Search

This paper proposes another dynamic prediction procedure that observes nurses' conversations to determine critical points in nursing accidents or incidents. The points would be be suggested by words that have a certain feature. We regard such words that might cause accidents or incidents as chances. This paper analyzes these types of words and describes their features to dynamically determine the point at which an accident or incident occurs. [ABSTRACT FROM AUTHOR]

The objective of this paper is to present and discuss methods for formulating optimum pricing strategies for maximizing store profit levels using consumer purchase data. In order to maximize outlet profit levels, it is necessary to seek such pricing strategies after achieving an in-depth understanding of the various features of consumer purchase behavior concerning a wide range of products and their related prices. We authors have used a very large amount of consumer purchase behavior data in order to clarify the effects on store-level profits of a wide range of specific products to develop a support system for pricing specialists. At the end of this paper, we analyze the framework that has been presented for the system from the standpoint of its utility for discovery of new business chances and discuss the need to clarify the problems connected with the use of data mining-based pricing strategies. [ABSTRACT FROM AUTHOR]

Third generation mobile networks were designed to satisfy raising requests of performance, reliability and availability on behalf of customers all over the world. These networks have a new architecture where new Network Entities carry out complex functionalities and can serve many calls at the time. In order to grant high efficiency and the best performance of the network, such a complex scenario must be monitored and controlled by a certain number of Operation & Maintenance Centres (OMCs). Typically, these centres pose queries to the underlying DBMS that require complex operations over Gigabytes or Terabytes of disk-resident data, and thus, take a very long time to execute to completion and produce exact answers. Due to the exploratory nature of these applications, an exact answer may not be required, and a user may in fact prefer a fast, approximate answer. In this paper we propose an architecture for approximate query processing to be integrated in the OTS architecture of Siemens Mobile S.p.A. The main purpose of this paper is to propose a practical application of wavelet-based synopses techniques in order to improve the performances of the management system of real telecommunication network. [ABSTRACT FROM AUTHOR]

This paper is concerned with a quantitative computational trust model which takes into account multiple evaluation criteria and uses the recommendation from others in order to get the trust value for entities. In the proposed trust model, the trust for an entity is defined as the expectation for the entity to yield satisfactory outcomes in the given situation. Once an interaction has been made with an entity, it is assumed that outcomes are observed with respect to evaluation criteria. When the trust information is needed, the satisfaction degree, which is the probability to generate satisfactory outcomes for each evaluation criterion, is computed based on the outcome probability distributions and the entity's preference degrees on the outcomes. Then, the satisfaction degrees for evaluation criteria are aggregated into a trust value. At that time, the reputation information is also incorporated into the trust value. This paper presents in detail how the trust model works. [ABSTRACT FROM AUTHOR]

Hiding users' real ID is one of promising approaches to protecting their privacy in ubiquitous computing environment. Policy-based privacy protection is also known as another useful approach. In the previous work, we have proposed a privacy preservation platform, called AP3(the Anonymity-based Privacy-Preserving ID-based service Platform), which allows users to use pseudonyms for hiding real IDs and enables ID-based services like buddy service at the same time in the ubiquitous environment. AP3 does not yet support privacy policy mechanism which allows users to control the accessibility of others to themselves according to their preference. In this paper, we propose an extended version of AP3, named PAP3(the Policy-incorporated Anonymity-based Privacy-Preserving ID-based service Platform), which incorporates a privacy policy mechanism to control the accessibility about which application or user can get access to whom at what time and at which place. This paper presents the PAP3 architecture and describes how to enforce privacy policy for the access control in PAP3. [ABSTRACT FROM AUTHOR]

In this paper, an Intelligent Context - Aware News Reporting System called iJADE Reporter is presented. This system focuses on how context mining techniques are applied on news reporting under a multi-agent architecture, and categorize news content by information retrieval algorithm. This paper also investigates how to improve the similarity measurement between documents by ontology with WordNet graph structure of words. In a web querying case, a common information retrieval algorithm, Term Frequency with Inverse Document Frequency (TFIDF) is used to cluster news contents. The proposed system provides a simple, fast and efficient query in WWW. The proposed system makes use of multi-agent technology to increase the scalability and efficiency of the system. By using TFIDF algorithm and multi-agent based techniques, an online updating news reporter from popular News Website, such as BBC & CNN News Website is developed. [ABSTRACT FROM AUTHOR]

