Un-Gu Kang

Context and profile based cascade classifier for efficient people detection and safety care system

This study propose a system of extracting and tracking objects for a multimedia system and addresses how to extract the head feature from an object area. It is observed in images taken from real-time records like a video, there is always a variance in human behavior, such as the position, size, etc. of the person being tracked or recorded. This study discusses how to extract and track multiple objects based on context as opposed to a single object. Via cascade extraction, the proposed system allows tracking of more than one human at a time. For this process, an extraction method based on internal and external contexts, which defines features to distinguish a human, is proposed. The proposed method defines shapes of shoulder and head area to recognize the head-shape of a human, and creates an extractor according to its edge information and geometrical shapes context. In this paper, humans in images are extracted and recognized using contexts and profiles. The proposed method is compared with a single face detector system and it shows better performance in terms of precision and speed. This trace information can be applied in safety care system. Extractions can be improved by validating the image using a context based detector when there are duplicated images.

Healthcare Decision Support System for Administration of Chronic Diseases

Objectives A healthcare decision-making support model and rule management system is proposed based on a personalized rule-based intelligent concept, to effectively manage chronic diseases. Methods A Web service was built using a standard message transfer protocol for interoperability of personal health records among healthcare institutions. An intelligent decision service is provided that analyzes data using a service-oriented healthcare rule inference function and machine-learning platform; the rules are extensively compiled by physicians through a developmental user interface that enables knowledge base construction, modification, and integration. Further, screening results are visualized for the self-intuitive understanding of personal health status by patients. Results A recommendation message is output through the Web service by receiving patient information from the hospital information recording system and object attribute values as input factors. The proposed system can verify patient behavior by acting as an intellectualized backbone of chronic diseases management; further, it supports self-management and scheduling of screening. Conclusions Chronic patients can continuously receive active recommendations related to their healthcare through the rule management system, and they can model the system by acting as decision makers in diseases management; secondary diseases can be prevented and health management can be performed by reference to patient-specific lifestyle guidelines.

Content-Based Filtering for Music Recommendation Based on Ubiquitous Computing

In music search and recommendation methods used in the present time, a general filtering method that obtains a result by inquiring music information and recommends a music list using users’ profiles is used. However, this filtering method presents a certain difficulty to obtain users’ information according to their circumstances because it only considers users’ static information, such as personal information. In order to solve this problem, this paper defines a type of context information used in music recommendations and develops a new filtering method based on statistics by applying it to a content-based filtering method. In addition, a recommendation system using a content-based filtering method that was implemented by a ubiquitous computing technology was used to support service mobility and distribution processes. Based on the results of the performance evaluation of the system used in this study, it significantly increases not only the satisfaction for the music selection, but also the quality of services.

Clinical decision support system in medical knowledge literature review

The current study involved methodology and content analyses of abstracts of 30 clinical decision support system (CDSS) related studies with high impact factors. The main aim of the current work was to identify the performance and efficiency of CDSS, and enhance the understanding of CDSS for a better health management among the physicians and the patients. To add structure to the current study, major research areas were categorized based on a multidimensional unfolding analysis. In this regard, eight studies were conducted based on theoretical research, ten studies were related to the system and performance of CDSS, and 12 studies verified the efficacy through analysis and evaluation of CDSS. The results indicated that the above-mentioned studies on improvement in systematic performance. Then, based on the improvement, effectively used evaluations were conducted comparably. Moreover, 14 studies analyzed patients’ data and assessed decision support system (DSS). The related findings denoted that DSS has been mainly used for patient management and a large number of studies have verified its effectiveness, using several data to ensure its accuracy and reliability. In addition, the analyzed results of the abstracts and the titles were compared to find whether the titles of the literature articles reveal their content. Using these methodological studies, the academic outlook of medical informatics could be forecasted and the academic quality could be improved by resolving the problems, arising out of system development and realization processes. Such problems can be solved through analyses and interpretation of multilateral parameters, such as the trend in academic development, research direction, topics and methods.

