Search

Estimating animal's genetic merit (or breeding value) plays a major role in the Manchego sheep selection scheme (ESROM), started fifteen years ago with the goal of improving Manchego sheep production figures. In the ESROM scheme the breeding value is estimated each semester by using BLUP animal model. In this paper we study the use of data mining techniques to deal with breeding value classification. The purpose of the paper is not to replace the use of BLUP in the ESROM, on the contrary, we intend to learn in a supervised way from the results produced by BLUP, and to use the learned models to provide preliminary information about the breeding value of an animal. We use standard classification techniques combined with feature subset selection in order to identify good (subsets of) predictors. We also show that the classifiers accuracy can be considerably improved by attribute construction. [ABSTRACT FROM AUTHOR]

In 1965 L.A. Zadeh presented a fuzzy set. After then, fuzzy clustering method was proposed in early stage. L.A. Zadeh presented the concept of similarity for a fuzzy set in 1981. Ruspini proposed a clustering method based on fuzzy decomposition. Dunn and Bezdek wrote a clustering based on IDODATA algorithm in terms of fuzzy concept. Many methods for fuzzy multivariate analysis were presented . For example, there are several approaches to multivariant analysis such as dynamic programming, M. Sugeno's measure, similarity concepts and clustering. M. Roubens and M.P. Windham discussed about the validity of clustering. Regarding hierarchical clustering, N. Osumi et al discussed it using fuzzy concepts. J. Watada et al proposed a heuristic hierarchical clustering which is employing similarity concepts of L.A. Zadeh's. There are many papers which discuss fuzzy clustering. In 1979 H. Tanaka et al proposed fuzzy linear regression model. This development broke through fuzzy multivariate analysis because no methods are proposed except clustering and hierarchical clustering till then. There are also various applications of fuzzy multicariant analyses. Furthermore, various data analyses were proposed based on the fuzzy linear regression model. For example, J. Watada et al developed Fuzzy time-series analysis and I. Hayashi developed GMDH method. This paper summarizes the 40 year history of Fuzzy Multivariate Methods. Keyword: Fuzzy Multivariate Analysis, Fuzzy Statistics, Fuzzy Linear Programming. [ABSTRACT FROM AUTHOR]

The paper presents a reversible watermark scheme based on hash function and lossless compression technology. The paper extracts the abstract information of the image as hash code and lossless compresses the LSB(Least Significant Bit) of the image to make some space where the image hash can be completely inserted. It needs to be done without introducing a large distortion to the image. The scheme can achieve the authentication purpose by hash code and restores the original image by retrieving the watermark sequence completely because of the lossless decompression of the LSB of the image. [ABSTRACT FROM AUTHOR]

Because the networks and systems become more complex, the implementation of the security countermeasures becomes more critical consideration. The designers and developers of the security policy should recognize the importance of building security countermeasures by using both technical and non-technical methods, such as personnel and operational facts. Security countermeasures may be made for formulating an effective overall security solution to address threats at all layers of the information infrastructure. This paper uses the security engineering principles for determining appropriate security countermeasures. This paper proposes a intelligent method for building security countermeasures by modeling and dividing IT systems and security components into some blocks. [ABSTRACT FROM AUTHOR]

This paper designs and implements a unified and intelligent tool for vulnerability assessment which can efficiently assess vulnerabilities of computer systems in which functions of the vulnerability assessment were distributed. Developing a vulnerability assessment tool needs two steps; constructing a vulnerability analysis database and implementing a vulnerability assessment tool. The vulnerability analysis database is constructed based on CVE to report vulnerabilities in standard assessment result forms by updating newest information, and is organized to be suitable to the distributed network. The vulnerability assessment tool is implemented using Nessus and OVAL. The vulnerability assessment tool suggested in this paper can provide fast and more accurate vulnerability assessment and proper guidelines to corresponding vulnerabilities. [ABSTRACT FROM AUTHOR]

