IEICE Transactions on Information and Systems
Online ISSN : 1745-1361
Print ISSN : 0916-8532
Volume E104.D, Issue 2
Displaying 1-17 of 17 articles from this issue
Regular Section
  • Sho KANAMARU, Kazushi KAWAMURA, Shu TANAKA, Yoshinori TOMITA, Nozomu T ...
    Article type: PAPER
    Subject area: Fundamentals of Information Systems
    2021 Volume E104.D Issue 2 Pages 226-236
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    Ising machines have attracted attention, which is expected to obtain better solutions of various combinatorial optimization problems at high speed by mapping the problems to natural phenomena. A slot-placement problem is one of the combinatorial optimization problems, regarded as a quadratic assignment problem, which relates to the optimal logic-block placement in a digital circuit as well as optimal delivery planning. Here, we propose a mapping to the Ising model for solving a slot-placement problem with additional constraints, called a constrained slot-placement problem, where several item pairs must be placed within a given distance. Since the behavior of Ising machines is stochastic and we map the problem to the Ising model which uses the penalty method, the obtained solution does not always satisfy the slot-placement constraint, which is different from the conventional methods such as the conventional simulated annealing. To resolve the problem, we propose an interpretation method in which a feasible solution is generated by post-processing procedures. We measured the execution time of an Ising machine and compared the execution time of the simulated annealing in which solutions with almost the same accuracy are obtained. As a result, we found that the Ising machine is faster than the simulated annealing that we implemented.

    Download PDF (1185K)
  • Yoshihiro OSAKABE, Shigeo SATO, Hisanao AKIMA, Mitsunaga KINJO, Masao ...
    Article type: PAPER
    Subject area: Fundamentals of Information Systems
    2021 Volume E104.D Issue 2 Pages 237-245
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    Utilizing the enormous potential of quantum computers requires new and practical quantum algorithms. Motivated by the success of machine learning, we investigate the fusion of neural and quantum computing, and propose a learning method for a quantum neural network inspired by the Hebb rule. Based on an analogy between neuron-neuron interactions and qubit-qubit interactions, the proposed quantum learning rule successfully changes the coupling strengths between qubits according to training data. To evaluate the effectiveness and practical use of the method, we apply it to the memorization process of a neuro-inspired quantum associative memory model. Our numerical simulation results indicate that the proposed quantum versions of the Hebb and anti-Hebb rules improve the learning performance. Furthermore, we confirm that the probability of retrieving a target pattern from multiple learned patterns is sufficiently high.

    Download PDF (5057K)
  • Zhouwen TAN, Ziji MA, Hongli LIU, Keli PENG, Xun SHAO
    Article type: PAPER
    Subject area: Fundamentals of Information Systems
    2021 Volume E104.D Issue 2 Pages 246-253
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    Impulsive noise (IN) is the most dominant factor degrading the performance of communication systems over powerlines. In order to improve performance of high-speed power line communication (PLC), this work focuses on mitigating burst IN effects based on compressive sensing (CS), and an adaptive burst IN mitigation method, namely combination of adaptive interleaver and permutation of null carriers is designed. First, the long burst IN is dispersed by an interleaver at the receiver and the characteristic of noise is estimated by the method of moment estimation, finally, the generated sparse noise is reconstructed by changing the number of null carriers(NNC) adaptively according to noise environment. In our simulations, the results show that the proposed IN mitigation technique is simple and effective for mitigating burst IN in PLC system, it shows the advantages to reduce the burst IN and to improve the overall system throughput. In addition, the performance of the proposed technique outpeformences other known nonlinear noise mitigation methods and CS methods.

    Download PDF (744K)
  • Shi QIU, Daniel M. GERMAN, Katsuro INOUE
    Article type: PAPER
    Subject area: Software Engineering
    2021 Volume E104.D Issue 2 Pages 254-263
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    Software copyright claims an exclusive right for the software copyright owner to determine whether and under what conditions others can modify, reuse, or redistribute this software. For Free and Open Source Software (FOSS), it is very important to identify the copyright owner who can control those activities with license compliance. Copyright notice is a few sentences mostly placed in the header part of a source file as a comment or in a license document in a FOSS project, and it is an important clue to establish the ownership of a FOSS project. Repositories of FOSS projects contain rich and varied information on the development including the source code contributors who are also an important clue to establish the ownership. In this paper, as a first step of understanding copyright owner, we will explore the situation of the software copyright in the Linux kernel, a typical example of FOSS, by analyzing and comparing two kinds of datasets, copyright notices in source files and source code contributors in the software repositories. The discrepancy between two kinds of analysis results is defined as copyright inconsistency. The analysis result has indicated that copyright inconsistencies are prevalent in the Linux kernel. We have also found that code reuse, affiliation change, refactoring, support function, and others' contributions potentially have impacts on the occurrence of the copyright inconsistencies in the Linux kernel. This study exposes the difficulty in managing software copyright in FOSS, highlighting the usefulness of future work to address software copyright problems.

