Mu-Hsing Kuo

Building and evaluating a location-based service recommendation system with a preference adjustment mechanism

The location-based service (LBS) of mobile communication and the personalization of information recommendation are two important trends in the development of electric commerce. However, many previous researches have only emphasized on one of the two trends. In this paper, we integrate the application of LBS with recommendation technologies to present a location-based service recommendation model (LBSRM) and design a prototype system to simulate and measure the validity of LBSRM. Due to the accumulation and variation of preference, in the recommendation model we conduct an adaptive method including long-term and short-term preference adjustment to enhance the result of recommendation. Research results show, with the assessments of relative index, the rate of recommendation precision could be 85.48%.

An intelligent agent-based collaborative information security framework

Abstract In this paper we proposed a framework for collaborative intelligent agents in a distributed environment to execute sound security strategies for protecting information resources. First, the intelligent agent-based Duty Reliable Center (DRC) in the model uses the group decision method to determine a global information threat level. With the threat level, local agent employs the Bayes’ decision procedure to calculate the expected loss of its all-possible actions, and then chooses an action among them with the minimum expected loss to protect its information resources. The proposed framework enables an agent to choose among alternatives in an optimal fashion, taking into account the worth of acquiring prior information to reduce uncertainty. Because system operations are distributed, hackers are unlikely to wreck the whole system. Thus, it is expected to yield information security cost-effective solutions.

Cloud computing for healthcare research information sharing

With the widespread application of healthcare Information and Communication Technology (ICT), constructing a stable and sustainable data sharing circumstance has attracted rapidly growing attention in both academic research area and healthcare industry. Cloud computing is one of long dreamed visions of Healthcare Cloud (HC), which matches the need of healthcare information sharing directly to various health providers over the Internet, regardless of their location and the amount of data. In this paper, we discuss important research tool related to health information sharing and integration in HC and investigate the arising challenges and issues. We describe many potential solutions to provide more opportunities to implement EHR cloud. As well, we introduce the development of a HC related collaborative healthcare research example, thus illustrating the prospective of applying Cloud Computing in the health information science research.

A Proof of Concept for Assessing Emergency Room Use with Primary Care Data and Natural Language Processing

OBJECTIVE The objective of this study was to undertake a proof of concept that demonstrated the use of primary care data and natural language processing and term extraction to assess emergency room use. The study extracted biopsychosocial concepts from primary care free text and related them to inappropriate emergency room use through the use of odds ratios. METHODS De-identified free text notes were extracted from a primary care clinic in Guelph, Ontario and analyzed with a software toolkit that incorporated General Architecture for Text Engineering (GATE) and MetaMap components for natural language processing and term extraction. RESULTS Over 10 million concepts were extracted from 13,836 patient records. Codes found in at least 1% percent of the sample were regressed against inappropriate emergency room use. 77 codes fell within the realm of biopsychosocial, were very statistically significant (p < 0.001) and had an OR > 2.0. Thematically, these codes involved mental health and pain related concepts. CONCLUSIONS Analyzed thematically, mental health issues and pain are important themes; we have concluded that pain and mental health problems are primary drivers for inappropriate emergency room use. Age and sex were not significant. This proof of concept demonstrates the feasibly of combining natural language processing and primary care data to analyze a system use question. As a first work it supports further research and could be applied to investigate other, more complex problems.

Automatic extraction of quadric surfaces from wire-frame models

Abstract The automatic conversion of 3D wire-frame models to boundary representation solids is very important for the one-off conversion of line drawing to solid modeling system. In this paper, a minimum internal angle (MIA) algorithm that efficiently finds all quadric surfaces in a wire-frame model is proposed. It requires considerably less searching time than depth-first search that could grow exponentially in complexity. In addition, the proposed method is advantageous in easy description of the geometry of the traced surfaces when compared to other methods.

