As medical data and information technologies advance, an increasing number of practitioners are recognizing or planning to use artificial intelligence. Radically alter medical practice through the use of cutting-edge machine learning techniques. Research is now being done to determine how machine learning and predictive analysis might be used to tailor individual therapies. In order to create a medical model that can rapidly and reliably forecast new data, machine learning must first learn a large quantity of medical data and investigate the dependencies in data concentration. This allows for the early detection of diseases and the support of therapeutic decisions. Clinical medicine must continue to identify and treat severely ill emergency patients quickly while dealing with a relative paucity of medical resources. The age of big data has made clinical demands and thoughtful medical treatment generate demand. The solution to the fore mentioned challenges lies in the assistance supplied by machines.
We consider the task of speech based automatic classification of patients with amyotrophic lateral sclerosis (ALS) and healthy subjects. The role of different speech tasks and recording devices on classification accuracy is examined. Sustained phoneme production (PHON), diadochokinetic task (DDK) and spontaneous speech (SPON) have been used as speech tasks. The chosen five recording devices include a high quality microphone and built-in smartphone microphones at various price ranges. Experiments are performed using speech data from 25 ALS patients and 25 healthy subjects using support vector machines and deep neural networks as classifiers and suprasegmental features based on mel frequency cepstral coefficients. Results reveal that DDK consistently performs better than SPON and PHON across all devices for discriminating ALS patients and healthy subjects. Considering DDK, the best classification accuracy of 92.2% is obtained using a high quality microphone but the accuracy drops if there is a mismatch between the microphones for training and test. However, a classifier trained with recordings from all devices together performs more uniformly across all devices. The findings from this study could aid in determining the choice of the task and device in developing an assistive tool for detection and monitoring of ALS.
It is a must to bring the fall detection system in to use with the increasing number of elder people in the world, because the most of them tend live voluntarily and at risk of injuries. Falls are dangerous in a few cases and could even lead to deadly injuries. A very robust fall detection
system must be built in order to counter this problem. Here, we establish fall detection and recognition of daily live behavior through machine learning system. In order to detect different types of activities, including the detection of falls and day to-day activities, We use 2 shared archives
for the accelerating and lateral speed data during this development. Logistic regression is used to determine motions such as drop, walk, climb, sit, stand and lie bases on the accelerating data and data on angular velocities. More specifically, the triaxial acceleration average value is used
to achieve fall detection accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.