Decision diagrams are often used for efficient representation of discrete functions in terms of needed storage space and processing time. In this paper, we propose an XML (Extensible Markup Language) based standard for the structural description of various types of decision diagrams. The proposed standard describes elements of the structure common to various types of decision diagrams. It also provides facilities for storing additional information, specific to particular types of decision diagrams. Properties of XML enable us to define a standard that is flexible enough to be applicable to various existing types of decision diagrams as well as new types that could be defined in the future. The existence of such a standard permits efficient storage and exchange of data in decision diagram form between various software systems. In this way, it supports benchmarking, testing and verification of various procedures using decision diagrams as a basic data structure.

In the current broadcasting system or Internet content distribution system, content providers distribute decoders (STB) that contain secret keys for content decryption, prior to content distribution. A content provider sends encrypted content to each user, who then decodes it with his or her STB. While users can get the services at their houses if they have an STB, it is hard for them to get the services outside their houses. A system that allowed users to carry around their secret keys would improve usability, but it would require countermeasures against secret key exposure. In this paper, we propose such an extended broadcasting system using tokens and group signature. The content providers can control the number of keys that users can use outside their houses. The system enables the broadcasters to minimize the damage caused by group signature key exposures and the user to get services outside his or her home.

This paper presents 3D keyframe animation watermarking using orientation interpolators. 3D keyframe animation consists of a number of transform nodes, including a geometrical node from the initial model and several interpolator nodes that represent object movement. Therefore, the proposed algorithm randomly selects transform nodes with orientation interpolator nodes, then resamples the quaternion components to maintain a uniform key time. Thereafter, watermark bits are embedded into quaternion components with large rotation angles. Experimental results verify the robustness of the proposed algorithm to geometrical and timeline attacks, along with the subjective and objective quality of its invisibility.

This work is concerned with the problem of robot localization using standard RFID tags as landmarks and an RFID reader as a landmark sensor. A main advantage of such an RFID-based localization system is the availability of landmark ID measurement, which trivially solves the data association problem. While the main drawback of an RFID system is its low spatial accuracy. The result in this paper is an improvement of the localization accuracy for a standard short-range RFID sensor. One of the main contributions is a proposal of a machine learning approach in which multiple classifiers are trained to distinguish RFID-signal features of each location. Another contribution is a design tool for tag arrangement by which the tag configuration needs not be manually designed by the user, but can be automatically recommended by the system. The effectiveness of the proposed technique is evaluated experimentally with a real mobile robot and an RFID system.

Eye tracking is a useful tool for accurately mapping where and for how long an individual learner looks at a video/image, in order to obtain immediate information regarding the distribution of a learner's attention among the elements of a video/image. This paper describes a quantitative investigation into the effect of voice navigation in web-based learning materials.

In order to obtain better generalization performance in supervised learning, model parameters should be determined appropriately, i.e., they should be determined so that the generalization error is minimized. However, since the generalization error is inaccessible in practice, the model parameters are usually determined so that an estimator of the generalization error is minimized. The regularized subspace information criterion (RSIC) is such a generalization error estimator for model selection. RSIC includes an additional regularization parameter and it should be determined appropriately for better model selection. A meta-criterion for determining the regularization parameter has also been proposed and shown to be useful in practice. In this paper, we show that there are several drawbacks in the existing meta-criterion and give an alternative meta-criterion that can solve the problems. Through simulations, we show that the use of the new meta-criterion further improves the model selection performance.

The support vector machine has received wide acceptance for its high generalization ability in real world classification applications. But a drawback is that it uniquely classifies each pattern to one class or none. This is not appropriate to be applied in classification problem involves overlapping patterns. In this paper, a novel multi-model classifier (DR-SVM) which combines SVM classifier with kNN algorithm under rough set technique is proposed. Instead of classifying the patterns directly, patterns lying in the overlapped region are extracted firstly. Then, upper and lower approximations of each class are defined on the basis of rough set technique. The classification operation is carried out on these new sets. Simulation results on synthetic data set and benchmark data sets indicate that, compared with conventional classifiers, more reasonable and accurate information about the pattern's category could be obtained by use of DR-SVM.

The open-vocabulary name recognition technique is one of the most challenging tasks in the application of automatic Chinese speech recognition technology. It can be used as the free name input method for telephony speech applications and automatic directory assistance systems. A Chinese name usually has two to three characters, each of which is pronounced as a single tonal syllable. Obviously, it is very confusing to recognize a three-syllable word from millions to billions of possible candidates. A novel interactive automatic-speech-recognition system is proposed to resolve this highly challenging task. This system was built as an open-vocabulary Chinese name recognition system using character-based approaches. Two important character-input speech-recognition modules were designed as backoff approaches in this system to complete the name input or to correct any misrecognized characters. Finite-state networks were compiled from regular grammar of syllable spellings and character descriptions for these two speech recognition modules. The possible candidate names cover more than five billions. This system has been tested publicly and proved a robust way to interact with the speaker. An 86.7% name recognition success rate was achieved by the interactive open-vocabulary Chinese name input system.