This paper describes the end-users programming system that generates computer programs through interaction using linguistic expressions with users who have little knowledge of computer programming. The present system employs the idea of computer programming by paraphrasing, which is used as the useful method of human's everyday communication. The system also uses the case-based reasoning method for paraphrasing. Therefore users can add the meanings of linguistic expressions that the system does not have. Two subject experiments are carried out in order to confirm the usefulness of the present system. The one task is simple text editing and the other task is more complex one. Ten subjects in all perform the experiments and the experimental results are discussed in this paper. [ABSTRACT FROM AUTHOR]

Recently, Car Sharing System is focused as a new public transportation system in Japan. However, traditional car sharing systems which we call Pre-Reserve Car Sharing System require advance reservations, and the number of stations where users get on/off for the systems is small. Thus, the number of users is limited availability and most of users only apply the system to round driving. On the other hand, the advances of global positioning systems and communication techniques improve the system in a new and different way. We call the new system On-Demand Car Sharing System. In the new system, users are available for the system on demand, i.e., users can get on/off any time and any stations. Thus, users apply the system to one-way driving in addition to round driving. In this paper, we focus on location balances of cars which is a key factor to improve utilization rate of the system. We propose a relocation algorithm for waiting cars based on virtual spring forces. In the last of this paper, we report our simulation results and show the effectiveness of our algorithm. [ABSTRACT FROM AUTHOR]

This paper illustrates a goal oriented approach to model agent mediated e-learning system. Most of the traditional e-learning systems are not learner-centric, and they often ignore the diversity of learner population; thus very often their service is not able to directly or effectively match the learner's goal. From the learner's point of view, we propose a goal oriented approach to develop an agent-mediated e-learning system which provides leaner-centric and personalized e-learning services. In this paper, we illustrate how to use Goal Net to model the learner's goal and how to develop such a multi-agent system to provide efficient learning services. [ABSTRACT FROM AUTHOR]

In order to solve a stress problem, researchers have studied music therapy. It takes the therapist and patient a long time to select the music. Because the music used in music therapy is of various type. If the music for it is easily selectable, the music therapy can be carried out more effectively. In this paper, the purpose is extraction of features that may be influenced by the music. We pay attention to EEG (electroencephalogram) as an objective and absolute scale. In this paper, we propose a method that extracts features of the EEG by PCA (principal component analysis) and CDA (canonical discriminant analysis). Then we analyze each feature data by NN (neural network). In order to examine whether the proposal system is effective, we try computer simulations for the EEG classification. According to recognition rate by the NN, it was considered that the CDA extracted and classified the features of the EEG better than the PCA. [ABSTRACT FROM AUTHOR]

In this paper, the Clonal Selection Algorithm (CSA) is employed by the natural immune system to define the basic features of an immune response to an antigenic stimulus. This paper synthesizes the advantages of clonal selection algorithm and proposed optimal design problem using clonal selection algorithm which is a basis of the immune system. CSA, the essence of immune algorithm, is effective to solve optimal problem. The clonal selection algorithm is highly parallel and presents a fine tractability in terms of computational cost. Like the genetic algorithm, clonal selection algorithm is a tool for optimum solution. Clonal selection algorithm and genetic algorithm are used to reach the optimization performances for two numerical function. Then those results are compared each other. These proposed algorithms are shown to be an evolutionary strategy capable of solving optimal design problem. [ABSTRACT FROM AUTHOR]

The goal of the research presented in this paper is to support users in exploring a huge amount of data for the purpose of decision-making and problem-solving. Our approach is to design human-computer interaction as a natural discourse between the user who explores the data and the system that supports the user's exploration process. For that purpose, we developed a prototype system named InTREND that interprets the user's natural language query and presents statistical charts as a result of the query. InTREND encourages iterative exploration by maintaining the context of past interactions and uses this context to improve discourse with the user. This paper explains our research motivation and presents a framework for supporting exploratory data analysis. Our user studies evaluate the context preservation mechanisms of InTREND. [ABSTRACT FROM AUTHOR]

