IEICE Transactions on Information and Systems
Online ISSN : 1745-1361
Print ISSN : 0916-8532
Volume E103.D , Issue 3
Showing 1-31 articles out of 31 articles from the selected issue
Special Section on Foundations of Computer Science- Frontiers of Theory of Computation and Algorithm -
  • Kohei HATANO
    2020 Volume E103.D Issue 3 Pages 480
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS
    Download PDF (107K)
  • Hiroshi FUJIWARA, Kei SHIBUSAWA, Kouki YAMAMOTO, Hiroaki YAMAMOTO
    Type: PAPER
    2020 Volume E103.D Issue 3 Pages 481-488
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    The multislope ski-rental problem is an online optimization problem that generalizes the classical ski-rental problem. The player is offered not only a buy and a rent options but also other options that charge both initial and per-time fees. The competitive ratio of the classical ski-rental problem is known to be 2. In contrast, the best known so far on the competitive ratio of the multislope ski-rental problem is an upper bound of 4 and a lower bound of 3.62. In this paper we consider a parametric version of the multislope ski-rental problem, regarding the number of options as a parameter. We prove an upper bound for the parametric problem which is strictly less than 4. Moreover, we give a simple recurrence relation that yields an equation having a lower bound value as its root.

    Download PDF (387K)
  • Yuichi SUDO, Fukuhito OOSHITA, Hirotsugu KAKUGAWA, Toshimitsu MASUZAWA
    Type: PAPER
    2020 Volume E103.D Issue 3 Pages 489-499
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    We consider the leader election problem in the population protocol model, which Angluin et al. proposed in 2004. A self-stabilizing leader election is impossible for complete graphs, arbitrary graphs, trees, lines, degree-bounded graphs, and so on unless the protocol knows the exact number of nodes. In 2009, to circumvent the impossibility, we introduced the concept of loose stabilization, which relaxes the closure requirement of self-stabilization. A loosely stabilizing protocol guarantees that starting from any initial configuration, a system reaches a safe configuration, and after that, the system keeps its specification (e.g., the unique leader) not forever but for a sufficiently long time (e.g., an exponentially long time with respect to the number of nodes). Our previous works presented two loosely stabilizing leader election protocols for arbitrary graphs; one uses agent identifiers, and the other uses random numbers to elect a unique leader. In this paper, we present a loosely stabilizing protocol that solves leader election on arbitrary graphs without agent identifiers or random numbers. Given upper bounds N and Δ of the number of nodes n and the maximum degree of nodes δ, respectively, the proposed protocol reaches a safe configuration within O(mn2d log n+mNΔ2 log N) expected steps and keeps the unique leader for Ω(NeN) expected steps, where m is the number of edges and d is the diameter of the graph.

    Download PDF (454K)
  • Chuzo IWAMOTO, Tatsuaki IBUSUKI
    Type: PAPER
    2020 Volume E103.D Issue 3 Pages 500-505
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

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

    Download PDF (789K)
  • Kazuyuki AMANO, Shin-ichi NAKANO
    Type: PAPER
    2020 Volume E103.D Issue 3 Pages 506-508
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Let P be a set of points on the plane, and d(p, q) be the distance between a pair of points p, q in P. For a point pP and a subset S ⊂ P with |S|≥3, the 2-dispersion cost, denoted by cost2(p, S), of p with respect to S is the sum of (1) the distance from p to the nearest point in S\setminus{p} and (2) the distance from p to the second nearest point in S\setminus{p}. The 2-dispersion cost cost2(S) of S ⊂ P with |S|≥3 is minp∈S{cost2(p, S)}. Given a set P of n points and an integer k we wish to compute k point subset S of P with maximum cost2(S). In this paper we give a simple 1/({4\sqrt{3}}) approximation algorithm for the problem.

