The phenomenon where a speaker mixes two or more languages within the same conversation is called code-switching (CS). Handling CS is challenging for automatic speech recognition (ASR) and text-to-speech (TTS) because it requires coping with multilingual input. Although CS text or speech may be found in social media, the datasets of CS speech and corresponding CS transcriptions are hard to obtain even though they are required for supervised training. This work adopts a deep learning-based machine speech chain to train CS ASR and CS TTS with each other with semisupervised learning. After supervised learning with monolingual data, the machine speech chain is then carried out with unsupervised learning of either the CS text or speech. The results show that the machine speech chain trains ASR and TTS together and improves performance without requiring the pair of CS speech and corresponding CS text. We also integrate language embedding and language identification into the CS machine speech chain in order to handle CS better by giving language information. We demonstrate that our proposed approach can improve the performance on both a single CS language pair and multiple CS language pairs, including the unknown CS excluded from training data.

In this study, we propose a method to estimate body composition-related health indicators (e.g., ratio of body fat, body water, and muscle, etc.) using video-based gait analysis. This method is more efficient than individual measurement using a conventional body composition meter. Specifically, we designed a deep-learning framework with a convolutional neural network (CNN), where the input is a gait energy image (GEI) and the output consists of the health indicators. Although a vast amount of training data is typically required to train network parameters, it is unfeasible to collect sufficient ground-truth data, i.e., pairs consisting of the gait video and the health indicators measured using a body composition meter for each subject. We therefore use a two-step approach to exploit an auxiliary gait dataset that contains a large number of subjects but lacks the ground-truth health indicators. At the first step, we pre-train a backbone network using the auxiliary dataset to output gait primitives such as arm swing, stride, the degree of stoop, and the body width — considered to be relevant to the health indicators. At the second step, we add some layers to the backbone network and fine-tune the entire network to output the health indicators even with a limited number of ground-truth data points of the health indicators. Experimental results show that the proposed method outperforms the other methods when training from scratch as well as when using an auto-encoder-based pre-training and fine-tuning approach; it achieves relatively high estimation accuracy for the body composition-related health indicators except for body fat-relevant ones.

Rapid building damage identification plays a vital role in rescue operations when disasters strike, especially when rescue resources are limited. In the past years, supervised machine learning has made considerable progress in building damage identification. However, the usage of supervised machine learning remains challenging due to the following facts: 1) the massive samples from the current damage imagery are difficult to be labeled and thus cannot satisfy the training requirement of deep learning, and 2) the similarity between partially damaged and undamaged buildings is high, hindering accurate classification. Leveraging the abundant samples of auxiliary domains, domain adaptation aims to transfer a classifier trained by historical damage imagery to the current task. However, traditional domain adaptation approaches do not fully consider the category-specific information during feature adaptation, which might cause negative transfer. To address this issue, we propose a novel domain adaptation framework that individually aligns each category of the target domain to that of the source domain. Our method combines the variational autoencoder (VAE) and the Gaussian mixture model (GMM). First, the GMM is established to characterize the distribution of the source domain. Then, the VAE is constructed to extract the feature of the target domain. Finally, the Kullback-Leibler (KL) divergence is minimized to force the feature of the target domain to observe the GMM of the source domain. Two damage detection tasks using post-earthquake and post-hurricane imageries are utilized to verify the effectiveness of our method. Experiments show that the proposed method obtains improvements of 4.4% and 9.5%, respectively, compared with the conventional method.

Tourist satisfaction plays a very important role in the development of local community tourism. For the development of tourist destinations in local communities, it is important to measure, maintain, and improve tourist destination royalties over the medium to long term. It has been proven that improving tourist satisfaction is a major factor in improving tourist destination royalties. Therefore, to improve tourist satisfaction in local communities, we identified multiple clusters of sightseeing spots and determined that the satisfaction of tourists can be increased based on these clusters of sightseeing spots. Our discovery flow can be summarized as follows. First, we extracted tourism keywords from guidebooks on sightseeing spots. We then constructed a complex network of tourists and sightseeing spots based on the data collected from experiments conducted in Kyoto. Next, we added the corresponding tourism keywords to each sightseeing spot. Finally, by analyzing network motifs, we successfully discovered multiple clusters of sightseeing spots that could be used to improve tourist satisfaction.

