Search

Early fall detection imposes a challenge for preventing life-threatening conditions to the health in geriatrics. As per the World Health Organization, around that half of total elderly individuals fall every year, which is considered a major cause of death. Fall-down detection and prediction is an active research topic to track seniors who reside at home alone or under treatment in a hospital. With the advancement of pervasive sensing technology and artificial intelligence techniques, automatic and contactless fall detection is now possible via passive monitoring systems. However, such systems’ accuracy is not up to an admissible limit due to the context and ambient conditions. Among the two main categories of fall detection systems, such as wearable sensor-based and contactless sensor-based, security issues of wearable sensor-based detection systems make it unacceptable to researchers. Moreover, wearable sensors are required to be worn by the user for a longer period, making it undesirable by the users. As a result, throughout recent years, ambient and wireless sensor-based systems have been commonly used for fall detection. To define existing approaches for potential research directions, it is important to analyze the elderly fall detection system’s ongoing practices. This book chapter aims to provide a detailed overview of different existing methods/systems of fall detection based on contactless sensors.

Every year around one million women are diagnosed with breast cancer. Conventionally it seems like a disease of the developed countries, but the fatality rate in low and middle-income countries is preeminent. Early detection of breast cancers turns out to be beneficial for clinical and survival outcomes. Machine Learning Algorithms have been effective in detecting breast cancer. In the first step, four distinct machine learning algorithms (SVM, KNN, Naive Bayes, Random forest) were implemented to show how their performance varies on different datasets having different set of attributes or features by keeping the same number of data instances, for predicting breast cancer and it’s recurrence. In the second step, analyzed different sets of attributes that are related to the performance of different machine learning classification algorithms to select cost-effective attributes. As outcomes, the most desirable performance was observed by KNN in breast cancer prediction and SVM in recurrence of breast cancer. Again, Random Forest predicts better for recurrence of breast cancer and KNN for breast cancer prediction, while the less number of attributes were considered in both the cases.

Nowadays, cardiovascular diseases are considered as one of the fatal and main reasons for mortality all around the globe. The mortality or high-risk rate can be reduced if an early detection system for cardiovascular disease is introduced. A massive amount of data gets collected by healthcare organizations. A proper and careful study regarding the data can be carried out to extract some important and interesting insight that may help out the professionals. Keeping that in mind, in this paper, at first six distinct machine learning algorithms(Logistic Regression, SVM, KNN, Naive Bayes, Random Forest, Gradient Boosting) were applied to four different datasets encompasses different set of features to show their performance over them. Secondly, the prediction accuracy of the ML algorithms was analyzed to find out the best set of features and the best algorithm to predict cardiovascular diseases. The results find out the best suited eleven feature and also showed that Random Forest performs well in terms of accuracy in predicting cardiovascular diseases.