Web-based social engineering (SE) attacks manipulate users to perform specific actions, such as downloading malware and exposing personal information. Aiming to effectively lure users, some SE attacks, which we call multi-step SE attacks, constitute a sequence of web pages starting from a landing page and require browser interactions at each web page. Also, different browser interactions executed on a web page often branch to multiple sequences to redirect users to different SE attacks. Although common systems analyze only landing pages or conduct browser interactions limited to a specific attack, little effort has been made to follow such sequences of web pages to collect multi-step SE attacks. We propose STRAYSHEEP, a system to automatically crawl a sequence of web pages and detect diverse multi-step SE attacks. We evaluate the effectiveness of STRAYSHEEP's three modules (landing-page-collection, web-crawling, and SE-detection) in terms of the rate of collected landing pages leading to SE attacks, efficiency of web crawling to reach more SE attacks, and accuracy in detecting the attacks. Our experimental results indicate that STRAYSHEEP can lead to 20% more SE attacks than Alexa top sites and search results of trend words, crawl five times more efficiently than a simple crawling module, and detect SE attacks with 95.5% accuracy. We demonstrate that STRAYSHEEP can collect various SE attacks, not limited to a specific attack. We also clarify attackers' techniques for tricking users and browser interactions, redirecting users to attacks.

Artificial intelligence (AI), especially deep learning (DL), has been remarkable and applied to various industries. However, adversarial examples (AE), which add small perturbations to input data of deep neural networks (DNNs) for misclassification, are attracting attention. In this paper, we propose a novel black-box attack to craft AE using only processing time which is side-channel information of DNNs, without using training data, model architecture and parameters, substitute models or output probability. While, several existing black-box attacks use output probability, our attack exploits a relationship between the number of activated nodes and the processing time of DNNs. The perturbations for AE are decided by the differential processing time according to input data in our attack. We show experimental results in which our attack's AE increase the number of activated nodes and cause misclassification to one of the incorrect labels effectively. In addition, the experimental results highlight that our attack can evade gradient masking countermeasures which mask output probability to prevent crafting AE against several black-box attacks.

Dense deployments of wireless local area network (WLAN) access points (APs) are accelerating to accommodate the massive wireless traffic from various mobile devices. The AP densification improves the received power at mobile devices; however, total throughput in a target area is saturated by inter-cell interference (ICI) because of the limited number of frequency channels available for WLANs. To substantially mitigate ICI, we developed and described a distributed smart antenna system (D-SAS) proposed for dense WLAN AP deployment in this paper. We also describe a system configuration based on our D-SAS approach. In this approach, the distributed antennas externally attached to each AP can be switched so as to make the transmit power match the mobile device's conditions (received power and packet type). The gains obtained by the antenna switching effectively minimize the transmission power required of each AP. We also describe experimental measurements taken in a stadium using a system prototype, the results show that D-SAS offers double the total throughput attained by a centralized smart antenna system (C-SAS).

Multimodal embedding is a crucial research topic for cross-modal understanding, data mining, and translation. Many studies have attempted to extract representations from given entities and align them in a shared embedding space. However, because entities in different modalities exhibit different abstraction levels and modality-specific information, it is insufficient to embed related entities close to each other. In this study, we propose the Target-Oriented Deformation Network (TOD-Net), a novel module that continuously deforms the embedding space into a new space under a given condition, thereby providing conditional similarities between entities. Unlike methods based on cross-modal attention applied to words and cropped images, TOD-Net is a post-process applied to the embedding space learned by existing embedding systems and improves their performances of retrieval. In particular, when combined with cutting-edge models, TOD-Net gains the state-of-the-art image-caption retrieval model associated with the MS COCO and Flickr30k datasets. Qualitative analysis reveals that TOD-Net successfully emphasizes entity-specific concepts and retrieves diverse targets via handling higher levels of diversity than existing models.

