Random network topologies have been proposed as a low-latency network for parallel computers. Although multicast is a common collective-communication operation, multicast algorithms each of which consists of a large number of unicasts are not well optimized for random network topologies. In this study, we firstly apply a two-opt algorithm for building efficient multicast on random network topologies. The two-opt algorithm creates a skilled ordered list of visiting nodes to minimize the total path hops or the total possible contention counts of unicasts that form the target multicast. We secondly extend to apply the two-opt algorithm for the other collective-communication operations, e.g., allreduce and allgather. The SimGrid discrete-event simulation results show that the two-opt multicast outperforms that in typical MPI implementation by up to 22% of the execution time of an MPI program that repeats the MPI_Bcast function. The two-opt allreduce and the two-opt allgather operations also improve by up to 15% and 14% the execution time when compared to those used in typical MPI implementations, respectively.

Communication networks for wide-scale distributed energy resources (DERs) including photovoltaics (PVs), wind, storage and battery systems and electric vehicles (EVs) will be indispensable in future power grids. In this paper, we compare optical fronthaul networks using existing optical ground wires (OPGWs) for centralized radio access network (C-RAN) architecture to realize cost effective wireless communication network expansion including low population area. We investigate the applicability of optical data transport technologies of physical layer split (PLS), analog radio-on-fiber (ARoF), and common public radio interface (CPRI). The deployment costs of them are comparatively analyzed. It was shown that physical layer split and analog radio-on-fiber with subcarrier multiplexing (SCM) result in lower cost than other technologies.

In recent years, deep neural network (DNN) has achieved considerable results on many artificial intelligence tasks, e.g. natural language processing. However, the computation complexity of DNN is extremely high. Furthermore, the performance of traditional von Neumann computing architecture has been slowing down due to the memory wall problem. Processing in memory (PIM), which places computation within memory and reduces the data movement, breaks the memory wall. ReRAM PIM is thought to be a available architecture for DNN accelerators. In this work, a novel design of ReRAM neuromorphic system is proposed to process DNN fully in array efficiently. The binary ReRAM array is composed of 2T2R storage cells and current mirror sense amplifiers. A dummy BL reference scheme is proposed for reference voltage generation. A binary DNN (BDNN) model is then constructed and optimized on MNIST dataset. The model reaches a validation accuracy of 96.33% and is deployed to the ReRAM PIM system. Co-design model optimization method between hardware device and software algorithm is proposed with the idea of utilizing hardware variance information as uncertainness in optimization procedure. This method is analyzed to achieve feasible hardware design and generalizable model. Deployed with such co-design model, ReRAM array processes DNN with high robustness against fabrication fluctuation.

An active gate driver IC generates arbitrary switching waveform is proposed to reduce the switching loss, the voltage overshoot, and the electromagnetic interference (EMI) by optimizing the switching pattern. However, it is hard to find optimal switching pattern because the switching pattern has huge possible combinations. In this paper, the method to estimate the switching loss and the voltage overshoot from the switching pattern with neural network (NN) is proposed. The implemented NN model obtains reasonable learning results for data-sets.

A long-reach coexisting PON system (1G/10G-EPON, video, and TWDM-PON) that uses the Wavelength Selective-Asymmetrical optical SPlitter (WS-ASP) without any active devices like optical amplifiers is proposed. The proposal can take into account the subscriber distribution in an access network and provide specific services in specific areas by varying the splitting ratios and the branch structure in the optical splitter. Simulations confirm the key features of WS-ASP, its novel process for deriving the splitting-ratios and greater transmission distance than possible with symmetrical splitters. Experiments on a prototype system demonstrate how wavelengths can be assigned to specific areas and optical link budget enhancement. For 1G-EPON systems, the prototype system with splitting-ratio of 60% attains the optical link budget enhancement of 4.2dB compared with conventional symmetrical optical splitters. The same prototype offers the optical link budget enhancement of 4.0dB at the bit rate of 10G-EPON systems. The values measured in the experiment agree well with the simulation results with respect to the transmission distance.