The knowledge-based economy is approaching rapidly, and knowledge management (KM) has disseminated in leaps and bounds in academic circles as well as in the business world. This paper develops a unifying framework to evaluate KM activities for supporting intelligent knowledge-based system (KBS) using web interface, and expert system technology to help inexperienced administrators in insuring the smooth operation of KM performance. This paper makes three important contributions: (1) it proposes an efficient KM Ontology Construction Algorithm to fast conceptualize KM domain concept; (2) it provides a hybrid model used for knowledge acquisition through skeletal concept model and IDEF (Integrated DEFinition function modeling) analysis; and (3) it presents a methodology for using KM ontology in building a unifying framework and evaluation guideline for KM that works well and effective. [ABSTRACT FROM AUTHOR]

This paper is a part of a comprehensive study in which a decision support system is developed to facilitate traffic mangers in tackling the post incident traffic flows on the freeway network in Korea. The system employs Cellular Automata, which is a microscopic simulation platform. This paper suggests two additional rules to in the modified version of the conventional model. This has enabled us to model more realistically the dynamic flow parameters in post incident scenario. A comparative study of the proposed model with the conventional and modified models suggests that our model displays more realistic results. [ABSTRACT FROM AUTHOR]

IT security is becoming an area of increasing importance especially with the increasing dependency of humans and businesses on computers and computer networks. This paper outlines a generic framework to deal with security issues. The framework proposed is based on a multi agent architecture. Each specialist task for security requirement is modeled as a specialist agent task and to address the global security tasks an environment is invoked in which the multiple agents execute their specialist skills and communicate to produce the desired behavior. This paper presents the framework and its constituent parts and discusses the characteristics of the security problems, the agent roles and how they link up. The security related areas investigated in the current study are discussed and modeled in the proposed framework. [ABSTRACT FROM AUTHOR]

In this paper, we propose an effective algorithm of gray-level watermarks based on the characteristics of image. The DCT coefficients of the watermark image are embedded into the position of DCT domain of host image by considering the similarity of DCT blocks energy of both images. The algorithm recovers the watermark without any reference to the original image and we propose a post-processing procedure, which can correct the errors by the survived information, to obtain higher quality watermark. The experimental results show that the proposed algorithm adapted to the original image produces the most imperceptible and the most robust watermarked image under print-and-scanner and various attacks. [ABSTRACT FROM AUTHOR]

Material in music, film, book and software publishing industries can be easily duplicated on a large scale by personal computers, and unauthorised or illegal copies have become a serious problem in recent years. In this situation the digital watermark can be used as a direct method of preventing unauthorised copying. This paper presents a novel digital watermarking system based on Vector Quantisation (VQ) and Discrete Cosine Transform (DCT), which can embed a grey level image. The proposed new system can embed 16 times more information than other traditional DCT based watermarking systems. The recovered images have high Peak Signal to Noise Ratio (PSNR) value and good visual quality. This system is robust in terms of both JPEG compression and other signal processing attacks. [ABSTRACT FROM AUTHOR]

The proposed work includes CMOS design of a Neuron to generate binary logic Artificial Neural Network (ANN) as well as Multilayer Neural network. Several neural net chips exist on the market today. Some of these chips operate as analog devices by running below threshold on the transistors thereby gaining continuous properties instead of discrete properties afforded by CMOS transistor logic. In the current paper, authors have proposed a weighter circuit. It is designed with the help of NAND & XOR gates & binary connections are stored in flops. Both the gates provide more flexibility than the way the neuron deals with the input. Two-phase clocking with no overlap is used to ensure that all weights are properly shifted in without any data corruption. The same concept is extended to multilayer network. [ABSTRACT FROM AUTHOR]

