Big Data Analytics in Health Monitoring at Home

This paper proposed a big data analytics approach applied in the projects ESS-H and E-care@home in the context of biomedical and health informatics with the advancement of information fusion, data abstraction, data mining, knowledge discovery, learning, and reasoning [1][2].Data are collected through the projects, considering both the health parameters, e.g. temperature, bio-impedance, skin conductance, heart sound, blood pressure, pulse, respiration, weight, BMI, BFP, movement, activity, oxygen saturation, blood glucose, heart rate, medication compliance, ECG, EMG, and EEG, and the environmental parameters e.g. force/pressure, infrared (IR), light/luminosity, photoelectric, room-temperature, room-humidity, electrical usage, water usage, RFID localization and accelerometers. They are collected as semi-structured/unstructured, continuous/periodic, digital/paper record, single/multiple patients, once/several-times, etc. and stored in a central could server [5]. Thus, with the help of embedded system, digital technologies, wireless communication, Internet of Things (IoT) and smart sensors, massive quantities of data (so called ‘Big Data’) with value, volume, velocity, variety, veracity and variability are achieved [2].The data analysis work in the following three steps. In Step1, pre-processing, future extraction and selection are performed based on a combination of statistical, machine learning and signal processing techniques. A novel strategy to fuse the data at feature level and as well as at data level considers a defined fusion mechanism [3]. In Step2, a combination of potential sequences in the learning and search procedure is investigated. Data mining and knowledge discovery, using the refined data from the above for rule extraction and knowledge mining, with support for anomaly detection, pattern recognition and regression are also explored here [4]. In Step3, adaptation of knowledge representation approaches is achieved by combining different artificial intelligence methods [3] [4]. To provide decision support a hybrid approach is applied utilizing different machine learning algorithms, e.g. case-based reasoning, and clustering [4].The approach offers several data analytics tasks, e.g. information fusion, anomaly detection, rules and knowledge extraction, clustering, pattern identification, correlation analysis, linear regression, logic regression, decision trees, etc. Thus, the approach assist in decision support, early detection of symptoms, context awareness and patient’s health status in a personal environment.