In order to achieve the maximum gain along the desired signal, this paper propose beamforming algorithm that utilize Generalized on-off algorithm. The new algorithm that provides a maximum SINR(Signal to Interference plus Noise Ratio) based on the conventional on-off algorithm for obtaining optimal weight vector. Also, in this paper, we present a novel demodulation method enhancing the performance of smart antenna by using the pilot channel of CDMA2000 1X channel to obtain the exact weight vector. From various computer simulation, we could conform that the proposed algorithm has superior performance in terms of SER(Symbol Error Rate) than conventional algorithm with multipath fading. [ABSTRACT FROM AUTHOR]

Model updating, as a new concept to be employed as a standard and universal method for system modification, has been started in [4] and further developed in this paper. This paper introduces algorithms for Computation Tree Logic (CTL) model update. The algorithms correct errors in a CTL Kripke model to make this model satisfy its various required properties. These update algorithms are designed through pseudo-code, which details the logic of the algorithms. The microwave oven example in [3] has been correctly treated by the pseudo-code, which demonstrates the feasibility of these algorithms. The algorithms and their pseudo-code are the foundations for later implementation of a CTL model updater and integration of a CTL model checker and this updater. [ABSTRACT FROM AUTHOR]

Even though there are many databases for gene/protein interactions, most such data still exist only in the biomedical literature. They are spread in biomedical literature written in natural languages and they require much effort such as data mining for constructing well-structured data forms. As genomic research advances, knowledge discovery from a large collection of scientific papers is becoming more important for efficient biological and biomedical researches. In this paper, we present a relation kernel based interaction extraction method to resolve this problem. We extract gene/protein interactions of Yeast (S.cerevisiae) from text documents with relation kernel. Kernel for relation extraction is constructed with predefined interaction corpus and set of interaction patterns. Proposed relation kernel for interaction extraction only exploits shallow parsed documents. Experimental results show that the proposed kernel method achieves a recall rate of 78.3% and precision rate of 79.9% for gene/protein interaction extraction without full parsing efforts. [ABSTRACT FROM AUTHOR]

The basic belief-desire-intention (BDI) agent model appears to be inappropriate for building complex system that that must learn and adapt their behaviour dynamically. The contribution of the paper is the introduction of a new "intelligent-Deliberation" process in the hybrid BDI (h-BD[I]) architecture that enables an improved decision making features in a dynamic, and complex environment. Shared learning vector quantization (SLVQ) based neural network is proposed for the intelligent deliberation of the agent model. Paper discusses the benefits of incorporating knowledge based techniques in the deliberation process of the extended h-BD[I] model. [ABSTRACT FROM AUTHOR]

This paper presents the trends and directions of future agent design. These trends focus on advances in Agent-Oriented programming techniques and describe how agent technologies have developed with increasingly sophisticated techniques. The paper traces the origins of agent technology and describes related principles, especially those that reflect heavily on "Intelligence with Interaction". This interaction, especially with operator-in-the-loop scenarios, is demonstrated as a critical component of modern Distributed Artificial intelligence. Unfortunately many applications fail to address this fact, creating an interruption to ongoing research. Therefore we believe the next generation of agent systems should focus on human centric interaction to achieve a level of shared- intelligence made possible with modern computational techniques. [ABSTRACT FROM AUTHOR]

This paper introduces the invited session of "Innovations in Intelligent Agents" being presented at the ninth International Conference on Knowledge-Based & Intelligent Information & Engineering Systems. This session concentrates on the use of the Belief-Desire-Intention (BDI) architecture to produce Multi-Agent Systems (MAS) that enable "human-centric" teaming. A brief summary of the innovations that led to the evolution of research into this topic is also provided with the papers that detail the concepts raised in this session. [ABSTRACT FROM AUTHOR]

In this paper we describe our experiences with multi-programming (pair and tri programming) in a second level course. The course, "Application Software Development" is a second year course, which has a heavy emphasis on java programming in the labs as well as the development of a full-fledged project. The objective of the course is to build an entire project that comprises of various software engineering activities that span across the semester. In general, we observe that multi-programming improves the students' ability in analytical thinking and communicating the conceptual ideas. It also raises certain issues when this approach is adopted in the educational context. In this paper we discuss some of these issues. Overall, multi-programming experience has been a rewarding experience for the students in spite of certain problems that were encountered. [ABSTRACT FROM AUTHOR]

