Chih-Ping Chu

Followers

Following

Co-author

Public Views

Interests

Uploads

Papers by Chih-Ping Chu

Establish Controllable Process Performance Model for Software Cost Prediction and Management in Software Development

Fuzzy intelligent inference scheme for self-health estimation via blood pressure and body mass index in out-of-hospital

Journal of Intelligent & Fuzzy Systems, 2015

E-health for both chronic patients and wellness persons has recently attracted the interest of re... more E-health for both chronic patients and wellness persons has recently attracted the interest of researchers and practitioners. The physical vital signs are one of the most important factors used to evaluate individual wellness. The variations of daily vital signs are even significant in analyzing physical health trends that can be applied in self-caring for individuals at home. In this paper, an Intelligent-Mamdani Inference Scheme (IMIS) based on fuzzy markup language (FML) is proposed to define approximate health conditions of the individuals via the blood pressure and the body mass index in out-of-hospital. The IMIS can fuse these vital signs and infer semantic health summary using the constructed fuzzy rules and the knowledge base. The main contributions of the this paper are: (1) to leverage personal vital signs by fuzzy logic technology for self-health management at home; (2) to design the novel scheme in detail for practicability and reproduction. The experimental results show that the scheme is feasible to infer personal health status. An individual can easily recognize self-health trend through semantic sentence generation, which further advances self-health management in out-of-hospital.

Novel Approach to Facilitating Tradeoff Multi-Objective Grouping Optimization

IEEE Transactions on Learning Technologies, 2016

The grouping problem is critical in collaborative learning (CL) because of the complexity and dif... more The grouping problem is critical in collaborative learning (CL) because of the complexity and difficulty in adequate grouping, based on various grouping criteria and numerous learners. Previous studies have paid attention to certain research questions, and the consideration for a number of learner characteristics has arisen. Such a multi-objective grouping problem is with conflicting grouping objectives, involving the benefit objective (e.g. learning achievement) and cost objective (e.g. class rank) which are conflicting in different directions. This study first proposed a novel approach based on the enhancement of a Genetic Algorithm (GA) with the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) for facilitating the tradeoff multi-objective grouping optimization, and based on the proposed approach further developed a web-based group support system to help educators for adequate grouping of homogeneous inter-group and heterogeneous intra-group. In addition, the distribution of learners in the class was considered for group formation. Two types of experiments were conducted; one involved a performance analysis against a GA and the Random approach, and the other entailed a study on CL with 90 participants. The experimental results showed the following: 1) The proposed approach is not only more effective than a GA and the Random approach but also more efficient than a GA. 2) As a grouping strategy, the proposed approach can facilitate improved learning performance with statistical significance; in other words, the developed system is able to adequately allocate learners to teams for facilitating CL.

Download

Improving Tree-Based Multicasting for Wormhole Switch-Based Networks

Fibrous products, including single fibers, yarn and fibrous webs, of improved fineness are produc... more Fibrous products, including single fibers, yarn and fibrous webs, of improved fineness are produced from extruded sheet material extruding in the form of a sheet-like, multi-layer composite stream a plurality of extrudable materials, at least one of which is a synthetic thermoplastic fiber-forming polymer and another of which is expandable or swellable in nature, which layers extend generally parallel to the faces of the stream, with each such layer containing either a fiber-forming polymer or an expandable or swellable extrudable material with the different layers being interspersed in the composite stream; solidifying this composite stream into a multi-layer sheet, not earlier than during such solidification subjecting the multi-layer sheet to a swelling or expanding treatment to aid in its mechanical disruption, and then mechanically disrupting the swollen or expanded sheet to produce a fibrous product of increased fineness. Alternatively, the other extrudable material can be incompatible with the polymer so as to separate therefrom during mechanical disruption. Instead of solidifying the extruded stream while intact, the stream can be divided during extrusion along spaced generally parallel planes extending through the stream at an angle to its faces and solidified in this divided state to form separate strips each containing a section of the multi-layer composite stream. These separate strips are then treated as indicated to at least partially remove the removable material and at least partially separate the polymeric layers therein. Alternatively, the stream can be divided and re-united before solidification.

