The supercomputer, “Fugaku”, which ranked number one in multiple supercomputing lists, including the Top500 in June 2020, has various power control features, such as (1) an eco mode that utilizes only one of two floating-point pipelines while decreasing the power supply to the chip; (2) a boost mode that increases clock frequency; and (3) a core retention feature that turns unused cores to the low-power state. By orchestrating these power-performance features while considering the characteristics of running applications, we can potentially gain even better system-level energy efficiency. In this paper, we report on the performance and power consumption of Fugaku using SPEC HPC benchmarks. Consequently, we confirmed that it is possible to reduce the energy by about 17% while improving the performance by about 2% from the normal mode by combining boost mode and eco mode.

This paper proposes an efficient reference image sharing method for the image-division parallel video encoding architecture. This method efficiently reduces the amount of data transfer by using pre-transfer with area prediction and on-demand transfer with a transfer management table. Experimental results show that the data transfer can be reduced to 19.8-35.3% of the conventional method on average without major degradation of coding performance. This makes it possible to reduce the required bandwidth of the inter-chip transfer interface by saving the amount of data transfer.

The demand for low-latency transmission of large-capacity video, such as 4K and 8K, is increasing for various applications such as live-broadcast program production, sports viewing, and medical care. In the broadcast industry, low-latency video transmission is required in remote production, an emerging workflow for outside broadcasting. For ideal remote production, long-distance transmission of uncompressed 8K60p video signals, ultra-low latency less than 16.7 ms, and PTP synchronization through network are required; however, no existing video-transmission system fully satisfy these requirements. We focused on optical transport technologies capable of long-distance and large-capacity communication, which were previously used only in telecommunication-carrier networks. To fully utilize optical transport technologies, we propose the first-ever video-transmission system architecture capable of sending and receiving uncompressed 8K video directly through large-capacity optical paths. A transmission timing control in seamless protection switching is also proposed to improve the tolerance to network impairment. As a means of implementation, we focused on whitebox transponder, an emerging type of optical transponder with a disaggregation configuration. The disaggregation configuration enables flexible configuration changes, additional implementations, and cost reduction by separating various functions of optical transponders and controlling them with a standardized interface. We implemented the ultra-low-latency video-transmission system utilizing whitebox transponder Galileo. We developed a hardware plug-in unit for video transmission (VideoPIU), and software to control the VideoPIU. In the video-transmission experiments with 120-km optical fiber, we confirmed that it was capable of transmitting uncompressed 8K60p video stably in 1.3 ms latency and highly accurate PTP synchronization through the optical network, which was required in the ideal remote production. In addition, the application to immersive sports viewing is also presented. Consequently, excellent potential to support the unprecedented applications is demonstrated.

In a free-space method using a pair of horn antennas with dielectric lenses, we demonstrated that the permittivity of a sample can be estimated with good accuracy by equalizing a measured transmission coefficient of a sample to a transmission coefficient for a Gaussian beam, which is approximately equal to the transmission coefficient for a plane wave multiplied by a term that changes the phase. In this permittivity estimation method, because the spot size at the beam waist in a Gaussian beam needs to be determined, we proposed an estimation method of the spot size by employing the measurement of the Line in Thru-Reflect-Line calibration; thus, no additional measurement is required. The permittivity estimation method was investigated for the E-band (60-90 GHz), and it was demonstrated that the relative permittivity of air with a thickness of 2mm and a sample with the relative permittivity of 2.05 and a thickness of 1mm is estimated with errors less than ±0.5% and ±0.2%, respectively. Moreover, in measuring a sample without displacing the receiving horn antenna to avoid the error in measurement, we derived an expression of the permittivity estimation for S parameters measured using a vector network analyzer, and demonstrated that the measurement of a sample without antenna displacement is valid.

Peg solitaire is a single-player board game. The goal of the game is to remove all but one peg from the game board. Peg solitaire on graphs is a peg solitaire played on arbitrary graphs. A graph is called solvable if there exists some vertex s such that it is possible to remove all but one peg starting with s as the initial hole. In this paper, we prove that it is NP-complete to decide if a graph is solvable or not.

