We present a scalable approach to automatically discovering particular objects (as opposed to object categories) from a set of images. The basic idea is to search for local image features that consistently appear in the same images under the assumption that such co-occurring features underlie the same object. We first represent each image in the set as a set of visual words (vector quantized local image features) and construct an inverted file to memorize the set of images in which each visual word appears. Then, our object discovery method proceeds by searching the inverted file and extracting visual word sets whose elements tend to appear in the same images; such visual word sets are called co-occurring word sets. Because of unstable and polysemous visual words, a co-occurring word set typically represents only a part of an object. We observe that co-occurring word sets associated with the same object often share many visual words with one another. Hence, to obtain the object models, we further cluster highly overlapping co-occurring word sets in an agglomerative manner. Remarkably, we accelerate both extraction and clustering of co-occurring word sets by Min-Hashing. We show that the models generated by our method can effectively discriminate particular objects. We demonstrate our method on the Oxford buildings dataset. In a quantitative evaluation using a set of ground truth landmarks, our method achieved higher scores than the state-of-the-art methods.

This paper proposes a method for setting the threshold for ultra-wide-band (UWB) threshold-based ranging in indoor scenarios. The optimum threshold is derived based on the full analysis of the ranging error, which is equivalent to the probability of correct detection of first arriving signal in time-based ranging techniques. It is shown that the probability of correct detection is a function of first arriving signal, which has variations with two independent distributions. On the one hand, the first arriving signal varies in different positions with the same range due to multipath interference and on the other, it is a function of distance due to free space path-loss. These two distributions are considered in the derivation of the ranging error, based on which the optimum threshold is obtained. A practical method to derive this threshold is introduced based on the standard channel model. Extensive Monte Carlo simulations, ray-tracing simulations and ranging measurements confirm the analysis and the superior performance of the proposed threshold scheme.

Kernel biased discriminant analysis (KBDA), as a subspace learning algorithm, has been an attractive approach for the relevance feedback in content-based image retrieval. Its performance, however, still suffers from the “small sample learning” problem and “kernel learning” problem. Aiming to solve these problems, in this paper, we present a new semi-supervised scheme of KBDA (S-KBDA), in which the projection learning and the “kernel learning” are interweaved into a constrained optimization framework. Specifically, S-KBDA learns a subspace that preserves both the biased discriminant structure among the labeled samples, and the geometric structure among all training samples. In kernel optimization, we directly optimize the kernel matrix, rather than a kernel function, which makes the kernel learning more flexible and appropriate for the retrieval task. To solve the constrained optimization problem, a fast algorithm based on gradient ascent is developed. The image retrieval experiments are given to show the effectiveness of the S-KBDA scheme in comparison with the original KBDA, and the other two state-of-the-art algorithms.

With the increasing demand of high video quality and large image size, adaptive interpolation filter (AIF) addresses these issues and conquers the time varying effects resulting in increased coding efficiency, comparing with recent H.264 standard. However, currently most AIF algorithms are based on either frame level or macroblock (MB) level, which are not flexible enough for different video contents in a real codec system, and most of them are facing a severe time consuming problem. This paper proposes a content based coarse to fine AIF algorithm, which can adapt to video contents by adding different filters and conditions from coarse to fine. The overall algorithm has been mainly made up by 3 schemes: frequency analysis based frame level skip interpolation, motion vector modeling based region level interpolation, and edge detection based macroblock level interpolation. According to the experiments, AIF are discovered to be more effective in the high frequency frames, therefore, the condition to skip low frequency frames for generating AIF coefficients has been set. Moreover, by utilizing the motion vector information of previous frames the region level based interpolation has been designed, and Laplacian of Gaussian based macroblock level interpolation has been proposed to drive the interpolation process from coarse to fine. Six 720p and six 1080p video sequences which cover most typical video types have been tested for evaluating the proposed algorithm. The experimental results show that the proposed algorithm reduce total encoding time about 41% for 720p and 25% for 1080p sequences averagely, comparing with Key Technology Areas (KTA) Enhanced AIF algorithm, while obtains a BDPSNR gain up to 0.004 and 3.122 BDBR reduction.

