The prevalence of automobile accidents as a major cause of violent deaths around the world has prompted researchers to develop an automated method for detecting them. The effectiveness of medical response to accident scenes and the chances of survival are influenced by the human element, underscoring the need for an automated system. With the widespread use of video surveillance and advanced traffic systems, researchers have proposed a model to automatically detect traffic accidents on video. The proposed approach assumes that visual elements occurring in a temporal sequence correspond to traffic accidents. The model architecture consists of two phases: visual feature extraction and temporal pattern detection. Convolution and recurrent layers are employed during training to learn visual and temporal features from scratch as well as from publicly available datasets. The proposed accident detection and alerting system using Convolution Neural Network models with Rectified Linear Unit and Softmax activation functions is an effective tool for detecting different types of accidents in real-time. The system of accident detection, integrated with the alerting mechanism for prompt medical assistance achieved high accuracy and recall rates.

An epileptic seizure is a type of seizure induced by aberrant brain activity caused by an epileptic condition, which is a brain Central Nervous System disorder (CNS). CNSs are relatively prevalent and include a wide range of symptoms, including loss of awareness, and strange behaviour. These symptoms frequently result in injuries as a result of walking imbalance, tongue biting, and hearing loss. For many researchers, detecting a prospective seizure in advance has been a difficult undertaking. In this research work we have used non-imaging data and applied supervised learning algorithms to determine the classification of epilepsy and try to improve the efficiency of the model, compared to the existing ones. Random Forest algorithm was found to have highest accuracy compared to other machine learning models. The paper can be helpful in diagnosing high-risk brain diseases and predicting diseases such as Alzheimer's with symptoms challenging to predict and diseases with overlapping symptoms and overlapping symptoms and attribute values. The scope of the research work can be further extended to determine at which stage the epilepsy is present in a patient, in order to provide a correct diagnosis and medical treatment.