In this paper, a stochasic geometry analysis of the inversely proportional setting (IPS) of carrier sense threshold (CST) and transmission power for densely deployed wireless local area networks (WLANs) is presented. In densely deployed WLANs, CST adjustment is a crucial technology to enhance spatial reuse, but it can starve surrounding transmitters due to an asymmetric carrier sensing relationship. In order for the carrier sensing relationship to be symmetric, the IPS of the CST and transmission power is a promising approach, i.e., each transmitter jointly adjusts its CST and transmission power in order for their product to be equal to those of others. This setting is used for spatial reuse in IEEE 802.11ax. By assuming that the set of potential transmitters follows a Poisson point process, the impact of the IPS on throughput is formulated based on stochastic geometry in two scenarios: an adjustment at a single transmitter and an identical adjustment at all transmitters. The asymptotic expression of the throughput in dense WLANs is derived and an explicit solution of the optimal CST is achieved as a function of the number of neighboring potential transmitters and signal-to-interference power ratio using approximations. This solution was confirmed through numerical results, where the explicit solution achieved throughput penalties of less than 8% relative to the numerically evaluated optimal solution.

Service composition optimization is a classic NP-hard problem. How to quickly select high-quality services that meet user needs from a large number of candidate services is a hot topic in cloud service composition research. An efficient second-order beetle swarm optimization is proposed with a global search ability to solve the problem of cloud service composition optimization in this study. First, the beetle antennae search algorithm is introduced into the modified particle swarm optimization algorithm, initialize the population bying using a chaotic sequence, and the modified nonlinear dynamic trigonometric learning factors are adopted to control the expanding capacity of particles and global convergence capability. Second, modified secondary oscillation factors are incorporated, increasing the search precision of the algorithm and global searching ability. An adaptive step adjustment is utilized to improve the stability of the algorithm. Experimental results founded on a real data set indicated that the proposed global optimization algorithm can solve web service composition optimization problems in a cloud environment. It exhibits excellent global searching ability, has comparatively fast convergence speed, favorable stability, and requires less time cost.

In this paper, the world's first experimental evaluation of the Wi-SUN Japan Utility Telemetering Association (JUTA) profile-compliant feathery receiver-initiated transmission (JUTA F-RIT) protocol is conducted. Firstly, the transmission success rate in an interference environment is evaluated by theoretical analysis and computer simulations. The analysis is derived from the interference model focusing on the carrier sense. The analysis and simulation results agree as regards the transmission success rate of the JUTA F-RIT protocol. Secondly, we develop the dongle-type prototype that hosts the JUTA F-RIT protocol. Measurement results in a cochannel interference environment show that the transmission success rate at the lower MAC layer is around 94% when the number of terminals is 20. When the waiting time for the establishment of the communication link can be extended to exceed 10 s, the JUTA F-RIT protocol can achieve the transmission success rate of over 90% without the re-establishment of the communication link and re-transmission of data frames. Moreover, the experimental results are examined from two viewpoints of the performance of the frame transmissions and the timeout incident, and the feature of the JUTA F-RIT protocol are discussed.

Research on wireless power transmission technology is being actively conducted, and studies on spatial transmission methods such as SSPS are currently underway for applications such as power transfer to the upper part of steel towers and power transfer to flying objects such as drones. To enable such applications, it is necessary to examine the configuration of the power-transfer and power-receiving antennas and to improve the RF-DC conversion efficiency (hereinafter referred to as conversion efficiency) of the rectifier circuit on the power-receiving antenna. To improve the conversion efficiency, various methods that utilize full-wave rectification rather than half-wave rectification have been proposed. However, these come with problems such as a complicated circuit structure, the need for additional capacitors, the selection of components at high frequencies, and a reduction in mounting yield. In this paper, we propose a method to improve the conversion efficiency by loading a high-impedance microstrip line as a feedback line in part of the rectifier circuit. We analyzed a class-F rectifier circuit using circuit analysis software and found that the conversion efficiency of the conventional configuration was 54.2%, but the proposed configuration was 69.3%. We also analyzed a measuring circuit made with a discrete configuration in the 5.8-GHz band and found that the conversion efficiency was 74.7% at 24dBm input.

Home Energy Management Systems (HEMS) contain devices of multiple manufacturers. Also, a large number of groups of devices must be managed according to several clustering situations. Hence, since it is necessary to establish a common secret group key among group members, the group key management scheme of IEEE 802.21 is used. However, no security verification result by formal methods is known. In this paper, we give the first formal verification result of secrecy and authenticity of the group key management scheme of IEEE 802.21 against insider and outsider attacks using ProVerif, which is an automatic verification tool for cryptographic protocols. As a result, we clarify that a spoofing attack by an insider and a replay attack by an outsider are found for the basic scheme, but these attacks can be prevented by using the scheme with the digital signature option.

