Integrated Computer-Aided Engineering - Volume 16, issue 3

Authors: Rubin, S.H. | Chen, S.-C.

Article Type: Introduction

DOI: 10.3233/ICA-2009-0319

Citation: Integrated Computer-Aided Engineering, vol. 16, no. 3, pp. 179-179, 2009

Authors: Novak Jr., Gordon S.

Article Type: Research Article

Abstract: Engineered systems, including computer programs, are mainly composed of versions of known components. We describe systems that produce computer software by composition and specialization of generic software components. The work of the human designer is reduced because components can infer or default many specifications, propagating them to connected components. Specialized programs can be constructed rapidly and easily using a graphical programming interface. We describe systems that can capture and understand data from the web, allowing a user to write programs easily to analyze the data. Web pages that perform calculations or data lookup can be treated as remote procedure calls, …allowing calculations, proprietary data and real-time data to be used. Examples are presented to illustrate construction of programs for analysis of web data. These capabilities provide connectivity between web data, codified knowledge, and generic programs, providing a pathway to fulfillment of the promise of integration of the vast amount of information on the web. Show more

DOI: 10.3233/ICA-2009-0312

Citation: Integrated Computer-Aided Engineering, vol. 16, no. 3, pp. 181-191, 2009

Authors: Seiffert, Chris | Khoshgoftaar, Taghi M. | Van Hulse, Jason

Article Type: Research Article

Abstract: Building a classification model on imbalanced datasets can be a challenging endeavor. Models built on data where examples of one class are greatly outnumbered by examples of the other class(es) tend to sacrifice accuracy with respect to the underrepresented class in favor of maximizing the overall classification rate. Several methods have been suggested to alleviate the problem of class imbalance. One common technique that has received much attention in recent research is data sampling. Data sampling either adds examples to the minority class (oversampling) or removes examples from the majority class (undersampling) in order to create a more balanced data …set. Both oversampling and undersampling have their strengths and drawbacks. In this work we propose a hybrid sampling procedure that uses a combination of two sampling techniques to create a balanced data set. By using more than one sampling technique, we can combine the strengths of the individual techniques while lessening the drawbacks. We perform a comprehensive set of experiments, with more than one million classifiers built, showing that our hybrid sampling procedure almost always outperforms the individual sampling techniques. Show more

Keywords: Class imbalance, classification, sampling, binary classification, hybrid sampling

DOI: 10.3233/ICA-2009-0314

Citation: Integrated Computer-Aided Engineering, vol. 16, no. 3, pp. 193-210, 2009

Authors: Harrington, Brian | Brazile, Robert | Swigger, Kathleen

Article Type: Research Article

Abstract: Standard search engines have made the task of looking for information relatively easy and painless. In sharp contrast, most relational database interfaces make searching for information complicated and confusing – mainly because they require knowledge of specialized languages and the schema of the underlying data. In this paper, the authors describe a technique that supports the querying of a relational database (RDB) using a standard search engine. The technique involves expressing database queries through URLs. The technique also includes the development of a special wrapper that can process the URL-query and generate web pages that contain the answer to the …query as well as links to additional data. By following these specialized links, a standard web crawler can index the RDB along with all the URL-queries. Once the content and their corresponding URL-queries have been indexed, a user may submit keyword queries through a standard search engine and receive the most current information in the database. Moreover, the system has been recently augmented with standard query syntax and metadata that allows users to formulate more expressive queries and search engines to index the database more efficiently. The authors describe the technique for making database content accessible to the web; they provide an evaluation of a prototype system that shows the correctness of our approach; and they present experimental results that show how adding metadata can improve the overall efficiency of the search. Show more

DOI: 10.3233/ICA-2009-0317

Citation: Integrated Computer-Aided Engineering, vol. 16, no. 3, pp. 211-223, 2009

Authors: Pathak, Jyotishman | Johnson, Thomas M. | Chute, Christopher G.