To reduce the error of channel estimation caused by noise, a novel noise suppression method based on the degree of confidence is proposed in this paper. The false alarm and false dismissal probabilities, corresponding to noise being taken as part of channel impulse response (CIR) and part of the CIR being mis-detected as noise, respectively, are also investigated. A false alarm reduction method is therefore presented to reduce the false alarms in the estimated CIR while the mis-detection ratio still remains low. Simulation results show the effectiveness of the proposed method.

This paper presents and evaluates a new acoustic imaging system that uses multicarrier signals for correlation division in synthetic transmit aperture (CD-STA). CD-STA is a method that transmits uncorrelated signals from different transducers simultaneously to achieve high-speed and high-resolution acoustic imaging. In CD-STA, autocorrelations and cross-correlations in transmitted signals must be suppressed because they cause artifacts in the resulting images, which narrow the dynamic range as a consequence. To suppress the correlation noise, we had proposed to use multicarrier signals optimized by a genetic algorithm. Because the evaluation of our proposed method was very limited in the previous reports, we analyzed it more deeply in this paper. We optimized three pairs of multicarrier waveforms of various lengths, which correspond to 5th-, 6th- and 7th-order M-sequence signals, respectively. We built a CD-STA imaging system that operates in air. Using the system, we conducted imaging experiments to evaluate the image quality and resolution of the multicarrier signals. We also investigated the ability of the proposed method to resolve both positions and velocities of target scatterers. For that purpose, we carried out an experiment, in which both moving and fixed targets were visualized by our system. As a result of the experiments, we confirmed that the multicarrier signals have lower artifact levels, better axial resolution, and greater tolerance to velocity mismatch than M-sequence signals, particularly for short signals.

In this paper, we briefly review kernel methods for analysis of chemical compounds with focusing on the authors' works. We begin with a brief review of existing kernel functions that are used for classification of chemical compounds and prediction of their activities. Then, we focus on the pre-image problem for chemical compounds, which is to infer a chemical structure that is mapped to a given feature vector, and has a potential application to design of novel chemical compounds. In particular, we consider the pre-image problem for feature vectors consisting of frequencies of labeled paths of length at most K. We present several time complexity results that include: NP-hardness result for a general case, polynomial time algorithm for tree structured compounds with fixed K, and polynomial time algorithm for K=1 based on graph detachment. Then we review practical algorithms for the pre-image problem, which are based on enumeration of chemical structures satisfying given constraints. We also briefly review related results which include efficient enumeration of stereoisomers of tree-like chemical compounds and efficient enumeration of outerplanar graphs.

Microwave/millimeter-wave phase and amplitude characteristics of the optically controlled phased array antenna with a different SMF for each antenna feed were measured. Suitable phases for the beam steering can be realized by the adjustment of the LD wavelength independently with multiple SMFs. In addition to the phase, amplitude of each antenna feed can be controlled stably using LD current without phase variation. Furthermore, effectiveness of the calibration method of the phased array using multiple SMFs by LD wavelength adjustment is experimentally verified. Excellent microwave/millimeter-wave phase characteristics using 2- and 3-element optically controlled phased array feed were experimentally demonstrated with calibration of the phases. Phase characteristics of the array using multiple SMFs were also compared with that using a single SMF experimentally.

This study focused on three simplified models, namely (1) one set of single-phase DC-DC converter, (2) two sets of parallel connection single-phase DC-DC converter, and (3) two sets of series connection single-phase DC-DC converter. The purposes are: (1) to propose the simplification conditions and procedures for the three-phase AC-DC converter; (2) propose a set of new simplification steps for modeling, and present the examples of different three-phase AC-DC circuit topologies, detailed discussion on the simplification steps for modeling of a three-phase AC-DC converter is offered, to help people simplify and analyze the simplified model easily; (3) according to three types of simplified modeling in the three-phase AC-DC converter, this study established a useful reference for the design and analysis of the control systems of the three-phase AC-DC converter simply; (4) to acquire PWM control strategy beforehand based on PFC-Controlled property; (5) to reduce the switching loss for the PWM control strategy of the simplified model; (6) to maintain the original circuit topology and verify that the theory can extensively apply the knowledge of single-phase DC-DC converter to the simplified modeling of three-phase AC-DC converter.