    Download PDF (215K)
  • Takashi HARADA, Ken TANAKA, Kenji MIKAWA
    Type: PAPER
    2020 Volume E103.D Issue 3 Pages 509-515
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Recent years have witnessed a rapid increase in cyber-attacks through unauthorized accesses and DDoS attacks. Since packet classification is a fundamental technique to prevent such illegal communications, it has gained considerable attention. Packet classification is achieved with a linear search on a classification rule list that represents the packet classification policy. As such, a large number of rules can result in serious communication latency. To decrease this latency, the problem is formalized as optimal rule ordering (ORO). In most cases, this problem aims to find the order of rules that minimizes latency while satisfying the dependency relation of the rules, where rules ri and rj are dependent if there is a packet that matches both ri and rj and their actions applied to packets are different. However, there is a case in which although the ordering violates the dependency relation, the ordering satisfies the packet classification policy. Since such an ordering can decrease the latency compared to an ordering under the constraint of the dependency relation, we have introduced a new model, called relaxed optimal rule ordering (RORO). In general, it is difficult to determine whether an ordering satisfies the classification policy, even when it violates the dependency relation, because this problem contains unsatisfiability. However, using a zero-suppressed binary decision diagram (ZDD), we can determine it in a reasonable amount of time. In this paper, we present a simulated annealing method for RORO which interchanges rules by determining whether rules ri and rj can be interchanged in terms of policy violation using the ZDD. The experimental results show that our method decreases latency more than other heuristics.

    Download PDF (558K)
  • Ryohei BANNO, Kazuyuki SHUDO
    Type: PAPER
    2020 Volume E103.D Issue 3 Pages 516-525
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Skip Graph is a promising distributed data structure for large scale systems and known for its capability of range queries. Although several methods of routing range queries in Skip Graph have been proposed, they have inefficiencies such as a long path length or a large number of messages. In this paper, we propose a novel routing method for range queries named Split-Forward Broadcasting (SFB). SFB introduces a divide-and-conquer approach, enabling nodes to make full use of their routing tables to forward a range query. It brings about a shorter average path length than existing methods, as well as a smaller number of messages by avoiding duplicate transmission. We clarify the characteristics and effectiveness of SFB through both analytical and experimental comparisons. The results show that SFB can reduce the average path length roughly 30% or more compared with a state-of-the-art method.

    Download PDF (1392K)
  • Satoshi MATSUMOTO, Tomoyuki UCHIDA, Takayoshi SHOUDAI, Yusuke SUZUKI, ...
    Type: PAPER
    2020 Volume E103.D Issue 3 Pages 526-539
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    A regular pattern is a string consisting of constant symbols and distinct variable symbols. The language of a regular pattern is the set of all constant strings obtained by replacing all variable symbols in the regular pattern with non-empty strings. The present paper deals with the learning problem of languages of regular patterns within Angluin's query learning model, which is an established mathematical model of learning via queries in computational learning theory. The class of languages of regular patterns was known to be identifiable from one positive example using a polynomial number of membership queries, in the query learning model. In present paper, we show that the class of languages of regular patterns is identifiable from one positive example using a linear number of membership queries, with respect to the length of the positive example.

    Download PDF (1194K)
  • Ryoma SENDA, Yoshiaki TAKATA, Hiroyuki SEKI
    Type: PAPER
    2020 Volume E103.D Issue 3 Pages 540-548
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Register context-free grammars (RCFG) is an extension of context-free grammars to handle data values in a restricted way. In RCFG, a certain number of data values in registers are associated with each nonterminal symbol and a production rule has the guard condition, which checks the equality between the content of a register and an input data value. This paper starts with RCFG and introduces register type, which is a finite representation of a relation among the contents of registers. By using register type, the paper provides a translation of RCFG to a normal form and ϵ-removal from a given RCFG. We then define a generalized RCFG (GRCFG) where an arbitrary binary relation can be specified in the guard condition. Since the membership and emptiness problems are shown to be undecidable in general, we extend register type for GRCFG and introduce two properties of GRCFG, simulation and progress, which guarantee the decidability of these problems. As a corollary, these problems are shown to be EXPTIME-complete for GRCFG with a total order over a dense set.

    Download PDF (352K)
  • Keehang KWON
    Type: LETTER
    2020 Volume E103.D Issue 3 Pages 549-552
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Inspired by the efficient proof procedures discussed in Computability logic [3],[5],[6], we describe a heuristic proof procedure for first-order logic. This is a variant of Gentzen sequent system [2] and has the following features: (a) it views sequents as games between the machine and the environment, and (b) it views proofs as a winning strategy of the machine. From this game-based viewpoint, a poweful heuristic can be extracted and a fair degree of determinism in proof search can be obtained. This article proposes a new deductive system LKg with respect to first-order logic and proves its soundness and completeness.