Article Type: Research Article

Abstract: In the past several years, various ontologies and terminologies such as the Gene Ontology have been developed to enable interoperability across multiple diverse medical information systems. They provide a standard way of representing terms and concepts thereby supporting easy transmission and interpretation of data for various applications. However, with their growing utilization, not only has the number of available ontologies increased considerably, but they are also becoming larger and more complex to manage. Toward this end, a growing body of work is emerging in the area of modular ontologies where the emphasis is on either extracting and managing “modules” of …an ontology relevant to a particular application scenario (ontology decomposition) or developing them independently and integrating into a larger ontology (ontology composition). In this paper, we investigate state-of-the-art approaches in modular ontologies focusing on techniques that are based on rigorous logical formalisms as well as well-studied graph theories. We analyze and compare how such approaches can be leveraged in developing tools and applications in the biomedical domain. We conclude by highlighting some of the limitations of the modular ontology formalisms and put forward additional requirements to steer their future development. Show more

DOI: 10.3233/ICA-2009-0315

Citation: Integrated Computer-Aided Engineering, vol. 16, no. 3, pp. 225-242, 2009

Authors: Tan, Li | Xu, Shenghan

Article Type: Research Article

Abstract: Supply chain strategy has become an important factor that dictates the successes of companies in today's competitive world. Nowadays more and more companies are tapping into the mergers and acquisitions in hope of getting the synergistic gain in supply chain consolidation. In this paper we use a model-checking-based approach to study the impact of different consolidation strategies on risks in supply chains and compare their capacity of risk reduction. We model stochastic behaviors of supply chains using an extension of Markov Decision Processes and translate the goal of risk analysis into a temporal logic. We then apply probabilistic model checking …to analyzing risks inherent in a stochastic supply chain model. In our computational study, we consider three different consolidation strategies initially modeled in [18] and compare their capability of risk reduction in a generic three-echelon supply chain network. Our results reveal some key factors that improve the benefit of supply chain consolidation on risk reduction. Show more

DOI: 10.3233/ICA-2009-0318

Citation: Integrated Computer-Aided Engineering, vol. 16, no. 3, pp. 243-257, 2009

Authors: Sung, Cheng-Lung | Lee, Cheng-Wei | Yen, Hsu-Chun | Hsu, Wen-Lian

Article Type: Research Article

Abstract: We propose an alignment-based surface pattern approach, called ABSP, which integrates semantic information into syntactic patterns for question answering (QA). ABSP employs a new strategy to extract surface patterns from non-segmented passages. It uses the surface patterns to extract important terms from questions, and then constructs the terms' relations from sentences in the corpus. Finally, the relations are used to rank answer candidates. Our experiments show that ABSP is highly accurate, and it can be incorporated into other QA systems that have high coverage. It can also be used in cross-lingual QA systems. The approach is robust and portable to …other domains. Show more

DOI: 10.3233/ICA-2009-0313

Citation: Integrated Computer-Aided Engineering, vol. 16, no. 3, pp. 259-269, 2009

Authors: Lin, Ryan T.K. | Chiu, Justin Liang-Te | Dai, Hong-Jie | Tsai, Richard Tzong-Han | Day, Min-Yuh | Hsu, Wen-Lian

Article Type: Research Article

Abstract: Biologists rely on keyword-based search engines to retrieve superficially relevant papers, from which they must filter out the irrelevant information manually. Question answering (QA) systems can offer more efficient and user-friendly ways of retrieving such information. Two contributions are provided in this paper. First, a factoid QA system is developed to employ a named entity recognition module to extract answer candidates and a linear model to rank them. The linear model uses various semantic features, such as named entity types and semantic roles. To tune the weights of features used by the model, a novel supervised learning algorithm, which only …needs small amounts of training data, is provided. Second, a QA system may assign several answers with the same score, making evaluation unfair. To solve this problem, an efficient formula for a mean average reciprocal rank (MARR) is proposed to reduce the complexity of its computation. After employing all effective semantic features, our system achieves a top-1 MARR of 74.11% and top-5 MARR of 76.68%. In comparison of the baseline system, the top-1 and top-5 MARR increase by 9.5% and 7.1%. In addition, the experiment result on test set shows our ranking method, which achieves 55.58% top-1 MARR and 66.99% top-5 MARR, significantly surpasses traditional BM25 and simple voting in performance by averagely 35.23% and 36.64%, respectively. Show more

DOI: 10.3233/ICA-2009-0316

Citation: Integrated Computer-Aided Engineering, vol. 16, no. 3, pp. 271-281, 2009