Haichuan YANG Shangce GAO Rong-Long WANG Yuki TODO
In 2019, a completely new algorithm, spherical evolution (SE), was proposed. The brand new search style in SE has been proved to have a strong search capability. In order to take advantage of SE, we propose a novel method called the ladder descent (LD) method to improve the SE' population update strategy and thereafter propose a ladder spherical evolution search (LSE) algorithm. With the number of iterations increasing, the range of parent individuals eligible to produce offspring gradually changes from the entire population to the current optimal individual, thereby enhancing the convergence ability of the algorithm. Experiment results on IEEE CEC2017 benchmark functions indicate the effectiveness of LSE.
Satoshi DENNO Ryoko SASAKI Yafei HOU
This paper proposes non-orthogonal packet access based on low density signature with phase only adaptive precoding. The proposed access allows multiple user terminals to send their packets simultaneously for implementing massive connectivity, though only one antenna is put on every terminal and on an access point. This paper proposes a criterion that defines the optimum rotation angles for the phase only precoding, and an algorithm based on the steepest descent to approach the optimum rotation angles. Moreover, this paper proposes two complexity-reduced algorithms that converge much faster than the original algorithm. When 6 packets are transmitted in 4 time slots, i.e., overloading ratio of 1.5, the proposed adaptive precoding based on all the proposed algorithms attains a gain of about 4dB at the BER of 10-4 in Rician fading channels.
Noriyuki TONAMI Keisuke IMOTO Ryosuke YAMANISHI Yoichi YAMASHITA
Sound event detection (SED) and acoustic scene classification (ASC) are important research topics in environmental sound analysis. Many research groups have addressed SED and ASC using neural-network-based methods, such as the convolutional neural network (CNN), recurrent neural network (RNN), and convolutional recurrent neural network (CRNN). The conventional methods address SED and ASC separately even though sound events and acoustic scenes are closely related to each other. For example, in the acoustic scene “office,” the sound events “mouse clicking” and “keyboard typing” are likely to occur. Therefore, it is expected that information on sound events and acoustic scenes will be of mutual aid for SED and ASC. In this paper, we propose multitask learning for joint analysis of sound events and acoustic scenes, in which the parts of the networks holding information on sound events and acoustic scenes in common are shared. Experimental results obtained using the TUT Sound Events 2016/2017 and TUT Acoustic Scenes 2016 datasets indicate that the proposed method improves the performance of SED and ASC by 1.31 and 1.80 percentage points in terms of the F-score, respectively, compared with the conventional CRNN-based method.
Masakazu IWAI Takuya FUTAGAMI Noboru HAYASAKA Takao ONOYE
In this paper, we improve upon the automatic building extraction method, which uses a variational inference Gaussian mixture model for performing color clustering, by accelerating its computational speed. The improved method decreases the computational time using an image with reduced resolution upon applying color clustering. According to our experiment, in which we used 106 scenery images, the improved method could extract buildings at a rate 86.54% faster than that of the conventional methods. Furthermore, the improved method significantly increased the extraction accuracy by 1.8% or more by preventing over-clustering using the reduced image, which also had a reduced number of the colors.
Chenxu WANG Yutong LU Zhiguang CHEN Junnan LI
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.
Yoshihiro HIROHASHI Tsuyoshi KATO
Currently, the top-k error ratio is one of the primary methods to measure the accuracy of multi-category classification. Top-k multiclass SVM was designed to minimize the empirical risk based on the top-k error ratio. Two SDCA-based algorithms exist for learning the top-k SVM, both of which have several desirable properties for achieving optimization. However, both algorithms suffer from a serious disadvantage, that is, they cannot attain the optimal convergence in most cases owing to their theoretical imperfections. As demonstrated through numerical simulations, if the modified SDCA algorithm is employed, optimal convergence is always achieved, in contrast to the failure of the two existing SDCA-based algorithms. Finally, our analytical results are presented to clarify the significance of these existing algorithms.