Novel Methods for Divisible Load Distribution with Start-up Costs on a Complete b-Ary Tree

IEEE Transactions on Parallel and Distributed Systems, 2015

This work investigates divisible load distribution using multi-installment processing on complete... more This work investigates divisible load distribution using multi-installment processing on complete <italic>b</italic> -ary tree networks. Classic methods of distributing a divisible load divide the computation and communication processes into multiple time intervals in a pipelined fashion. The algorithm <inline-formula><tex-math>$\mathbb {M}$ </tex-math><alternatives><inline-graphic xlink:type="simple" xlink:href="chen-ieq1-2362137.gif"/></alternatives></inline-formula> (<italic> m</italic>ulti-installment) herein uses multi-installment processing with pipelined communication to reduce the initial distribution time and to improve the performance. Closed-form expressions for the parallel processing time and speed-up are derived. This work reveals that the asymptotic speed-up of the proposed algorithm is <inline-formula> <tex-math>$b\beta +1$</tex-math><alternatives><inline-graphic xlink:type="simple" xlink:href="chen-ieq2-2362137.gif"/> </alternatives></inline-formula> where <inline-formula><tex-math>$\beta$</tex-math><alternatives> <inline-graphic xlink:type="simple" xlink:href="chen-ieq3-2362137.gif"/></alternatives></inline-formula> is the computation-to-communication ratio of a node in the system. Algorithm <inline-formula><tex-math> $\mathbb {M}$</tex-math><alternatives><inline-graphic xlink:type="simple" xlink:href="chen-ieq4-2362137.gif"/></alternatives> </inline-formula> outperforms the classic algorithm in all cases. The algorithm <inline-formula><tex-math> $\mathbb {S}$</tex-math><alternatives><inline-graphic xlink:type="simple" xlink:href="chen-ieq5-2362137.gif"/></alternatives> </inline-formula> (<italic>s</italic>tart-up cost) that is developed herein includes the computation and communication start-up costs. Finally, two algorithms <inline-formula><tex-math>$\mathbb {M}$</tex-math><alternatives> <inline-graphic xlink:type="simple" xlink:href="chen-ieq6-2362137.gif"/></alternatives></inline-formula> and <inline-formula><tex-math> $\mathbb {S}$</tex-math><alternatives><inline-graphic xlink:type="simple" xlink:href="chen-ieq7-2362137.gif"/></alternatives> </inline-formula> are combined to form algorithm <inline-formula><tex-math>$\mathbb {MS}$</tex-math> <alternatives><inline-graphic xlink:type="simple" xlink:href="chen-ieq8-2362137.gif"/></alternatives></inline-formula> with even better performance than each.

A Novel Computational Model for Non-linear Divisible Loads on a Linear Network

IEEE Transactions on Computers, 2016

This work investigates the problem of a non-linear divisible load distribution on a homogeneous l... more This work investigates the problem of a non-linear divisible load distribution on a homogeneous linear network. A novel computational model of non-linear loads that includes complete steps for processing them, is proposed. This model solves the problem of the classical model, whose performance degrades by separating the load. This work also presents an algorithm S (Single-installment) that uses single-installment processing to distribute a non-linear divisible load on a homogeneous linear network. An algorithm M (Multi-installment) that applies multi-installment processing to reduce the initial distribution time for load is also proposed. Closed-form expressions for the parallel processing time and speed-up of the proposed algorithms are derived. The speed-up of algorithm S is much better than that of the classical algorithm that is based on the classical model. Algorithm M outperforms algorithm S in terms of speed-up when the load to be processed is very large or when the start-up costs are small.

Download

Using group fine-grained locking scheme in software transactional memory for multiprocessing systems

2010 International Computer Symposium (ICS2010), 2010

In a multi-process or multi-thread software trans-actional memory(STM) system, the transactional ... more In a multi-process or multi-thread software trans-actional memory(STM) system, the transactional locking scheme is commonly separated into fine-grained and coarsegrained schemes by protection granularity. In our definition, the protection granularity of fine-grained schemes is varied depending on implementation. Types of protection granularity include per-word, per-object, etc. The coarse-grained scheme is using a global lock for all shared resources. These two types of schemes are preferred under different test environments. The coarse-grained scheme lacks scalability under high contention situation and the fine-grained scheme produces higher overhead than coarse-grained scheme. In this paper, we propose a new type of fine-grained scheme which adds an intermediate locking level. The new scheme separates shared resources into different groups. Groups are organized under the number of executing transactions, and resources are joined to the first accessed transaction group. Thus the overhead of fine-grained scheme is reduced by locking a group of resources. In the experiment of the proposed scheme, the results showed that the new scheme preserves the scalability and reduces the overhead of fine-grained scheme.