Visual sentiment analysis has a lot of applications, including image captioning, opinion mining, and advertisement; however, it is still a difficult problem and existing algorithms cannot produce satisfactory results. One of the difficulties in classifying images into emotions is that visual sentiments are evoked by different types of information - visual and semantic information where visual information includes colors or textures, and semantic information includes types of objects evoking emotions and/or their combinations. In contrast to the existing methods that use only visual information, this paper shows a novel algorithm for image emotion recognition that uses both information simultaneously. For semantic features, we introduce an object vector and a word vector. The object vector is created by an object detection method and reflects existing objects in an image. The word vector is created by transforming the names of detected objects through a word embedding model. This vector will be similar among objects that are semantically similar. These semantic features and a visual feature made by a fine-tuned convolutional neural network (CNN) are concatenated. We perform the classification by the concatenated feature vector. Extensive evaluation experiments using emotional image datasets show that our method achieves the best accuracy except for one dataset against other existing methods. The improvement in accuracy of our method from existing methods is 4.54% at the highest.

Pedestrian detection is an essential but challenging task in computer vision, especially in crowded scenes due to heavy intra-class occlusion. In human visual system, head information can be used to locate pedestrian in a crowd because it is more stable and less likely to be occluded. Inspired by this clue, we propose a dual-task detector which detects head and human body simultaneously. Concretely, we estimate human body candidates from head regions with statistical head-body ratio. A head-body alignment map is proposed to perform relational learning between human bodies and heads based on their inherent correlation. We leverage the head information as a strict detection criterion to suppress common false positives of pedestrian detection via a novel pull-push loss. We validate the effectiveness of the proposed method on the CrowdHuman and CityPersons benchmarks. Experimental results demonstrate that the proposed method achieves impressive performance in detecting heavy-occluded pedestrians with little additional computation cost.

This paper presents linearization technologies for high efficiency power amplifiers of cellular base stations. These technologies are important to actualizing highly efficient power amplifiers that reduce power consumption of the base station equipment and to achieving a sufficient non-linear distortion compensation level. It is well known that it is very difficult for a power amplifier using linearization technologies to achieve simultaneously high efficiency and a sufficient non-linear distortion compensation level. This paper presents two approaches toward addressing this technical issue. The first approach is a feed-forward power amplifier using the Doherty amplifier as the main amplifier. The second approach is a digital predistortion linearizer that compensates for frequency dependent intermodulation distortion components. Experimental results validate these approaches as effective for providing power amplification for base stations.

The recent development of deep learning-based generative models has sharply intensified the interest in data synthesis and its applications. Data synthesis takes on an added importance especially for some pattern recognition tasks in which some classes of data are rare and difficult to collect. In an iris dataset, for instance, the minority class samples include images of eyes with glasses, oversized or undersized pupils, misaligned iris locations, and iris occluded or contaminated by eyelids, eyelashes, or lighting reflections. Such class-imbalanced datasets often result in biased classification performance. Generative adversarial networks (GANs) are one of the most promising frameworks that learn to generate synthetic data through a two-player minimax game between a generator and a discriminator. In this paper, we utilized the state-of-the-art conditional Wasserstein generative adversarial network with gradient penalty (CWGAN-GP) for generating the minority class of iris images which saves huge amount of cost of human labors for rare data collection. With our model, the researcher can generate as many iris images of rare cases as they want and it helps to develop any deep learning algorithm whenever large size of dataset is needed.

Iterative block decision feedback equalization with hard-decision feedback (HD-IBDFE) was proposed for single-carrier transmission with frequency-domain equalization (SC-FDE). The detection performance hinges upon not only error propagation, but also the accuracy of estimating the parameters used to re-compute the equalizer coefficients at each iteration. In this paper, we use the erasure zone (EZ) to de-emphasize the feedback values when the hard decisions are not reliable. EZ use also enables a more accurate, and yet computationally more efficient, parameter estimation method than HD-IBDFE. We show that the resulting equalizer coefficients share the same mathematical form as that of the HD-IBDFE, thereby preserving the merit of not requiring matrix inverse operations in calculating the equalizer coefficients. Simulations show that, by using the EZ and the proposed parameter estimation method, a significant performance improvement over the conventional HD-IBDFE can be achieved, but with lower complexity.