It is said that the UC(Ubiquitous Computing) Environment will be come by the technological revolution in the future. This paper firstly points out the problem that engineer thinks that Ubiquitous computing connected to network have become more complexes and distributed, but most system-related research is still focused on the 'performance' or 'efficiency'. And that most studied papers in privacy have been focused on encryption technology and protocols for securing the personal information data transaction. This paper secondly points out the problem that law-related researcher thinks that law can controller technology beyond human control. Today, due to the complexity of the problem, new privacy-related research based on total solution is integrative needed to consider laws, technology, economy, norms and so on. This paper will focus on analysis about Privacy in Ubiquitous computing Environment and total protection considerations on privacy. We present new privacy-related considerations in UC (Ubiquitous computing) Environment, point out the mechanism which new re-design privacy concept (protection scope) is affected from the UC (Ubiquitous computing) Environment and provide the total considerations for Privacy protection especially personal information protection by improve the intelligent technology applied in context aware technology. [ABSTRACT FROM AUTHOR]

To specify, verify, and reason about various reciprocal relationships in a human society and/or a cyber space, we need a right fundamental logic system to provide us with a criterion of logical validity of reasoning as well as a representation and specification language. This paper proposes a new family of conservative extensions of relevant logic, named "reciprocal logic," for specifying, verifying, and reasoning about reciprocal relationships. The paper shows that various reciprocal logics can be obtained by introducing predicates and related axioms about reciprocal relationships into strong relevant logics and spatial-temporal relevant logics. A case study is focused on trust relationships. [ABSTRACT FROM AUTHOR]

Modelling support for knowledge acquisition is a tool for modelling domain knowledge. However, during the implementation of the knowledge new knowledge is created. Event though this knowledge is found in the knowledge base, the model usually is not updated with the new knowledge and do, therefore, not contain all the knowledge in the system. This paper describes how different graphical models support the complex knowledge acquisition process of handling domain knowledge and how these models can be extended by modelling knowledge from rules in a knowledge base including probability. Thus, the models are designed from domain knowledge to create production rules but the models are also extended with new generated knowledge, i.e., generated rules. The paper also describes how different models can support the domain expert to grasp this new generated knowledge and to understand the uncertainty calculated from rules during consultation. To this objective, graphic representation and visualisation is used as modelling support through the use of diagrams of Unified Modelling Language (UML), which is used for modelling production rules. Presenting rules in a static model can make the contents more comprehensible and in a dynamic model can make the uncertainty more evident. [ABSTRACT FROM AUTHOR]

This paper describes, using situational awareness and Genetic algorithm, a run-time optimization methodology of the Gabor wavelet parameters so that it produces a feature space for efficient object recognition. Gabor wavelet efficiently extracts the feature space of orientation selectivity, spatial frequency and spatial localization. Most previous object recognition approaches using Gabor wavelet do not include systematic optimization of the parameters for the Gabor kernel, even though the system performance might be much sensitive to the characteristics of the Gabor parameters. This paper explores efficient object recognition using adaptive Gabor wavelet based situational aware method. The superiority of the proposed system is shown using IT-Lab, FERET and Yale face database. We achieved encouraging experimental results. [ABSTRACT FROM AUTHOR]

Emotion knowledge is a fundamental part of human commonsense knowledge. For the lack of solid knowledge extraction work in this domain, this paper focuses on acquiring and representing the antecedent situations of various emotions as well as the emotion subjects' interpretation to these situations in real-world emotion-eliciting scenarios. After a comprehensive analysis on the meaning structure of three critical notions in emotion understanding and modeling (i.e. role, context and event), this paper introduces a pragmatic emotion knowledge acquisition method and presents a context-restricted, role-oriented, frame-based representational model of emotion knowledge, with a case study which demonstrates the applicability of the model. [ABSTRACT FROM AUTHOR]

