Network throughput has become an important issue for big-data analysis on Warehouse-Scale Computing (WSC) systems. It has been reported that randomly-connected inter-switch networks can enlarge the network throughput. For irregular networks, a multi-path routing method called k-shortest path routing is conventionally utilized. However, it cannot efficiently exploit longer-than-shortest paths that would be detour paths to avoid bottlenecks. In this work, a novel routing method called k-optimized path routing to achieve high throughput is proposed for irregular networks. We introduce a heuristic to select detour paths that can avoid bottlenecks in the network to improve the average-case network throughput. Experimental results by network simulation show that the proposed k-optimized path routing can improve the saturation throughput by up to 18.2% compared to the conventional k-shortest path routing. Moreover, it can reduce the computation time required for optimization to 1/2760 at a minimum compared to our previously proposed method.

Stochastic computing (SC), which is an approximate computation with probabilities, has attracted attention owing to its small area, small power consumption and high fault tolerance. In this paper, we focus on the transient fault tolerance of SC based on linear finite state machines (linear FSMs). We show that state assignment of FSMs considerably affects the fault tolerance of linear FSM-based SC circuits, and present a Markov model for representing the impact of the state assignment on the behavior of faulty FSMs and estimating the expected error significance of the faulty FSM-based SC circuits. Furthermore, we propose a heuristic algorithm for appropriate state assignment that can mitigate the influence of transient faults. Experimental analysis shows that the state assignment has an impact on the transient fault tolerance of linear FSM-based SC circuits and the proposed state assignment algorithm can achieve a quasi-optimal state assignment in terms of high fault tolerance.

In a multiple-user MIMO system in which numerous users simultaneously communicate in a cell, the channel matrix properties depend on the parameters of the individual users in such a way that they can be modeled as points randomly moving within the cell. Although these properties can be simulated by computer, they need to be expressed analytically to develop MIMO systems with diversity. Given a small area with an equivalent multi-path, we assume that a user u is at a certain “user point” $P^u(lambda _p^u,xi _p^u)$ in a cell, or (radius $lambda _p^u$ from origin, angle $xi _p^u)$ and that the user moves with movement $M^u(f_{max}^u, xi_v^u)$ around that point, or (Doppler frequency $f_{max}^u$, direction $xi_v^u$). The MU-MIMO channel model consists of a multipath environment, user parameters, and antenna configuration. A general formula of the correlation $ ho_{i - j,i' - j'}^{u - u'} (bm)$ between the channel matrix elements of users u and u' and one for given multipath conditions are derived. As a feature of the MU-MIMO channel, the movement factor $F^{u - u'}(gamma^u,xi_n ,xi_v^u)$, which means a fall coefficient of the spatial correlation calculated from only the user points of u and u', is also derived. As the difference in speed or direction between u and u' increases, $F^{u - u'}(gamma^u,xi_n ,xi_v^u)$ becomes smaller. Consequently, even if the path is LOS, $ ho_{i - j,i' - j'}^{u - u'} (bm)$ becomes low enough owing to the movement factor, even though the correlation in the single-user MIMO channel is high. If the parameters of u and u' are the same, the factor equals 1, and the channels correspond to the users' own channels and work like SU-MIMO channel. These analytical findings are verified by computer simulation.

We propose a novel hue-correction scheme for multi-exposure image fusion (MEF). Various MEF methods have so far been studied to generate higher-quality images. However, there are few MEF methods considering hue distortion unlike other fields of image processing, due to a lack of a reference image that has correct hue. In the proposed scheme, we generate an HDR image as a reference for hue correction, from input multi-exposure images. After that, hue distortion in images fused by an MEF method is removed by using hue information of the HDR one, on the basis of the constant-hue plane in the RGB color space. In simulations, the proposed scheme is demonstrated to be effective to correct hue-distortion caused by conventional MEF methods. Experimental results also show that the proposed scheme can generate high-quality images, regardless of exposure conditions of input multi-exposure images.

