How to mitigate the influence of unfair testimonies remains an open issue in the research of rating systems. Methods have been proposed to filter the unfair testimonies in order to mitigate the influence of unfair testimonies. However, existing methods depend on assumptions that ratings follow a particular distribution to carry out the testimony filtering. This constrains them in specific rating systems and hinders their applications in other reputation systems. Moreover, existing methods do not scale well with the increase of testimony number due to their iterative nature. In this paper, a novel entropy-based method is proposed to measure the testimony quality, based on which unfair testimonies are further filtered. The proposed method does not require the assumption regarding the rating distribution. Moreover, it scales linearly with the increase of the testimony number. Experimental results show that the proposed method is effective in mitigating the influence of various types of unfair testimonies.

We present a novel precomputed radiance transfer method for efficient relighting under all-frequency environment illumination. Environment illumination is represented as a set of environment lights. Each environment light comprises a direction and an intensity. In a preprocessing step, the environment lights are clustered into several clusters, taking into account only the light directions. By experiment, we confirmed that the environment lights can be clustered into a much smaller number of clusters than their original number. Given any environment illumination, sampled as an environment map, an efficient relighting is then achieved by computing the radiance using the precomputed clusters. The proposed method enables relighting under very high-resolution environment illumination. In addition, unlike previous approaches, the proposed method can efficiently perform relighting when some regions of the given environment illumination change.

Resource performance prediction is known to be useful in resource scheduling in the Grid. The disk I/O workload is another important factor that influences the performance of the CPU and the network which are commonly used in resource scheduling. In the case of disk I/O workload time-series, the adaptation of a prediction algorithm to new time-series should be rapid. Further, the prediction should ensure that the prediction error is minimum in the heterogeneous environment. The storage workload (i.e., the disk I/O load) is a dynamic variable. A prediction parameter based on the characteristics of the current workload must be prepared for prediction purposes. In this paper, we propose and implement the OPHB (On-Line Parameter History Bank). This is a method that stabilizes the incoming disk I/O workload time-series fairly quickly with the help of accurately determined ESM (Exponential Smoothing Method) parameters. The parameters are drawn from a history database. In the case of forecasting with ESM, a smoothing parameter must be specified in advance. If the parameter is statically estimated from observed data found in previous executions, the forecasts would be inaccurate because they do not capture the actual I/O behavior. The smoothing parameter has to be adjusted in accordance with the shape of the new disk I/O workload. The ESM algorithms utilise one of the accumulated parameter histories chronicled by OPHB's Deposit operation. When a new time-series is started, an appropriate parameter value is looked up in the Bank by OPHB's Lookup operation. This is used for the time-series. This process is fully adaptive. We evaluate the proposed method with SES (Single Exponential Smoothing) and ARRSES (Auto-Responsive SES) methods.

We discuss a new design methodology of polynomial neural networks (PNN) in the framework of genetic algorithm (GA). The PNN is based on the ideas of group method of data handling (GMDH). Each node in the network is very flexible and can carry out polynomial type mapping between input and output variables. But the performances of PNN depend strongly on the number of input variables available to the model, the number of input variables, and the type (order) of the polynomials to each node. In this paper, GA is implemented to better use the optimal inputs and the order of polynomial in each node of PNN. The appropriate inputs and order are evolved accordingly and are tuned gradually throughout the GA iterations. We employ a binary coding for encoding key factors of the PNN into the chromosomes. The chromosomes are made of three sub-chromosomes which represent the order, number of inputs, and input candidates for modeling. To construct model by using significant approximation and generalization, we introduce the fitness function with a weighting factor. Comparisons with other modeling methods and conventional PNN show that the proposed design method offers encouraging advantages and better performance.

In difficult classification problems of the z-dimensional points into two groups giving 0-1 responses due to the messy data structure, we try to find the denser regions for the favorable customers of response 1, instead of finding the boundaries to separate the two groups. Such regions are called the bumps, and finding the boundaries of the bumps is called the bump hunting. The main objective of this paper is to find the largest region of the bumps under a specified ratio of the number of the points of response 1 to the total. Then, we may obtain a trade-off curve between the number of points of response 1 and the specified ratio. The decision tree method with the Gini's index will provide the simple-shaped boundaries for the bumps if the marginal density for response 1 shows a rather simple or monotonic shape. Since the computing time searching for the optimal trees will cost much because of the NP-hardness of the problem, some random search methods, e.g., the genetic algorithm adapted to the tree, are useful. Due to the existence of many local maxima unlike the ordinary genetic algorithm search results, the extreme-value statistics will be useful to estimate the global optimum number of captured points; this also guarantees the accuracy of the semi-optimal solution with the simple descriptive rules. This combined method of genetic algorithm search and extreme-value statistics use is new. We apply this method to some artificial messy data case which mimics the real customer database, showing a successful result. The reliability of the solution is discussed.