This paper deals with the GA-PSO (Genetic Algorithm-Particle Swarm Optimization) based vector control for loss minimization operation of induction motor. It is estimated that more than around 50% of the world electric energy generated is consumed by electric machines such as induction motor, DC motor. So, improving efficiency in electric drives is important and control strategy for minimum energy loss is needed as one of optimal operation strategy. In this paper, vector control approach is suggested for an optimal operation of induction motor using GA-PSO tuning method through simulation. [ABSTRACT FROM AUTHOR]

This paper presents a technique for an intelligent robot to adaptively behave in unforeseen and dynamic circumstances. Since the traditional methods utilized the relatively reliable information about the environment to control intelligent robots, they were robust but could not behave adaptively in complex and dynamic world. On the contrary, behavior-based approach is suitable for generating autonomous behaviors in the environment, but it still lacks of the capabilities to infer dynamic situations for high-level behaviors. This paper proposes a 2-layer control architecture to generate adaptive behaviors, which perceive and avoid dynamic moving obstacles as well as static obstacles. The first level is to generate reflexive and autonomous behaviors with the behavior network, and the second level is to infer dynamic situation of mobile robots with Bayesian network. Experimental results with various situations have shown that the robot reaches the goal points while avoiding static or moving obstacles with the proposed architecture. [ABSTRACT FROM AUTHOR]

This paper presents a new learning method for automatic acquisition of translation knowledge from parallel corpora. We apply this learning method to automatic extraction of bilingual word pairs from parallel corpora. In general, similarity measures are used to extract bilingual word pairs from parallel corpora. However, similarity measures are insufficient because of the sparse data problem. The essence of our learning method is this presumption: in local parts of bilingual sentence pairs, the equivalents of words that adjoin the source language words of bilingual word pairs also adjoin the target language words of bilingual word pairs. Such adjacent information is acquired automatically in our method. We applied our method to systems based on various similarity measures, thereby confirming the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Piracy is a major issue in the content business, and although digital technologies raise the efficiency of new content production, pirates also accelerate their piracy. Commercial cameras have become sufficiently good to re-shoot images displayed on screens, and TV monitors are becoming larger with better picture quality; this combination will enable content to be pirated in the home in the near future. Re-shooting with a commercial camera is the ultimate piracy method because there is no engineering way to stop it. We have developed a new watermark method that remains even after images displayed on a monitor have been re-shot. This paper describes the concept and experimental results. [ABSTRACT FROM AUTHOR]

In this paper properties of an originally introduced idea of epistemic satisfaction relation are discussed. It is assumed that this relation defines states of artificial cognition in which particular cases of modal conjunctions are well grounded. Presented theorems show that the epistemic satisfaction preserves the desirable similarity between artificially realized grounding and its natural counterpart known from the context of natural language discourse. The most important conclusion is that as regards to the set of modal conjunctions it is possible to develop an artificial cognitive agent that is able to carry out semantic communication reflecting the natural language communication. In order to achieve this property the artificial cognitive agent needs to be equipped with a certain system modality thresholds. [ABSTRACT FROM AUTHOR]

In the last decades, there has been extensive use of hypermedia systems in education as a tool for enhancing learning and teaching strategies. But the result of researches shows that little research effort has been directed towards making the presentation and navigation of a hypermedia system more knowledge-based, i.e. driven by knowledge about the information contents [2]. One approach to achieve this is to extend the hypermedia system with techniques from knowledge-based systems. In a hypermedia system chunks of information, stored in nodes, are presented in a non-linear way, similar to the way the human brain process information. Therefore hypermedia systems can be seen as naturally augmenting human abilities to access and process information. Development of a knowledge based hypermedia system for learning is not just about designing a few screens and specifying their relationship. It is also about pedagogical support for learning. Therefore, in this paper some aspects that are important to consider when designing knowledge based hypermedia systems for learning have been addressed. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach for implementing reasoning and learning systems based on Intelligent Agents. It is particularly suited for agent systems working in complex and cooperative dynamic environments. This approach was developed to overcome limitations confronted while researching the use of agents in such environments. A brief background of the underlying conceptual reasoning model is described, followed by details of the implemented framework and concluded with some final remarks and future work. [ABSTRACT FROM AUTHOR]