Massive multiple-input multiple-output (MIMO) is an enabling technology for next-generation wireless systems because it provides significant improvements in data rates compared to existing small-scale MIMO systems. However, the increased number of antennas results in high computational complexity for data detection, and requires more efficient detection algorithms. In this paper, we propose a new data detector based on a box-constrained complex-valued dichotomous coordinate descent (BCC-DCD) algorithm for large-scale MIMO systems. The proposed detector involves two steps. First, a transmitted data vector is detected using the BCC-DCD algorithm with a large number of iterations and high solution precision. Second, an improved soft output is generated by reapplying the BCC-DCD algorithm, but with a considerably smaller number of iterations and 1-bit solution precision. Numerical results demonstrate that the proposed method outperforms existing advanced detectors while possessing lower complexity. Specifically, the proposed method provides significantly better detection performance than a BCC-DCD algorithm with similar complexity. The performance advantage increases as the signal-to-noise ratio and the system size increase.
Kenji MII Akihito NAGAHAMA Hirobumi WATANABE
This paper proposes an ultra-low quiescent current low-dropout regulator (LDO) with a flipped voltage follower (FVF)-based load transient enhanced circuit for wireless sensor network (WSN). Some characteristics of an FVF are low output impedance, low voltage operation, and simple circuit configuration [1]. In this paper, we focus on the characteristics of low output impedance and low quiescent current. A load transient enhanced circuit based on an FVF circuit configuration for an LDO was designed in this study. The proposed LDO, including the new circuit, was fabricated in a 0.6 µm CMOS process. The designed LDO achieved an undershoot of 75 mV under experimental conditions of a large load transient of 100 µA to 10 mA and a current slew rate (SR) of 1 µs. The quiescent current consumed by the LDO at no load operation was 204 nA.
In this paper, we propose an effective and robust method of spatial feature extraction for acoustic scene analysis utilizing partially synchronized and/or closely located distributed microphones. In the proposed method, a new cepstrum feature utilizing a graph-based basis transformation to extract spatial information from distributed microphones, while taking into account whether any pairs of microphones are synchronized and/or closely located, is introduced. Specifically, in the proposed graph-based cepstrum, the log-amplitude of a multichannel observation is converted to a feature vector utilizing the inverse graph Fourier transform, which is a method of basis transformation of a signal on a graph. Results of experiments using real environmental sounds show that the proposed graph-based cepstrum robustly extracts spatial information with consideration of the microphone connections. Moreover, the results indicate that the proposed method more robustly classifies acoustic scenes than conventional spatial features when the observed sounds have a large synchronization mismatch between partially synchronized microphone groups.
In this paper, a new transceiver system for the in-vehicle communication system is proposed to enhance data transmission rate and timing accuracy in TDM-based application. The proposed system utilizes point-to-point (P2P) channel, a closed-loop clock forwarding path, and a transceiver with a repeater and clock delay adjuster. The proposed system with 4 ECU (Electronic Computing Unit) nodes is implemented in 180nm CMOS technology and, when compared with conventional bus-based system, achieved more than 125 times faster data transmission. The maximum data rate was 2.5Gbps at 1.8V power supply and the worst peak-to-peak jitter for the data and clock signals over 5000 data symbols were about 49.6ps and 9.8ps respectively.
Constrained by quality-of-service (QoS), a robust transceiver design is proposed for multiple-input multiple-output (MIMO) interference channels with imperfect channel state information (CSI) under bounded error model. The QoS measurement is represented as the signal-to-interference-plus-noise ratio (SINR) for each user with single data stream. The problem is formulated as sum power minimization to reduce the total power consumption for energy efficiency. In a centralized manner, alternating optimization is performed at each node. For fixed transmitters, closed-form expression for the receive beamforming vectors is deduced. And for fixed receivers, the sum-power minimization problem is recast as a semi-definite program form with linear matrix inequalities constraints. Simulation results demonstrate the convergence and robustness of the proposed algorithm, which is important for practical applications in future wireless networks.