In this paper, we propose a new robust model predictive control (MPC) technique for linear parameter varying (LPV) systems expressed as linear systems with feedback parameters. It is based on the minimization of the upper bound of finite horizon cost function using a new parameter dependent terminal weighting matrix. The proposed parameter dependent terminal weighting matrix for norm-bounded uncertain models provides a less conservative condition for terminal inequality. The optimization problem that satisfies the terminal inequality is solved by semi-definite programming involving linear matrix inequalities (LMIs). A numerical example is included to illustrate the effectiveness of the proposed method.

A function approximation based on an orthonormal wave function expansion in a complex space is derived. Although a probability density function (PDF) cannot always be expanded in an orthogonal series in a real space because a PDF is a positive real function, the function approximation can approximate an arbitrary PDF with high accuracy. It is applied to an actor-critic method of reinforcement learning to derive an optimal policy expressed by an arbitrary PDF in a continuous-action continuous-state environment. A chaos control problem and a PDF approximation problem are solved using the actor-critic method with the function approximation, and it is shown that the function approximation can approximate a PDF well and that the actor-critic method with the function approximation exhibits high performance.

We consider the problem of dynamically apportioning resources among a set of options in a worst-case online framework. The model we investigate is a generalization of the well studied online learning model. In particular, we allow the learner to see as additional information how high the risk of each option is. This assumption is natural in many applications like horse-race betting, where gamblers know odds for all options before placing bets. We apply Vovk's Aggregating Algorithm to this problem and give a tight performance bound. The results support our intuition that it is safe to bet more on low-risk options. Surprisingly, the loss bound of the algorithm does not depend on the values of relatively small risks.

Solving the error correcting code is an important goal with regard to communication theory. To reveal the error correcting code characteristics, several researchers have applied a statistical-mechanical approach to this problem. In our research, we have treated the error correcting code as a Bayes inference framework. Carrying out the inference in practice, we have applied the NMF (naive mean field) approximation to the MPM (maximizer of the posterior marginals) inference, which is a kind of Bayes inference. In the field of artificial neural networks, this approximation is used to reduce computational cost through the substitution of stochastic binary units with the deterministic continuous value units. However, few reports have quantitatively described the performance of this approximation. Therefore, we have analyzed the approximation performance from a theoretical viewpoint, and have compared our results with the computer simulation.

Visual criteria for diagnosing liver diseases, such as cirrhosis, from ultrasound images can be assisted by computerized texture classification. This paper proposes a system applying a PNN (Pyramid Neural Network) for classifying the hepatic parenchymal diseases in ultrasonic B-scan texture. In this study, we propose a multifractal-dimensions method to select the patterns for the training set and the validation sets. A modified box-counting algorithm is used to calculate the dimensions of the B-scan images. FDWT (Fast Discrete Wavelet Transform) is applied for feature extraction during the preprocessing. The structure of the proposed neural network is testified by training and validation sets by cross-validation method. The performance of the proposed system and a system based on the conventional multilayer network architecture is compared. The results show that, compared with the conventional 3-layer neural network, the performance of the proposed pyramid neural network is improved by efficiently utilizing the lower layer of the neural network.

We analytically investigated the feasibility of multiplier operation in the terahertz range for our original plasmon resonant photomixer. The photomixer features two unique structures (doubly interdigitated gate gratings and a vertical cavity) for higher radiation efficiencies. Its total field emission properties are the result of a combination of plasmon excitation dynamics and electromagnetic field dynamics. The plasmon excitation formulated by the hydrodynamic equations exhibits fundamental and harmonic resonances whose intensities monotonically decrease with the number of harmonics due to the dispersive plasma damping factors. The electromagnetic dynamics, on the other hand, formulated by the Maxwell's equations, reflect material- and structure-dependent device parameters; the grating-bi-coupled plasmonic cavity together with the vertical cavity structures produce nonlinear field emission properties. This results in extraordinary field enhancement at distinct frequencies inconsistent with the plasmon resonances. The frequency-dependent FDTD (finite difference time domain method) Maxwell's simulation revealed that the field emission peak frequency shifted upward apart from the fundamental mode of plasmon resonant frequency and approached to its second harmonic frequency with increasing the electron density in the plasmon cavity. Calculated total field emission spectra indicated that highly dense 2D-plasmon conditions enable frequency-doubler operation in the terahertz range.