Many deep convolutional neural network (CNN) inference accelerators on the field-programmable gate array (FPGA) platform have been widely adopted due to their low power consumption and high performance. In this paper, we develop the following to improve performance and power efficiency. First, we use a high bandwidth memory (HBM) to expand the bandwidth of data transmission between the off-chip memory and the accelerator. Second, a fully-pipelined manner, which consists of pipelined inter-layer computation and a pipelined computation engine, is implemented to decrease idle time among layers. Third, a multi-core architecture with shared-dual buffers is designed to reduce off-chip memory access and maximize the throughput. We designed the proposed accelerator on the Xilinx Alveo U280 platform with in-depth Verilog HDL instead of high-level synthesis as the previous works and explored the VGG-16 model to verify the system during our experiment. With a similar accelerator architecture, the experimental results demonstrate that the memory bandwidth of HBM is 13.2× better than DDR4. Compared with other accelerators in terms of throughput, our accelerator is 1.9×/1.65×/11.9× better than FPGA+HBM2 based/low batch size (4) GPGPU/low batch size (4) CPU. Compared with the previous DDR+FPGA/DDR+GPGPU/DDR+CPU based accelerators in terms of power efficiency, our proposed system provides 1.4-1.7×/1.7-12.6×/6.6-37.1× improvement with the large-scale CNN model.

The increasing attention to the interpretability of machine learning models has led to the development of methods to explain the behavior of black-box models in a post-hoc manner. However, such post-hoc approaches generate a new explanation for every new input, and these explanations cannot be checked by humans in advance. A method that selects decision rules from a finite ruleset as explanation for neural networks has been proposed, but it cannot be used for other models. In this paper, we propose a model-agnostic explanation method to find a pre-verifiable finite ruleset from which a decision rule is selected to support every prediction made by a given black-box model. First, we define an explanation model that selects the rule, from a ruleset, that gives the closest prediction; this rule works as an alternative explanation or supportive evidence for the prediction of a black-box model. The ruleset should have high coverage to give close predictions for future inputs, but it should also be small enough to be checkable by humans in advance. However, minimizing the ruleset while keeping high coverage leads to a computationally hard combinatorial problem. Hence, we show that this problem can be reduced to a weighted MaxSAT problem composed only of Horn clauses, which can be efficiently solved with modern solvers. Experimental results showed that our method found small rulesets such that the rules selected from them can achieve higher accuracy for structured data as compared to the existing method using rulesets of almost the same size. We also experimentally compared the proposed method with two purely rule-based models, CORELS and defragTrees. Furthermore, we examine rulesets constructed for real datasets and discuss the characteristics of the proposed method from different viewpoints including interpretability, limitation, and possible use cases.

One key to implementing the smart city is letting the smart space know where and how many people are. The visual method is a scheme to recognize people with high accuracy, but concerns arise regarding potential privacy leakage and user nonacceptance. Besides, being functional in a limited environment in an emergency should also be considered. We propose a real-time people counting and tracking system based on a millimeter wave radar (mmWave) as an alternative to the optical solutions in a restaurant. The proposed method consists of four main procedures. First, capture the point cloud of obstacles and generate them using a low-cost, commercial off-the-shelf (COTS) mmWave radar. Next, cluster the individual point with similar properties. Then the same people in sequential frames would be associated with the tracking algorithm. Finally, the estimated people would be counted, tracked, and shown in the next frame. The experiment results show that our proposed system provided a median position error of 0.17 m and counting accuracy of 83.5% for ten insiders in various scenarios in an actual restaurant environment. In addition, the real-time estimation and visualization of people's numbers and positions show a potential capability to help prevent crowds during the pandemic of Covid-19 and analyze customer visitation patterns for efficient management and target marketing.