This letter has retrained an MQDF classifier on the retraining set, which is constructed by samples locating near classification boundary. The method is evaluated on HCL2000 and HCD Chinese handwriting sets. The results show that the retrained MQDF outperforms MQDF and cascade MQDF on all test sets.

We propose multiscale bagging as a modification of the bagging procedure. In ordinary bagging, the bootstrap resampling is used for generating bootstrap samples. We replace it with the multiscale bootstrap algorithm. In multiscale bagging, the sample size m of bootstrap samples may be altered from the sample size n of learning dataset. For assessing the output of a classifier, we compute bootstrap probability of class label; the frequency of observing a specified class label in the outputs of classifiers learned from bootstrap samples. A scaling-law of bootstrap probability with respect to σ2=n/m has been developed in connection with the geometrical theory. We consider two different ways for using multiscale bagging of classifiers. The first usage is to construct a confidence set of class labels, instead of a single label. The second usage is to find inputs close to decision boundaries in the context of query by bagging for active learning. It turned out, interestingly, that an appropriate choice of m is m =-n, i.e., σ2=-1, for the first usage, and m =∞, i.e., σ2=0, for the second usage.

In this paper, we propose a spectral difference approach for noise power estimation in speech enhancement. The noise power estimate is given by recursively averaging past spectral power values using a smoothing parameter based on the current observation. The smoothing parameter in time and frequency is adjusted by the spectral difference between consecutive frames that can efficiently characterize noise variation. Specifically, we propose an effective technique based on a sigmoid-type function in order to adaptively determine the smoothing parameter based on the spectral difference. Compared to a conventional method, the proposed noise estimate is computationally efficient and able to effectively follow noise changes under various noise conditions.

In multiple-input multiple-output (MIMO) systems, the multiuser MIMO (MU-MIMO) systems have the potential to provide higher channel capacity owing to multiuser and spatial diversity. Block diagonalization (BD) is one of the techniques to realize MU-MIMO systems, where multiuser interference can be completely cancelled and therefore several users can be supported simultaneously. When the number of multiantenna users is larger than the number of simultaneously receiving users, it is necessary to select the users that maximize the system capacity. However, computation complexity becomes prohibitive, especially when the number of multiantenna users is large. Thus simplified user scheduling algorithms are necessary for reducing the complexity of computation. This paper proposes a simplified capacity-based user scheduling algorithm, based on analysis of the capacity-based user selection criterion. We find a new criterion that is simplified by using the properties of Gram-Schmidt orthogonalization (GSO). In simulation results, the proposed algorithm provides higher sum rate capacity than the conventional simplified norm-based algorithm; and when signal-to-noise power ratio (SNR) is high, it provides performance similar to that of the conventional simplified capacity-based algorithm, which still requires high complexity. Fairness of the users is also taken into account. With the proportionally fair (PF) criterion, the proposed algorithm provides better performance (sum rate capacity or fairness of the users) than the conventional algorithms. Simulation results also shows that the proposed algorithm has lower complexity of computation than the conventional algorithms.

Weight perturbation learning was proposed as a learning rule in which perturbation is added to the variable parameters of learning machines. The generalization performance of weight perturbation learning was analyzed by statistical mechanical methods and was found to have the same asymptotic generalization property as perceptron learning. In this paper we consider the difference between perceptron learning and AdaTron learning, both of which are well-known learning rules. By applying this difference to weight perturbation learning, we propose adaptive weight perturbation learning. The generalization performance of the proposed rule is analyzed by statistical mechanical methods, and it is shown that the proposed learning rule has an outstanding asymptotic property equivalent to that of AdaTron learning.

This paper concerns cancel minimal linear grammars ([5]) that was introduced to generalize Geffert normal forms for phrase structure grammars. We consider the generative power of restricted cancel minimal linear grammars: the grammars have only one nonterminal symbol C except the start symbol S, and their productions consist of context-free type productions, the left-hand side of which is S and the right-hand side contains at most one occurrence of S, and a unique cancellation production Cm ε that replaces the string Cm by the empty string ε. We show that, for any given positive integer m, the class of languages generated by cancel minimal linear grammars with Cm ε, is properly included in the class of linear languages. Conversely, we show that for any linear language L, there exists some positive integer m such that a cancel minimal linear grammar with Cm ε generates L. We also show how the generative power of cancel minimal linear grammars with a unique cancellation production Cm ε vary according to changes of m and restrictions imposed on occurrences of terminal symbols in the right-hand side of productions.