In order to enhance the fifth generation (5G) mobile communication system further toward 5G Evolution, high bit-rate transmission using high SHF bands (28GHz or EHF bands) should be more stable even in high-mobility environments such as high speed trains. Of particular importance, dynamic changes in the beam direction and the larger Doppler frequency shift can degrade transmission performances in such high frequency bands. Thus, we conduct the world's first 28 GHz-band 5G experimental trial on an actual Shinkansen running at a speed of 283km/h in Japan. This paper introduces the 28GHz-band experimental system used in the 5G experimental trial using the Shinkansen, and then it presents the experimental configuration in which three base stations (BSs) are deployed along the Tokaido Shinkansen railway and a mobile station is located in the train. In addition, transmission performances measured in this ultra high-mobility environment, show that a peak throughput of exceeding 1.0Gbps and successful consecutive BS connection among the three BSs.

This letter reports on the effectiveness of applying the K-singular value decomposition (SVD) dictionary learning to the electroencephalogram (EEG) compressed sensing framework with outlier detection and independent component analysis. Using the K-SVD dictionary matrix with our design parameter optimization, for example, at compression ratio of four, we improved the normalized mean square error value by 31.4% compared with that of the discrete cosine transform dictionary for CHB-MIT Scalp EEG Database.

In this paper, we address the problem of detector design in severely frequency-selective channels for spatial multiplexing systems that adopt filter bank multicarrier based on offset quadrature amplitude modulation (FBMC/OQAM) as the communication waveforms. We consider decision feedback equalizers (DFEs) that use multiple feedback filters to jointly cancel the post-cursor components of inter-symbol interference, inter-antenna interference, and, in some configuration, inter-subchannel interference. By exploiting the special structures of the correlation matrix and the staggered property of the FBMC/OQAM signals, we obtain an efficient method of computing the DFE coefficients that requires a smaller number of multiplications than the linear equalizer (LE) and conventional DFE do. The simulation results show that the proposed detectors considerably outperform the LE and conventional DFE at moderate-to-high signal-to-noise ratios.

Data parallelism is the dominant method used to train deep learning (DL) models on High-Performance Computing systems such as large-scale GPU clusters. When training a DL model on a large number of nodes, inter-node communication becomes bottle-neck due to its relatively higher latency and lower link bandwidth (than intra-node communication). Although some communication techniques have been proposed to cope with this problem, all of these approaches target to deal with the large message size issue while diminishing the effect of the limitation of the inter-node network. In this study, we investigate the benefit of increasing inter-node link bandwidth by using hybrid switching systems, i.e., Electrical Packet Switching and Optical Circuit Switching. We found that the typical data-transfer of synchronous data-parallelism training is long-lived and rarely changed that can be speed-up with optical switching. Simulation results on the Simgrid simulator show that our approach speed-up the training time of deep learning applications, especially in a large-scale manner.

In this letter, we investigate tight analytical and asymptotic upper bounds for bit error rate (BER) of constitutional codes over exponentially correlated Nakagami-m fading channels. Specifically, we derive the BER expression depending on an exact closed-form formula for pairwise error event probabilities (PEEP). Moreover, the corresponding asymptotic analysis in high signal-to-noise ratio (SNR) regime is also explored, which is verified via numerical results. This allows us to have explicit insights on the achievable coding gain and diversity order.

Capsules are fundamental informative units that are introduced into capsule networks to manipulate the hierarchical presentation of patterns. The part-hole relationship of an entity is learned through capsule layers, using a routing-by-agreement mechanism that is approximated by a voting procedure. Nevertheless, existing routing methods are computationally inefficient. We address this issue by proposing a novel routing mechanism, namely “shortcut routing”, that directly learns to activate global capsules from local capsules. In our method, the number of operations in the routing procedure is reduced by omitting the capsules in intermediate layers, resulting in lighter routing. To further address the computational problem, we investigate an attention-based approach, and propose fuzzy coefficients, which have been found to be efficient than mixture coefficients from EM routing. Our method achieves on-par classification results on the Mnist (99.52%), smallnorb (93.91%), and affNist (89.02%) datasets. Compared to EM routing, our fuzzy-based and attention-based routing methods attain reductions of 1.42 and 2.5 in terms of the number of calculations.