Automatic prosody labeling is the task of automatically annotating prosodic labels such as syllable stresses or break indices into speech corpora. Prosody-labeled corpora are important for speech synthesis and automatic speech understanding. However, the subtleness of physical features makes accurate labeling difficult. Since errors in the prosodic labels can lead to incorrect prosody estimation and unnatural synthetic sound, the accuracy of the labels is a key factor for text-to-speech (TTS) systems. In particular, mora accent labels relevant to pitch are very important for Japanese, since Japanese is a pitch-accent language and Japanese people have a particularly keen sense of pitch accents. However, the determination of the mora accents of Japanese is a more difficult task than English stress detection in a way. This is because the context of words changes the mora accents within the word, which is different from English stress where the stress is normally put at the lexical primary stress of a word. In this paper, we propose a method that can accurately determine the prosodic labels of Japanese using both acoustic and linguistic models. A speaker-independent linguistic model provides mora-level knowledge about the possible correct accentuations in Japanese, and contributes to reduction of the required size of the speaker-dependent speech corpus for training the other stochastic models. Our experiments show the effectiveness of the combination of models.

In this paper, we propose a new scheme to represent three-dimensional (3-D) dynamic scenes using a hierarchical decomposition of depth maps. In the hierarchical decomposition, we split a depth map into four types of images: regular mesh, boundary, feature point and number-of-layer (NOL) images. A regular mesh image is obtained by down-sampling a depth map. A boundary image is generated by gathering pixels of the depth map on the region of edges. For generating feature point images, we select pixels of the depth map on the region of no edges according to their influence on the shape of a 3-D surface, and convert the selected pixels into images. A NOL image includes structural information to manage the other three images. In order to render a frame of 3-D dynamic scenes, we first generate an initial surface utilizing the information of regular mesh, boundary and NOL images. Then, we enhance the initial surface by adding the depth information of feature point images. With the proposed scheme, we can represent consecutive 3-D scenes successfully within the framework of a multi-layer structure. Furthermore, we can compress the data of 3-D dynamic scenes represented by a mesh structure by a 2-D video coder.

This paper introduces a texture analysis mechanism utilizing multiresolution technique to reduce false motion detection and hence thoroughly improve the interpolation results for high-quality deinterlacing. Conventional motion-adaptive deinterlacing algorithm selects from inter-field and intra-field interpolations according to motion. Accurate determination of motion information is essential for this purpose. Fine textures, having high local pixel variation, tend to cause false detection of motion. Based on hierarchical wavelet analysis, this algorithm provides much better perceptual visual quality and considerably higher PSNR than other motion adaptive deinterlacers as shown. In addition, a recursive 3-field motion detection algorithm is also proposed to achieve better performance than the traditional 2-field motion detection algorithm with little memory overhead.

In this study, we propose a simple, yet general and powerful framework for constructing accurate affine invariant regions. In our framework, a method for extracting reliable seed points is first proposed. Then, regions which are invariant to most common affine transformations can be extracted from seed points by two new methods the Path Growing (PG) or the Thresholding Seeded Growing Region (TSGR). After that, an improved ellipse fitting method based on the Direct Least Square Fitting (DLSF) is used to fit the irregularly-shaped contours from the PG or the TSGR to obtain ellipse regions as the final invariant regions. In the experiments, our framework is first evaluated by the criterions of Mikolajczyk's evaluation framework [1], and then by near-duplicate detection problem [2]. Our framework shows its superiorities to the other detectors for different transformed images under Mikolajczyk's evaluation framework and the one with TSGR also gives satisfying results in the application to near-duplicate detection problem.

We have built a CLQA (Cross Language Question Answering) system for a source language with limited data resources (e.g. Indonesian) using a machine learning approach. The CLQA system consists of four modules: question analyzer, keyword translator, passage retriever and answer finder. We used machine learning in two modules, the question classifier (part of the question analyzer) and the answer finder. In the question classifier, we classify the EAT (Expected Answer Type) of a question by using SVM (Support Vector Machine) method. Features for the classification module are basically the output of our shallow question parsing module. To improve the classification score, we use statistical information extracted from our Indonesian corpus. In the answer finder module, using an approach different from the common approach in which answer is located by matching the named entity of the word corpus with the EAT of question, we locate the answer by text chunking the word corpus. The features for the SVM based text chunking process consist of question features, word corpus features and similarity scores between the word corpus and the question keyword. In this way, we eliminate the named entity tagging process for the target document. As for the keyword translator module, we use an Indonesian-English dictionary to translate Indonesian keywords into English. We also use some simple patterns to transform some borrowed English words. The keywords are then combined in boolean queries in order to retrieve relevant passages using IDF scores. We first conducted an experiment using 2,837 questions (about 10% are used as the test data) obtained from 18 Indonesian college students. We next conducted a similar experiment using the NTCIR (NII Test Collection for IR Systems) 2005 CLQA task by translating the English questions into Indonesian. Compared to the Japanese-English and Chinese-English CLQA results in the NTCIR 2005, we found that our system is superior to others except for one system that uses a high data resource employing 3 dictionaries. Further, a rough comparison with two other Indonesian-English CLQA systems revealed that our system achieved higher accuracy score.