    Download PDF (76K)
Regular Section
  • Yuanbang LI, Rong PENG, Bangchao WANG
    Type: SURVEY PAPER
    Subject area: Software Engineering
    2020 Volume E103.D Issue 3 Pages 553-565
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    A context-aware system always needs to adapt its behaviors according to context changes; therefore, modeling context-aware requirements is a complex task. With the increasing use of mobile computing, research on methods of modeling context-aware requirements have become increasingly important, and a large number of relevant studies have been conducted. However, no comprehensive analysis of the challenges and achievements has been performed. The methodology of systematic literature review was used in this survey, in which 68 reports were selected as primary studies. The challenges and methods to confront these challenges in context-aware requirement modeling are summarized. The main contributions of this work are: (1) four challenges and nine sub-challenges are identified; (2) eight kinds of methods in three categories are identified to address these challenges; (3) the extent to which these challenges have been solved is evaluated; and (4) directions for future research are elaborated.

    Download PDF (1900K)
  • Yoshiyuki MIHARA, Shuichi MIYAZAKI, Yasuo OKABE, Tetsuya YAMAGUCHI, Ma ...
    Type: PAPER
    Subject area: Fundamentals of Information Systems
    2020 Volume E103.D Issue 3 Pages 566-577
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    In this article, we propose a method to identify the link layer home network topology, motivated by applications to cost reduction of support centers. If the topology of home networks can be identified automatically and efficiently, it is easier for operators of support centers to identify fault points. We use MAC address forwarding tables (AFTs) which can be collected from network devices. There are a couple of existing methods for identifying a network topology using AFTs, but they are insufficient for our purpose; they are not applicable to some specific network topologies that are typical in home networks. The advantage of our method is that it can handle such topologies. We also implemented these three methods and compared their running times. The result showed that, despite its wide applicability, our method is the fastest among the three.

    Download PDF (1086K)
  • Jun IWAMOTO, Yuma KIKUTANI, Renyuan ZHANG, Yasuhiko NAKASHIMA
    Type: PAPER
    Subject area: Computer System
    2020 Volume E103.D Issue 3 Pages 578-589
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    A paradigm shift toward edge computing infrastructures that prioritize small footprint and scalable/easy-to-estimate performance is increasing. In this paper, we propose the following to improve the footprint and the scalability of systolic arrays: (1) column multithreading for reducing the number of physical units and maintaining the performance even for back-to-back floating-point accumulations; (2) a cascaded peer-to-peer AXI bus for a scalable multichip structure and an intra-chip parallel local memory bus for low latency; (3) multilevel loop control in any unit for reducing the startup overhead and adaptive operation shifting for efficient reuse of local memories. We designed a systolic array with a single column × 64 row configuration with Verilog HDL, evaluated the frequency and the performance on an FPGA attached to a ZYNQ system as an AXI slave device, and evaluated the area with a TSMC 28nm library and memory generator and identified the following: (1) the execution speed of a matrix multiplication/a convolution operation/a light-field depth extraction, whose size larger than the capacity of the local memory, is 6.3× / 9.2× / 6.6× compared with a similar systolic array (EMAX); (2) the estimated speed with a 4-chip configuration is 19.6× / 16.0× / 8.5×; (3) the size of a single-chip is 8.4 mm2 (0.31× of EMAX) and the basic performance per area is 2.4×.

    Download PDF (1786K)
  • Hisao OGATA, Tomoyoshi ISHIKAWA, Norichika MIYAMOTO, Tsutomu MATSUMOTO
    Type: PAPER
    Subject area: Dependable Computing
    2020 Volume E103.D Issue 3 Pages 590-601
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Recently, criminals frequently utilize logical attacks to Automated Teller Machines (ATMs) and financial institutes' (FIs') networks to steal cash. We proposed a security measure utilizing peripheral devices in an ATM for smart card transactions to prevent “unauthorized cash withdrawals” of logical attacks, and the fundamental framework as a generalized model of the measure in other paper. As the measure can prevent those logical attacks with tamper-proof hardware, it is quite difficult for criminals to compromise the measure. However, criminals can still carry out different types of logical attacks to ATMs, such as “unauthorized deposit”, to steal cash. In this paper, we propose a security measure utilizing peripheral devices to prevent unauthorized deposits with a smart card. The measure needs to protect multiple transaction sub-processes in a deposit transaction from multiple types of logical attacks and to be harmonized with existing ATM system/operations. A suitable implementation of the fundamental framework is required for the measure and such implementation design is confusing due to many items to be considered. Thus, the measure also provides an implementation model analysis of the fundamental framework to derive suitable implementation for each defense point in a deposit transaction. Two types of measure implementation are derived as the result of the analysis.

