Abstract: Stress diagnosis based on finger temperature signals is receiving increasing interest in the psycho-physiological domain. However, in practice, it is difficult and tedious for a clinician and parti ...

Abstract: In this paper, a new particle swarm optimisation algorithm, called MeanPSO, is presented, based on a novel philosophy by modifying the velocity update equation. This is done by replacing two terms of original velocity update equation by two new terms based on the linear combination of pbest and gbest. Its performance is compared with the standard PSO (SPSO) by testing it on a set of 15 scalable and 15 nonscalable test problems. Based on the numerical and graphical analyses of results it is shown that the MeanPSO outperforms the SPSO, in terms of efficiency, reliability, accuracy and stability.

Abstract: This paper presents a simple method of counting feeder fish automatically using image processing techniques. A video of a school of fish is taken and every frame is processed singly and independently. The first step is to obtain blobs marking the positions of the fish. Several ways of accomplishing this task are discussed. Noise and background objects are filtered from the image of the blobs. Area information of the blobs is used to count the number of fish in one frame, and the average number of fish over all frames is then recorded. Experimental results show that the correct number of fish can be obtained for a school of 5, 10, 15, and 50 fish. Errors within frames increase with the number of fish, mainly resulting from the fact that area thresholding can be quite sensitive. Finally, a discussion about the method's effectiveness and possible improvements are provided.

Abstract: This paper addresses the questions of improving convergence performance for back propagation (BP) neural network. For traditional BP neural network algorithm, the learning rate selection is depended on experience and trial. In this paper, based on Taylor formula the function relationship between the total quadratic training error change and connection weights and biases changes is obtained, and combined with weights and biases changes in batch BP learning algorithm, the formula for self-adaptive learning rate is given. Unlike existing algorithm, the self-adaptive learning rate depends on only neural network topology, training samples, average quadratic error and error curve surface gradient but not artificial selection. Simulation results show iteration times is significant less than that of traditional batch BP learning algorithm with constant learning rate.

Abstract: Rice leaf diseases have occurred all over the world,including china.They have had a significant impact on rice quality and yield.Now,the control method rely mainly on artificial means.In this study,BP neural network classifiers were designed for classifying the healthy and diseased parts of rice leaves.This paper select rice brown spot as study object,the training and testing samples of the images are gathered from the northern part of Ningxia Hui Autonomous Region.The result shows that the scheme is feasible to identify rice brown spot using image analysis and BP neural network classifier. Keywords-rice brown spot;BP neuralnetwork;color feature;feature extraction

Abstract: The increasing number of service providers on the Web makes it challenging to select a provider for a specific service demand. Each service consumer has different expectations for a given service in different contexts, so the selection process should be consumer-oriented and context-dependent. Current approaches for service selection typically have consumers receive ratings of providers from other consumers, where the ratings reflect the consumers' overall subjective opinions. This may be misleading if consumers have different contexts and satisfaction criteria. In this paper, we propose that consumers objectively record their experiences, using an ontology to capture subtle details. This can then be interpreted by consumers according to their own criteria and contexts. We then integrate a method for addressing consumers who lie about their experiences, filtering them out during service selection. We demonstrate the value of our approach through experiments comparing our model with three recent rating-based service selection models. Our experiments show that using the proposed approach, service consumers can select the service providers for their needs more accurately even if the consumers have different criteria, they change the contexts of their service demands over time, or a significant portion of them are liars.

Abstract: Three major principles for the selection of indicator data normalization methods in multi-attribute evaluation are presented in this paper. Principle 1: The relative gap between the data for the same indicator should remain constant; Principle 2: The relative gap between different indicators should remain variable ; and Principle 3: The maximum values after normalization should be equal. According to these three major principles, a normalization method for positive indicators is screened out from several alternatives, and a new normalization method for negative indicators is proposed. These two methods are very good for the comparison among panel data,. The requirement for data normalization methods is different when the evaluation goals are different, Ranking-order-based evaluation is insensitive to data normalization methods.

Abstract: Software cost estimation is a key open issue for the software industry, which suffers from cost overruns frequently. As the most popular technique for object-oriented software cost estimation, Use Case Points(UCP) method, however, has two major drawbacks: the uncertainty of the cost factors and the abrupt classification. To address these two issues, we propose the Extended Use Case Points (EUCP) method. With a probabilistic cost model constructed from integrating fuzzy set theory and Bayesian Belief Networks(BBNs) with the UCP method, EUCP provides a probability distribution of cost and a refined gradual classification, which mitigate the uncertainty of cost factors and improve the accuracy of classification. In this paper, we provides two case studies to demonstrate the effectiveness of EUCP in the real life.