This paper describes a method for the classification of bank-notes. The algorithm has three stages, and classifies bank-notes with very low error rates and at high speeds. To achieve the very low error rates, the result of classification is checked in the final stage by using different features to those used in the first two. High-speed processing is mainly achieved by the hierarchical structure, which leads to low computational costs. In evaluation on 32,850 samples of US bank-notes, with the same number used for training, the algorithm classified all samples precisely with no error sample. We estimate that the worst error rate is 3.1E-9 for the classification statistically.

For hybrid Multimedia-on-Demand (MoD) systems which support broadcast, batch and interactive services, the charging scheme employed plays an important role in the delivery of good service quality to users, while also determining the revenue generated for the service provider. In this letter a new charging scheme is proposed. This scheme provides the same quality of service to the users as previous charging schemes while providing higher revenue. Numerical results are presented to evaluate the performance of the new charging scheme in comparison with previous schemes.

Expressions are presented for the probability of target detection and the measurement accuracy of the detection, taking into account the effects of antenna beam-pointing error. Evaluation of these expressions requires numerical integration, which is computationally expensive. Approximate but analytic and efficient expressions are also presented. Numerical examples are given to present the relative accuracy of our analytic approximations.

Ultrahigh-speed continuous-tine delta-sigma modulators (DSMs) have been designed by using a fully-differential comparator consisting of resonant-tunneling diodes (RTDs) and HEMTs. Continuous-time lowpass and bandpass filters using HEMTs have also been incorporated to obtain lowpass- and bandpass-type DSMs, respectively. Circuit simulation assuming 0.1-µm InP-based HEMT and RTD technology has revealed a successful operation of the 2nd-order lowpass DSM at a sampling frequency of 20 GHz. The clock frequency was 10 GHz because of the double sampling function of the present comparator. The 2nd-order bandpass DSM has also been designed with a center frequency of 3 GHz. These results clearly show high potential of the present delta-sigma modulators.

A self-starting pulse laser with an erbium-doped fiber cooled at liquid-nitrogen temperature was demonstrated. The self-starting-pulse fiber-ring laser can produce an approximately 1 ns pulse train without the need for devices for polarization control and compensation of birefringence.

This paper presents a 3D feature-based binocular tracking algorithm for tracking crowded people indoors. The algorithm consists of a two stage 3D feature points grouping method and a robust 3D feature-based tracking method. The two stage 3D feature points grouping method can use kernel-based ISODATA method to detect people accurately even though the part or almost full occlusion occurs among people in surveillance area. The robust 3D feature-based Tracking method combines interacting multiple model (IMM) method with a cascade multiple feature data association method. The robust 3D feature-based tracking method not only manages the generation and disappearance of a trajectory, but also can deal with the interaction of people and track people maneuvering. Experimental results demonstrate the robustness and efficiency of the proposed framework. It is real-time and not sensitive to the variable frame to frame interval time. It also can deal with the occlusion of people and do well in those cases that people rotate and wriggle.

In 2005, Yong and Lee proposed a buyer-seller fingerprinting protocol using symmetric and commutative encryptions. They claimed that their protocol was practical and anonymous since they used symmetric and commutative encryptions. However, an attacker can get the content embedded with one or more honest buyers' fingerprints using man-in-the-middle attack. In this letter, we point out the weakness and propose methods for improving to their protocol.

We performed numerical analyses on structure sensitive field emission properties of our proposing plasmon resonant photomixer (PRX) in the terahertz range. The photomixer incorporates doubly interdigitated grating strips for gate electrodes and a vertical resonator structure for realizing highly efficient terahertz emission even at room temperature. We investigated the dependence of total field emission properties of PRX's on their material and dimension parameters. Introduction of low-conductive gate electrodes and ac-coupled 2D periodic plasmon gratings with depleted connecting portions are effective for expanding its lower cutoff frequency. The cutoff frequency, which is around 1.0 THz in standard metal-gates configuration, is expanded to less than 500 GHz. The output intensity could also be amplified more than double. On the other hand, a shorter vertical cavity is effective for expanding its upper cutoff frequency, which is expanded close to vertical resonant frequency, while maintaining the lower cutoff frequency. The combination of these design rules can realize much broader bandwidth operation.

Self-controlled sub-nanosecond pulse generator was demonstrated with an ytterbium-doped fiber. This fiber laser consisted simply of all non-polarization fiber without any devices for polarization control and birefringence compensation. The self-pulse operation system gave an average output power of 0.9 mW in 800-ps duration pulses.