An organization can optimize a project and strengthen control of it and thus, accomplish its objectives by determining its project capability through the proposed models, by planning the most suitable project to its vision. The approach combines two methods. One looks at an organization's measurement framework in goal-oriented fashion and the other looks at it in vision driven. The goal-oriented method was applied to improve the quality and delivery measurement from the point of view. It identified several new metrics, and also contributed to better understanding the collected data of user requirement. The vision-driven method was used to gain new insights into the existing PCM(Performance Calculation Model) data.This paper gives the case study and its results to qualitatively compare our approach against current ad hoc practices used to improve existing Opportunity Tree frameworks(OTF). [ABSTRACT FROM AUTHOR]

In the semiconductor manufacturing, yield enhancement is an important issue. It is ideal to prevent all failures. However, when a failure occurs, it is important to quickly specify the cause stage and take countermeasures. Reviewing wafer level and composite lot level yield patterns has always been an effective way of identifying yield inhibitors and driving process improvement. This process is very time consuming and as such generally occurs only when the overall yield of a device has dropped significantly enough to warrant investigation. The automatic method of failure pattern extraction from fail bit map provides reduced time to analysis and facilitates yield enhancement. The automatic method of failure pattern extraction from fail bit map provides reduced time to analysis and facilitates yield enhancement. This paper describes the techniques to automatically recognize and classifies a failure pattern using a fail bit map, a new simple schema which facilitates the failure analysis. [ABSTRACT FROM AUTHOR]

It is important that we produce a business rule and schedule in the manufacture process. The business rule is related at the dispatching to assign the material(lot) at the resource(equipment). The schedule is to plan a daily job scheduling of a total processes. In this paper, we develop the builder and editor for business rule flow and the workflow engine for dispatching and scheduling. We propose systemical development process using component and UML(Unified Modeling Language) technology to analysis, design and develop. The development process is an attempt to consider all of the best features of existing domain requirements. Also, we define rule format of XML(eXtended Markup Language) for mapping between a rule engine and builder. The builder generates XML from a rule and parses to save the rule at the repository. Finally we describe how these concepts may assist in increasing the efficiency and productivity in business application and manufacture process. Keywords: Business Rule, Business Rule Engine & Builder, Component Based Architecture, Component Based Development, UML [ABSTRACT FROM AUTHOR]

It is difficult to define a comfortable space for each individual. It is partly because comfortness relates to many attributes that specify a space, partly because each individual has different preference, and also because even the same person changes his/her preference according health states, body conditions, working states and so on. Various parameters and attributes should be controlled in order to realize such a comfortable space according the data-base of past usages. Information obtained from human bodies such as temperature, blood pressure, α brainwave and etc. can be employed to adjust the space to the best condition. The objective of this paper is to achieve a comfortable space in terms of Kansei engineering. It is required to realize our comfortable environment suitable to feelings and customers often have their individual preference so that they feel comfortable, too. Kansei Engineering is a technology to offer better products to the customers by employing human sensitivity. [ABSTRACT FROM AUTHOR]

The correspondence between precision dance movements and the accompanying musical arrangement is imperative to the reception of the performance. Whether the choreography is excellent or not becomes irrelevant if the performer's movements do not coincide with the score. This paper proposes an evaluation method based on an audience's impression of the correspondence between the music and the dancer's movements. This evaluation method is called "Kansei (Sensibility) Matching." For the matching method developed in this research, the term Kansei refers to a set of terms that express, verbally, the sentiment of music and movement. [ABSTRACT FROM AUTHOR]