Constructing personal concept map automatically via Correlative Test-Items Structure

2012 International Conference on Information Technology Based Higher Education and Training (ITHET), 2012

Concept map model has been widely used in e-learning for various applications. However, in the pa... more Concept map model has been widely used in e-learning for various applications. However, in the past researches, there are few attentions paid on constructing the personal concept map for diagnosing learner's learning status. Actually, it is difficult to construct the individual concept maps to reflect the real knowledge structure by learners themselves. To cope with this problem, this study proposes an approach based on Correlative Test-Items Structure to construct the personal concept map automatically. Firstly, according to the standard concept map from expert, questions for examination to test learners' abilities are formulated. After collecting individual learner's answers, an algorithm based on association rule is used to construct the personal concept map automatically, including the learning degree of each interrelated concept and independent concept. Finally, comparing with the standard concept map of expert, a near-optimal guidance learning path for adaptive learning is derived.

Fast Parallel Molecular Solution to the Hitting-Set Problem

2008 Eighth International Conference on Intelligent Systems Design and Applications, 2008

The hitting-set problem is an NP-complete problem in set theory. Assume that we have collection C... more The hitting-set problem is an NP-complete problem in set theory. Assume that we have collection C of subsets of a finite set S, and a positive integer K les |S|, and we would like to know if there is a subset S&#39; sube S with |S&#39;| les K such that S&#39; hits (contains) at least one element from each subset

A DNA-Based Algorithm for the Solution of Not-All-Equal 3-SAT Problem

2009 WASE International Conference on Information Engineering, 2009

Satisfiability problem is given a Boolean formula, and decide if a satisfying truth assignment ex... more Satisfiability problem is given a Boolean formula, and decide if a satisfying truth assignment exists. ((x12)macr or x5) nland ((x24)macr or x3 or (x13)macr or x9) nland ... nland (x12) nland (x17 or x8 or (x18)macr) is an example of Boolean formula. k-SAT means that each clause has exactly k literals. Not-all-equal (NAE) 3-SAT problem is defined by Garey and

A DNA-Based Algorithm for the Solution of One-in-Three 3-SAT Problem

2009 WASE International Conference on Information Engineering, 2009

Satisfiability problem is given a Boolean formula, and decide if a satisfying truth assignment ex... more Satisfiability problem is given a Boolean formula, and decide if a satisfying truth assignment exists.K-SAT means that each clause has exactly k literals. One in three (1IN3) 3 SAT problem is defined by Garey and Johnson in 1979 as follows: there is a set V of variables and a collection C of clauses over V such that each clause has

An improvement of tree-based multicasting for irregular switch-based networks with wormhole routing

In this paper, we propose an efficient dual-tree-based multicasting scheme with three destination... more In this paper, we propose an efficient dual-tree-based multicasting scheme with three destination- switch partition strategies on irregular switch-based networks. The dual-tree-based routing scheme sup- ports adaptive, distributed, and deadlock-free multicast on irregular networks with double channels. We first describe a dual-tree structure constructed from the irregular networks and prove that the multicast- ing based on such a structure is

Dual-tree-based multicasting on wormhole-routed irregular switch-based networks

Journal of Systems Architecture, 2002

Recently, network of workstations (NOWs) is emerging as an inexpensive alternative to massively p... more Recently, network of workstations (NOWs) is emerging as an inexpensive alternative to massively parallel processors (MPPs). The irregular switch-based networks are proposed to build NOWs for high performance parallel computing. In this paper, we address a dual-tree-based routing model and propose an efficient dual-tree-based multicasting algorithm with optimum level-based destination-switch partition strategy on irregular switch-based networks. The dual-tree-based routing scheme supports adaptive, distributed, and deadlock-free multicast on switch-based networks with double channels. We first describe a dual-tree structure established, based on the concept of network partitioning, from the irregular networks and prove that the multicasting based on this structure is deadlock-free. Then, an efficient multicast routing algorithm with optimum level-based partition strategy is proposed. Finally, the experimental results are given to show that the multicast performance based on tree-based multicasting scheme can be promoted by the dual-tree-based multicasting scheme with optimum level-based destination-switch partition strategy.