Abstract: License plate recognition plays an important role in Intelligent Transport System; however, plate region extraction is the key step before the final recognition. In this paper, an effective license plate extraction algorithm based on vertical edge detection and mathematical morphology is proposed, which can exactly extract the plate from complex background. The proposed algorithm mainly consists of two modules: license plate region's rough detection and license plate accurate detection. The former aims to find out Region of Interest (ROI) through a sequence of steps including vertical edge detection, edge detection and mathematical morphology, while the latter analyzes the ROI by taking full advantage of outer shape feature and inner texture feature of license plate. Experiments have been conducted for this algorithm.400 images taken from various scenes were employed, including diverse angles, different lightening conditions, etc. The proposed algorithm can detect the region of license plate quickly with 98.1 percent accuracy.

Abstract: Intelligence is the core function of cognitive radio (CR). Intelligence is achieved by learning engine through knowledge acquisition. In this paper, a kind of learning engine is designed based on support vector machine (SVM). The proposed approach is demonstrated by data come from 802.11a protocol platform that the classification and regression results of SVM are very promising which ensure the effectiveness of learning engine. As a result, learning engine based on SVM can acquire knowledge of wireless environment through learning to realize the core function of CR: intelligence.

Abstract: Estimating the cost of development is one of the most crucial and daunting tasks for a software project manager. A lot of cost estimation models were reported in the literature but many of these models became obsolete because of the rapid changes in technology. Earlier cost estimation models used the size of the ultimate software product as the primary factor which, in many cases, was difficult to estimate. For example, COCOMO model used the number of Delivered Source Instructions (DSI) which is hard to estimate for products developed using modern programming languages. On the other hand, models such as Function Point (FP) metrics were designed to consider functional requirements instead of lines of code. These models were applicable only to procedural paradigm, and are not directly applicable to software products developed using the objectoriented methodology. It is this idea that gave birth to the creation of Use Case Point (UCP) metrics, originally developed by Gustav Karner[9]. UCP uses use cases as the primary factor; use case model is the first model developed in an object-oriented design process using UML. In this paper, the authors extended the original UCP model with additional information obtained from use case narratives.

Abstract: An adaptive hybrid model (AHM) based on nondominated solutions is presented in this study for multi-objective optimization problems (MOPs). In this model, three search phases are devised according to the number of nondominated solutions in the current population: 1) emphasizing the dominated solutions when the population contains very few nondominated solutions; 2) maintaining the balance between nondominated and dominated solutions when nondominated ones become more; 3) when the population consists of adequate nondominated solutions, dominated ones could be ignored and the isolated nondominated ones are allocated more computational budget by their crowding distance values for heuristic search. To exploit local information efficiently, a local incremental search algorithm, LISA, is proposed and merged into the model. This model maintains the adaptive mechanism between the optimization process by the online discovered nondominated solutions. The proposed model is validated using five ZDT and five DTLZ problems. Compared with three other state-of-the-art multi-objective algorithms, namely NSGA-II, SPEA2, and PESA-II, AHM achieves comparable results in terms of convergence and diversity metrics. Finally, the sensitivity of introduced parameters and scalability to the number of objectives are investigated.

Abstract: With the rapid development of the Internet, the Web is full of valuable information. Enterprises are increasingly faced with a big challenge of how to integrate the distributed data and applications effectively. The concept of SOA solves the traditional problem of tight coupling and Web Services are the major technology for implementing SOA. However, in recent years, another trend is that REST has increasingly gained much attention and been widely used for Web Services development. In this paper, we make an in-depth analysis about traditional Web Services and RESTful Web Services and design a testing scheme to test and analyze the performance of RESTful Web Services to demonstrate that RESTful Web Services are more suitable for Internet-scale distributed data integration. Keywords-Web Services; REST; Distributed Data Integration

Abstract: Nowadays computer programs are objectively tested and marked by automated programming assessment systems in computer science education. Dynamic analysis and static analysis are two major approaches in the field of automated programming assessment. Methods adopted by dynamic and static analysis have been emphasized and detailed in this paper. Advantages and disadvantages of them implemented in instruction have been analyzed when taking instructional practice into consideration. Although many automated programming assessment systems have been proved to be of great help to both instructors and students in programming instruction, several problems remain unsolved, such as the security problem and algorithms for automatic generation of test data in dynamic analysis, low accuracy and precision of correctness and functionality assessment in static analysis, thus optimal approaches are still under research. The way of effective use of dynamic analysis and static analysis in instructional practice is also suggested in order that instructors can use the results of this study to choose the most appropriate approach in the context of a particular instructional goal. Finally, standardization of automated programming assessment systems, way to open source code and intelligent tutor system for automated programming assessment are expected to come into exist in the future. Keywords-automated programming assessment, static analysis, dynamic analysis