In this paper, we present a first attempt at self-adapting the population size parameter in addition to self-adapting crossover and mutation rates for the Differential Evolution (DE) algorithm. The objective is to demonstrate the feasibility of self-adapting the population size parameter in DE. Using De Jong's F1-F5 benchmark test problems, we showed that DE with self-adaptive populations produced highly competitive results compared to a conventional DE algorithm with static populations. In addition to reducing the number of parameters used in DE, the proposed algorithm performed better in terms of best solution found than the conventional DE algorithm for one of the test problems. It was also found that that an absolute encoding methodology for self-adapting population size in DE produced results with greater optimization reliability compared to a relative encoding methodology. [ABSTRACT FROM AUTHOR]

Many approach strategies can be employed to resolve word sense ambiguity with a reasonable degree of accuracy. These strategies are: knowledge-based, corpus-based, and hybrid-based. This paper pays attention to the corpus-based strategy that employs an unsupervised learning method for disambiguation. We report our investigation of Latent Semantic Indexing (LSI), an unsupervised learning, to the task of Thai noun and verbal word sense disambiguation. We report experiments on two Thai polysemous words, namely /hua4/ and /kep1/ that are used as a representative of Thai nouns and verbs respectively. The results of these experiments demonstrate the effectiveness and indicate the potential of applying vector-based distributional information measures to semantic disambiguation. Our approach performs better than a baseline system, which picks the most frequent sense. [ABSTRACT FROM AUTHOR]

This paper proposes a segmentation method of SAR (Synthetic Aperture Radar) images based on a SOM (Self-Organizing Map) neural network. SAR images are obtained by observation using microwave sensor. For teacher data generation, they are segmented into the drift ice (thick and thin), and sea regions manually, and then their features are extracted from partitioned data. However they are not necessarily effective for neural network learning because they might include incorrectly segmented data. Therefore, in particular, a multi-step SOM is used as a learning method to improve reliability of teacher data, and carry out classification. This process enable us to fix all mistook data and segment the SAR image data using just data. The validity of this method was demonstrated by means of computer simulations using the actual SAR images. [ABSTRACT FROM AUTHOR]

In this paper, a kidney region is extracted as a preprocessing of kidney disease detection. The kidney region is detected based on its contour information that is extracted from a CT image using a dynamic gray scale value refinement method based on the Q-learning. An initial point to extract the kidney contour is decided by training gray scale values along horizontal direction with Neural Network (NN). Furthermore the kidney contour is corrected by using the snakes more accurately. It is demonstrated that the proposed method can detect stably the kidney contour from CT images of any patients. [ABSTRACT FROM AUTHOR]

In this paper we present a cryptanalysis of the generalized patchwork algorithm under the assumption that the attacker possesses only a single copy of the watermarked image. In the scheme, watermark is inserted by modifying randomly chosen DCT values in each block of the original image. Towards the attack we first fit low degree polynomials (which minimize the mean square error) on the data available from each block of the watermarked content. Then we replace the corresponding DCT data of the attacked image by the available data from the polynomials to construct an attacked image. The technique nullifies the modification achieved during watermark embedding. Experimental results show that recovery of the watermark becomes difficult after the attack. Keywords: Cryptanalysis, Digital Watermarking, Information Security, Multimedia Systems, Discrete Cosine Transform. [ABSTRACT FROM AUTHOR]

In this paper, a coarse to fine strategy is presented to achieve the geometrical synchronization incorporating Zernike moments and the template. At the coarse stage, the rotation and scaling parameters are estimated with Zernike moments of the translation-normalized image, while the translation parameters are estimated with the centroid's increments between the original image and the image that is corrected for rotation and scaling. At the fine stage, the accurate Rotation, Scaling and Translation (RST) parameters are obtained by matching the template around the roughly estimated RST values. A watermarking scheme based on the vector Hidden Markov Model in wavelet domain (DWT-HMM) is also adopted. High robustness is observed against geometric manipulations and other StirMark attacks in our simulations. [ABSTRACT FROM AUTHOR]