    Download PDF (283K)
  • Rei NAKAGAWA, Satoshi OHZAHATA, Ryo YAMAMOTO, Toshihiko KATO
    Article type: PAPER
    Subject area: Information Network
    2021 Volume E104.D Issue 2 Pages 264-274
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    Recently, adaptive streaming over information centric network (ICN) has attracted attention. In adaptive streaming over ICN, the bitrate adaptation of the client often overestimates a bitrate for available bandwidth due to congestion because the client implicitly estimates congestion status from the content download procedures of ICN. As a result, streaming overestimated bitrate results in QoE degradation of clients such as cause of a stall time and frequent variation of the bitrate. In this paper, we propose a congestion-aware adaptive streaming over ICN combined with the explicit congestion notification (CAAS with ECN) to avoid QoE degradation. CAAS with ECN encourages explicit feedback of congestion detected in the router on the communication path, and introduces the upper band of the selectable bitrate (bitrate-cap) based on explicit feedback from the router to the bitrate adaptation of the clients. We evaluate the effectiveness of CAAS with ECN for client's QoE degradation due to congestion and behavior on the QoS metrics based on throughput. The simulation experiments show that the bitrate adjustment for all the clients improves QoE degradation and QoE fairness due to effective congestion avoidance.

    Download PDF (2615K)
  • Vu-Tran-Minh KHUONG, Khanh-Minh PHAN, Huy-Quang UNG, Cuong-Tuan NGUYEN ...
    Article type: PAPER
    Subject area: Educational Technology
    2021 Volume E104.D Issue 2 Pages 275-284
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    Many approaches enable teachers to digitalize students' answers and mark them on the computer. However, they are still limited for supporting marking descriptive mathematical answers that can best evaluate learners' understanding. This paper presents clustering of offline handwritten mathematical expressions (HMEs) to help teachers efficiently mark answers in the form of HMEs. In this work, we investigate a method of combining feature types from low-level directional features and multiple levels of recognition: bag-of-symbols, bag-of-relations, and bag-of-positions. Moreover, we propose a marking cost function to measure the marking effort. To show the effectiveness of our method, we used two datasets and another sampled from CROHME 2016 with synthesized patterns to prepare correct answers and incorrect answers for each question. In experiments, we employed the k-means++ algorithm for each level of features and considered their combination to produce better performance. The experiments show that the best combination of all the feature types can reduce the marking cost to about 0.6 by setting the number of answer clusters appropriately compared with the manual one-by-one marking.

    Download PDF (1295K)
  • Kazunori IWATA, Hiroki YAMAMOTO, Kazushi MIMURA
    Article type: PAPER
    Subject area: Pattern Recognition
    2021 Volume E104.D Issue 2 Pages 285-293
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    Shape matching with local descriptors is an underlying scheme in shape analysis. We can visually confirm the matching results and also assess them for shape classification. Generally, shape matching is implemented by determining the correspondence between shapes that are represented by their respective sets of sampled points. Some matching methods have already been proposed; the main difference between them lies in their choice of matching cost function. This function measures the dissimilarity between the local distribution of sampled points around a focusing point of one shape and the local distribution of sampled points around a referring point of another shape. A local descriptor is used to describe the distribution of sampled points around the point of the shape. In this paper, we propose an extended scheme for shape matching that can compensate for errors in existing local descriptors. It is convenient for local descriptors to adopt our scheme because it does not require the local descriptors to be modified. The main idea of our scheme is to consider the correspondence of neighboring sampled points to a focusing point when determining the correspondence of the focusing point. This is useful because it increases the chance of finding a suitable correspondence. However, considering the correspondence of neighboring points causes a problem regarding computational feasibility, because there is a substantial increase in the number of possible correspondences that need to be considered in shape matching. We solve this problem using a branch-and-bound algorithm, for efficient approximation. Using several shape datasets, we demonstrate that our scheme yields a more suitable matching than the conventional scheme that does not consider the correspondence of neighboring sampled points, even though our scheme requires only a small increase in execution time.

