Find Research Output

Research Output
  • All
  • Scholar Profiles
  • Research Units
  • Research Output
Department Publication Year Content Type Data Sources


Clear all

1.MidSens'09 - International Workshop on Middleware Tools, Services and Run-Time Support for Sensor Networks, Co-located with the 10th ACM/IFIP/USENIX International Middleware Conference Preface

Author:Michiels, Sam ; Hughes, Danny

Source:MidSens'09 - International Workshop on Middleware Tools, Services and Run-Time Support for Sensor Networks, Co-located with the 10th ACM/IFIP/USENIX International Middleware Conference,2009,Vol.

2.Artificial neural networks for optimization of gold-bearing slime smelting

Author:Liu, D;Yuan, YD;Liao, SF


Abstract:Pyrometallurgy is often used in the industrial process for treating gold-bearing slime. Slag compositions have remarkable influences on the recovery of gold and the gold content in slag. A method for determining optimum flux compounding with neural networks is studied in this paper, and the neural network model for estimating the gold contents with different slag compositions is presented. On the basis of the neural network model, an algorithm for searching the optimum flux compounding in the gold-slime smelting process is proposed, and the optimum flux compositions are obtained accordingly. (C) 2009 Elsevier Ltd. All rights reserved.

3.Gait classification in children with cerebral palsy by Bayesian approach

Author:Zhang, Bai-ling ; Zhang, Yanchun ; Begg, Rezaul K.

Source:Pattern Recognition,2009,Vol.42

Abstract:Cerebral palsy (CP) is a non-progressive neuro-developmental condition that occurs in early childhood and is associated with a motor impairment, usually affecting mobility and posture. Automatic accurate identification of CP gait has many potential applications, for example, assistance in diagnosis, clinical decision-making and communication among the clinical professionals. In previous studies, support vector machine (SVM) and neural networks have been applied to classify CP gait patterns. However, one of the disadvantages of SVM and many neural network models is that given a gait sample, it only predicts a gait pattern class label without providing any estimate of the underlying probability, which is particularly important in computer aided diagnostics applications. The objective of this study is to first investigate different pattern classification paradigms in the automatic gait analysis and address the significance of Bayesian classifier model, and then give a comprehensive performances comparison. Bayesian classification is based on Bayes' decision theory, which compute the probability of a given data point belonging to a class. Then among all classes, we choose the one that has the largest probability, and classify the data point as being of that class. Using a publicly available CP gait data set (68 normal healthy and 88 with spastic diplegia form of CP), different features including the two basic temporal-spatial gait parameters (stride length and cadence) have been experimented. Various hold-out and cross-validation testing show that the Bayesian model offers excellent classification performances compared with some popular classifiers such as random forest and multiple layer perceptron. With many advantages considered, Bayesian classifier model is very significant in establishing a clinical decision system for gait analysis. © 2008 Elsevier Ltd. All rights reserved.

4.A technique for blood detection in wireless capsule endoscopy images

Author:Penna, Barbara ; Tillo, Tammam ; Grangetto, Marco ; Magli, Enrico ; Olmo, Gabriella

Source:European Signal Processing Conference,2009,Vol.

Abstract:Wireless capsule endoscopy is an innovative technology for visualizing anomalies in the gastrointestinal tract, useful to replace traditional endoscopic diagnosis. Its advantages are related to the capability to reach the duodenum and small intestine, while eliminating the discomfort of patients. The time spent by a physician analyzing the results of wireless capsule endoscopy video can vary between 45 and 180 minutes, limiting its widespread diffusion. Therefore, methods able to perform an automatic pre-screening of images of interest are necessary. This paper presents an innovative technique to detect bleeding regions in wireless capsule en-doscopy video. Experimental results show that the proposed algorithm exhibits a low false alarm rate, and is effective at reducing the time needed to analyze video sequences. © EURASIP, 2009.

5.Case Studies with Process Analysis Toolkit (PAT)

Author:Man, KL;Krilavicius, T;Leung, HL


Abstract:Ad-hoc approach for the development of electronic systems does not satisfy current needs of industry. Therefore, new approaches and techniques are required. Formal Methods are well-known in Software Engineering for a long time, as a potential tool for a faultless development of safety critical systems. Moreover, Process Algebras are one of the most successful techniques that allow formally specifying and analyzing diverse systems. We exemplify application of formal methods by applying Process Analysis Toolkit (PAT), a toolset based on a CPS-style process algebra, to model and analyze a pipeline process and a TLM buffer. In addition, we present the analysis results of several benchmark systems using PAT, namely asynchronous arbiter, hazardous circuit and four-tap FIR filter.