With the development of mobile communication and internet technologies, digital media can be transmitted conveniently over the network. In this process the algorithms used to protect secret messages during transmission become an important issue. This paper presents a new high capacity image steganograpic model based on wavelet transform [1] and modified adaptive Wavelet zerotrees [2]. The proposed new system can embed more information than traditional algorithms without compression. The recovered hiding image has high Peak Signal to Noise Ratio (PSNR) value and good visual quality. The system is robust in terms of both JPEG compression and other signal processing attacks. [ABSTRACT FROM AUTHOR]

In recent years, digital watermarking is a technique for labeling digital images by hiding secret information which can protect the copyright. The goal of this paper is to develop a DCT-based watermarking algorithm for low power and high performance. Our energy-efficient of technique focus on algorithm level processing. We improve Hsu and Wu's algorithm by using DCT coefficients to pairing blocks directly. The experimental results show our approach not only can reduce a halt of pairing operations required, but also increase the PSNR around 0.2 db. [ABSTRACT FROM AUTHOR]

This paper proposes a new image-adaptive watermarking technique which utilizes a new combination of an adaptive quantization step size and a HVS(human visual system) model in the wavelet domain. Here we use Quantization Index Modulation(QIM) method with an adaptive quantization step size to realize the embedding scheme. The HVS masking is accomplished pixel by pixel by take into account the luminance and the frequency content of all the image subbands. The watermarking consists of a pseudorandom sequence which is adaptively embedded into the subbands. As usual, the watermark bits are detected by a minimum distance detector. Experimental results prove the effectiveness of the new algorithm. [ABSTRACT FROM AUTHOR]

According to the rapid change of a computing environment, it is coming an age of ubiquitous computing that we can make use of information service at any time and anywhere as the paradigm of digital convergence such as broadcasting, communication, and appliances. Consequently, Smart Home environment is constructed in the house. Various services such as security/automation, health monitoring, medical examination and treatment, entertainment, education, and e-business are realized at home. Both affective, systematic managements and services that correspond with the above environment are required inmultimedia services as well. In this paper, we propose a Intelligent Multimedia Service System(IMSS) based on context awareness in Smart Home which provides multimedia interoperability among incompatible multimedia play devices, intelligently processes context awareness information, transparent, and provides safe services. [ABSTRACT FROM AUTHOR]

In this paper, we describe an algorithm which can automatically recognize human gesture for Human-Robot interaction by utilizing attention control method. In early works, many systems for recognizing human gestures work under many restricted conditions. To solve the problem, we propose a novel model called APM(Active Plane Model),which can represent 3D and 2D gesture information simultaneously. Also we present the state transition algorithm for selection of attention. In the algorithm, first we obtain the information about 2D and 3D shape by deforming the APM, and then the feature vectors are extracted from the deformed APM. The next step is constructing a gesture space by analyzing the statistical information of training images with PCA. And then, input images are compared to the model and individually symbolized to one of the pose model in the space. In the last step, the symbolized poses are recognized with HMM as one of model gestures. The experimental results show that the proposed algorithm is very efficient to construct intelligent interface system. [ABSTRACT FROM AUTHOR]

To achieve the goal of assuring short development cycles for new products, they are developing a process-based knowledge-driven product development environment by employing information technology. The success of a KBS critically depends on the amount of knowledge embedded in the system. Expert knowledge, which results from an individual's extensive problem-solving experience, has been described as unconscious knowledge. Besides shortening development time, properly handled reuse will also improve the reliability since code is executed for longer time and in different contexts. In this paper, We propose a design process suitable for developing product lines for mobile embedded systems with KBS. The process starts in a requirement-capturing phase where the requirements from all products in the line are collected. The contributions of this work with respect to mobile embedded systems are an outline of a development process, focusing on the special considerations that must be taken into account when designing a PLA for the systems. Keywords: Knowledge Based Systems, Intelligent Agents, Mobile Embedded Systems, CBD, Domain Engineering [ABSTRACT FROM AUTHOR]

IT systems consist on very many components and very complex, so the implementation of the security countermeasures needs more critical considerations. Indeed, IT systems contain many subsystems, and most of subsystems consist of one or more IT products. In this hierarchy structure, the security characteristics of each IT product may affect the total assurance of the IT systems. Therefore, the security should be considered at the base level of the IT systems, in other words, IT product the base of the IT systems. For this work, this paper presents our research results about the security and assurance relationship between IT products and IT systems. [ABSTRACT FROM AUTHOR]