Yuta SAKAGAWA Kosuke NAKAJIMA Gosuke OHASHI
We propose a method that detects vehicles from in-vehicle monocular camera images captured during nighttime driving. Detecting vehicles from their shape is difficult at night; however, many vehicle detection methods focusing on light have been proposed. We detect bright spots by appropriate binarization based on the characteristics of vehicle lights such as brightness and color. Also, as the detected bright spots include lights other than vehicles, we need to distinguish the vehicle lights from other bright spots. Therefore, the bright spots were distinguished using Random Forest, a multiclass classification machine-learning algorithm. The features of bright spots not associated with vehicles were effectively utilized in the vehicle detection in our proposed method. More precisely vehicle detection is performed by giving weights to the results of the Random Forest based on the features of vehicle bright spots and the features of bright spots not related to the vehicle. Our proposed method was applied to nighttime images and confirmed effectiveness.
Junshan LUO Shilian WANG Qian CHENG
Joint transmit and receive antenna selection (JTRAS) for transceive spatial modulation (TRSM) is investigated in this paper. A couple of low-complexity and efficient JTRAS algorithms are proposed to improve the reliability of TRSM systems by maximizing the minimum Euclidean distance (ED) among all received signals. Specifically, the QR decomposition based ED-JTRAS achieves near-optimal error performance with a moderate complexity reduction as compared to the optimal ED-JTRAS method. The singular value decomposition based ED-JTRAS achieves sub-optimal error performance with a significant complexity reduction. Simulation results show that the proposed methods remarkably improve the system reliability in both uncorrelated and spatially correlated Rayleigh fading channels, as compared to the conventional norm based JTRAS method.
Mototsugu HAMADA Tadahiro KURODA
This paper describes transmission line couplers for non-contact connecters. Their characteristics are formulated in closed forms and design methodologies are presented. As their applications, three different types of transmission line couplers, two-fold transmission line coupler, single-ended to differential conversion transmission line coupler, and rotatable transmission line coupler are reviewed.
Fei GUO Yuan YANG Yang XIAO Yong GAO Ningmei YU
Currently, visual perceptions generated by visual prosthesis are low resolution with unruly color and restricted grayscale. This severely restricts the ability of prosthetic implant to complete visual tasks in daily scenes. Some studies explore existing image processing techniques to improve the percepts of objects in prosthetic vision. However, most of them extract the moving objects and optimize the visual percepts in general dynamic scenes. The application of visual prosthesis in daily life scenes with high dynamic is greatly limited. Hence, in this study, a novel unsupervised moving object segmentation model is proposed to automatically extract the moving objects in high dynamic scene. In this model, foreground cues with spatiotemporal edge features and background cues with boundary-prior are exploited, the moving object proximity map are generated in dynamic scene according to the manifold ranking function. Moreover, the foreground and background cues are ranked simultaneously, and the moving objects are extracted by the two ranking maps integration. The evaluation experiment indicates that the proposed method can uniformly highlight the moving object and keep good boundaries in high dynamic scene with other methods. Based on this model, two optimization strategies are proposed to improve the perception of moving objects under simulated prosthetic vision. Experimental results demonstrate that the introduction of optimization strategies based on the moving object segmentation model can efficiently segment and enhance moving objects in high dynamic scene, and significantly improve the recognition performance of moving objects for the blind.
Hiroshi ARUGA Keita MOCHIZUKI Tadashi MURAO Mizuki SHIRAO
Ethernet has become an indispensable technology for communications, and has come into use for many applications. At the IEEE, high-speed standardization has been discussed and has seen the adoption of new technologies such as multi-level modulation formats, high baud rate modulation and dense wave length division multiplexing. The MSA transceiver form factor has also been discussed following IEEE standardization. Optical devices such as TOSA and ROSA have been required to become more compact and higher-speed, because each transceiver form factor has to be miniaturized for high-density construction. We introduce the technologies for realizing 100GbE and those applicable to 400GbE. We also discuss future packages for optical devices. There are many similarities between optical device packages and electrical device packages, and we predict that optical device packages will follow the trends seen in electrical devices. But there are also differences between optical and electrical devices. It is necessary to utilize new technology for specific optical issues to employ advanced electrical packaging and catch up the trends.