This paper addresses an integrated information mining techniques for multimedia TV-news archive. The utilizes techniques from the fields of acoustic, image, and video analysis, for information retrieval on news story title, newsman and scene identification. The goal is to construct a compact yet meaningful abstraction of broadcast news video, allowing users to browse through large amounts of data in a non-linear fashion with flexibility and efficiency. By using acoustic analysis, the system can classify video into news versus commercials, with 90% accuracy on a data set of 400 hours TV-news recorded off the air from July 2003 to August of 2004. By applying speaker identification and/or image detection techniques, each news stories can be segmented with an accuracy of 96%. On screen captions or subtitles are recognized by OCR techniques to produce the text title of each news stories. The extracted title words can be used to link or to navigate more related News contents on the WWW. In cooperation with facial and scene analysis and recognition techniques, OCR results can provide users with multimodality query for specific news stories. Some experimental results are presented and discussed for the system reliability and performance evaluation and comparison. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a dynamic supervising model based on grid environment. This model can utilize the grid resources, e.g., CPU, storages, etc., more flexible and optimal. There are three modules in this model, saying, connecting authentication module (CAM), trusting module (TM), and resource monitor module (RMM). CAM can authenticate the demander. TM can adjust trust degrees of the other collaborators by fuzzy inferences, and provide these trust degrees for RMM to schedule the works process. RMM can discover the resources, schedule and distribute works to others nodes. Once the demander passes the authentication, RMM will schedule and distribute works depending on the trust degrees from TM. RMM will dynamically monitor the resource variation of these collaborators. This model not only can make the collaboration more flexible and reliable, but also can optimize the grid resources. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a distributed backup agent based on grid computing architecture. In grid environment, this agent can assist user to backup the data files in different nodes storages,update replicas synchronously, and access the replicas if necessary. There are two modules in this agent, saying, grid consistency service module (GCSM) and grid transaction module (GTM). GCSM can monitor the grid backup nodes status, e.g. storages space, on-line available, etc. GTM can maintain the consistency and integrity of backup files. This agent makes the distributed backups of the data files be more convenient and secure to access. [ABSTRACT FROM AUTHOR]

In this paper, we proposed an emergency model of home network environment based on genetic algorithm. This model can not only adapt the home network environment by using genetic algorithm but also detect the emergency events automatically. There are four modules in this model, saying, training knowledge base (TKB), genetic operator module (GOM), emergency knowledge base (EKB), and emergency early warning module (EEWM). TKB receives the messages from the environment and provides them for GOM to train EKB. GOM trains the EKB to fit the real situation by using genetic algorithm. EKB includes the database and the rule base which can provide messages for EEWM to infer. EEWM determines the emergency situations by fuzzy inferences and sends the caution messages to the users by mobile devices. Via this model, our home network environment will become more reliable and safer. [ABSTRACT FROM AUTHOR]

Image registration is a crucial step in all image analysis tasks. In this paper, an edge projection-based image registration method is proposed. First, Radon transform is used to project the edges of images along different directions, then cross-correlation-based approach is used to estimate global rotation and shift, finally polynomial fit is used to improve the accuracy of image registration. Simulation indicates that the proposed method can estimate global rotation and shift accurately and speedily. [ABSTRACT FROM AUTHOR]

In this paper, we propose a Generalized Probabilistic decision based Neural Network (GPDNN) for content-based image retrieval (CBIR). Instead of receiving the numerical values of each data points as the input, the proposed GPDNN models the I/O relationship via the distribution of input data and their corresponding outputs. The GPDNN involves the Multiple-Instance learning techniques to learn a desired concept. A set of exemplar images are selected by a user, each of which is labeled as conceptual related (positive) or conceptual unrelated (negative) image. Then, by using the proposed learning algorithm, an image classification system can learn the user's preferred image class from the positive and negative examples. The experimental results show that for only a few times of relearning, a user can use the prototype system to retrieve favor images from the database. [ABSTRACT FROM AUTHOR]

Searching for similar images is an important research topic for multimedia database management. This paper uses a quality index model to search for similar images from digital image databases. In order to speed up retrieval, the quality index model is partitioned into three factors: loss of correlation, luminance distortion, and contrast distortion. The method is performed on three different image databases to test for retrieval accuracy and category retrieval ability. The experimental results show that the proposed method performs better than the color histogram method, the color moment method, and the CDESSO method. [ABSTRACT FROM AUTHOR]

In this paper, we present a new method for classifying shot type in sports video using fuzzy information granular. The problem is important for applications such as video structure analysis and content understanding. In particular,two-stage off-line learning processes perform knowledge extraction of semantic concepts and automatic shot classification, respectively. In the first stage, the extracted prominent regions are used as a good pattern in semantic concept level. Then a number of global features are defined as efficient input of the shot type classifier in the second stage. The identification of semantic concepts and classification of shot are based on soft decisions. Hence, this framework can adequately capture the uncertainty or ambiguity of scales of a shot. Experimental results show the excellent performance of the approach. [ABSTRACT FROM AUTHOR]