We propose two types of autonomic and distributed cooperative behaviors of peers for peer-to-peer (P2P) file-sharing networks. Cooperative behaviors of peers are mediated by query trails, and allows the exploration of better trade-off points between file search and storage load balancing performance. Query trails represent previous successful search paths and indicate which peers contributed to previous file searches and were at the same time exposed to the storage load. The first type of cooperative behavior is to determine the locations of replicas of files through the medium of query trails. Placement of replicas of files on strong query trails contributes to improvement of search performance, but a heavy load is generated due to writing files in storage to peers on the strong query trails. Therefore, we attempt to achieve storage load balancing between peers, while avoiding significant degradation of the search performance by creating replicas of files in peers adjacent to peers on strong query trails. The second type of cooperative behavior is to determine whether peers provide requested files through the medium of query trails. Provision of files by peers holding requested files on strong query trails contributes to better search performance, but such provision of files generates a heavy load for reading files from storage to peers on the strong query trails. Therefore, we attempt to achieve storage load balancing while making only small sacrifices in search performance by having peers on strong query trails refuse to provide files. Simulation results show that the first type of cooperative behavior provides equal or improved ability to explore trade-off points between storage load balancing and search performance in a static and nearly homogeneous P2P environment, without the need for fine tuning parameter values, compared to replication methods that require fine tuning of their parameters values. In addition, the combination of the second type and the first type of cooperative behavior yields better storage load balancing performance with little degradation of search performance. Moreover, even in a dynamic and heterogeneous P2P environment, the two types of cooperative behaviors yield good ability to explore trade-off points between storage load balancing and search performance.

This study develops a fuzzy logic control mechanism in eigenspace-based MLLR speaker adaptation. Specifically, this mechanism can determine hidden Markov model parameters to enhance overall recognition performance despite ordinary or adverse conditions in both training and operating stages. The proposed mechanism regulates the influence of eigenspace-based MLLR adaptation given insufficient training data from a new speaker. This mechanism accounts for the amount of adaptation data available in transformation matrix parameter smoothing, and thus ensures the robustness of eigenspace-based MLLR adaptation against data scarcity. The proposed adaptive learning mechanism is computationally inexpensive. Experimental results show that eigenspace-based MLLR adaptation with fuzzy control outperforms conventional eigenspace-based MLLR, and especially when the adaptation data acquired from a new speaker is insufficient.

In this paper, a novel visual signal reliability (VSR) measure is proposed to consider video degradation at the signal level in audio-visual speaker identification (AVSI). The VSR estimation is formulated using a~ Gaussian fuzzy membership function (GFMF) to measure lighting variations. The variance parameters of GFMF are optimized in order to maximize the performance of the overall AVSI. The experimental results show that the proposed method outperforms the score-based reliability measuring technique.

One of the efficient methods to build the index of continuous window queries over moving objects is by means of region quadtree index. In this paper, we present an optimal algorithm to search for the optimal position translation of query windows, where the total number of decomposed quadtree blocks for those windows in quadtree representation is minimal. We exploit the branch-and-bound concept to prune the particular paths of recursions in the search space. Evaluation proves that our optimal algorithm reduces search time greatly and the quadtree index based on optimal position translation works efficiently for continuous window queries. To the best of our knowledge, the algorithms and experiments reported in this paper are novel.

Histogram-based image features such as HoG, SIFT and histogram of visual words are generally represented as high-dimensional, non-negative vectors. We propose a supervised method of reducing the dimensionality of histogram-based features by using non-negative matrix factorization (NMF). We define a cost function for supervised NMF that consists of two terms. The first term is the generalized divergence term between an input matrix and a product of factorized matrices. The second term is the penalty term that reflects prior knowledge on a training set by assigning predefined constants to cannot-links and must-links in pairs of training data. A multiplicative update rule for minimizing the newly-defined cost function is also proposed. We tested our method on a task of scene classification using histograms of visual words. The experimental results revealed that each of the low-dimensional basis vectors obtained from the proposed method only appeared in a single specific category in most cases. This interesting characteristic not only makes it easy to interpret the meaning of each basis but also improves the power of classification.