A novel shuffle converter by using 3D waveguide of MCF (multi-core fiber)/SMF (single mode fiber) ribbon fan-in fan-out configuration towards over 1,000 port count optical matrix switch has been proposed. The shuffle converter enables to avoid waveguide crossing section in the optical matrix switch configuration, and the principle device showed sufficient crosstalk of less than -54.2 dB, and insertion loss of 2.1 dB successfully.

This paper proposes an encryption-then-compression (EtC) system-friendly data hiding scheme for images, where an EtC system compresses images after they are encrypted. The EtC system divides an image into non-overlapping blocks and applies four block-based processes independently and randomly to the image for visual encryption of the image. The proposed scheme hides data to a plain, i.e., unencrypted image and the scheme can take hidden data out from the image encrypted by the EtC system. Furthermore, the scheme serves reversible data hiding, so it can perfectly recover the unmarked image from the marked image whereas the scheme once distorts unmarked image for hiding data to the image. The proposed scheme copes with the three of four processes in the EtC system, namely, block permutation, rotation/flipping of blocks, and inverting brightness in blocks, whereas the conventional schemes for the system do not cope with the last one. In addition, these conventional schemes have to identify the encrypted image so that image-dependent side information can be used to extract embedded data and to restore the unmarked image, but the proposed scheme does not need such identification. Moreover, whereas the data hiding process must know the block size of encryption in conventional schemes, the proposed scheme needs no prior knowledge of the block size for encryption. Experimental results show the effectiveness of the proposed scheme.

Ontology describes concepts and relations in a specific domain-knowledge that are important for knowledge representation and knowledge sharing. In the past few years, several tools have been introduced for ontology modeling and editing. To design and develop an ontology is one of the challenge tasks and its challenges are quite similar to software development as it requires many collaborative activities from many stakeholders (e.g. domain experts, knowledge engineers, application users, etc.) through the development cycle. Most of the existing tools do not provide collaborative feature to support stakeholders to collaborate work more effectively. In addition, there are lacking of standard process adoption for ontology development task. Thus, in this work, we incorporated ontology development process into Scrum process as used for process standard in software engineering. Based on Scrum, we can perform standard agile development of ontology that can reduce the development cycle as well as it can be responding to any changes better and faster. To support this idea, we proposed a Scrum Ontology Development Framework, which is an online collaborative framework for agile ontology design and development. Each ontology development process based on Scrum model will be supported by different services in our framework, aiming to promote collaborative activities among different roles of stakeholders. In addition to services such as ontology visualized modeling and editing, we also provide three more important features such as 1) concept/relation misunderstanding diagnosis, 2) cross-domain concept detection and 3) concept classification. All these features allow stakeholders to share their understanding and collaboratively discuss to improve quality of domain ontologies through a community consensus.

Location and feature representation of object's parts play key roles in fine-grained visual recognition. To promote the final recognition accuracy without any bounding boxes/part annotations, many studies adopt object location networks to propose bounding boxes/part annotations with only category labels, and then crop the images into partial images to help the classification network make the final decision. In our work, to propose more informative partial images and effectively extract discriminative features from the original and partial images, we propose a two-stage approach that can fuse the original features and partial features by evaluating and ranking the information of partial images. Experimental results show that our proposed approach achieves excellent performance on two benchmark datasets, which demonstrates its effectiveness.

A robust adaptive beamforming algorithm is proposed based on the precise interference-plus-noise covariance matrix reconstruction and steering vector estimation of the desired signal, even existing large gain-phase errors. Firstly, the model of array mismatches is proposed with the first-order Taylor series expansion. Then, an iterative method is designed to jointly estimate calibration coefficients and steering vectors of the desired signal and interferences. Next, the powers of interferences and noise are estimated by solving a quadratic optimization question with the derived closed-form solution. At last, the actual interference-plus-noise covariance matrix can be reconstructed as a weighted sum of the steering vectors and the corresponding powers. Simulation results demonstrate the effectiveness and advancement of the proposed method.