In the realization of convolutional neural networks (CNNs) in resource-constrained embedded hardware, the memory footprint of weights is one of the primary problems. Pruning techniques are often used to reduce the number of weights. However, the distribution of nonzero weights is highly skewed, which makes it more difficult to utilize the underlying parallelism. To address this problem, we present SENTEI*, filter-wise pruning with distillation, to realize hardware-aware network architecture with comparable accuracy. The filter-wise pruning eliminates weights such that each filter has the same number of nonzero weights, and retraining with distillation retains the accuracy. Further, we develop a zero-weight skipping inter-layer pipelined accelerator on an FPGA. The equalization enables inter-filter parallelism, where a processing block for a layer executes filters concurrently with straightforward architecture. Our evaluation of semantic-segmentation tasks indicates that the resulting mIoU only decreased by 0.4 points. Additionally, the speedup and power efficiency of our FPGA implementation were 33.2× and 87.9× higher than those of the mobile GPU. Therefore, our technique realizes hardware-aware network with comparable accuracy.

This article proposes a dynamic linkage service which is a specific service model of integrated broadcast — broadband services based ATSC 3.0. The dynamic linkage service is useful to the viewer who wants to continue watching programs using TV or their personal devices, even after the terrestrial broadcast ends due to the start of the next regular programming. In addition, we verify the feasibility of the proposed extended dynamic linkage service through developed emulation system based on ATSC 3.0. In consideration of the personal network capabilities of the viewer environment, the service was tested with 4K/2K Ultra HD and receiving the service was finished within 4 second over intranet.

In this paper, we propose a method which enables us to control the variance of the coefficients of the LMS-type adaptive filters. In the method, each coefficient of the adaptive filter is modeled as an random variable with a Gaussian distribution, and its value is estimated as the mean value of the distribution. Besides, at each time, we check if the updated value exists within the predefined range of distribution. The update of a coefficient will be canceled when its updated value exceeds the range. We propose an implementation method which has similar formula as the Gaussian mixture model (GMM) widely used in signal processing and machine learning. The effectiveness of the proposed method is evaluated by the computer simulations.

Gaussian integer has a potential to enhance the safety of elliptic curve cryptography (ECC) on system under the condition fixing bit length of integral and floating point types, in viewpoint of the order of a finite field. However, there seems to have been no algorithm which makes Gaussian integer ECC safer under the condition. We present the algorithm to enhance the safety of ECC under the condition. Then, we confirm our Gaussian integer ECC is safer in viewpoint of the order of finite field than rational integer ECC or Gaussian integer ECC of naive methods under the condition.

In this work, we introduce notions of quantum frequency arrangements consisting of quantum frequency squares, cubes, hypercubes and a notion of orthogonality between them. We also propose a notion of quantum mixed orthogonal array (QMOA). By using irredundant mixed orthogonal array proposed by Goyeneche et al. we can obtain k-uniform states of heterogeneous systems from quantum frequency arrangements and QMOAs. Furthermore, some examples are presented to illustrate our method.

The nearest neighbor method is a simple and flexible scheme for the classification of data points in a vector space. It predicts a class label of an unseen data point using a majority rule for the labels of known data points inside a neighborhood of the unseen data point. Because it sometimes achieves good performance even for complicated problems, several derivatives of it have been studied. Among them, the discriminant adaptive nearest neighbor method is particularly worth revisiting to demonstrate its application. The main idea of this method is to adjust the neighbor metric of an unseen data point to the set of known data points before label prediction. It often improves the prediction, provided the neighbor metric is adjusted well. For statistical shape analysis, shape classification attracts attention because it is a vital topic in shape analysis. However, because a shape is generally expressed as a matrix, it is non-trivial to apply the discriminant adaptive nearest neighbor method to shape classification. Thus, in this study, we develop the discriminant adaptive nearest neighbor method to make it slightly more useful in shape classification. To achieve this development, a mixture model and optimization algorithm for shape clustering are incorporated into the method. Furthermore, we describe several helpful techniques for the initial guess of the model parameters in the optimization algorithm. Using several shape datasets, we demonstrated that our method is successful for shape classification.

Graphics processing units (GPUs) are highly efficient architectures for parallel stencil code; however, the small device (i.e., GPU) memory capacity (several tens of GBs) necessitates the use of out-of-core computation to process excess data. Great programming effort is needed to manually implement efficient out-of-core stencil code. To relieve such programming burdens, directive-based frameworks emerged, such as the pipelined accelerator (PACC); however, they usually lack specific optimizations to reduce data transfer. In this paper, we extend PACC with two data-centric optimizations to address data transfer problems. The first is a direct-mapping scheme that eliminates host (i.e., CPU) buffers, which intermediate between the original data and device buffers. The second is a region-sharing scheme that significantly reduces host-to-device data transfer. The extended PACC was applied to an acoustic wave propagator, automatically extending the length of original serial code 2.3-fold to obtain the out-of-core code. Experimental results revealed that on a Tesla V100 GPU, the generated code ran 41.0, 22.1, and 3.6 times as fast as implementations based on Open Multi-Processing (OpenMP), Unified Memory, and the previous PACC, respectively. The generated code also demonstrated usefulness with small datasets that fit in the device capacity, running 1.3 times as fast as an in-core implementation.