Many countries are facing the aging problem caused by the growth of the elderly population. Nursing home (NH) is a common solution to long-term care for the elderly. This paper develops a simulator to model elder behavior in an NH, which considers public areas where elders interact and imitates their general, group, and special activities. Elders have their preferences to decide activities taken by them. The simulator takes account of the movement of elders and abnormal events. Based on the simulator, two seeking methods are proposed for caregivers to search lost elders efficiently, which helps them fast find out elders who may incur accidents.

We propose a framework for the integration of heterogeneous networks in human pose estimation (HPE) with the aim of balancing accuracy and computational complexity. Although many existing methods can improve the accuracy of HPE using multiple frames in videos, they also increase the computational complexity. The key difference here is that the proposed heterogeneous framework has various networks for different types of frames, while existing methods use the same networks for all frames. In particular, we propose to divide the video frames into two types, including key frames and non-key frames, and adopt three networks including slow networks, fast networks, and transfer networks in our heterogeneous framework. For key frames, a slow network is used that has high accuracy but high computational complexity. For non-key frames that follow a key frame, we propose to warp the heatmap of a slow network from a key frame via a transfer network and fuse it with a fast network that has low accuracy but low computational complexity. Furthermore, when extending to the usage of long-term frames where a large number of non-key frames follow a key frame, the temporal correlation decreases. Therefore, when necessary, we use an additional transfer network that warps the heatmap from a neighboring non-key frame. The experimental results on PoseTrack 2017 and PoseTrack 2018 datasets demonstrate that the proposed FSPose achieves a better balance between accuracy and computational complexity than the competitor method. Our source code is available at https://github.com/Fenax79/fspose.

Neuromorphic computing with a spiking neural network (SNN) is expected to provide a complement or alternative to deep learning in the future. The challenge is to develop optimal SNN models, algorithms, and engineering technologies for real use cases. As a potential use cases for neuromorphic computing, we have investigated a person monitoring and worker support with a video surveillance system, given its status as a proven deep neural network (DNN) use case. In the future, to increase the number of cameras in such a system, we will need a scalable approach that embeds only a few neuromorphic devices in a camera. Specifically, this will require a shallow SNN model that can be implemented in a few neuromorphic devices while providing a high recognition accuracy comparable to a DNN with the same configuration. A shallow SNN was built by converting ResNet, a proven DNN for image recognition, and a new configuration of the shallow SNN model was developed to improve its accuracy. The proposed shallow SNN model was evaluated with a few neuromorphic devices, and it achieved a recognition accuracy of more than 80% with about 1/130 less energy consumption than that of a GPU with the same configuration of DNN as that of SNN.

Fully homomorphic encryption (FHE) enables secret computations. Users can perform computation using data encrypted with FHE without decryption. Uploading private data without encryption to a public cloud has the risk of data leakage, which makes many users hesitant to utilize a public cloud. Uploading data encrypted with FHE avoids this risk, while still providing the computing power of the public cloud. In many cases, data are stored in HDDs because the data size increases significantly when FHE is used. One important data analysis is Apriori data mining. In this application, two files are accessed alternately, and this causes long-distance seeking on its HDD and low performance. In this paper, we propose a new striping layout with reservations for write areas. This method intentionally fragments files and arranges blocks to reduce the distance between blocks in a file and another file. It reserves the area for intermediate files of FHE Apriori. The performance of the proposed method was evaluated based on the I/O processing of a large FHE Apriori, and the results showed that the proposed method could improve performance by up to approximately 28%.

A Boolean network (BN) is well known as a discrete model for analysis and control of complex networks such as gene regulatory networks. Since complex networks are large-scale in general, it is important to consider model reduction. In this paper, we consider model reduction that the information on fixed points (singleton attractors) is preserved. In model reduction studied here, the interaction graph obtained from a given BN is utilized. In the existing method, the minimum feedback vertex set (FVS) of the interaction graph is focused on. The dimension of the state is reduced to the number of elements of the minimum FVS. In the proposed method, we focus on complement and absorption laws of Boolean functions in substitution operations of a Boolean function into other one. By simplifying Boolean functions, the dimension of the state may be further reduced. Through a numerical example, we present that by the proposed method, the dimension of the state can be reduced for BNs that the dimension of the state cannot be reduced by the existing method.