Large-scale disasters can lead to a severe damage or destruction of optical transport networks including the data-plane (D-plane) and control and management-plane (C/M-plane). In addition to D-plane recovery, quick recovery of the C/M-plane network in modern software-defined networking (SDN)-based fiber optical networks is essential not only for emergency control of surviving optical network resources, but also for quick collection of information related to network damage/survivability to enable the optimal recovery plan to be decided as early as possible. With the advent of the Internet of Things (IoT) technologies, low energy consumption, and low-cost IoT devices have been more common. Corresponding long-distance networking technologies such as low-power wide-area (LPWA) and LPWA-based mesh (LPWA-mesh) networks promise wide coverage sensing and environment data collection capabilities. We are motivated to take an infrastructure-less IoT approach to provide long-distance, low-power and inexpensive wireless connectivity and create an emergency C/M-plane network for early disaster recovery. In this paper, we investigate the feasibility of fiber networks C/M-plane recovery using an IoT-based extremely narrow-band, and lossy links system (FRENLL). For the first time, we demonstrate a field-trial experiment of a long-latency/loss tolerable SDN C/M-plane that can take advantage of widely available IoT resources and easy-to-create wireless mesh networks to enable the timely recovery of the C/M-plane after disaster.

Effective user accommodation will be more and more important in passive optical networks (PONs) in the next decade since the number of subscribers has been leveling off as well and it is becoming more difficult for network operators to keep sufficient numbers of maintenance workers. Drastically reducing the number of small-scale communication buildings while keeping the number of accommodated users is one of the most attractive solutions to meet this situation. To achieve this, we propose two types of long-reach repeater-free upstream transmission configurations for PON systems; (i) one utilizes a semiconductor optical amplifier (SOA) as a pre-amplifier and (ii) the other utilizes distributed Raman amplification (DRA) in addition to the SOA. Our simulations assuming 10G-EPON specifications and transmission experiments on a 10G-EPON prototype confirm that configuration (i) can add a 17km trunk fiber to a normal PON system with 10km access reach and 1 : 64 split (total 27km reach), while configuration (ii) can further expand the trunk fiber distance to 37km (total 47km reach). Network operators can select these configurations depending on their service areas.

We propose a new design approach to improve the computational efficiency of an optimal design of optical waveguide devices utilizing coupled mode theory (CMT) and a neural network (NN). Recently, the NN has begun to be used for efficient optimal design of optical devices. In this paper, the eigenmode analysis required in the CMT is skipped by using the NN, and optimization with an evolutionary algorithm can be efficiently carried out. To verify usefulness of our approach, optimal design examples of a wavelength insensitive 3dB coupler, a 1 : 2 power splitter, and a wavelength demultiplexer are shown and their transmission properties obtained by the CMT with the NN (NN-CMT) are verified by comparing with those calculated by a finite element beam propagation method (FE-BPM).

Modern deep learning has significantly improved performance and has been used in a wide variety of applications. Since the amount of computation required for the inference process of the neural network is large, it is processed not by the data acquisition location like a surveillance camera but by the server with abundant computing power installed in the data center. Edge computing is getting considerable attention to solve this problem. However, edge computing can provide limited computation resources. Therefore, we assumed a divided/distributed neural network model using both the edge device and the server. By processing part of the convolution layer on edge, the amount of communication becomes smaller than that of the sensor data. In this paper, we have evaluated AlexNet and the other eight models on the distributed environment and estimated FPS values with Wi-Fi, 3G, and 5G communication. To reduce communication costs, we also introduced the compression process before communication. This compression may degrade the object recognition accuracy. As necessary conditions, we set FPS to 30 or faster and object recognition accuracy to 69.7% or higher. This value is determined based on that of an approximation model that binarizes the activation of Neural Network. We constructed performance and energy models to find the optimal configuration that consumes minimum energy while satisfying the necessary conditions. Through the comprehensive evaluation, we found that the optimal configurations of all nine models. For small models, such as AlexNet, processing entire models in the edge was the best. On the other hand, for huge models, such as VGG16, processing entire models in the server was the best. For medium-size models, the distributed models were good candidates. We confirmed that our model found the most energy efficient configuration while satisfying FPS and accuracy requirements, and the distributed models successfully reduced the energy consumption up to 48.6%, and 6.6% on average. We also found that HEVC compression is important before transferring the input data or the feature data between the distributed inference processes.

With the rapid evolution and increase of cyberthreats in recent years, it is necessary to detect and understand it promptly and precisely to reduce the impact of cyberthreats. A darknet, which is an unused IP address space, has a high signal-to-noise ratio, so it is easier to understand the global tendency of malicious traffic in cyberspace than other observation networks. In this paper, we aim to capture global cyberthreats in real time. Since multiple hosts infected with similar malware tend to perform similar behavior, we propose a system that estimates a degree of synchronizations from the patterns of packet transmission time among the source hosts observed in unit time of the darknet and detects anomalies in real time. In our evaluation, we perform our proof-of-concept implementation of the proposed engine to demonstrate its feasibility and effectiveness, and we detect cyberthreats with an accuracy of 97.14%. This work is the first practical trial that detects cyberthreats from in-the-wild darknet traffic regardless of new types and variants in real time, and it quantitatively evaluates the result.