Abstract: This paper presents a case-based decision support system prototype to assist patients with Type 1 diabetes on insulin pump therapy. These patients must vigilantly maintain blood glucose levels within prescribed target ranges to prevent serious disease complications, including blindness, neuropathy, and heart failure. Case-based reasoning (CBR) was selected for this domain because (a) existing guidelines for managing diabetes are general and must be tailored to individual patient needs; (b) physical and lifestyle factors combine to influence blood glucose levels; and (c) CBR has been successfully applied to the management of other long-term medical conditions. An institutional reviewboard(IRB)approvedpreliminaryclinicalstudy,involving20patients,wasconductedtoassessthefeasibility of providing case-based decision support for these patients. Fifty cases were compiled in a case library, situation assessment routines were encoded to detect common problems in blood glucose control, and retrieval metrics were developed tofind the most relevant past cases for solving current problems. Preliminary results encourage continued research and work toward development of a practical tool for patients.

Abstract: To achieve a effective segmentation for liver cancer CT image, this paper utilizes comprehensive the edge detection, the watershed algorithm and region merging approach, propose a segmentation method of liver cancer CT image based on the watershed algorithm, gain a better effect in the course of liver cancer CT image segmentation, and solve effectively the over-segmentation phenomenon of the traditional method, get closed, continuous, more accurate lesion region contour. The experimental results show that the method can be used to achieve better liver cancer CT image lesions region segmentation.

Abstract: Emotion recognition from Electrocardiography (ECG) signal has become an important research topic in the field of affective computing. In the current work, ECG signals from multiple subjects were collected when film clips shown to them, and then feature sets were extracted from precise location of P-QRS-T wave by continuous wavelet transform (CWT). Hybrid Particle Swarm Optimization (HPSO) was utilized for feature selection, whose discrimination criteria was the correct rate of fisher classifier and the number of features selected. For recognizing two emotions of joy and sadness, effective features and better recognition rate were obviously obtained. Experimental results indicate that the features that acquired from experimental simulation can represent the changes of emotions, HPSO and fisher classifier are effective ways for emotion recognition.

Abstract: Computational gaming requires the automatic generation of virtual opponents for different game levels. We have turned to artificial evolution to automatically generate such game players. In particular, we have used Genetic Programming to automatically evolve computer programs for computer gaming. With Genetic Programming, in theory, it is possible to generate any kind of program. The programs are not constrained as much as they are in other computational learning approaches, e.g. neural networks. We show how Genetic Programming improved upon a manually crafted race car driver (proportional controller). The open race car simulator TORCS was used to evaluate the virtual drivers.

Abstract: Despite the recognized advantages that can be obtained in clinical practice when following clinical guidelines (GL), situations of noncompliance with them may emerge. Keeping track of such deviations from the default GL execution, and documenting the physician's motivations, would clearly be an added value. Moreover, repeated alterations of GL actions (or flow) may highlight the need for an adaptation of the GL itself to the local reality, or may even indicate an improper or weak initial GL definition. In this article, we propose an approach for managing noncompliance with GL, based on the case-based reasoning methodology. In front of a new noncompliance case, our tool allows the physician to retrieve past situations similar to the current one, and to decide whether to reapply the same GL modifications adopted in them. Moreover, the tool is able to learn indications from the ground noncompliance cases that can be deployed for local adaptation, and possibly, for suggesting more formal GL revisions to be carried out by a committee of expert physicians.

Abstract: This paper proposes a novel, reactive algorithm for real time obstacle avoidance, compatible with low cost sonar or infrared sensors, fast enough to be implemented on embedded microcontrollers. We called this algorithm "the bubble rebound algorithm". According to this algorithm, only the obstacles detected within an area called "sensitivity bubble" around the robot are considered. The shape and size of the sensitivity bubble are dynamically adjusted, depending on the kinematics of the robot. Upon detection of an obstacle, the robot "rebounds" in a direction having the lowest density of obstacles, and continues its motion in this direction until the goal becomes visible, or a new obstacle is encountered. The performances and drawbacks of the method are described, based on the experimental results with simulators and real robots.

Abstract: This paper first gives a new validity function for fuzzy clustering, then presents a method of the optimal selecting of the cluster number in the standard fuzzy c-means clustering algorithm, and finally outlines the fuzzy c-means clustering algorithm with parameters self-adapted. Experimental results carried on synthetic data set and data set based on actual background illustrate the performance of the new validity function and the corresponding fuzzy clustering algorithm.

Abstract: This paper expresses an algorithm of finger-vein recognition based on the score level moment invariants fusion. With regard the both characteristics of low contrast and intensity inhomogeneity in the infrared vein images; the maximum curvature model is adopted to extract the finger-vein pattern. Then, seven moment invariants are extracted to be matched by the Euclidean distance. In order to solve the problem of high false rate in finger-vein recognition using the single-feature method and the equal weights fusion strategy, the matching scores are fused by the weighted average strategy, and the equal error rate (EER) is minimized to obtain the optimum weights. Finally, the fused matching score is used to make the final decision. Experiment results prove that our algorithm has high performance on recognition rate, which at least reduces 11% in EER compared with the single-feature method and the equal weights fusion strategy.