In this paper, a balance operation Transimpedance Amplifier (TIA) with low-noise has been implemented for optical receivers in 130 nm SiGe BiCMOS Technology, in which the optimal tradeoff emitter current density and the location of high-frequency noise corner were analyzed for acquiring low-noise performance. The Auto-Zero Feedback Loop (AZFL) without introducing unnecessary noises at input of the TIA, the tail current sink with high symmetries and the balance operation TIA with the shared output of Operational Amplifier (OpAmp) in AZFL were designed to keep balanced operation for the TIA. Moreover, cascode and shunt-feedback were also employed to expanding bandwidth and decreasing input referred noise. Besides, the formula for calculating high-frequency noise corner in Heterojunction Bipolar Transistor (HBT) TIA with shunt-feedback was derived. The electrical measurement was performed to validate the notions described in this work, appearing 9.6 pA/√Hz of input referred noise current Power Spectral Density (PSD), balance operation (VIN1=896mV, VIN2=896mV, VOUT1=1.978V, VOUT2=1.979V), bandwidth of 32GHz, overall transimpedance gain of 68.6dBΩ, a total 117mW power consumption and chip area of 484µm × 486µm.

Since wild animals are causing more accidents and damages, it is important to safely detect them as early as possible. In this paper, we propose two battery-powered wild animal detection nodes based on deep learning that can automatically detect wild animals; the detection information is notified to the people concerned immediately. To use the proposed nodes outdoors where power is not available, we devise power saving techniques for the proposed nodes. For example, deep learning is used to save power by avoiding operations when wild animals are not detected. We evaluate the operation time and the power consumption of the proposed nodes. Then, we evaluate the energy consumption of the proposed nodes. Also, we evaluate the detection range of the proposed nodes, the accuracy of deep learning, and the success rate of communication through field tests to demonstrate that the proposed nodes can be used to detect wild animals outdoors.

Silver electrical contacts were separated at constant opening speed in a 200V-500VDC/10A resistive circuit. Break arcs were extinguished by magnetic blowing-out with transverse magnetic field of a permanent magnet. The permanent magnet was appropriately located to simplify the lengthened shape of the break arcs. Magnetic flux density of the transverse magnetic field was varied from 20 to 140mT. Images of the break arcs were observed from the horizontal and vertical directions using two high speed cameras simultaneously. Arc length just before extinction was analyzed from the observed images. It was shown that shapes of the break arcs were simple enough to trace the most part of paths of the break arcs for all experimental conditions owing to simplification of the shapes of the break arcs by appropriate arrangement of the magnet. The arc length increased with increasing supply voltage and decreased with increasing magnetic flux density. These results will be discussed in the view points of arc lengthening time and arc lengthening velocity.

In a multiple-user MIMO system in which numerous users simultaneously communicate in a cell, the channel matrix properties depend on the parameters of the individual users in such a way that they can be modeled as points randomly moving within the cell. Although these properties can be simulated by computer, they need to be expressed analytically to develop MIMO systems with diversity. Given a small area with an equivalent multi-path, we assume that a user u is at a certain “user point” $P^u(lambda _p^u,xi _p^u)$ in a cell, or (radius $lambda _p^u$ from origin, angle $xi _p^u)$ and that the user moves with movement $M^u(f_{max}^u, xi_v^u)$ around that point, or (Doppler frequency $f_{max}^u$, direction $xi_v^u$). The MU-MIMO channel model consists of a multipath environment, user parameters, and antenna configuration. A general formula of the correlation $ ho_{i - j,i' - j'}^{u - u'} (bm)$ between the channel matrix elements of users u and u' and one for given multipath conditions are derived. As a feature of the MU-MIMO channel, the movement factor $F^{u - u'}(gamma^u,xi_n ,xi_v^u)$, which means a fall coefficient of the spatial correlation calculated from only the user points of u and u', is also derived. As the difference in speed or direction between u and u' increases, $F^{u - u'}(gamma^u,xi_n ,xi_v^u)$ becomes smaller. Consequently, even if the path is LOS, $ ho_{i - j,i' - j'}^{u - u'} (bm)$ becomes low enough owing to the movement factor, even though the correlation in the single-user MIMO channel is high. If the parameters of u and u' are the same, the factor equals 1, and the channels correspond to the users' own channels and work like SU-MIMO channel. These analytical findings are verified by computer simulation.