Download

Defect prevention in software processes: An action-based approach

Journal of Systems and Software, 2007

Download

Parallelizing subroutines in sequential programs

IEEE Software, 1994

An olgorithm for moking sequenftol progroms porollel first idenftfies 011 subroutines, then deter... more An olgorithm for moking sequenftol progroms porollel first idenftfies 011 subroutines, then determines the oppropriote execufton mode ond restructures code. It works recursively to porollelize the entire progrom. A prototype of a system to implement the algorithm is under development on an engineering, object-oriented sofrn.'are development, and distributed processing. Carvcr receivcd a BA in mathematics from Carson Newman College. an MS in mathematics from the University of Ten nessee, and a PhD in computer sci ence from Te xas A&.\1 U niversitv. She is a member of the IEEE Comput er Society, wh�re she serves on the board of govcrnors, and AC�i\1 .

Download

Reordering the statements with dependence cycles to improve the performance of parallel loops

Proceedings 1997 International Conference on Parallel and Distributed Systems

In this paper, we study the exploitation of statementlevel parallelism in dependence cycles of Do... more In this paper, we study the exploitation of statementlevel parallelism in dependence cycles of Do-loops executed in a random (general) synchronization mode, with emphasis on the effect of statement ordering on parallelism level. For a dependence cycle of a single parallel loop, the parallelism exposed, in general, varies with the alignment of statements. Statement reordering (without modifying the semantics) relies on the compiletime prediction of execution-time of the loop. An improved timing formula and the derived algorithm of statement reordering in single Do loop with dependence cycles to improve the pe8ormance of parallel loops are proposed and discussed.

Download

Applying Input-Output Tree to the Implementation of a Rapid Prototyping Tool for Java Web Applications

J. Inf. Sci. Eng., 2014

A prototyping tool which facilitates the design of Java applets based on existing Java classes in... more A prototyping tool which facilitates the design of Java applets based on existing Java classes in the repository is developed and embedded into an eLearning platform. An input-output tree is proposed to graphically show the data flow from the input to output of a specific application. In the future, the possible direction of using such similar application as the proposed tool will assist the programmer to assemble the reusable software components from the repository, in which the source codes are generated automatically by means of automatic programming.

Download

The in®nity Lambda test: A multi-dimensional version of Banerjee in®nity test

The Banerjee in®nity test accurately determines data dependence for one linear equation under sym... more The Banerjee in®nity test accurately determines data dependence for one linear equation under symbolic limits and any given direction vectors (U. Banerjee, Depence Analysis for Supercomputing, Kluwer Academic Publishers, Norwell, MA, 1988; P.M. Petersen, Evaluation of programs and parallelizing compilers using dynamic analysis techniques, Ph.D. Thesis, University of Illinois at Urbana±Champaign, January 1993). For m linear equations with the same constraints, as each linear equation has to be tested separately, the Banerjee in®nity test may generally lose the accuracy. In this paper, we proposed the in®nity Lambda test ± a multidimensional version of the Banerjee in®nity test. The in®nity Lambda test can be applied to deal with data dependence of coupled arrays with symbolic (unknown at compile time) bounds. Experiments with benchmark showed that the in®nity Lambda test increases the success rate of the Lambda test by approximately 12%. Ó 2000 Elsevier Science B.V. All rights reserved.

Download

An Analysis of the Root Causes of Defects Injected Into the Software by the Software Team: An Industrial Study of the Distributed Health-Care System

International Journal of Software Engineering and Knowledge Engineering, 2013

A root cause is a source of software defect, whose removal decreases or removes the defect. A roo... more A root cause is a source of software defect, whose removal decreases or removes the defect. A root cause of software defect is injected into the software by software engineers during the development process. One of the main concerns of the software team leader, such as the project manager, is to determine who injected various root causes of the defects into the software and when these have been injected. In this paper, a cost-benefit scheme is presented, which allows a software team to determine skill weakness and improve team capability. The scheme provides effective in-process feedback based on the causal analysis of software defects. The proposed analysis scheme includes orthogonal root cause definitions, role-based root cause types, and gradational correction actions. In the experiment, the projects of a distributed health-care system are used to verify the efficiency of the proposed scheme. The results show that the root cause ratios (RCR) are 33.8%, 30.6%, 21.9%, 10.7%, and 3....

Urban-Areas based Mobility Model for Wireless Network Simulations

2007 15th IEEE International Conference on Networks, 2007

... Node F then turns to ran-dom-based mobile model to look for other fares when it reached H. ..... more

Chih-Ping Chu

Uploads

Papers by Chih-Ping Chu

Log In