    Download PDF (3091K)
  • Rui CHEN, Ying TONG, Ruiyu LIANG
    Type: PAPER
    Subject area: Artificial Intelligence, Data Mining
    2020 Volume E103.D Issue 3 Pages 602-611
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Deep neural networks have achieved great success in visual tracking by learning a generic representation and leveraging large amounts of training data to improve performance. Most generic object trackers are trained from scratch online and do not benefit from a large number of videos available for offline training. We present a real-time generic object tracker capable of incorporating temporal information into its model, learning from many examples offline and quickly updating online. During the training process, the pre-trained weight of convolution layer is updated lagging behind, and the input video sequence length is gradually increased for fast convergence. Furthermore, only the hidden states in recurrent network are updated to guarantee the real-time tracking speed. The experimental results show that the proposed tracking method is capable of tracking objects at 150 fps with higher predicting overlap rate, and achieves more robustness in multiple benchmarks than state-of-the-art performance.

    Download PDF (1545K)
  • Chunting WAN, Dongyi CHEN, Juan YANG, Miao HUANG
    Type: PAPER
    Subject area: Human-computer Interaction
    2020 Volume E103.D Issue 3 Pages 612-620
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Real-time pulse rate (PR) monitoring based on photoplethysmography (PPG) has been drawn much attention in recent years. However, PPG signal detected under movement is easily affected by random noises, especially motion artifacts (MA), affecting the accuracy of PR estimation. In this paper, a parallel method structure is proposed, which effectively combines wavelet threshold denoising with recursive least squares (RLS) adaptive filtering to remove interference signals, and uses spectral peak tracking algorithm to estimate real-time PR. Furthermore, we propose a parallel structure RLS adaptive filtering to increase the amplitude of spectral peak associated with PR for PR estimation. This method is evaluated by using the PPG datasets of the 2015 IEEE Signal Processing Cup. Experimental results on the 12 training datasets during subjects' walking or running show that the average absolute error (AAE) is 1.08 beats per minute (BPM) and standard deviation (SD) is 1.45 BPM. In addition, the AAE of PR on the 10 testing datasets during subjects' fast running accompanied with wrist movements can reach 2.90 BPM. Furthermore, the results indicate that the proposed approach keeps high estimation accuracy of PPG signal even with strong MA.

    Download PDF (948K)
  • Yan LI, Zhijie CHU, Yizhong XIN
    Type: PAPER
    Subject area: Human-computer Interaction
    2020 Volume E103.D Issue 3 Pages 621-630
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Aiming at the complexity of posture recognition with Kinect, a method of posture recognition using distance characteristics is proposed. Firstly, depth image data was collected by Kinect, and three-dimensional coordinate information of 20 skeleton joints was obtained. Secondly, according to the contribution of joints to posture expression, 60 dimensional Kinect skeleton joint data was transformed into a vector of 24-dimensional distance characteristics which were normalized according to the human body structure. Thirdly, a static posture recognition method of the shortest distance and a dynamic posture recognition method of the minimum accumulative distance with dynamic time warping (DTW) were proposed. The experimental results showed that the recognition rates of static postures, non-cross-subject dynamic postures and cross-subject dynamic postures were 95.9%, 93.6% and 89.8% respectively. Finally, posture selection, Kinect placement, and comparisons with literatures were discussed, which provides a reference for Kinect based posture recognition technology and interaction design.

    Download PDF (1243K)
  • Keisuke IMOTO
    Type: PAPER
    Subject area: Speech and Hearing
    2020 Volume E103.D Issue 3 Pages 631-638
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    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.