Neural networks have received considerable attention in sentence similarity measuring systems due to their efficiency in dealing with semantic composition. However, existing neural network methods are not sufficiently effective in capturing the most significant semantic information buried in an input. To address this problem, a novel weighted-pooling attention layer is proposed to retain the most remarkable attention vector. It has already been established that long short-term memory and a convolution neural network have a strong ability to accumulate enriched patterns of whole sentence semantic representation. First, a sentence representation is generated by employing a siamese structure based on bidirectional long short-term memory and a convolutional neural network. Subsequently, a weighted-pooling attention layer is applied to obtain an attention vector. Finally, the attention vector pair information is leveraged to calculate the score of sentence similarity. An amalgamation of both, bidirectional long short-term memory and a convolutional neural network has resulted in a model that enhances information extracting and learning capacity. Investigations show that the proposed method outperforms the state-of-the-art approaches to datasets for two tasks, namely semantic relatedness and Microsoft research paraphrase identification. The new model improves the learning capability and also boosts the similarity accuracy as well.

Many studies of deep neural networks have reported inference accelerators for improved energy efficiency. We propose methods for further improving energy efficiency while maintaining recognition accuracy, which were developed by the co-design of a filter-by-filter quantization scheme with variable bit precision and a hardware architecture that fully supports it. Filter-wise quantization reduces the average bit precision of weights, so execution times and energy consumption for inference are reduced in proportion to the total number of computations multiplied by the average bit precision of weights. The hardware utilization is also improved by a bit-parallel architecture suitable for granularly quantized bit precision of weights. We implement the proposed architecture on an FPGA and demonstrate that the execution cycles are reduced to 1/5.3 for ResNet-50 on ImageNet in comparison with a conventional method, while maintaining recognition accuracy.

Road traffic collisions are an extremely serious and often fatal issue. One promising approach to mitigate such collisions is the use of connected car services that share road traffic information obtained from vehicles and cameras over mobile networks. In connected car services, it is important for data chunks to arrive at a destination node within a certain deadline constraint. In this paper, we define a flow from a vehicle (or camera) to the same vehicle (or camera) via an MEC server, as a mission critical (MC) flow, and call a deadline of the MC flow the MC deadline. Our research objective is to achieve a higher arrival ratio within the MC deadline for the MC flow that passes through both the radio uplink and downlink. We previously developed a deadline-aware scheduler with consideration for quality fluctuation (DAS-QF) that considers chunk size and a certain deadline constraint in addition to radio quality and utilizes these to prioritize users such that the deadline constraints are met. However, this DAS-QF does not consider that the congestion levels of evolved NodeB (eNB) differ depending on the eNB location, or that the uplink congestion level differs from the downlink congestion level in the same eNB. Therefore, in the DAS-QF, some data chunks of a MC flow are discarded in the eNB when they exceed either the uplink or downlink deadline in congestion, even if they do not exceed the MC deadline. In this paper, to reduce the eNB packet drop probability due to exceeding either the uplink and downlink deadline, we propose a deadline coordination function (DCF) that adaptively sets each of the uplink and downlink deadlines for the MC flow according to the congestion level of each link. Simulation results show that the DAS-QF with DCF offers higher arrival ratios within the MC deadline compared to DAS-QF on its own

To tackle the distributed power optimization problems in wireless sensor networks localization systems, we model the problem as a hierarchical game, i.e. a multi-leader multi-follower Stackelberg game. Existing researches focus on the power allocation of anchor nodes for ranging signals or the power management of agent nodes for cooperative localization, individually. However, the power optimizations for different nodes are indiscerptible due to the common objective of localization accuracy. So it is a new challenging task when the power allocation strategies are considered for anchor and agent nodes simultaneously. To cope with this problem, a hierarchical game is proposed where anchor nodes are modeled as leaders and agent nodes are modeled as followers. Then, we prove that games of leaders and followers are both potential games, which guarantees the Nash equilibrium (NE) of each game. Moreover, the existence of Stackelberg equilibrium (SE) is proved and achieved by the best response dynamics. Simulation results demonstrate that the proposed algorithm can have better localization accuracy compared with the decomposed algorithm and uniform strategy.