6.DARMA Adaptable service and resource management for wireless sensor networks

Author:Del Cid, Pedro Javier ; Hughes, Danny ; Ueyama, Jó ; Michiels, Sam ; Joosen, Wouter

Source:MidSens'09 - International Workshop on Middleware Tools, Services and Run-Time Support for Sensor Networks, Co-located with the 10th ACM/IFIP/USENIX International Middleware Conference,2009,Vol.

Abstract:This paper argues that service oriented architectures provide a good mechanism for managing outside interaction with software resources on wireless sensor networks. Specifically, this paper introduces a lightweight service platform designed to meet the specific characteristics of wireless sensor networks. The proposed architecture provides lightweight, yet flexible service-level agreements, together with adaptive management of sensor network resources. Critically for resource constrained sensor networks, our framework ensures that services are shared in an optimal manner between multiple client applications, while providing autonomic mechanisms to reason about fault tolerance and optimization. Furthermore, our approach actively promotes point of action processing which provides significant benefits in both embedded and enterprise deployments. We illustrate the appropriateness of the proposed architecture through a prototype implementation and evaluation using the LooCI component model and the SunSPOT platform. Copyright 2009 ACM.

7.Single development project

Author:Stankovic, N


Abstract:An often-cited problem in undergraduate software engineering courses states that some topics are difficult to teach in a university setting and, although laboratory work is a useful supplement to the lectures, it is difficult to make projects realistic and relevant. In recognition of this problem, and based on our past experience, we started preparing a new course by examining the pedagogies and curricular aspects of software engineering that are important for the Net Generation of software engineers. The course project described in this paper concentrates on those aspects that can be dealt with effectively within the environment, i.e., the software lifecycle, system interdependences, teamwork, and realistic yet manageable project dynamics, all supported by various means of communication. The workload per students must be balanced with their lack of knowledge and skills. so that their unpreparedness to deal with complex issues does not abate their motivation. The approach was tested on six large projects over the period of one semester. We believe that the results reflect the students' strong interest and commitment, and demonstrate their ability to stay focused and work at a level that is well above the obvious. (C) 2009 Elsevier Inc. All rights reserved.

8.Tracking the soccer ball using multiple fixed cameras

Author:Ren, JC;Orwell, J;Jones, GA;Xu, M


Abstract:This paper demonstrates innovative techniques for estimating the trajectory of a soccer ball from multiple fixed cameras. Since the ball is nearly always moving and frequently occluded, its size and shape appearance varies over time and between cameras. Knowledge about the soccer domain is utilized and expressed in terms of field, object and motion models to distinguish the ball from other movements in the tracking and matching processes. Using ground plane velocity, longevity, normalized size and color features, each of the tracks obtained from a Kalman filter is assigned with a likelihood measure that represents the ball. This measure is further refined by reasoning through occlusions and back-tracking in the track history. This can be demonstrated to improve the accuracy and continuity of the results. Finally, a simple 3D trajectory model is presented, and the estimated 3D ball positions are fed back to constrain the 2D processing for more efficient and robust detection and tracking. Experimental results with quantitative evaluations from several long sequences are reported. (C) 2008 Elsevier Inc. All rights reserved.

9.Computer-supported collaboration in language learning

Author:Zou, Bin

Source:Monitoring and Assessment in Online Collaborative Environments Emergent Computational Technologies for E-Learning Support,2009,Vol.

Abstract:Studies suggest that the computer can support collaborative learning between learners. This chapter discusses collaboration between language learners while using computer-based tasks. The researcher aims to look at in what ways students collaborate when completing tasks using computers during language learning, particularly in developing their listening and speaking skills. This chapter also explores the possibilities of monitoring and assessment for this collaborative language learning. The analysis is based on interview, observation and questionnaire data from both teachers and students at two UK university language centers. The findings indicate that collaboration in computer-based environments organized by teachers is useful for students to develop their language skills. Computer-supported collaboration increases students' confidence and encourages them to maintain active learning, thus reduces the passive reliance on teachers' feedback. © 2010, IGI Global.
Total 9 results found
Copyright 2006-2020 © Xi'an Jiaotong-Liverpool University 苏ICP备07016150号-1 京公网安备 11010102002019号