Data sorting is an important operation in computer science. It is extensively used in several applications such as database and searching. While high-performance sorting accelerators are in demand, it is very important to pay attention to the hardware resources for such kind of high-performance sorters. In this paper, we propose three FPGA based architectures to accelerate sorting operation based on the merge sorting algorithm. We call our proposals as WMS: Wide Merge Sorter, EHMS: Efficient Hardware Merge Sorter, and EHMSP: Efficient Hardware Merge Sorter Plus. We target the Virtex UltraScale FPGA device. Evaluation results show that our proposed merge sorters maintain both the high-performance and cost-effective properties. While using much fewer hardware resources, our proposed merge sorters achieve higher performance compared to the state-of-the-art. For instance, with 256 sorted records are produced per cycle, implementation results of proposed EHMS show a significant reduction in the required number of Flip Flops (FFs) and Look-Up Tables (LUTs) to about 66% and 79%, respectively over the state-of-the-art merge sorter. Moreover, while requiring fewer hardware resources, EHMS achieves about 1.4x higher throughput than the state-of-the-art merge sorter. For the same number of produced records, proposed WMS also achieves about 1.6x throughput improvement over the state-of-the-art while requiring about 81% of FFs and 76% of LUTs needed by the state-of-the-art sorter.

In this paper we analyze the interval algorithm for random number generation proposed by Han and Hoshi in the case of Markov coin tossing. Using the expression of real numbers on the interval [0,1), we first establish an explicit representation of the interval algorithm with the representation of real numbers on the interval [0,1) based one number systems. Next, using the expression of the interval algorithm, we give a rigorous analysis of the interval algorithm. We discuss the difference between the expected number of the coin tosses in the interval algorithm and their upper bound derived by Han and Hoshi and show that it can be characterized explicitly with the established expression of the interval algorithm.

A quadratic extension field (QEF) defined by F1 = Fp[α]/(α2+1) is typically used for a supersingular isogeny Diffie-Hellman (SIDH). However, there exist other attractive QEFs Fi that result in a competitive or rather efficient performing the SIDH comparing with that of F1. To exploit these QEFs without a time-consuming computation of the initial setting, the authors propose to convert existing parameter sets defined over F1 to Fi by using an isomorphic map F1 → Fi.

Aggregate signature (AS) schemes enable anyone to compress signatures under different keys into one. In sequential aggregate signature (SAS) schemes, the aggregate signature is computed incrementally by the sighers. Several trapdoor-permutation-based SAS have been proposed. In this paper, we give a constructions of SAS based on the first SAS scheme with lazy verification proposed by Brogle et al. in ASIACRYPT 2012. In Brogle et al.'s scheme, the size of the aggregate signature is linear of the number of the signers. In our scheme, the aggregate signature has constant length which satisfies the original ideal of compressing the size of signatures.

Recently, the ECG-based diagnosis system based on wearable devices has attracted more and more attention of researchers. Existing studies have achieved high classification accuracy by using deep neural networks (DNNs), but there are still some problems, such as: imprecise heart beat segmentation, inadequate use of medical knowledge, the same treatment of features with different importance. To address these problems, this paper: 1) proposes an adaptive segmenting-reshaping method to acquire abundant useful samples; 2) builds a set of hand-crafted features and deep features on the inner-beat, beat and inter-beat scale by integrating enough medical knowledge. 3) introduced a modified channel attention module (CAM) to augment the significant channels in deep features. Following the Association for Advancement of Medical Instrumentation (AAMI) recommendation, we classified the dataset into four classes and validated our algorithm on the MIT-BIH database. Experiments show that the accuracy of our model reaches 96.94%, a 3.71% increase over that of a state-of-the-art alternative.