Abstract: This paper introduces an automatic liver parenchyma segmentation algorithm that can delineate liver in abdominal CT images. The proposed approach consists of three main steps. Firstly, a texture analysis is applied onto input abdominal CT images to extract pixel level features. Here, two main categories of features, namely Wavelet coefficients and Haralick texture descriptors are investigated. Secondly, support vector machines (SVM) are implemented to classify the data into pixel-wised liver or non-liver. Finally, specially combined morphological operations are designed as a post processor to remove noise and to delineate the liver. Our unique contributions to liver segmentation are twofold: one is that it has been proved through experiments that wavelet features present better classification than Haralick texture descriptors when SVMs are used; the other is that the combination of morphological operations with a pixel-wised SVM classifier can delineate volumetric liver accurately. The algorithm can be used in an advanced computer-aided liver disease diagnosis and surgical planning systems. Examples of applying the algorithm on real CT data are presented with performance validation based on the automatically segmented results and that of manually segmented ones.

Abstract: Direct Anonymous Attestation (DAA) is adopted by the Trusted Platform Module (TPM) of v1.2 standard described by the Trusted Computing Group (TCG), aimed at settling protocols for trusted platform attestation and platform privacy protection. This paper gives a presentation of the new DAA protocol based on bilinear pairings and an analysis of its capacity to realize both attestation anonymity and detection of malicious attacks. Comparing with the existing three kinds of DAA protocols (the initial one, the improved one and the one based on oblivious transfer), this new protocol is of the simplest but also the most efficient.

Abstract: A data preprocessing system for constructing the transactions in web usage mining is presented. To implement transaction identification, the user sessions and the user access paths are extracted from the web access log and missing information is appended. These tasks are accomplished with the application of the referer-based method, which is an effective solution to the problems introduced by using proxy servers, local caching and firewall. Meanwhile, the reference length of accessed pages is calculated with the consideration of the time spent on data transfer over internet. Then two kinds of transactions are defined, i.e. travel-path transactions and content-only transactions. These two kinds of transactions are constructed by the maximal forward references (MFR) algorithm and the reference length (RL) algorithm, respectively. As verified by practical web access log, it is shown that the transactions can be efficiently identified while the reliability of the original web access data is obviously improved for the further researches.

Abstract: Object-relational mapping (ORM) in computer software is a programming technique for converting data between incompatible type systems in relational databases and object-oriented programming languages. ORM technologies mediates between object oriented architecture system and relational environment; it is a solution for paradigm mismatch. This creates, in effect, a "virtual object database" that can be used from within the programming language. There are both free and commercial packages available that perform objectrelational mapping, although some programmers opt to create their own ORM tools. The ORM approach was first realized in Hibernate, an open source project for Java systems started in 2002, which will be introduced here. Keywords-ORM; hibernate; J2EE; persistent

Abstract: Online social networks (OSNs) have gained popularity among users from all over the world during the past few years. And E-learning has made learning process quite convenient for users by using the networks. However, combing OSNs with E-learning is a new idea. And the role of OSNs in students' E-learning experiences is focused on in this paper. A study of Xiaonei which is one of the most popular online social network sites in China is conducted to explore the perception of students of OSNs based on the analysis of questionnaires. And the reasons that E-learning associating with OSNs will impact students' learning experiences are presented. And it is believed that online social networks can be effectively used in E-learning in the future.

Abstract: Travel time is widely used to measure the effective- ness of transportation systems and becoming one of the most popular traffic information which travelers are interested in. The ability to accurately predict travel time in transportation networks is a critical component in Advanced Traveler Informa- tion System (ATIS). This paper focuses on large-scale travel time prediction for urban arterial roads and proposes a new prediction method based on Kalman filter. To estimate the parameters in the method, the hierarchical clustering is used to gain the spatial relation of roads and the idea to estimate the state transition matrix from temporal and spatial perspectives separately is proposed. A large number of float car data in Beijing are used to evaluate the prediction method and the experiment results prove that it could predict travel time accurately.

Abstract: Based on Lagrange polynomials and variation of constants, we devise a novel 2n-1-point interpolatory ternary subdivision scheme that reproduces polynomials of degree 2n-2. We illustrate the technique with a 3-point ternary interpolatory subdivision scheme which can rebuild Hassan and Dodgson’s interpolating 3-point ternary subdivision scheme and a new 5point ternary interpolatory subdivision scheme which can achieve C-continuity. The smoothness of the new schemes is proved using Laurent polynomial method. Keywordsternary subdivision; Lagrange polynomial; variation of constant