In this paper, we propose a semi-supervised triplet loss function that realizes semi-supervised representation learning in a novel manner. We extend conventional triplet loss, which uses labeled data to achieve representation learning, so that it can deal with unlabeled data. We estimate, in advance, the degree to which each label applies to each unlabeled data point, and optimize the loss function with unlabeled features according to the resulting ratios. Since the proposed loss function has the effect of adjusting the distribution of all unlabeled data, it complements methods based on consistency regularization, which has been extensively studied in recent years. Combined with a consistency regularization-based method, our method achieves more accurate semi-supervised learning. Experiments show that the proposed loss function achieves a higher accuracy than the conventional fine-tuning method.

Machine reading comprehension with multi-hop reasoning always suffers from reasoning path breaking due to the lack of world knowledge, which always results in wrong answer detection. In this paper, we analyze what knowledge the previous work lacks, e.g., dependency relations and commonsense. Based on our analysis, we propose a Multi-dimensional Knowledge enhanced Graph Network, named MKGN, which exploits specific knowledge to repair the knowledge gap in reasoning process. Specifically, our approach incorporates not only entities and dependency relations through various graph neural networks, but also commonsense knowledge by a bidirectional attention mechanism, which aims to enhance representations of both question and contexts. Besides, to make the most of multi-dimensional knowledge, we investigate two kinds of fusion architectures, i.e., in the sequential and parallel manner. Experimental results on HotpotQA dataset demonstrate the effectiveness of our approach and verify that using multi-dimensional knowledge, especially dependency relations and commonsense, can indeed improve the reasoning process and contribute to correct answer detection.

To maintain blockchain-based services with ensuring its security, it is an important issue how to decide a mining reward so that the number of miners participating in the mining increases. We propose a dynamical model of decision-making for miners using an evolutionary game approach and analyze the stability of equilibrium points of the proposed model. The proposed model is described by the 1st-order differential equation. So, it is simple but its theoretical analysis gives an insight into the characteristics of the decision-making. Through the analysis of the equilibrium points, we show the transcritical bifurcations and hysteresis phenomena of the equilibrium points. We also design a controller that determines the mining reward based on the number of participating miners to stabilize the state where all miners participate in the mining. Numerical simulation shows that there is a trade-off in the choice of the design parameters.

Visual Question Answering (VQA) is multi-task research that requires simultaneous processing of vision and text. Recent research on the VQA models employ a co-attention mechanism to build a model between the context and the image. However, the features of questions and the modeling of the image region force irrelevant information to be calculated in the model, thus affecting the performance. This paper proposes a novel dual self-guided attention with sparse question networks (DSSQN) to address this issue. The aim is to avoid having irrelevant information calculated into the model when modeling the internal dependencies on both the question and image. Simultaneously, it overcomes the coarse interaction between sparse question features and image features. First, the sparse question self-attention (SQSA) unit in the encoder calculates the feature with the highest weight. From the self-attention learning of question words, the question features of larger weights are reserved. Secondly, sparse question features are utilized to guide the focus on image features to obtain fine-grained image features, and to also prevent irrelevant information from being calculated into the model. A dual self-guided attention (DSGA) unit is designed to improve modal interaction between questions and images. Third, the sparse question self-attention of the parameter δ is optimized to select these question-related object regions. Our experiments with VQA 2.0 benchmark datasets demonstrate that DSSQN outperforms the state-of-the-art methods. For example, the accuracy of our proposed model on the test-dev and test-std is 71.03% and 71.37%, respectively. In addition, we show through visualization results that our model can pay more attention to important features than other advanced models. At the same time, we also hope that it can promote the development of VQA in the field of artificial intelligence (AI).

This work proposes NFD.P4, a cache implementation scheme in Named Data Networking (NDN), to solve the problem of insufficient cache space of prgrammable switch and realize the practical application of NDN. We transplant the cache function of NDN.P4 to the NDN Forwarding Daemon (NFD) cache server, which replace the memory space of programmable switch.

Five Cells and Tilepaint are Nikoli's pencil puzzles. We study the computational complexity of Five Cells and Tilepaint puzzles. It is shown that deciding whether a given instance of each puzzle has a solution is NP-complete.

A rep-cube is a polyomino that is a net of a cube, and it can be divided into some polyominoes such that each of them can be folded into a cube. This notion was invented in 2017, which is inspired by the notions of polyomino and rep-tile, which were introduced by Solomon W. Golomb. A rep-cube is called regular if it can be divided into the nets of the same area. A regular rep-cube is of order k if it is divided into k nets. Moreover, it is called uniform if it can be divided into the congruent nets. In this paper, we focus on these special rep-cubes and solve several open problems.

