Motion and activity recognition and characterization, plays a major role in our life. Activity includes body’s daily life activities, body’s gestures, and its more wide sense also facial expressions. Accurate characterization of the activity, can contribute to well-being by assisting in fields like sport, and in medicine, where it enable detect abnormalities in human behavior, estimate medical score in diseases like Huntington, and Parkinson diseases, and enable continuous monitoring of medical condition. The advantages of automated medical diagnosis, while doing daily life activities are: 1) higher accuracy by applying advanced machine learning techniques and massive trained data, that can overcome human limitation and biases; 2)save patient time travel time to the clinic, clinician time, and minimize hospital resources; and 3) can be used to to optimize drag delivery. In this talk, we will review the current activity assessment methodologies, like inertial sensors and video, and will show new ways for seamless activity monitoring, achieved by deploying new sensing techniques, like radar, sonar, Kinect, and pressure sensors. We will further present advanced methods, that were tailored to the sensors, and can recognize the activity type, level, and estimate medical scores.
Gaddi Blumrosen is a scientist specializing in activity recognition, medical assessment, and medical and biological signal modeling and processing. He holds a BsC, MsC, from the Technion, Tel Aviv, respectively in electrical engineering, and Phd degree from Hebrew University in computer science and biomedical engineering. His research span different areas of signal processing and modeling, and was published in over 25 papers in leading peer reviewed journals and conferences, and he holds 4 patents. In recent years, he conducted research in Tel Aviv University in collaboration of Tel-hashomer, Berkeley, MGH-Harvard medical school, and in New York University, in activity analysis, in providing methods to determine electrical stimulation parameters, and in facial expression analysis. Recently, Gaddi has finished two years research position in sensing computational biology in IBM research at the Computational Biology Center (CBC), where he used signal processing and machine learning techniques for gestures recognition, and for evaluation of Parkinson disease severity.