    Download PDF (474K)
  • Noriyuki TONAMI, Keisuke IMOTO, Ryosuke YAMANISHI, Yoichi YAMASHITA
    Article type: PAPER
    Subject area: Speech and Hearing
    2021 Volume E104.D Issue 2 Pages 294-301
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    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.

    Download PDF (977K)
  • Kiyoshi KURIHARA, Nobumasa SEIYAMA, Tadashi KUMANO
    Article type: PAPER
    Subject area: Speech and Hearing
    2021 Volume E104.D Issue 2 Pages 302-311
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS
    Supplementary material

    This paper describes a method to control prosodic features using phonetic and prosodic symbols as input of attention-based sequence-to-sequence (seq2seq) acoustic modeling (AM) for neural text-to-speech (TTS). The method involves inserting a sequence of prosodic symbols between phonetic symbols that are then used to reproduce prosodic acoustic features, i.e. accents, pauses, accent breaks, and sentence endings, in several seq2seq AM methods. The proposed phonetic and prosodic labels have simple descriptions and a low production cost. By contrast, the labels of conventional statistical parametric speech synthesis methods are complicated, and the cost of time alignments such as aligning the boundaries of phonemes is high. The proposed method does not need the boundary positions of phonemes. We propose an automatic conversion method for conventional labels and show how to automatically reproduce pitch accents and phonemes. The results of objective and subjective evaluations show the effectiveness of our method.

    Download PDF (3651K)
  • Kohei NAKAI, Takashi MATSUBARA, Kuniaki UEHARA
    Article type: PAPER
    Subject area: Image Recognition, Computer Vision
    2021 Volume E104.D Issue 2 Pages 312-321
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    The recent development of neural architecture search (NAS) has enabled us to automatically discover architectures of neural networks with high performance within a few days. Convolutional neural networks extract fruitful features by repeatedly applying standard operations (convolutions and poolings). However, these operations also extract useless or even disturbing features. Attention mechanisms enable neural networks to discard information of no interest, having achieved the state-of-the-art performance. While a variety of attentions for CNNs have been proposed, current NAS methods have paid a little attention to them. In this study, we propose a novel NAS method that searches attentions as well as operations. We examined several patterns to arrange attentions and operations, and found that attentions work better when they have their own search space and follow operations. We demonstrate the superior performance of our method in experiments on CIFAR-10, CIFAR-100, and ImageNet datasets. The found architecture achieved lower classification error rates and required fewer parameters compared to those found by current NAS methods.

    Download PDF (999K)
  • Young-Woo KWON, Sung-Mun PARK, Joon-Young CHOI
    Article type: LETTER
    Subject area: Software System
    2021 Volume E104.D Issue 2 Pages 322-326
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    We propose a system time synchronization method between ARM-based embedded Linux systems. The master Linux with reference clock sends its own system time to the slave Linux via Transmission Control Protocol communication along with a general-purpose input/output (GPIO) signal, and then the slave Linux corrects its own system time by the difference between its own system time at receiving the GPIO signal and the received reference time. The synchronization performance is significantly improved by compensating for the GPIO signal detection latency and the system time acquisition and setting latencies in Linux. These latencies are precisely measured by exploiting the function of Cycle Counter register in ARM coprocessor. Extensive experiments are performed with two ARM-based embedded Linux systems, and the results demonstrate the validity and performance of the proposed synchronization method.

    Download PDF (629K)
  • Teruki HAYAKAWA, Masateru TSUNODA, Koji TODA, Keitaro NAKASAI, Amjed T ...
    Article type: LETTER
    Subject area: Software Engineering
    2021 Volume E104.D Issue 2 Pages 327-331
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    Various software fault prediction models have been proposed in the past twenty years. Many studies have compared and evaluated existing prediction approaches in order to identify the most effective ones. However, in most cases, such models and techniques provide varying results, and their outcomes do not result in best possible performance across different datasets. This is mainly due to the diverse nature of software development projects, and therefore, there is a risk that the selected models lead to inconsistent results across multiple datasets. In this work, we propose the use of bandit algorithms in cases where the accuracy of the models are inconsistent across multiple datasets. In the experiment discussed in this work, we used four conventional prediction models, tested on three different dataset, and then selected the best possible model dynamically by applying bandit algorithms. We then compared our results with those obtained using majority voting. As a result, Epsilon-greedy with ϵ=0.3 showed the best or second-best prediction performance compared with using only one prediction model and majority voting. Our results showed that bandit algorithms can provide promising outcomes when used in fault prediction.