To realize a stable and efficient wireless power transfer (WPT) system that can be used in any environment, it is necessary to inspect the influence of environmental interference along the power transmission path of the WPT system. In this paper, attempts have been made to reduce the influence of the medium with a dielectric and conductive loss on the WPT system using spiral resonators for resonator-coupled type wireless power transfer (RC-WPT) system. An important element of the RC-WPT system is the resonators because they improve resonant characteristics by changing the shape or combination of spiral resonators to confine the electric field that mainly causes electrical loss in the system as much as possible inside the resonator. We proposed a novel dual-spiral resonator as a candidate and compared the basic characteristics of the RC-WPT system with conventional single-spiral and dual-spiral resonators. The parametric values of the spiral resonators, such as the quality factors and the coupling coefficients between resonators with and without a lossy medium in the power transmission path, were examined. For the lossy mediums, pure water or tap water filled with acryl bases was used. The maximum transmission efficiency of the RC-WPT system was then observed by tuning the matching condition of the system. Following that, the transmission efficiency of the system with and without lossy medium was investigated. These inspections revealed that the performance of the RC-WPT system with the lossy medium using the modified shape spiral resonator, which is the dual-spiral resonator proposed in our laboratory, outperformed the system using the conventional single-spiral resonator.

Betweenness centrality is one of the most significant and commonly used centralities, where centrality is a notion of measuring the importance of nodes in networks. In 2001, Brandes proposed an algorithm for computing betweenness centrality efficiently, and it can compute those values for all nodes in O(nm) time for unweighted networks, where n and m denote the number of nodes and links in networks, respectively. However, even Brandes' algorithm is not fast enough for recent large-scale real-world networks, and therefore, much faster algorithms are expected. The objective of this research is to theoretically improve the efficiency of Brandes' algorithm by introducing graph decompositions, and to verify the practical effectiveness of our approaches by implementing them as computer programs and by applying them to various kinds of real-world networks. A series of computational experiments shows that our proposed algorithms run several times faster than the original Brandes' algorithm, which are guaranteed by theoretical analyses.

A three-stage padding configuration providing a larger continuous virtual aperture and achieving more degrees-of-freedom (DOFs) for the direction-of-arrival (DOA) estimation is presented. The improvement is realized by appropriately cascading three-stages of an identical inter-element spacing. Each stage advantageously exhibits a continuous virtual array, which subsequently produces a hole-free resulting uniform linear array. The geometrical approach remains applicable for any existing sparse array structures with a hole-free coarray, as well as designed in the future. In addition to enlarging the continuous virtual aperture and DOFs, the proposed design offers flexibility so that it can be realized for any given number of antennas. Moreover, a special padding configuration is demonstrated, which further increases the number of continuous virtual sensors. The precise antenna locations and the number of continuous virtual positions are benefited from the closed-form expressions. Experimental works are carried out to demonstrate the effectiveness of the proposed configuration.

The challenges posed by big data in the 21st Century are complex: Under the previous common sense, we considered that polynomial-time algorithms are practical; however, when we handle big data, even a linear-time algorithm may be too slow. Thus, sublinear- and constant-time algorithms are required. The academic research project, “Foundations of Innovative Algorithms for Big Data,” which was started in 2014 and will finish in September 2021, aimed at developing various techniques and frameworks to design algorithms for big data. In this project, we introduce a “Sublinear Computation Paradigm.” Toward this purpose, we first provide a survey of constant-time algorithms, which are the most investigated framework of this area, and then present our recent results on sublinear progressive algorithms. A sublinear progressive algorithm first outputs a temporary approximate solution in constant time, and then suggests better solutions gradually in sublinear-time, finally finds the exact solution. We present Sublinear Progressive Algorithm Theory (SPA Theory, for short), which enables to make a sublinear progressive algorithm for any property if it has a constant-time algorithm and an exact algorithm (an exponential-time one is allowed) without losing any computation time in the big-O sense.

We propose two systematic constructions of deletion-correcting codes for protecting quantum inforomation. The first one works with qudits of any dimension l, which is referred to as l-adic, but only one deletion is corrected and the constructed codes are asymptotically bad. The second one corrects multiple deletions and can construct asymptotically good codes. The second one also allows conversion of stabilizer-based quantum codes to deletion-correcting codes, and entanglement assistance.

The prediction of the malfunction timing of wind turbines is essential for maintaining the high profitability of the wind power generation industry. Studies have been conducted on machine learning methods that use condition monitoring system data, such as vibration data, and supervisory control and data acquisition (SCADA) data to detect and predict anomalies in wind turbines automatically. Autoencoder-based techniques that use unsupervised learning where the anomaly pattern is unknown have attracted significant interest in the area of anomaly detection and prediction. In particular, vibration data are considered useful because they include the changes that occur in the early stages of a malfunction. However, when autoencoder-based techniques are applied for prediction purposes, in the training process it is difficult to distinguish the difference between operating and non-operating condition data, which leads to the degradation of the prediction performance. In this letter, we propose a method in which both vibration data and SCADA data are utilized to improve the prediction performance, namely, a method that uses a power curve composed of active power and wind speed. We evaluated the method's performance using vibration and SCADA data obtained from an actual wind farm.