Hiroya MORITA Hideki KAWAI Kenji TAKEHARA Naoki MATSUDA Toshihiko NAGAMURA
Photophysical properties of water-soluble porphyrin were studied in aqueous solutions with/without DNA and in DNA solid films. Ultrathin films were prepared from aqueous DNA solutions by a spin-coating method on glass or on gold nanoparticles (AuNPs). Remarkable enhancement of phosphorescence was observed for porphyrin immobilized in DNA films spin-coated on AuNPs, which was attributed to the electric field enhancement and the increased radiative rate by localized surface plasmon resonance of AuNPs.
Satoshi YAMAMORI Masayuki HIROMOTO Takashi SATO
We propose an efficient training method for memristor neural networks. The proposed method is suitable for the mini-batch-based training, which is a common technique for various neural networks. By integrating the two processes of gradient calculation in the backpropagation algorithm and weight update in the write operation to the memristors, the proposed method accelerates the training process and also eliminates the external computing resources required in the existing method, such as multipliers and memories. Through numerical experiments, we demonstrated that the proposed method achieves twice faster convergence of the training process than the existing method, while retaining the same level of the accuracy for the classification results.
Ngochao TRAN Tetsuro IMAI Koshiro KITAO Yukihiko OKUMURA Takehiro NAKAMURA Hiroshi TOKUDA Takao MIYAKE Robin WANG Zhu WEN Hajime KITANO Roger NICHOLS
The fifth generation (5G) system using millimeter waves is considered for application to high traffic areas with a dense population of pedestrians. In such an environment, the effects of shadowing and scattering of radio waves by human bodies (HBs) on propagation channels cannot be ignored. In this paper, we clarify based on measurement the characteristics of waves scattered by the HB for typical non-line-of-sight scenarios in street canyon environments. In these scenarios, there are street intersections with pedestrians, and the angles that are formed by the transmission point, HB, and reception point are nearly equal to 90 degrees. We use a wide-band channel sounder for the 67-GHz band with a 1-GHz bandwidth and horn antennas in the measurements. The distance parameter between antennas and the HB is changed in the measurements. Moreover, the direction of the HB is changed from 0 to 360 degrees. The evaluation results show that the radar cross section (RCS) of the HB fluctuates randomly over the range of approximately 20dB. Moreover, the distribution of the RCS of the HB is a Gaussian distribution with a mean value of -9.4dBsm and the standard deviation of 4.2dBsm.
Zhong ZHANG Hong WANG Shuang LIU Tariq S. DURRANI
A rich and robust representation for scene characters plays a significant role in automatically understanding the text in images. In this letter, we focus on the issue of feature representation, and propose a novel encoding method named bilateral convolutional activations encoded with Fisher vectors (BCA-FV) for scene character recognition. Concretely, we first extract convolutional activation descriptors from convolutional maps and then build a bilateral convolutional activation map (BCAM) to capture the relationship between the convolutional activation response and the spatial structure information. Finally, in order to obtain the global feature representation, the BCAM is injected into FV to encode convolutional activation descriptors. Hence, the BCA-FV can effectively integrate the prominent features and spatial structure information for character representation. We verify our method on two widely used databases (ICDAR2003 and Chars74K), and the experimental results demonstrate that our method achieves better results than the state-of-the-art methods. In addition, we further validate the proposed BCA-FV on the “Pan+ChiPhoto” database for Chinese scene character recognition, and the experimental results show the good generalization ability of the proposed BCA-FV.