Air discharge immunity testing for electronic equipment is specified in the standard 61000-4-2 of the International Eelectrotechnical Commission (IEC) under the climatic conditions of temperature (T) from 15 to 35 degrees Celsius and relative humidity (RH) from 30 to 60%. This implies that the air discharge testing is likely to provide significantly different test results due to the wide climatic range. To clarify effects of the above climatic conditions on air discharge testing, we previously measured air discharge currents from an electrostatic discharge (ESD) generator with test voltages from 2kV to 15kV at an approach speed of 80mm/s under 6 combinations of T and RH in the IEC specified range and non-specified climatic range. The result showed that the same absolute humidity (AH), which is determined by T and RH, provides almost the identical waveforms of the discharge currents despite different T and RH, and also that the current peaks at higher test voltages decrease as the AH increases. In this study, we further examine the combined effects of air discharges on test voltages, T, RH and AH with respect to two different approach speeds of 20mm/s and 80mm/s. As a result, the approach speed of 80mm/s is confirmed to provide the same results as the previous ones under the identical climatic conditions, whereas at a test voltage of 15kV under the IEC specified climatic conditions over 30% RH, the 20mm/s approach speed yields current waveforms entirely different from those at 80mm/s despite the same AH, and the peaks are basically unaffected by the AH. Under the IEC non-specified climatic conditions with RH less than 20%, however, the peaks decrease at higher test voltages as the AH increases. These findings obtained imply that under the same AH condition, at 80mm/s the air discharge peak is not almost affected by the RH, while at 20mm/s the lower the RH is, the higher is the peak on air discharge current.

Training deep learning (DL) is a computationally intensive process; as a result, training time can become so long that it impedes the development of DL. High performance computing clusters, especially supercomputers, are equipped with a large amount of computing resources, storage resources, and efficient interconnection ability, which can train DL networks better and faster. In this paper, we propose a method to train DL networks distributed with high efficiency. First, we propose a hierarchical synchronous Stochastic Gradient Descent (SGD) strategy, which can make full use of hardware resources and greatly increase computational efficiency. Second, we present a two-level parameter synchronization scheme which can reduce communication overhead by transmitting parameters of the first layer models in shared memory. Third, we optimize the parallel I/O by making each reader read data as continuously as possible to avoid the high overhead of discontinuous data reading. At last, we integrate the LARS algorithm into our system. The experimental results demonstrate that our approach has tremendous performance advantages relative to unoptimized methods. Compared with the native distributed strategy, our hierarchical synchronous SGD strategy (HSGD) can increase computing efficiency by about 20 times.

Nowadays recommender systems (RS) keep drawing attention from academia, and collaborative filtering (CF) is the most successful technique for building RS. To overcome the inherent limitation, which is referred to as data sparsity in CF, various solutions are proposed to incorporate additional social information into recommendation processes, such as trust networks. However, existing methods suffer from multi-source data integration (i.e., fusion of social information and ratings), which is the basis for similarity calculation of user preferences. To this end, we propose a social collaborative filtering method based on novel trust metrics. Firstly, we use Graph Convolutional Networks (GCNs) to learn the associations between social information and user ratings while considering the underlying social network structures. Secondly, we measure the direct-trust values between neighbors by representing multi-source data as user ratings on popular items, and then calculate the indirect-trust values based on trust propagations. Thirdly, we employ all trust values to create a social regularization in user-item rating matrix factorization in order to avoid overfittings. The experiments on real datasets show that our approach outperforms the other state-of-the-art methods on usage of multi-source data to alleviate data sparsity.

Deep neural network (DNN)-based speech synthesis became popular in recent years and is expected to soon be widely used in embedded devices and environments with limited computing resources. The key intention of these systems in poor computing environments is to reduce the computational cost of generating speech parameter sequences while maintaining voice quality. However, reducing computational costs is challenging for two primary conventional DNN-based methods used for modeling speech parameter sequences. In feed-forward neural networks (FFNNs) with maximum likelihood parameter generation (MLPG), the MLPG reconstructs the temporal structure of the speech parameter sequences ignored by FFNNs but requires additional computational cost according to the sequence length. In recurrent neural networks, the recursive structure allows for the generation of speech parameter sequences while considering temporal structures without the MLPG, but increases the computational cost compared to FFNNs. We propose a new approach for DNNs to acquire parameters captured from the temporal structure by backpropagating the errors of multiple attributes of the temporal sequence via the loss function. This method enables FFNNs to generate speech parameter sequences by considering their temporal structure without the MLPG. We generated the fundamental frequency sequence and the mel-cepstrum sequence with our proposed method and conventional methods, and then synthesized and subjectively evaluated the speeches from these sequences. The proposed method enables even FFNNs that work on a frame-by-frame basis to generate speech parameter sequences by considering the temporal structure and to generate sequences perceptually superior to those from the conventional methods.