    Download PDF (471K)
  • Giang-Truong NGUYEN, Van-Quyet NGUYEN, Van-Hau NGUYEN, Kyungbaek KIM
    Article type: LETTER
    Subject area: Dependable Computing
    2021 Volume E104.D Issue 2 Pages 332-336
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    In a smart home environment, sensors generate events whenever activities of residents are captured. However, due to some factors, abnormal events could be generated, which are technically reasonable but contradict to real-world activities. To detect abnormal events, a number of methods has been introduced, e.g., clustering-based or snapshot-based approaches. However, they have limitations to deal with complicated anomalies which occur with large number of events and blended within normal sensor readings. In this paper, we propose a novel method of detecting sensor anomalies under smart home environment by considering spatial correlation and dependable correlation between sensors. Initially, we pre-calculate these correlations of every pair of two sensors to discover their relations. Then, from periodic sensor readings, if it has any unmatched relations to the pre-computed ones, an anomaly is detected on the correlated sensor. Through extensive evaluations with real datasets, we show that the proposed method outperforms previous approaches with 20% improvement on detection rate and reasonably low false positive rate.

    Download PDF (401K)
  • Didik Dwi PRASETYA, Tsukasa HIRASHIMA, Yusuke HAYASHI
    Article type: LETTER
    Subject area: Educational Technology
    2021 Volume E104.D Issue 2 Pages 337-340
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    This study compared two extended concept mapping approaches and investigated the distribution of students' understanding and knowledge structure. The students in the experimental group used Extended Kit-Build (EKB), where a learner extends a concept map built by kit-building, and those in the control group utilized the Extended Scratch-Build (ESB), where a learner extends a concept map made by scratch-building. The results suggested that the experimental group had better achievements in both the original material and the additional material.

    Download PDF (478K)
  • Zhaolin LU, Ziyan ZHANG, Yi WANG, Liang DONG, Song LIANG
    Article type: LETTER
    Subject area: Image Processing and Video Processing
    2021 Volume E104.D Issue 2 Pages 341-345
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    This letter presents an image quality assessment (IQA) metric for scanning electron microscopy (SEM) images based on texture inpainting. Inspired by the observation that the texture information of SEM images is quite sensitive to distortions, a texture inpainting network is first trained to extract texture features. Then the weights of the trained texture inpainting network are transferred to the IQA network to help it learn an effective texture representation of the distorted image. Finally, supervised fine-tuning is conducted on the IQA network to predict the image quality score. Experimental results on the SEM image quality dataset demonstrate the advantages of the presented method.

    Download PDF (2387K)
  • Hengyong XIANG, Li ZHOU, Xiaohui BA, Jie CHEN
    Article type: LETTER
    Subject area: Image Recognition, Computer Vision
    2021 Volume E104.D Issue 2 Pages 346-349
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    The traditional RANSAC samples uniformly in the dataset which is not efficient in the task with rich prior information. This letter proposes GUISAC (Guided Sample Consensus), which samples with the guidance of various prior information. In image matching, GUISAC extracts seed points sets evenly on images based on various prior factors at first, then it incorporates seed points sets into the sampling subset with a growth function, and a new termination criterion is used to decide whether the current best hypothesis is good enough. Finally, experimental results show that the new method GUISAC has a great advantage in time-consuming than other similar RANSAC methods, and without loss of accuracy.

    Download PDF (453K)
  • Sanghoon KANG, Hanhoon PARK, Jong-Il PARK
    Article type: LETTER
    Subject area: Image Recognition, Computer Vision
    2021 Volume E104.D Issue 2 Pages 350-353
    Published: February 01, 2021
    Released on J-STAGE: February 01, 2021
    JOURNAL FREE ACCESS

    Image deformations caused by different steganographic methods are typically extremely small and highly similar, which makes their detection and identification to be a difficult task. Although recent steganalytic methods using deep learning have achieved high accuracy, they have been made to detect stego images to which specific steganographic methods have been applied. In this letter, a staganalytic method is proposed that uses hierarchical residual neural networks (ResNet), allowing detection (i.e. classification between stego and cover images) and identification of four spatial steganographic methods (i.e. LSB, PVD, WOW and S-UNIWARD). Experimental results show that using hierarchical ResNets achieves a classification rate of 79.71% in quinary classification, which is approximately 23% higher compared to using a plain convolutional neural network (CNN).

    Download PDF (716K)
feedback
Top