    Download PDF (1340K)
  • Hiroki TAMARU, Yuki SAITO, Shinnosuke TAKAMICHI, Tomoki KORIYAMA, Hiro ...
    Type: PAPER
    Subject area: Speech and Hearing
    2020 Volume E103.D Issue 3 Pages 639-647
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    This paper proposes a generative moment matching network (GMMN)-based post-filtering method for providing inter-utterance pitch variation to singing voices and discusses its application to our developed mixing method called neural double-tracking (NDT). When a human singer sings and records the same song twice, there is a difference between the two recordings. The difference, which is called inter-utterance variation, enriches the performer's musical expression and the audience's experience. For example, it makes every concert special because it never recurs in exactly the same manner. Inter-utterance variation enables a mixing method called double-tracking (DT). With DT, the same phrase is recorded twice, then the two recordings are mixed to give richness to singing voices. However, in synthesized singing voices, which are commonly used to create music, there is no inter-utterance variation because the synthesis process is deterministic. There is also no inter-utterance variation when only one voice is recorded. Although there is a signal processing-based method called artificial DT (ADT) to layer singing voices, the signal processing results in unnatural sound artifacts. To solve these problems, we propose a post-filtering method for randomly modulating synthesized or natural singing voices as if the singer sang again. The post-filter built with our method models the inter-utterance pitch variation of human singing voices using a conditional GMMN. Evaluation results indicate that 1) the proposed method provides perceptible and natural inter-utterance variation to synthesized singing voices and that 2) our NDT exhibits higher double-trackedness than ADT when applied to both synthesized and natural singing voices.

    Download PDF (915K)
  • Xinyu ZHU, Jun ZHANG, Gengsheng CHEN
    Type: PAPER
    Subject area: Image Recognition, Computer Vision
    2020 Volume E103.D Issue 3 Pages 648-659
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Recent top-performing object detectors usually depend on a two-stage approach, which benefits from its region proposal and refining practice but suffers low detection speed. By contrast, one-stage approaches have the advantage of high efficiency while sacrifice their accuracies to some extent. In this paper, we propose a novel single-shot object detection network which inherits the merits of both. Motivated by the idea of semantic enrichment to the convolutional features within a typical deep detector, we propose two novel modules: 1) by modeling the semantic interactions between channels and the long-range dependencies between spatial positions, the self-attending module generates both channel and position attention, and enhance the original convolutional features in a self-guided manner; 2) leveraging the class-discriminative localization ability of classification-trained CNN, the semantic activating module learns a semantic meaningful convolutional response which augments low-level convolutional features with strong class-specific semantic information. The so called self-attending and semantic activating network (ASAN) achieves better accuracy than two-stage methods and is able to fulfil real-time processing. Comprehensive experiments on PASCAL VOC indicates that ASAN achieves state-of-the-art detection performance with high efficiency.

    Download PDF (3770K)
  • Yuki FUJIMURA, Motoharu SONOGASHIRA, Masaaki IIYAMA
    Type: PAPER
    Subject area: Image Recognition, Computer Vision
    2020 Volume E103.D Issue 3 Pages 660-673
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Three-dimensional (3D) reconstruction and scene depth estimation from 2-dimensional (2D) images are major tasks in computer vision. However, using conventional 3D reconstruction techniques gets challenging in participating media such as murky water, fog, or smoke. We have developed a method that uses a continuous-wave time-of-flight (ToF) camera to estimate an object region and depth in participating media simultaneously. The scattered light observed by the camera is saturated, so it does not depend on the scene depth. In addition, received signals bouncing off distant points are negligible due to light attenuation, and thus the observation of such a point contains only a scattering component. These phenomena enable us to estimate the scattering component in an object region from a background that only contains the scattering component. The problem is formulated as robust estimation where the object region is regarded as outliers, and it enables the simultaneous estimation of an object region and depth on the basis of an iteratively reweighted least squares (IRLS) optimization scheme. We demonstrate the effectiveness of the proposed method using captured images from a ToF camera in real foggy scenes and evaluate the applicability with synthesized data.