This paper proposes a novel compressed sensing (CS) framework for reconstructing electroencephalogram (EEG) signals. A feature of this framework is the application of independent component analysis (ICA) to remove the interference from artifacts after undersampling in a data processing unit. Therefore, we can remove the ICA processing block from the sensing unit. In this framework, we used a random undersampling measurement matrix to suppress the Gaussian. The developed framework, in which the discrete cosine transform basis and orthogonal matching pursuit were used, was evaluated using raw EEG signals with a pseudo-model of an eye-blink artifact. The normalized mean square error (NMSE) and correlation coefficient (CC), obtained as the average of 2,000 results, were compared to quantitatively demonstrate the effectiveness of the proposed framework. The evaluation results of the NMSE and CC showed that the proposed framework could remove the interference from the artifacts under a high compression ratio.

Recently, the ECG-based diagnosis system based on wearable devices has attracted more and more attention of researchers. Existing studies have achieved high classification accuracy by using deep neural networks (DNNs), but there are still some problems, such as: imprecise heart beat segmentation, inadequate use of medical knowledge, the same treatment of features with different importance. To address these problems, this paper: 1) proposes an adaptive segmenting-reshaping method to acquire abundant useful samples; 2) builds a set of hand-crafted features and deep features on the inner-beat, beat and inter-beat scale by integrating enough medical knowledge. 3) introduced a modified channel attention module (CAM) to augment the significant channels in deep features. Following the Association for Advancement of Medical Instrumentation (AAMI) recommendation, we classified the dataset into four classes and validated our algorithm on the MIT-BIH database. Experiments show that the accuracy of our model reaches 96.94%, a 3.71% increase over that of a state-of-the-art alternative.

The authors have been investigating the deterioration process of Au-plated slip-ring and Ag-Pd brush system with lubricant to realize stable and long lifetime. Through the past tests, it can be made clear that lubricant is very important for long lifetime, and a simple model of the deterioration process was proposed. However, it is still an issue how the lubricant is deteriorated and also what the relation between lubricant deterioration and contact voltage behavior is. In this paper, the contact voltage waveforms were regularly recorded during the test, and analyzed to obtain the time change of peak voltage and standard deviation during one rotation. Based on these results, it is discussed what happens at the interface between ring and brush with the lubricant. And the following results are made clear. The fluctuation of voltage waveforms, especially peaks of pulse-like fluctuation more easily occurs for minus rings than for plus rings. Further, peak values of the pulse-like fluctuation rapidly decreases and disappear at lower rotation speed as mentioned in the previous works. In addition, each peaks of the pulse-like fluctuation is identified at each position of the ring periphery. From these results, it can be assumed that lubricant film exists between brush and ring surface and electric conduction is realized by tunnel effect. In other words, it can be made clear that the fluctuation would be caused by the lubricant layer, not only by the ring surface. Finally, an electric conduction model is proposed and the above results can be explained by this model.

Training deep learning (DL) is a computationally intensive process; as a result, training time can become so long that it impedes the development of DL. High performance computing clusters, especially supercomputers, are equipped with a large amount of computing resources, storage resources, and efficient interconnection ability, which can train DL networks better and faster. In this paper, we propose a method to train DL networks distributed with high efficiency. First, we propose a hierarchical synchronous Stochastic Gradient Descent (SGD) strategy, which can make full use of hardware resources and greatly increase computational efficiency. Second, we present a two-level parameter synchronization scheme which can reduce communication overhead by transmitting parameters of the first layer models in shared memory. Third, we optimize the parallel I/O by making each reader read data as continuously as possible to avoid the high overhead of discontinuous data reading. At last, we integrate the LARS algorithm into our system. The experimental results demonstrate that our approach has tremendous performance advantages relative to unoptimized methods. Compared with the native distributed strategy, our hierarchical synchronous SGD strategy (HSGD) can increase computing efficiency by about 20 times.

