Traffic congestion and inefficiencies in traffic management systems continue to be a major problem in many cities around the world, including India. In this research, we aim to propose a dynamic, sensor-based traffic signal system that addresses the inefficiencies of static traffic management systems in India. The system proposed in this paper adapts the timing of signals based on traffic density on each lane and includes an IoT-based emergency override feature for an ambulance or VIP guest arrivals. We have also implemented a digital circuit that uses a decoder with select lines to manage and keep multiple lanes active at the same time without interference. This study includes a Verilog implementation of the digital circuit and a GUI-based Python implementation of the decoder-based circuit, which shows that the proposed system can significantly improve traffic management, reduce delays and congestion, and provide a more efficient response to emergencies. By combining sensor technology, IoT capabilities, and digital circuitry, the proposed system represents a significant step forward in traffic signal management and has the potential to be implemented in other cities and countries facing similar challenges.

Availability of key human parameters located remotely, to a trained medical professional can result in early diagnosis and prognosis of a patient, leading to better healthcare and thereby reducing the patient load in government hospitals. However, the testing of these key parameters requires sophisticated equipment and trained manpower, which requires heavy investment. The setup for ECG measurement in multi- specialty hospitals is quite costly and bulky, involving 12 sensors, which are attached to the patient’s limbs and chest. This study aims to develop machine-learning models, which can identify whether the cardiac rhythm is normal or abnormal directly using the sample values of the ECG waves, using just 3 leads instead of 12, hence reducing the complexity of setup. Secondly, the research aims at comparing the accuracy of several algorithms for this binary classification of rhythm. Lastly, the dataset used during the study has been prepared and processed on the basis of actual data of ECG records of heart patients by visiting various hospitals in Nagpur city.

Providing remote access to important health data for people can help detect and understand medical issues earlier, which can lead to better healthcare and lessen the pressure on hospitals. However, testing these health indicators usually needs expensive equipment and trained staff, which isn't available in remote areas. So, people in these places often have to spend money to travel to city hospitals for treatment. This research suggests creating a small device that can measure things like body temperature, ECG, and PPG without being invasive. It could also calculate heart rate and blood pressure. The focus is on making the device as small and light as possible. The study includes building a prototype and testing it, and looks at ways to improve it for better accuracy in the future.

People with speaking or auditory impairments frequently utilize sign language, which is a method of visual motions and signals. It's crucial to comprehend the gestures these individuals use to communicate to integrate them into the society of verbal communicators. People who don't utilize the gesture in everyday life frequently don't grasp what it means. Several algorithms have been developed for image detection and one such algorithm is YOLOv5. This research paper gives an in-depth comparison for performance analysis of the YOLOv5 algorithm using several frameworks like TensorFlow and PyTorch, on several computing devices with different micro-controllers such as Intel, raspberry-pi, etc. Further, thisresearch specifically also shows a comparison indicating which alphabets are particularly giving false positives or falsenegatives and hence leading to a decrease in the accuracy and performance of the model. Lastly, this paper throws light on ifsomeone wishes to design a product and commercialize it, then the Raspberry Pi platform, accompanied by the TensorFlow-fp16 framework at 320 image size and weight would be the best choice considering all other parameters.