Reducing power consumption is a crucial factor making industrial designs, such as mobile SoCs, competitive. Voltage scaling (VS) is the classical yet most effective technique that contributes to quadratic power reduction. A recent design technique called activation-aware slack assignment (ASA) enhances the voltage-scaling by allocating the timing margin of critical paths with a stochastic mean-time-to-failure (MTTF) analysis. Meanwhile, such stochastic treatment of timing errors is accepted in limited application domains, such as image processing. This paper proposes a design optimization methodology that achieves a mode-wise voltage-scalable (MWVS) design guaranteeing no timing errors in each mode operation. This work formulates the MWVS design as an optimization problem that minimizes the overall power consumption considering each mode duration, achievable voltage lowering and accompanied circuit overhead explicitly, and explores the solution space with the downhill simplex algorithm that does not require numerical derivation and frequent objective function evaluations. For obtaining a solution, i.e., a design, in the optimization process, we exploit the multi-corner multi-mode design flow in a commercial tool for performing mode-wise ASA with sets of false paths dedicated to individual modes. We applied the proposed design methodology to RISC-V design. Experimental results show that the proposed methodology saves 13% to 20% more power compared to the conventional VS approach and attains 8% to 15% gain from the conventional single-mode ASA. We also found that cycle-by-cycle fine-grained false path identification reduced leakage power by 31% to 42%.

Currently there has been increasing demand for real-time training on resource-limited IoT devices such as smart sensors, which realizes standalone online adaptation for streaming data without data transfers to remote servers. OS-ELM (Online Sequential Extreme Learning Machine) has been one of promising neural-network-based online algorithms for on-chip learning because it can perform online training at low computational cost and is easy to implement as a digital circuit. Existing OS-ELM digital circuits employ fixed-point data format and the bit-widths are often manually tuned, however, this may cause overflow or underflow which can lead to unexpected behavior of the circuit. For on-chip learning systems, an overflow/underflow-free design has a great impact since online training is continuously performed and the intervals of intermediate variables will dynamically change as time goes by. In this paper, we propose an overflow/underflow-free bit-width optimization method for fixed-point digital circuits of OS-ELM. Experimental results show that our method realizes overflow/underflow-free OS-ELM digital circuits with 1.0x - 1.5x more area cost compared to the baseline simulation method where overflow or underflow can happen.

Line detection is the fundamental image processing technique which has various applications in the field of computer vision. For example, lane keeping required to realize autonomous vehicles can be implemented based on line detection technique. For such purposes, however, low detection latency and power consumption are essential. Using hardware-based stream processing is considered as an effective way to achieve such properties since it eliminates the need of storing the whole frame into energy-consuming external memory. In addition, adopting FPGAs enables us to keep flexibility of software processing. The line segment detector (LSD) is the algorithm based on intensity gradient, and performs better than the well-known Hough transform in terms of processing speed and accuracy. However, implementing the original LSD on FPGAs as a pipeline structure is difficult mainly because of its iterative region growing approach. Therefore, we propose a simple and stream-friendly line segment detection algorithm based on the concept of LSD. The whole system is implemented on a Xilinx Zynq-7000 XC7Z020-1CLG400C FPGA without any external memory. Evaluation results reveal that the implemented system is able to detect line segments successfully and is compact with 7.5% of Block RAM and less than 7.0% of the other resources used, while maintaining 60 fps throughput for VGA videos. It is also shown that the system is power-efficient compared to software processing on CPUs.

Multiparty computation (MPC) is the technology that computes an arbitrary function represented as a circuit without revealing input values. Typical MPC uses secret sharing (SS) schemes, garbled circuit (GC), and homomorphic encryption (HE). These cryptographic technologies have a trade-off relationship for the computation cost, communication cost, and type of computable circuit. Hence, the optimal choice depends on the computing resources, communication environment, and function related to applications. The private decision tree evaluation (PDTE) is one of the important applications of secure computation. There exist several PDTE protocols with constant communication rounds using GC, HE, and SS-MPC over the field. However, to the best of our knowledge, PDTE protocols with constant communication rounds using MPC based on SS over the ring (requiring only lower computation costs and communication complexity) are non-trivial and still missing. In this paper, we propose a PDTE protocol based on a three-party computation (3PC) protocol over the ring with one corruption. We also propose another three-party PDTE protocol over the field with one corruption that is more efficient than the naive construction.