In the context-aware mobile computing environment, the context-aware mobile computing devices adapt their behavior to available services which require different communication protocols by the type of transmitted data (e.g. video, voice, text and etc.). In this paper, we present a novel architecture for an adaptive Reed-Solomon decoder which can apply to context-aware mobile computing device to support various code specifications for heterogeneous communication protocols. This decoder can vary the length of the codeword, generate polynomials and correct erasures. For this decoder, we use a modified Euclidean algorithm based on a GF(28) finite field for the error locator polynomial. Also, this decoder can support any specification in the range of (1 ≤ n ≤ 255) for the codeword and (1 ≤ t ≤ 255) for the errors. [ABSTRACT FROM AUTHOR]

Network-based systems are widely used in many application areas such as intelligent systems and distributed systems. To design distributed systems, distributed information processing and intelligent terminals are required. This paper deals with the design considerations and implementations of a distributed system using network architecture. Network nodes, called smart nodes, are designed for supporting the CAN(controller area network) protocol and a new message scheduling method is proposed in order to transfer data between these nodes. An experimental setup is built to perform velocity control of four DC-Motor subsystems. The experimental results verify that the proposed distributed system provides an acceptable control performance. [ABSTRACT FROM AUTHOR]

A 1:1 mapping model between a user thread and a system thread has a merit that supports parallelism, and a M:N mapping has a merit that supports parallelism and fast context exchange. It is necessary to improve performances in order to guarantee soft real-time by minimizing the context exchange between threads. This paper proposes a Java thread model, which supports a M:N mapping in a Linux Java virtual machine, by introducing the concept of LWP Light Weight Process (LWP) in a Java application level. The proposed model is able to maintain a fast processing speed, and independence from a Java platform. In addition, this model guarantees the soft real-time of a Java application program by applying a MTL-LS algorithm to LWP scheduling, and guarantees an excellent performance and soft real-time of the proposed model, which is introduced using a comparison between previous 1:1 model and previous M:1 mapping model. [ABSTRACT FROM AUTHOR]

Ultra-wideband(UWB) system is recently becoming very attractive candidate for low cost short range communication, due to recent development in high speed intelligent switching technology. In this paper, we theoretically analyze the probability of error for M-ary pulse position modulation (PPM) ultra-wideband (UWB) multiple access system using intelligent pulse shaping techniques. We first consider the optimum detection of UWB signals using M-ary orthogonal PPM in additive white Gaussian noise (AWGN). Then we derive receiver signal to noise power ratio (SNR) and bit error rate (BER) in multiple access interference (MAI) environment. Numerical results considering some practical parameters are presented and the BER performance according to different pulse shapes are compared. [ABSTRACT FROM AUTHOR]

In this paper we propose a highly adaptive bargaining model for agent shopping which stimulates two major human bargaining strategies: 1) Payoff-Oriented Strategy and 2) Real-time Adaptive Attitude Switching Strategy. Payoff-Oriented Strategy adjusts the rate of concession by determining the current payoff gained and the eagerness of the adopted attitude at each bargaining round. Also, the buying agent in this work is guided by the Real-time Adaptive Attitude Switching Strategy which comprises a set of attitude switching rules. These rules guide the buying agent to gain higher payoff and prohibit seller from gaining too much payoff. Owing to the substantial experimental results in this work, the two human-like bargaining strategies achieved the adaptive changing eagerness of a particular attitude and adaptive switching attitude in reacting to the opponent's feedback. [ABSTRACT FROM AUTHOR]

An adaptive repeater system for OFDM with frequency hopping control to reduce interferences is proposed. In this paper, we discuss a novel repeater to reduce the Inter Symbol Interference (ISI) caused by the delayed waves with Frequency Hopping controller in the frequency selective fading channel when the shadowing is occurred due to obstacles. The proposed system provides the solution for the shadowing, removing the interferences, results in improving the performance. An adaptive repeater system for OFDM with frequency hopping control improves the BER performance. Keyword:Repeater System, ISI (Inter Symbol Interference), Frequency Hopping Controller [ABSTRACT FROM AUTHOR]