This paper presents a motion suppression technique for video shot boundary detection based on 3D wavelet transform (3-DWT). Dramatic motion can be characterized in terms of energy and variance, and be differentiated from various video effects. Motion suppression value (MSV), which indicates intensity of motion energy, is extracted and used to suppress motion influence suffered by traditional video shot boundary detection algorithms. Unlike previous methods, our technique is robust to dramatic motion inherent in video sequence, experimental result validates our approach. [ABSTRACT FROM AUTHOR]

Semantics-based image retrieval is a challenging problem. In this paper, we propose an approach for image semantics abstraction, which constructs a multi-level semantics tree based on human subject and train hierarchical semantic classifier. According to our method, image features are selected by using priori knowledge. Then, those images are classified in every level by the classifier based on support vector machines (SVM). The SVM classifiers learn the semantics of specified classes from a training database of image. Experiments show that we can abstract multi-level semantics from image database by using less low-level features. [ABSTRACT FROM AUTHOR]

Scene detection is an essential step to organize the video data properly for content-based video analysis and its application. In this paper, an effective scene detection approach is proposed, which exploits the cinematic rules used by filmmakers as guideline to compute shot similarities and identify the video scenes in narrative film. First, a clustering method with time constraint is used to group the shots into scene slices. Then dialog scene's alternative structure and audio correlation are used to identify dialog scene. Finally, motion and audio correlation guided by cinematic rules are used to further detect action scene. Experimental results show that the proposed method works well and can deal with complex scene. [ABSTRACT FROM AUTHOR]

This paper proposes an effective technique which can detect malicious manipulations under video lossy compressing data (e.g. H.263) and still-image lossy compressing data (e.g. JPEG). A block-classification strategy is used to divide DCT-blocks into the flat-blocks and the normal-blocks. Simple features of the both blocks are embedded invisibly. For later authentication, the watermarked frame is then put back into the compressed bit-streams. The proposed method can detect and locate alterations of the tampered frame whether it is stored again into original bit-streams or not. This goal is for detecting tamper area and surviving most video lossy compression. Experimental results show that the proposed technique can detect various tampered areas and hence provides an effective image authentication for lossy compressed image and video in DVR (Digital Video Recorder) System. Keywords: watermarking, H.263, JPEG, image authentication, compressed video. [ABSTRACT FROM AUTHOR]

A new watermarking technique called associative watermarking is proposed in this paper. The watermark in our new scheme will be embedded by applying the concept of association rules borrowed from the field of data mining. We implant the watermark's rules into the original image by changing a very small portion of the image's pixels during the rules alignment process. As a result, the robustness can be enhanced by emphasizing the specific rules mined from critical areas in the original image. Instead of transforming the watermark into its bit pattern, we just mine the association rules from the watermark and embed them into a colorful image. Our experimental results reveal that the PSNR value of the image after watermark implanting exceeds 40, and more than 90% of the watermarked images can be accurately recognized after similarity checking. Keywords: Association rule, Digital Watermarking, Image, Similarity [ABSTRACT FROM AUTHOR]

In recent years, the method of spread spectrum watermarking (SSW) has become the one of the most promising technique used for digital watermarking technology. However, the major problems of SSW technology is that the effectiveness of SSW detection will drop fairly without subtracting the host image from watermarked image because of the effect of correlation remains calculated between the host image and original pseudo-random sequences. In our previous work, we have proposed a method to improve the detection of SSW techniques by reduction of correlation remains using pixel-correlations in an image. In this paper, we have investigated the effectiveness of the proposed method with image experiments in detail. The experimental results illustrate that the correlation remains can be reduced greatly by using pixel-correlations. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new secret sharing scheme (SSS) [1] for audio signals, called as "Binary audio secret sharing (BASS)." SSS is an encryption method and produces n shared data from an original data to hide useful information. Applying SSS to audio communications on the Internet can help to make it more robust against theft and the tapping of information. Thus, we focused on the 1-bit audio format and applied SSS to 1-bit audio signals to realize audio secret sharing. Moreover, we propose a method to make each shared data heard as its intended sound. [ABSTRACT FROM AUTHOR]