Design and Construction of a Big Data Analytics Framework for Health Applications

We propose to establish a framework for supporting Big Data Analytics (BDA) on real healthcare big data. To test the analytic framework, we used UVic WestGrid (4412 cores computer cluster) to analyze the emulation of 10 billion healthcare records that represented the main hospital system and its reporting via its data warehouse stored at Vancouver Island Health Authority (VIHA). The study showed that the build of the BDA platform requires changes to the configurations to the MapReduce component of Hadoop (HDFS) and to the indexing of HBASE. The ingestion and replication of the data over a large volume iteratively offers a method for data migration of large volumes of real healthcare data via HDFS and to query in that some distributed filing system. Furthermore, the query performance was very satisfied via Apache Phoenix layer that is run in parallel across all nodes on HBASE. The study has demonstrated that the proposed BDA process and configuration met patient data security and performance requirements of healthcare BDA.

Human Factors in the Large: Experiences from Denmark, Finland and Canada in Moving Towards Regional and National Evaluations of Health Information System Usability

OBJECTIVES The objective of this paper is to explore approaches to understanding the usability of health information systems at regional and national levels. METHODS Several different methods are discussed in case studies from Denmark, Finland and Canada. They range from small scale qualitative studies involving usability testing of systems to larger scale national level questionnaire studies aimed at assessing the use and usability of health information systems by entire groups of health professionals. RESULTS It was found that regional and national usability studies can complement smaller scale usability studies, and that they are needed in order to understand larger trends regarding system usability. Despite adoption of EHRs, many health professionals rate the usability of the systems as low. A range of usability issues have been noted when data is collected on a large scale through use of widely distributed questionnaires and websites designed to monitor user perceptions of usability. CONCLUSION As health information systems are deployed on a widespread basis, studies that examine systems used regionally or nationally are required. In addition, collection of large scale data on the usability of specific IT products is needed in order to complement smaller scale studies of specific systems.

Extracting association rules from liver cancer data using the FP-growth algorithm

The five-year survival rate of liver cancer is low, 14% according to the Surveillance, Epidemiology, and End Results (SEER) Program database of the National Cancer Institute from 2003 to 2007 [3]. Since in the early stages of liver cancer, patients usually do not show signs or symptoms, improving early diagnosis is essential in order to reduce morbidity and mortality rates. Association rule mining, a popular method for discovering interesting hidden relationships or patterns between variables in large databases, has demonstrated benefit when applied to cancer detection and management. To date, however, no studies have applied it to liver cancer. The objective of this study was to apply the FP-growth association algorithm to discover patterns from liver cancer data, which can hopefully be used for early detection.

Interpretation of 3-view engineering drawings as central quadric surface mechanical parts

Previous work on the reconstruction of planar-faced objects from 3-view engineering drawings is extended, to include objects having central quadric surfaces with conic-section boundary edges. Multiple solutions are available from the algorithm and pathological situations arising from back-projection are eliminated. The algorithm accepts a wider variety of curved surface objects and imposes fewer restrictions on acceptable input drawings than previous methods.

Interactive Healthcare Big Data Analytics Platform under Simulated Performance

To utilize data from hospital systems, big data analytics (BDA) has become increasingly important. BDA enable queries of large highly diverse and real volumes of patient data in an interactively dynamic way that enriches the use of the platform with data visualization for healthcare. We established a Healthcare BDA (HBDA) platform at the University of Victoria (UVic) with Compute Canada/Westgrid, and Vancouver Island Health Authority (VIHA), Victoria, BC, Canada. The framework was a proof-of-concept implementation that tested emulated patient data representative of the main hospital system at VIHA. We cross-referenced all data, its profiles and metadata, with the existing clinical reporting. Our HBDA platform and its performance was tested for different patient query types in simulation with the data ingested into Hadoop file system over different applications of Apache Spark with Zeppelin and Jupyter web-based interfaces, and Apache Drill interfaces. The results showed that the ingestion time of one billion records took circa 2 hours via Apache Spark. Apache Drill outperformed Spark/Zeppelin and Spark/Jupyter. However, it was restricted to running more simplified queries, and very limited in its visualizations exhibiting poor usability for healthcare. Zeppelin running on Spark showed ease-of-use interactions for health applications, but it lacked the flexibility of its interface tools and required extra setup time before running queries. Jupyter on Spark offered high performance stacks not only over our HBDA platform but also in unison to run all queries simultaneously with high usability for a variety of reporting requirements by providers and health professionals.