Kyeong-Hoon Do

Iterative relaxational stereo matching based on adaptive support between disparities

Abstract An adaptive relaxation method for stereo matching using matching probability and compatibility coefficients between disparities is presented. Relaxation labeling is an iterative procedure which reduces local ambiguity and noise, and selects the best label among several possible choices using compatibility coefficient. Stereo matching can be considered as labeling problem which assigns unique matches to feature points in the image. The compatibility coefficient between disparity classes is determined from highly reliable matches in the initial matching result and quantitatively expressed. The matching results of neighbor pixels support the center pixel through compatibility coefficients and update its matching probability. As the true matching results are propagated, so false matches are corrected and have high probability values. The conventional matching algorithms permit a uniform support from different disparity regions and it causes the degradation phenomena on the discontinuities of object. The results of experiments show that the proposed adaptive supporting method reduces the degradations and obtains fast convergence.

Health Decision Support for Biomedical Signals Monitoring System over a WSN

A biomedical signals monitoring system with multiple physiological signs measurement capability in real time is designed and implemented. This system performs a local vital sign data analysis using cell phone over wireless sensor network (WSN) technology and code division multiple access (CDMA) network. Cell phone-based personal medical recorder becomes popular to facilitate self-control of chronic diseases and observe patients’ condition continuously. The risk of ignoring monitoring patients’ physiological data by doctor is concerned since large quantities of data are processed and analyzed daily. An intelligent decision support system is developed to enhance healthcare providers’ review of monitoring data.

Mobile u-healthcare system in IEEE 802.15.4 WSN and CDMA network environments

This paper describes a robust mobile u-healthcare system with multiple physiological signs measurement capability in real time with integration of WSN(wireless sensor network) technology and CDMA(code division multiple access) network. A cellular phone receives health data in WSN and performs local physiological signs analysis at a phone processor, and then transmits abnormal data to server for further detail or precise health signal evaluation by a medical doctor over a CDMA network. Physiological signs of the patients are continuously monitored, processed and analyzed locally at cellular phone process to produce useful medical information for diagnosis and tracking purposes. By local simple analysis in cellular phone processor we can save the data transmission cost in CDMA network. By using the developed integrate ubiquitous healthcare service architecture, patients can realize self-health checking so that the prevention actions can be taken earlier. Appropriate self-monitoring and self-management can cure disease and relieve pain especially for patients who suffer from chronic diseases that need long term observation.

A SOLUTION OF REAL-WORLD OCST PROBLEMS WITH A NEW TREE ENCODING-BASED GENETIC ALGORITHM

For embodying and implementing the ubiquitous computing environments, the recent increase in concern for communication systems has been leading the evolution of the theory and technology of the related fields. Among these network-related problems, the minimum spanning tree (MST) problems have many applications in the communication systems field, because they are solved as one of the conventional combinatorial optimization problems. In particular, the optimal communication spanning tree (OCST) problem is a famous application of the MST problem. The OCST problem is defined by finding a spanning tree that connects all nodes and satisfies their communication requirements for connecting all nodes. This OCST problem can be applied to many network optimization fields, such as network topology design, multicast tree configuration, and ad-hoc network or ubiquitous sensor network routing, etc. This paper presents a genetic algorithm with a new encoding method, which is based on the Prüfer number (PN) and a clustering string, for solving the OCST problems. We will also demonstrate that the efficiency and effectiveness of our proposed method can be shown by several experimental results, employing the proposed method as the solution method of the OCST problems.

A Solution of Real-World OCST Problems through GA with a New Tree Encoding

For implementing the ubiquitous computing environments, the recent increasing attraction on communication systems has been driving the theory and technology of the related fields. Among these related problems, the minimum spanning tree (MST) problems, which are one of the basic combinatorial optimization problems, have many applications in the communication systems. Especially, the optimal communication spanning tree (OCST) problem is the famous application of MST problem. The OCST problem is defined by finding a spanning tree that connects all nodes and satisfies their communication requirements for connecting all nodes. This OCST problem can be applied in the many network optimization problems, such as network topology design problems, multicast tree configuration problems, and ad-hoc network or ubiquitous sensor network routing problems, and so forth. This paper presents a genetic algorithm with a new encoding method, which is based on the Prufer number (PN) and a clustering string, for solving the OCST problems. Finally, we will see clearly that the efficiency and effectiveness of our proposed method, employed as the solution method of the OCST problems, can be shown by several experimental results.