Energy management in buildings is vital for reducing electricity costs and maximizing the comfort of occupants. Excess solar generation can be used by combining a battery storage system and a heating, ventilation, and air-conditioning (HVAC) system so that occupants feel comfortable. Despite several studies on the scheduling of appliances, batteries, and HVAC, comprehensive and time scalable approaches are required that integrate such predictive information as renewable generation and thermal comfort. In this paper, we propose an thermal-comfort aware online co-scheduling framework that incorporates optimal energy scheduling and a prediction model of PV generation and thermal comfort with the model predictive control (MPC) approach. We introduce a photovoltaic (PV) energy nowcasting and thermal-comfort-estimation model that provides useful information for optimization. The energy management problem is formulated as three coordinated optimization problems that cover fast and slow time-scales by considering predicted information. This approach reduces the time complexity without a significant negative impact on the result's global nature and its quality. Experimental results show that our proposed framework achieves optimal energy management that takes into account the trade-off between electricity expenses and thermal comfort. Our sensitivity analysis indicates that introducing a battery significantly improves the trade-off relationship.

Event structures are a well-known modeling formalism for concurrent systems with causality and conflict relations. The flow event structure (FES) is a variant of event structures, which is a generalization of the prime event structure. In an FES, two events may be in conflict even though they are not syntactically in conflict; this is called a semantic conflict. The existence of semantic conflict in an FES motivates reducing conflict relations (i.e., conflict reduction) to obtain a simpler structure. In this paper, we study conflict reduction in acyclic FESs. A necessary and sufficient condition for conflict reduction is given; algorithms to compute semantic conflict, local configurations, and conflict reduction are proposed. A great time reduction was observed in computational experiments when comparing the proposed with the naive method.

A hopping rover is a robot that can move in low gravity planets by the characteristic motion called the hopping motion. For its autonomous explorations, the so-called SLAM (Simultaneous Localization and Mapping) is a basic function. SLAM is the combination of estimating the position of a robot and creating a map of an unknown environment. Most conventional methods of SLAM are based on odometry to estimate the position of the robot. However, in the case of the hopping rover, the error of odometry becomes considerably large because its hopping motion involves unpredictable bounce on the rough ground on an unexplored planet. Motivated by the above discussion, this paper addresses a problem of finding an optimal movement of the hopping rover for the estimation performance of the SLAM. For the problem, we first set the model of the SLAM system for the hopping rover. The problem is formulated as minimizing the expectation of the estimation error at a pre-specified time with respect to the sequence of control inputs. We show that the optimal input sequence tends to force the final position to be not at the landmark but in front of the landmark, and furthermore, the optimal input sequence is constant on the time interval for optimization.

In a power network, it is important to detect a cyber attack. In this paper, we propose a method for detecting false data injection (FDI) attacks in distributed state estimation. An FDI attack is well known as one of the typical cyber attacks in a power network. As a method of FDI attack detection, we consider calculating the residual (i.e., the difference between the observed and estimated values). In the proposed detection method, the tentative residual (estimated error) in ADMM (Alternating Direction Method of Multipliers), which is one of the powerful methods in distributed optimization, is applied. First, the effect of an FDI attack is analyzed. Next, based on the analysis result, a detection parameter is introduced based on the residual. A detection method using this parameter is then proposed. Finally, the proposed method is demonstrated through a numerical example on the IEEE 14-bus system.

This paper addresses an observer-design method only using data. Usually, the observer requires a mathematical model of a system for state prediction and observer gain calculation. As an alternative to the model-based prediction, the proposed predictor calculates the states using a linear combination of the given data. To design the observer gain, the data which represent dual systems are derived from the data which represent the original system. Linear matrix inequalities that depend on data of the dual system provides the observer gains.