, Kurhe Yashomati Satish, Kute Ruchika Santosh, Dr. V. M. Dhede, Prof. M. S. Nalawade

Abstract: The Internet of Things (IoT) links sensors, machines, vehicles and everyday objects so that they can exchange data and act with little human intervention. Fifth-generation (5G) networks introduced dedicated support for massive machine-type and ultra-reliable low-latency communication, but emerging applications such as autonomous transport, remote surgery, immersive extended reality and large-scale digital twins demand still higher data rates, lower latency, greater reliability, precise positioning and far denser connectivity. Sixth-generation (6G) networks, now being defined under the IMT-2030 framework, aim to meet these needs and to make artificial intelligence a native part of the network. This survey reviews 6G-enabled IoT. It summarises the requirements and key performance indicators, and explains the enabling technologies: terahertz and sub-terahertz communication, intelligent reflecting surfaces, integrated sensing and communication, edge intelligence, AI-native network management and non-terrestrial networks. A five-layer architecture for 6G-enabled IoT is presented, linking devices, access, edge, core and applications under a cross-layer security and energy plane. Applications in smart cities, connected vehicles, healthcare, industrial automation, precision agriculture and environmental monitoring are discussed. Finally, open challenges including infrastructure cost, spectrum regulation, energy consumption, security and privacy, and the management of billions of devices are identified.

DOI: https://doi.org/10.5281/zenodo.23881407

Published by: vikaspatanker

Authors: Dhavale Priyal Sandesh, Dhavale Pranjal Sandesh, Gaikar Aditi Bhausaheb, Dr. V. M. Dhede, Prof. M. S. Nalawade

Abstract: The rapid growth of online services, digital education and large-scale artificial intelligence has increased the electricity demand of cloud data centres, where servers, storage, networks and cooling equipment run around the clock. Rule-based management policies, which react to fixed thresholds, often leave servers underused and cooling plants over-provisioned. Artificial intelligence (AI) offers a different approach: models learn from operational data, anticipate demand and choose actions that save energy while protecting service quality. This review examines how AI is applied to four tasks in a green data centre: forecasting workload, allocating and consolidating virtual machines, scheduling tasks with awareness of energy and carbon, and controlling cooling systems. Statistical forecasting, recurrent neural networks, reinforcement learning and data-driven cooling control are explained and compared through representative studies. An AI-based green-cloud framework is then described that combines a learning-based demand predictor, an energy- and carbon-aware scheduler, a cooling optimiser and a renewable-supply monitor in a closed control loop. A simulation-based evaluation plan using energy, response time, utilization and carbon emission as metrics is outlined. Challenges including data quality, model interpretability, safety of autonomous control and the energy cost of the AI models themselves are discussed.

DOI: https://doi.org/10.5281/zenodo.23879779

Published by: vikaspatanker

Authors: Chaskar Siddhi Dattatray, Chinchawade Tanvi Santosh, Bhore Tanvi Santosh, Prof. P. S. Dumbre, Prof. M. S. Nalawade, Dr. V. M. Dhede

Abstract: Forest fires destroy trees, wildlife habitats and natural resources, release large amounts of smoke and threaten nearby communities. Their impact depends strongly on how quickly they are detected, yet traditional methods based on watchtowers and ground patrols require continuous human effort and are slow to cover remote terrain. Satellites observe large areas but revisit a location only a few times a day and cannot see small fires under cloud or canopy. Unmanned aerial vehicles, commonly called drones, fill this gap by carrying cameras and sensors over the forest on demand. This survey reviews forest fire detection methods and focuses on drone-based systems. It discusses the sensing payload, including visible and thermal cameras and gas and temperature sensors, the detection algorithms, from colour-rule methods to convolutional neural networks, and the communication links that deliver alerts with GPS coordinates to forest authorities. Representative studies and datasets are compared. A layered architecture for a smart drone-based fire detection and alert system is then presented, covering sensing, onboard processing, communication, ground-station verification and alert dissemination. Practical challenges such as limited flight time, false alarms, communication range and regulation are discussed along with future directions such as drone swarms and integration with satellite data.

DOI: https://doi.org/10.5281/zenodo.23862991

Published by: vikaspatanker

Authors: Bhise Pallavi Ramdas, Ganjale Tanishka Jayram, Ghule Srushti Suresh, Prof. M. S. Nalawade, Dr. V. M. Dhede

Abstract: The temperature of tap water changes with the seasons. In summer, water stored in rooftop tanks and exposed pipes can become uncomfortably warm, while in winter it can feel too cold for washing or drinking. Users often wait for the water to change temperature or depend on separate coolers and heaters, which wastes water and energy. A smart adaptive tap addresses this by sensing the ambient conditions, deciding a comfortable water temperature and conditioning the water automatically. This paper reviews the technologies required for such a device. It covers temperature sensors for air and water, flow sensing to detect when the tap is in use, cooling and heating methods with emphasis on thermoelectric Peltier modules and resistive heaters, and control strategies from hysteresis to PID and fuzzy logic. Basic heat-transfer relations are used to estimate the power needed to change the temperature of flowing water, showing why a small conditioned reservoir is more practical than instantaneous cooling for most household flows. A system architecture and control flow are proposed in which a microcontroller maps ambient temperature to a target water temperature, compares it with the measured value and drives cooling or heating only while water is drawn. Applications, safety requirements, limitations and future enhancements such as user profiles and IoT monitoring are discussed.

DOI: https://doi.org/10.5281/zenodo.23879037

Published by: vikaspatanker