Invertibility attack is a hostile measure to breach watermarking systems. In this paper, a novel watermarking protocol using a one-way hash function and a check of random watermarks is proposed in order to combat invertibility attacks. The described technique can be used in conjunction with any watermarking algorithm, no matter it is kept secret or made public, without resorting to a third party jury as required by some previous approaches. By introducing a set of reference sequences, segmentation of the digital information and iterative computation of watermarks, the protocol is further enhanced so that it can resist more sophisticated types of attack based on forging an illegitimate detector. [ABSTRACT FROM AUTHOR]

A hybrid watermark that consists of a robust part and a fragile part can be used to serve multiple purposes. The robust part can protect copyright information, the fragile part can detect tampering, and their combination enables identification of attacks encountered. This paper analyses an overlap and a non-overlap implementation of the robust and fragile parts in a hybrid system. The difference between the two implementation methods lies in the robust and fragile watermarks embedding positions. Embedding capacity, computational costs, watermark robustness, and tamper detection localization of the two implementations are analyzed. In addition, optimization issues of block size in the hybrid system are discussed. [ABSTRACT FROM AUTHOR]

In this paper, a novel application of SVG (Scalable Vector Graphics) is proposed in watermarking. Vector graphic is used to detect geometric transform and control geometric distortion. Experimental results show that the proposed method is efficient to solve geometric attack to watermarking. [ABSTRACT FROM AUTHOR]

A semi-fragile watermarking algorithm for digital image content authentication is proposed in this paper. The watermark is generated from the Zernike moments of the low frequency subband in IWT (integer wavelet transform) domain of the original image. This sort of image-dependent watermark can resist forgery attack and improve the watermark security. Watermark is embedded in the IWT domain of an image by exploiting the features of human visual system (HVS). It makes the high-fidelity and high-quality watermarked image. Moreover, we can distinguish mild distortion from severe distortion according to the difference of Zernike moments before and after attack. Experimental results show that the proposed algorithm is fragile to malicious tamper and can locate the tampered area accurately while is robust to content-preserved manipulation, such as JPEG lossy compression. [ABSTRACT FROM AUTHOR]

We have proposed a novel audio watermarking technology, which embeds a set of bitstream data by changing two-channel stereo locations of lower frequency components in an embedding target audio signal. This method features nearly lossless embedding, robustness against lossy data compression or analogue conversion, and enables contactless asynchronous detection of embedded watermarks through speaker and microphone devices without the original audio signals. In this paper, we propose an extended monaural audio watermark embedding method, which supports both monaural and stereo audio signals, and enables watermark detection by a single monaural microphone such as cell phone voice receiver devices. We describe an abstract of our proposed watermark embedding and extracting algorithm, and experimental results of watermark extraction precision. [ABSTRACT FROM AUTHOR]

In this paper we propose a video in video hiding technique for embedding and transmission of sign language video signal through another video communication channel. Our proposed system does not need modification of the main video coding and transmission system, and it can be implemented by addition of a pre- and post-processing block. We encode the sign language video and embed the encoded bit-stream in the main host video. We develop a low complexity and robust encoding scheme for sign language video by applying three-dimensional wavelet decomposition on the sign language video, and encoding the important subbands using multiple description scalar quantizers. We also apply three-dimensional wavelet decomposition on the host video and embed the encoded bit-stream of the sign language video in the host signal subbands. We select blocks of the host video with high texture content and embed the information in the middle frequency subbands to have highest robustness and with low visible distortion. At the receiver the system reconstructs the sign language video by recovering the embedded data in subbands. We examine the system performance by embedding video sequences of sign language messages into host video sequences. At the receiver we evaluate the percentage of correct sign language messages recovery. We further evaluate the system performance when the host video undergone compression and addition of noise during transmission. [ABSTRACT FROM AUTHOR]