There has been significant recent interest of particle filters for nonlinear state estimation. Particle filters evaluate a posterior probability distribution of the state variable based on observations in Monte Carlo simulation using so-called importance sampling. However, degeneracy phenomena in the importance weights deteriorate the filter performance. We propose in this paper a novel particle filter, which combines the ideas of Gaussian sum filter based on the Gaussian mixture approximation of the posteriori distribution and Evolution strategies based particle filter using selection process in evolution strategies. Numerical simulation study indicates the potential to create high performance filters for nonlinear state estimation. [ABSTRACT FROM AUTHOR]

This paper examines experience and knowledge, experience management and knowledge management, and their interrelationships. It also proposes process perspectives for both experience management and knowledge management, which integrate experience processing and corresponding management, knowledge processing and corresponding management respectively. The proposed approach will facilitate research and development of knowledge management and experience management as well as knowledge-based systems. Keywords: Knowledge management, experience management, knowledge-based systems, e-commerce. [ABSTRACT FROM AUTHOR]

The traffic sign detection and recognition system is an essential module of the driver warning and assistance system. During the last few years much research effort has been devoted to autonomous vehicle navigation using different algorithm. Proposed work includes a neural network based drivers assistance system for traffic sign detection. In this paper authors have implemented a high-speed color camera to enhance its performance in real time scanning. The proposed algorithm increases the efficiency of the system by 7 to 10% as compared to conventional algorithms. The system includes two main modules: detection module and recognition module. In the detection module, the thresholding is used to segment the image. The features of traffic signs are investigated and used to detect potential objects. In recognition module, we use complimenting and then ANDing techniques. The joint use of classification and validation networks can reduce the false positive rate. There liability demonstrated by the proposed method suggests that this system could be a part of an integrated driver warning and assistance system based on computer vision technology. [ABSTRACT FROM AUTHOR]

Due to the random nature of the ship's motion in an open water environment, the deployment and the landing of vehicles from a ship can often be difficult and even dangerous. The ability to predict reliably the motion will allow improvements in safety on board ships and facilitate more accurate deployment of vehicles off ships. This paper presents an investigation into the application of artificial neural network methods for the prediction of ship motion. Two training techniques for the determination of the artificial neural network weights are presented. It is shown that the artificial neural network based on the singular value decomposition produces excellent predictions and is able to predict the ship motion in real time for up to 10 seconds. [ABSTRACT FROM AUTHOR]

A rule-based system can be a solution for context reasoning in context-aware computing systems. In this paper we propose new flexible SoC (System-on-a-Chip) architecture for real-time rule-based system. The proposed architecture can match up values and variables of the left-hand sides of ‘if-then rules' (rule's LHS) in parallel. Compared to previous hardware rule-based system, we reduce the number of constraints on rule representations and combinations of condition terms in rule's LHS by using a modified contents addressable memory and a crossbar switch network (CSN). The modified contents addressable memory (CAM), in which the match operation of the system is processed in parallel, stores the rule-base of the system. The crossbar switch network is located between the input buffer that stores external raw input data and the working memory, and can freely configure condition operation of rule's LHS and working memory with stored data within the input buffer. The proposed SoC systems architecture has been designed and verified in a SoC development platform called SystemC. [ABSTRACT FROM AUTHOR]

This paper considers the problem of locating the wavelength converter in all optical Wavelength Division Multiplexing (WDM) network. The problem is formulated as an integer programming problem by using path variables. In order to solve the associated linear programming relaxation which has exponentially many variables, a polynomial time column generation procedure is exploited. Therewith, an LP-based branch-and-price algorithm is derived to obtain the optimal integer solution for the problem. Computational results show that the algorithm can solve practical size problems in a reasonable time. [ABSTRACT FROM AUTHOR]