Design of Ubiquitous Music Recommendation System Using MHMM

The existing music search and recommendation systems obtain results through query or answer and recommend music using data mining techniques. However, it is not possible to provide active services that satisfy customers in smart home environments because these systems consider only static information in Web environments. In order to solve these problems, this paper attempts to define context information to use select music and design a ubiquitous music recommendation system that is suited to a users interests and preferences using hidden Markov model for music items. The recommendation system used in this study uses an OSGi framework to recognize context information and increase satisfaction of service.

Lifestyle Recommendation System using Framingham Heart Study based Clinical Decision Support System (CDSS)

As the standard of living rises, people are more interested in their health and desire well-being life. However they cannot make sufficient effort regarding their health and life style due to the fast moving working environment. In order to attain their sound life, it is necessary for people to have support from user customized life management service. This paper proposes lifestyle recommendation system using Framingham Heart Study based Clinical Decision Support System (CDSS). The most prominent features of this system are rule based clinical decision supporting, life style recommendation based on user’s vital signs, existence of chronic disease, life pattern and family history, as well as life style enhancement promoting service that induces user to accomplish their mental and physical healthiness based on the recommendations. The prototype system is designed and implemented using smart objects such as smart mirror and Kiosk. The doctor side application is also built to enable medical doctors to examine systems’ appropriateness of clinical use.

Design of U-Healthcare Service System Based on Personalized Model in Smart Home

U-Healthcare provides healthcare and medical services, such as prevention, diagnosis, treatment, and follow-up services whenever and wherever it is needed, and its ultimate goal is to improve quality of life. This study defines the figure of U-Healthcare personalized services for providing U-Healthcare personalized services and proposes a disease-based personalized model. Also, this study performs a design for an upper level architecture in pilot services under smart home environments. This system is designed to mutually operate it with various environments and sensors/devices through exchanging Soap and XML.

Context Model Based CF Using HMM for Improved Recommendation

Users in ubiquitous environments can use dynamic services whenever and wherever they are located because these environments connect objects and users through wire and wireless networks. Also, there are many devices and services in these environments. However, it is difficult to effectively use conventional filtering method of the recommendation system in future ubiquitous environments because it does not reflect context information well in these environments. This paper attempt to define context model and propose new Collaborative Filtering (CF) based on Hidden Markov Models (HMMs) that are trained by context information. The Collaborative Filtering using HMMs (CFH) is suited to a users interests and preferences. The Ubiquitous Recommendation System (URS) used in this study based on CFH uses an Open Service Gateway Initiative (OSGi) framework to recognize context information and connect device in smart home.

Discovery of Behavior Sequence Pattern using Mining in Smart Home

With the development of ubiquitous computing and the construction of infrastructure for one-to-one personalized services, the importance of context-aware services based on user`s situation and environment is being spotlighted. The smart home technology connects real space and virtual space, and converts situations in reality into information in a virtual space, and provides user-oriented intelligent services using this information. In this paper, we proposed the discovery of the behavior sequence pattern using the mining in the smart home. We discovered the behavior sequence pattern by using mining to add time variation to the association rule between locations that occur in location transactions. We can predict the path or behavior of user according to the recognized time sequence and provide services accordingly. To evaluate the performance of behavior consequence pattern using mining, we conducted sample t-tests so as to verify usefulness. This evaluation found that the difference of satisfaction by service was statistically meaningful, and showed high satisfaction.

Advanced Point of Care System for reducing Adverse Drug Events using 13.56/900 MHz RFID, Wi-Fi, Text-To-Speech Technology in Ajou University Hospital

In hospitals, doctors and nurses may need realtime medical data anywhere and at any time. They waste over 30% of their working time searching for and reading information about patients[1]. Furthermore, it is very difficult to record patient information in real time during medical treatment. To overcome these problems, we propose a mobile system using a PDA and a Wi-Fi network. In the United States, adverse drug events (ADEs) are the eighth leading cause of death[2]. Thirty-eight percent of ADEs occur while the nurse or clinician is administering the drug[3]. To prevent ADEs, we propose an RFID system that reduces the risk of a fatal ADE by checking the Five Rights: 1. Identify the right patient, 2. Confirm the right medication, 3. Confirm the right dosage, 4. Confirm the right route, and 5. Confirm the right time[4]. We designed and produced software called A-POC (Advanced Point of Care), and tested it in the Department of pulmonary in Ajou University Medical Center.