Search

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.jss.2010.05.074 Byline: Thi Hong Nhan Vu (a), Namkyu Park (a), Yang Koo Lee (b), Yongmi Lee (b), Jong Yun Lee (c), Keun Ho Ryu (b) Keywords: Neural network; Wireless sensor network; Heart Rate Variability; Healthcare services Abstract: Recent years, advances in day-to-day wearable sensors have led to the development of low powered physiological sensor platforms, which can be integrated in body area networks, a new enabling technology for real-time health monitoring. The bottleneck in health state awareness is the algorithm that has to interpret the sensor data. Nowadays Coronary Heart Disease (CHD) is still the leading cause of death. Many classification techniques such as decision tree and neural networks proposed for an early detection of individual at risk for CHD are not able to continuously detect heart state based on sensor data stream. In this study, we propose an online three-layer neural network to recognize Heart Rate Variability (HRV) patterns related to CHD risk in consideration of daily activities. ECG sensor data is preprocessed using Poincare plot encoding. Incremental learning is utilized to train the network with new data without forgetting the previously learned patterns. The algorithm is named Poincare-based HRV patterns discovering Incremental Artificial neural Network (PHIAN). When a sample is presented, the nodes in the hidden layer of PHIAN compete for determining the node with the highest similarity to the input. Error variables associated with the neuron units are used as criteria for new node insertion in hopes of allowing the network to learn new patterns and reducing classification error. However, the node insertion has to be stopped in the overlapping decision areas. We suppose that the overlaps between classes have lower probability than the centric part of the classes. Therefore, after a period of learning we remove the nodes with no neighbor. Plus, the error probability density is taken into account instead of input probability density. Finally, the predictive capability of PHIAN is compared with three previous classification models, namely Self-Organizing Map (SOM), Growing Neural Gas (GNG), and Multilayer Perceptron (MLP) in terms of classification error and network structure. The results show that PHIAN outperforms the existing techniques. Our proposed model can be efficiently applied to early detection of abnormal conditions and prevent the abnormal becoming serious. Author Affiliation: (a) Department of Industrial and Systems Engineering, Ohio University, Athens, OH, USA (b) Department of Computer Science, Chungbuk National University, Cheongju, Republic of Korea (c) Department of Computer Education, Chungbuk National University, Cheongju, Republic of Korea Article History: Received 24 May 2009; Revised 7 May 2010; Accepted 14 May 2010

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.jss.2008.07.037 Byline: Yong Joon Lee (a), Jun Wook Lee (a), Duck Jin Chai (b), Bu Hyun Hwang (c), Keun Ho Ryu (b) Keywords: Data mining; Temporal data; Rule mining; Interval temporal mining Abstract: Temporal data mining is still one of important research topic since there are application areas that need knowledge from temporal data such as sequential patterns, similar time sequences, cyclic and temporal association rules, and so on. Although there are many studies for temporal data mining, they do not deal with discovering knowledge from temporal interval data such as patient histories, purchaser histories, and web logs etc. We propose a new temporal data mining technique that can extract temporal interval relation rules from temporal interval data by using Allen's theory: a preprocessing algorithm designed for the generalization of temporal interval data and a temporal relation algorithm for mining temporal relation rules from the generalized temporal interval data. This technique can provide more useful knowledge in comparison with conventional data mining techniques. Author Affiliation: (a) Telematics USN Research Division, Electronics and Telecommunications Research Institute, Republic of Korea (b) Database Laboratory, School of Electrical and Computer Engineering, Chungbuk National University, 12 Gaeshin-Dong, Heungduk-Gu, Cheongju, Chungbuk 361-763, Republic of Korea (c) Department of Computer Science, Chonnam National University, 300 Yongbong-dong, Gwangju 500-757, Republic of Korea Article History: Received 29 July 2005; Revised 22 July 2008; Accepted 22 July 2008