    Download PDF (3394K)
  • Johanes EFFENDI, Sakriani SAKTI, Katsuhito SUDOH, Satoshi NAKAMURA
    Type: PAPER
    Subject area: Natural Language Processing
    2020 Volume E103.D Issue 3 Pages 674-683
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Since a concept can be represented by different vocabularies, styles, and levels of detail, a translation task resembles a many-to-many mapping task from a distribution of sentences in the source language into a distribution of sentences in the target language. This viewpoint, however, is not fully implemented in current neural machine translation (NMT), which is one-to-one sentence mapping. In this study, we represent the distribution itself as multiple paraphrase sentences, which will enrich the model context understanding and trigger it to produce numerous hypotheses. We use a visually grounded paraphrase (VGP), which uses images as a constraint of the concept in paraphrasing, to guarantee that the created paraphrases are within the intended distribution. In this way, our method can also be considered as incorporating image information into NMT without using the image itself. We implement this idea by crowdsourcing a paraphrasing corpus that realizes VGP and construct neural paraphrasing that behaves as expert models in a NMT. Our experimental results reveal that our proposed VGP augmentation strategies showed improvement against a vanilla NMT baseline.

    Download PDF (730K)
  • Mingming YANG, Min ZHANG, Kehai CHEN, Rui WANG, Tiejun ZHAO
    Type: PAPER
    Subject area: Natural Language Processing
    2020 Volume E103.D Issue 3 Pages 684-694
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Attention mechanism, which selectively focuses on source-side information to learn a context vector for generating target words, has been shown to be an effective method for neural machine translation (NMT). In fact, generating target words depends on not only the source-side information but also the target-side information. Although the vanilla NMT can acquire target-side information implicitly by recurrent neural networks (RNN), RNN cannot adequately capture the global relationship between target-side words. To solve this problem, this paper proposes a novel target-attention approach to capture this information, thus enhancing target word predictions in NMT. Specifically, we propose three variants of target-attention model to directly obtain the global relationship among target words: 1) a forward target-attention model that uses a target attention mechanism to incorporate previous historical target words into the prediction of the current target word; 2) a reverse target-attention model that adopts a reverse RNN model to obtain the entire reverse target words information, and then to combine with source context information to generate target sequence; 3) a bidirectional target-attention model that combines the forward target-attention model and reverse target-attention model together, which can make full use of target words to further improve the performance of NMT. Our methods can be integrated into both RNN based NMT and self-attention based NMT, and help NMT get global target-side information to improve translation performance. Experiments on the NIST Chinese-to-English and the WMT English-to-German translation tasks show that the proposed models achieve significant improvements over state-of-the-art baselines.

    Download PDF (1057K)
  • Huan TANG, Ning CHEN
    Type: PAPER
    Subject area: Music Information Processing
    2020 Volume E103.D Issue 3 Pages 695-701
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Music classification has been inspired by the remarkable success of deep learning. To enhance efficiency and ensure high performance at the same time, a hybrid architecture that combines deep learning and Broad Learning (BL) is proposed for music classification tasks. At the feature extraction stage, the Random CNN (RCNN) is adopted to analyze the Mel-spectrogram of the input music sound. Compared with conventional CNN, RCNN has more flexible structure to adapt to the variance contained in different types of music. At the prediction stage, the BL technique is introduced to enhance the prediction accuracy and reduce the training time as well. Experimental results on three benchmark datasets (GTZAN, Ballroom, and Emotion) demonstrate that: i) The proposed scheme achieves higher classification accuracy than the deep learning based one, which combines CNN and LSTM, on all three benchmark datasets. ii) Both RCNN and BL contribute to the performance improvement of the proposed scheme. iii) The introduction of BL also helps to enhance the prediction efficiency of the proposed scheme.

    Download PDF (2556K)
  • Nao IGAWA, Tomoyuki YOKOGAWA, Sousuke AMASAKI, Masafumi KONDO, Yoichir ...
    Type: LETTER
    Subject area: Software System
    2020 Volume E103.D Issue 3 Pages 702-705
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Safety critical systems are often modeled using Time Petri Nets (TPN) for analyzing their reliability with formal verification methods. This paper proposed an efficient verification method for TPN introducing bounded model checking based on satisfiability solving. The proposed method expresses time constraints of TPN by Difference Logic (DL) and uses SMT solvers for verification. Its effectiveness was also demonstrated with an experiment.