In this paper, we propose a decentralized probabilistic frequency-block activation control method for the cellular downlink. The aim of the proposed method is to increase the downlink system throughput within the system coverage by adaptively controlling the individual activation of each frequency block at all base stations (BSs) to achieve inter-cell interference coordination (ICIC) and traffic load balancing. The proposed method does not rely on complicated inter-BS cooperation. It uses only the inter-BS information exchange regarding the observed system throughput levels with the neighboring BSs. Based on the shared temporal system throughput information, each BS independently controls online the activation of their respective frequency blocks in a probabilistic manner, which autonomously achieves ICIC and load balancing among BSs. Simulation results show that the proposed method achieves greater system throughput and a faster convergence rate than the conventional online probabilistic activation/deactivation control method. We also show that the proposed method successfully tracks dynamic changes in the user distribution generated due to mobility.

In the statistic en-route filtering, each report generation node must collect a certain number of endorsements from its neighboring nodes. However, at some point, a node may fail to collect an insufficient number of endorsements since some of its neighboring nodes may have dead batteries. This letter presents a report generation method that can enhance the generation process of sensing reports under such a situation. Simulation results show the effectiveness of the proposed method.

This paper presents a method for many-to-one voice conversion using phonetic posteriorgrams (PPGs) based on an adversarial training of deep neural networks (DNNs). A conventional method for many-to-one VC can learn a mapping function from input acoustic features to target acoustic features through separately trained DNN-based speech recognition and synthesis models. However, 1) the differences among speakers observed in PPGs and 2) an over-smoothing effect of generated acoustic features degrade the converted speech quality. Our method performs a domain-adversarial training of the recognition model for reducing the PPG differences. In addition, it incorporates a generative adversarial network into the training of the synthesis model for alleviating the over-smoothing effect. Unlike the conventional method, ours jointly trains the recognition and synthesis models so that they are optimized for many-to-one VC. Experimental evaluation demonstrates that the proposed method significantly improves the converted speech quality compared with conventional VC methods.

A limited number of types of sound event occur in an acoustic scene and some sound events tend to co-occur in the scene; for example, the sound events “dishes” and “glass jingling” are likely to co-occur in the acoustic scene “cooking.” In this paper, we propose a method of sound event detection using graph Laplacian regularization with sound event co-occurrence taken into account. In the proposed method, the occurrences of sound events are expressed as a graph whose nodes indicate the frequencies of event occurrence and whose edges indicate the sound event co-occurrences. This graph representation is then utilized for the model training of sound event detection, which is optimized under an objective function with a regularization term considering the graph structure of sound event occurrence and co-occurrence. Evaluation experiments using the TUT Sound Events 2016 and 2017 detasets, and the TUT Acoustic Scenes 2016 dataset show that the proposed method improves the performance of sound event detection by 7.9 percentage points compared with the conventional CNN-BiGRU-based detection method in terms of the segment-based F1 score. In particular, the experimental results indicate that the proposed method enables the detection of co-occurring sound events more accurately than the conventional method.

In this paper, we study a radio frequency (RF)-powered backscatter assisted cognitive radio network (CRN), where an eavesdropper exists. This network includes a primary transmitter, a pair of secondary transmitter and receiver, a friendly jammer and an eavesdropper. We assume that the secondary transmitter works in ambient backscatter (AmBack) mode and the friendly jammer works in harvest-then-transmit (HTT) mode, where the primary transmitter serves as energy source. To enhance the physical layer security of the secondary user, the friendly jammer uses its harvested energy from the primary transmitter to transmit jamming noise to the eavesdropper. Furthermore, for maximizing the secrecy rate of secondary user, the optimal time allocation including the energy harvesting and jamming noise transmission phases is obtained. Simulation results verify the superiority of the proposed scheme.

Rehabilitation and evaluation of motor function are important for motor disabled patients. In stride length estimation using an IMU attached to the foot, it is necessary to detect the time of the movement state, in which acceleration should be integrated. In our previous study, acceleration thresholds were used to determine the integration section, so it was necessary to adjust the threshold values for each subject. The purpose of this study was to develop a method for estimating stride length automatically using an artificial neural network (ANN). In this paper, a 4-layer ANN with feature extraction layers trained by autoencoder was tested. In addition, the methods of searching for the local minimum of acceleration or ANN output after detecting the movement state section by ANN were examined. The proposed method estimated the stride length for healthy subjects with error of -1.88 ± 2.36%, which was almost the same as the previous threshold based method (-0.97 ± 2.68%). The correlation coefficients between the estimated stride length and the reference value were 0.981 and 0.976 for the proposed and previous methods, respectively. The error ranges excluding outliers were between -7.03% and 3.23%, between -7.13% and 5.09% for the proposed and previous methods, respectively. The proposed method would be effective because the error range was smaller than the conventional method and no threshold adjustment was required.