Blind source separation(BSS) of independent sources from their convolutive mixtures is a problem in many real-world multi-sensor applications. However, the existing BSS solutions are more often than not based upon software and thus not suitable for direct implementation on hardware. In this paper, we present a new FPGA architecture for the blind source separation of a multiple input mutiple output(MIMO) measurement system. The algorithm is based on feedback network and is highly suited for parallel processing. The implementation is designed to operate in real time for speech signal sequences. It is systolic and easily scalable by simple adding and connecting chips or modules. In order to verify the proposed architecture, we have also designed and implemented it in a hardware prototyping with Xilinx FPGAs. [ABSTRACT FROM AUTHOR]

In this paper, we discuss employing a server in a router, the architecture of which is based on policy, for congestion management of IP traffic in Diffserv networks. We exploit the congestion information and employ that information to manipulate the network level parameters to adapt the traffic according to the current congestion state of the network. The congestion monitors interact with the policy server, which, depending on the network state, decides the policy/rules that should be enforced by the Diffserv network. The implementation of the selected policies typically leads to accepting, remarking or dropping the IP traffic packets entering the network. We have also indicated how these modules could functionally be used to generate and store appropriate rules based on policies for congestion management. Since the system will now be rule based, there is a need for policing action to monitor traffic and enforce these rules when congestion sets in, and we propose mobile agents accomplishing this job. Index Terms: Quality of service, IP Networks Congestion Management, Self-similar input, Policy based rules, Mobile Agents. [ABSTRACT FROM AUTHOR]

The existing three-dimensional bitmap indexing techniques have a performance problem in clustering the similar documents because they cannot detect the similar paths. The existing path clustering method which is based on the path construction similarity is one approach to solve the problem above. This method, however, consumes too much time in measuring the similarities between the similar paths for clustering. This paper defines the expected path construction similarity and proposes two-phase path retrieval method which effectively clustering the paths using it. The proposed method solved the performance degrade problem in path clustering by filtering the paths to be measured using the expected path construction similarity. [ABSTRACT FROM AUTHOR]

This paper reviews eight different inference rules for experience-based reasoning (EBR), and proposes a multiagent architecture for an EBR system, which constitutes an important basis for developing any multiagent EBR systems (EBRS). The proposed architecture consists of a global experience base (GEB), and a multi-inference engine (MIE), which is the mechanism for implementing eight reasoning paradigms based on eight inference rules for EBR. The proposed approach will facilitate research and development of experience management, knowledge-based systems, and recognition of fraud and deception in e-commerce. Keywords: Experience-based reasoning, experience management, knowledge-based system, multiagent system. [ABSTRACT FROM AUTHOR]

The management of knowledge and know-how becomes more and more important in organizations. Building corporate memories for conserving and sharing knowledge has become a rather common practice. However, we often forget that the efficiency of these activities is strictly connected to the appropriation capacities and learning of the organizational actors. It is through this learning that new skills can be acquired. In this paper, we propose general guidelines facilitating the process of creation and appropriation of professions memories built by means of methods from the knowledge engineering and from the educational engineering techniques. [ABSTRACT FROM AUTHOR]

Ontology-based applications always need checking subsumption relations between concepts. Current subsumption checking approaches are not appropriate to check subsumption relations between composite concepts in different ontologies. This paper proposes a framework, which is practical and effective to check subsumption relations between composite concepts in different ontologies. The framework is based on learning the mutual instances of different ontologies. It analyses the problems when generating and checking of mutual instances, and provides effective processes to solve them. The framework is fault tolerance and can deal with large-scale mutual instances; it can greatly reduce the manual annotation work, which is the main limitation in mutual instances approaches; intensions are also considered to avoid unnecessary instance checking and hit-and-miss results. [ABSTRACT FROM AUTHOR]

Among all knowledge forms, storing formal decision events in a knowledge-explicit way becomes an important development. Set of experience knowledge structure can help in achieving this purpose. Set of experience has been shown as a shape able to acquire explicit knowledge of formal decision events. However, to make set of experience knowledge structure practical, it must be worldwide transportable and understandable. The purpose of this paper is to show an effective form of transformation of the set of experience into a shareable and understandable shape able to travel among different systems and technologies. [ABSTRACT FROM AUTHOR]