    Download PDF (103K)
  • Ji-Hoon SHIN, Tae-Hwan KIM
    Type: LETTER
    Subject area: Software System
    2020 Volume E103.D Issue 3 Pages 706-710
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    This letter presents a novel technique to achieve a fast inference of the binarized convolutional neural networks (BCNN). The proposed technique modifies the structure of the constituent blocks of the BCNN model so that the input elements for the max-pooling operation are binary. In this structure, if any of the input elements is +1, the result of the pooling can be produced immediately; the proposed technique eliminates such computations that are involved to obtain the remaining input elements, so as to reduce the inference time effectively. The proposed technique reduces the inference time by up to 34.11%, while maintaining the classification accuracy.

    Download PDF (334K)
  • Xinxin HU, Caixia LIU, Shuxin LIU, Xiaotao CHENG
    Type: LETTER
    Subject area: Information Network
    2020 Volume E103.D Issue 3 Pages 711-713
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    More and more attacks are found due to the insecure channel between different network domains in legacy mobile network. In this letter, we discover an attack exploiting SUCI to track a subscriber in 5G network, which is directly caused by the insecure air channel. To cover this issue, a secure authentication scheme is proposed utilizing the existing PKI mechanism. Not only dose our protocol ensure the authentication signalling security in the channel between UE and SN, but also SN and HN. Further, formal methods are adopted to prove the security of the proposed protocol.

    Download PDF (499K)
  • Yoonhee KIM, Deokgyu YUN, Hannah LEE, Seung Ho CHOI
    Type: LETTER
    Subject area: Speech and Hearing
    2020 Volume E103.D Issue 3 Pages 714-715
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    This paper presents a deep learning-based non-intrusive speech intelligibility estimation method using bottleneck features of autoencoder. The conventional standard non-intrusive speech intelligibility estimation method, P.563, lacks intelligibility estimation performance in various noise environments. We propose a more accurate speech intelligibility estimation method based on long-short term memory (LSTM) neural network whose input and output are an autoencoder bottleneck features and a short-time objective intelligence (STOI) score, respectively, where STOI is a standard tool for measuring intrusive speech intelligibility with reference speech signals. We showed that the proposed method has a superior performance by comparing with the conventional standard P.563 and mel-frequency cepstral coefficient (MFCC) feature-based intelligibility estimation methods for speech signals in various noise environments.

    Download PDF (178K)
  • Bing LUO, Junkai XIONG, Li XU, Zheng PEI
    Type: LETTER
    Subject area: Image Recognition, Computer Vision
    2020 Volume E103.D Issue 3 Pages 716-719
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    This letter proposes a new superpixel segmentation algorithm based on global similarity and contour region transformation. The basic idea is that pixels surrounded by the same contour are more likely to belong to the same object region, which could be easily clustered into the same superpixel. To this end, we use contour scanning to estimate the global similarity between pixels and corresponded centers. In addition, we introduce pixel's gradient information of contour transform map to enhance the pixel's global similarity to overcome the missing contours in blurred region. Benefited from our global similarity, the proposed method could adherent with blurred and low contrast boundaries. A large number of experiments on BSDS500 and VOC2012 datasets show that the proposed algorithm performs better than traditional SLIC.

    Download PDF (2403K)
  • Weiwei JIANG, Le ZHANG
    Type: LETTER
    Subject area: Image Recognition, Computer Vision
    2020 Volume E103.D Issue 3 Pages 720-723
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    Handwritten numeral recognition is a classical and important task in the computer vision area. We propose two novel deep learning models for this task, which combine the edge extraction method and Siamese/Triple network structures. We evaluate the models on seven handwritten numeral datasets and the results demonstrate both the simplicity and effectiveness of our models, comparing to baseline methods.

    Download PDF (433K)
  • Toru HIRAOKA
    Type: LETTER
    Subject area: Computer Graphics
    2020 Volume E103.D Issue 3 Pages 724-727
    Published: March 01, 2020
    Released: March 01, 2020
    JOURNALS FREE ACCESS

    We propose a non-photorealistic rendering method for generating edge-preserving bubble images from gray-scale photographic images. Bubble images are non-photorealistic images embedded in many bubbles, and edge-preserving bubble images are bubble images where edges in photographic images are preserved. The proposed method is executed by an iterative processing using absolute difference in window. The proposed method has features that processing is simple and fast. To validate the effectiveness of the proposed method, experiments using various photographic images are conducted. Results show that the proposed method can generate edge-preserving bubble images by preserving the edges of photographic images and the processing speed is high.

    Download PDF (2211K)
feedback
Top