In this paper, we present a new method to enhance classification performance of a multiple classifier system by combining a boosting technique called AdaBoost.M2 and Kernel Discriminant Analysis (KDA). To reduce the dependency between classifier outputs and to speed up the learning, each classifier is trained in a different feature space, which is obtained by applying KDA to a small set of hard-to-classify training samples. The training of the system is conducted based on AdaBoost.M2, and the classifiers are implemented by Radial Basis Function networks. To perform KDA at every boosting round in a realistic time scale, a new kernel selection method based on the class separability measure is proposed. Furthermore, a new criterion of the training convergence is also proposed to acquire good classification performance with fewer boosting rounds. To evaluate the proposed method, several experiments are carried out using standard evaluation datasets. The experimental results demonstrate that the proposed method can select an optimal kernel parameter more efficiently than the conventional cross-validation method, and that the training of boosting classifiers is terminated with a fairly small number of rounds to attain good classification accuracy. For multi-class classification problems, the proposed method outperforms both Boosting Linear Discriminant Analysis (BLDA) and Radial-Basis Function Network (RBFN) with regard to the classification accuracy. On the other hand, the performance evaluation for 2-class problems shows that the advantage of the proposed BKDA against BLDA and RBFN depends on the datasets.

In this paper, we describe a new ultrasonic oscillosensor and its application in a biological information measurement system. This ultrasonic sensor has a cylindrical tank of 26 mm (diameter)20 mm (height) filled with water and an ultrasonic probe. It detects the vibration of the target object by obtaining echo signals reflected from the water surface. This sensor can noninvasively detect the vibration of a patient by placing it under a bed frame. We propose a recognition system for humans in bed. Using this sensor, we could determine whether or not a patient is in the bed. Moreover, we propose a heart rate monitoring system using this sensor. When our system was tested on four volunteers, we successfully detected a heart rate comparable to that in the case of using an electrocardiograph. Fuzzy logic plays a primary role in the recognition. Consequently, this system can noninvasively determine whether a patient is in the bed as well as their heart rate using a constraint-free and compact device.

In this paper, we propose two weighting techniques to improve performances of query expansion in biomedical document retrieval, especially when a short biomedical term in a query is expanded with its synonymous multi-word terms. When a query contains synonymous terms of different lengths, a traditional IR model highly ranks a document containing a longer terminology because a longer terminology has more chance to be matched with a query. However, such preference is clearly inappropriate and it often yields an unsatisfactory result. To alleviate the bias weighting problem, we devise a method of normalizing the weights of query terms in a long multi-word biomedical term, and a method of discriminating terms by using inverse terminology frequency which is a novel statistics estimated in a query domain. The experiment results on MEDLINE corpus show that our two simple techniques improve the retrieval performance by adjusting the inadequate preference for long multi-word terminologies in an expanded query.

This paper presents an active quality of service (QoS) aware service composition protocol for mobile ad hoc networks (MANETs), with the goal of conserving resources subject to QoS requirements. A problem of QoS based service composition in MANETs is transformed into a problem of the service path discovery. We extend Dynamic Source Routing protocol to discover and compose elementary services across the network. Some message processing measures are taken to effectively reduce control overhead. Simulation results demonstrate the effectiveness of the proposed protocol.

Imperfect transmission of satellite imagery results in the loss of image lines. This paper proposes a novel error concealment technique using LSB-based watermarking. We generate block description information and insert it into the LSB bit plane of the image. Missing lines after transmission are restored by extracting this block description information. Simulation results show outstanding performance of the proposed technique.

The intent of this letter is to propose an efficient timestamp based password authentication scheme using smart cards. We show various types of forgery attacks against Shen et al.'s timestamp-based password authentication scheme and improve their scheme to ensure robust security for the remote authentication process, keeping all the advantages of their scheme. Our scheme successfully defends the attacks that could be launched against other related previous schemes.

This paper analyses the features required to efficiently recognize five Japanese vowels for lip-reading. Various features, such as shape and radius, are calculated from the lip region and fed to the k Nearest Neighbor method. We calculated 15 feature sets and found that the feature set including the area and aspect ratio of the mouth cavity is effective for Japanese vowel recognition.

With the aim of improving speaker identification, we propose a likelihood-based integration method to combine the speaker identification results obtained through multiple microphones. In many cases, the composite result has lower error rate than that by any single channel. The proposed integration method can achieve more reliable identification performance in the ubiquitous robot companion (URC) environment in which the robot is connected to a server through an extremely high broadband penetration rate.

This paper proposed a region-based curve control function to detect the brain ventricle area by utilizing a geodesic active contour model. This is based on the average brightness of the brain ventricle area which is brighter in MRI images. Compared numerically by using various types of measurements, the proposed method can detect the brain ventricle area better than the existing methods.