Deep neural network (DNN)-based speech synthesis became popular in recent years and is expected to soon be widely used in embedded devices and environments with limited computing resources. The key intention of these systems in poor computing environments is to reduce the computational cost of generating speech parameter sequences while maintaining voice quality. However, reducing computational costs is challenging for two primary conventional DNN-based methods used for modeling speech parameter sequences. In feed-forward neural networks (FFNNs) with maximum likelihood parameter generation (MLPG), the MLPG reconstructs the temporal structure of the speech parameter sequences ignored by FFNNs but requires additional computational cost according to the sequence length. In recurrent neural networks, the recursive structure allows for the generation of speech parameter sequences while considering temporal structures without the MLPG, but increases the computational cost compared to FFNNs. We propose a new approach for DNNs to acquire parameters captured from the temporal structure by backpropagating the errors of multiple attributes of the temporal sequence via the loss function. This method enables FFNNs to generate speech parameter sequences by considering their temporal structure without the MLPG. We generated the fundamental frequency sequence and the mel-cepstrum sequence with our proposed method and conventional methods, and then synthesized and subjectively evaluated the speeches from these sequences. The proposed method enables even FFNNs that work on a frame-by-frame basis to generate speech parameter sequences by considering the temporal structure and to generate sequences perceptually superior to those from the conventional methods.

We propose a speech analysis-synthesis and deep neural network (DNN)-based text-to-speech (TTS) synthesis framework using Gaussian mixture model (GMM)-based approximation of full-band spectral envelopes. GMMs have excellent properties as acoustic features in statistic parametric speech synthesis. Each Gaussian function of a GMM fits the local resonance of the spectrum. The GMM retains the fine spectral envelope and achieve high controllability of the structure. However, since conventional speech analysis methods (i.e., GMM parameter estimation) have been formulated for a narrow-band speech, they degrade the quality of synthetic speech. Moreover, a DNN-based TTS synthesis method using GMM-based approximation has not been formulated in spite of its excellent expressive ability. Therefore, we employ peak-picking-based initialization for full-band speech analysis to provide better initialization for iterative estimation of the GMM parameters. We introduce not only prediction error of GMM parameters but also reconstruction error of the spectral envelopes as objective criteria for training DNN. Furthermore, we propose a method for multi-task learning based on minimizing these errors simultaneously. We also propose a post-filter based on variance scaling of the GMM for our framework to enhance synthetic speech. Experimental results from evaluating our framework indicated that 1) the initialization method of our framework outperformed the conventional one in the quality of analysis-synthesized speech; 2) introducing the reconstruction error in DNN training significantly improved the synthetic speech; 3) our variance-scaling-based post-filter further improved the synthetic speech.

In this paper, we aim to develop technologies for the circuit fault diagnosis and propose a formulation of a measure of a test pattern for the circuit fault diagnosis. Given a faulty circuit, the fault diagnosis is to deduce locations of faults that had occurred in the circuit. The fault diagnosis is executed in software before the failure analysis by which engineers inspect physical defects, and helps to improve the manufacturing process which yielded faulty circuits. The heart of the fault diagnosis is to distinguish between candidate faults by using test patterns, which are applied to the circuit-under-diagnosis (CUD), and thus test patterns that can distinguish as many faults as possible need to be generated. This fact motivates us to consider the test pattern measure based on the number of fault-pairs that become distinguished by a test pattern. To the best of the authors' knowledge, that measure requires the computational time of complexity order O(NF2), where NF denotes the number of candidate faults. Since NF is generally large for real industrial circuits, the computational time of the measure is long even when a high-performance computer is used. The formulation proposed in this paper makes it possible to calculate the measure in the computational complexity of O(NF log NF), and thus that measure is useful for the test pattern selection in the fault diagnosis. In computational experiments, the effectiveness of the formulation is demonstrated as samples of computational times of the measure calculated by the traditional and the proposed formulae and thorough comparisons between several greedy heuristics which are based on the measure.