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.

This paper analyzes and compares two methods to estimate electromagnetically coupled noises introduced to an antenna due to the nearby circuits at a circuit design stage. One of them is to estimate the power spectrum, and the other one is to estimate the active S11 parameter at the victim antenna, respectively, and both of them use simulated standard S-parameters for the electromagnetic coupling in the circuit. They also need the assumed or measured excitation of noise sources. To confirm the validness of the two methods, an evaluation board consisting of an antenna and noise sources were designed and fabricated in which voltage controlled oscillator (VCO) chips are placed as noise sources. The generated electromagnetic noises are transferred to an antenna via loop-shaped transmission lines, degrading the performance of the antenna. In this paper, detailed analysis procedures are described using the evaluation board, and it is shown that the two methods are equivalent to each other in terms of the induced voltages in the antenna. Finally, a procedure to estimate antenna performance degradation at the design stage is summarized.

The degradation of a SiC-MOSFET-based DC-AC converter-circuit efficiency due to aging of the electrically active devices is investigated. The newly developed compact aging model HiSIM_HSiC for high-voltage SiC-MOSFETs is used in the investigation. The model considers explicitly the carrier-trap-density increase in the solution of the Poisson equation. Measured converter characteristics during a 3-phase line-to-ground (3LG) fault is correctly reproduced by the model. It is verified that the MOSFETs experience additional stress due to the high biases occurring during the fault event, which translates to severe MOSFET aging. Simulation results predict a 0.5% reduction of converter efficiency due to a single 70ms-3LG, which is equivalent to a year of operation under normal conditions, where no additional stress is applied. With the developed compact model, prediction of the efficiency degradation of the converter circuit under prolonged stress, for which measurements are difficult to obtain and typically not available, is also feasible.

Here, we present a novel spectroscopic imaging method based on the boundary-extraction scheme for wide-beam terahertz (THz) three-dimensional imaging. Optical-lens-focusing systems for THz subsurface imaging generally require the depth of the object from the surface to be input beforehand to achieve the desired azimuth resolution. This limitation can be alleviated by incorporating a wide-beam THz transmitter into the synthetic aperture to automatically change the focusing depth in the post-signal processing. The range point migration (RPM) method has been demonstrated to have significant advantages in terms of imaging accuracy over the synthetic-aperture method. Moreover, in the RPM scheme, spectroscopic information can be easily associated with each scattering center. Thus, we propose an RPM-based terahertz spectroscopic imaging method. The finite-difference time-domain-based numerical analysis shows that the proposed algorithm provides accurate target boundary imaging associated with each frequency-dependent characteristic.

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.

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.

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.

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.

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.

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.

To estimate angle, velocity, and range information of multiple targets jointly in FMCW MIMO radar, two-dimensional (2D) MUSIC with matched filtering and FFT algorithm is proposed. By reformulating the received FMCW signal of the colocated MIMO radar, we exploit 2D MUSIC to estimate the angle and Doppler frequency of multiple targets. Then by using a matched filter together with the estimated angle and Doppler frequency and FFT operation, the range of the target is estimated. To effectively estimate the parameters of multiple targets with large distance differences, we also propose a successive interference cancellation method that uses the orthogonal projection. That is, rather than estimating the multiple target parameters simultaneously using 2D MUSIC, we estimate the target parameters sequentially, in which the parameters of the target having strongest reflected power are estimated first and then, their effect on the received signal is canceled out by using the orthogonal projection. Simulations verify the performance of the proposed algorithm.

Addition is a key fundamental function for many error-tolerant applications. Approximate addition is considered to be an efficient technique for trading off energy against performance and accuracy. This paper proposes a carry-maskable adder whose accuracy can be configured at runtime. The proposed scheme can dynamically select the length of the carry propagation to satisfy the quality requirements flexibly. Compared with a conventional ripple carry adder and a conventional carry look-ahead adder, the proposed 16-bit adder reduced the power consumption by 54.1% and 57.5%, respectively, and the critical path delay by 72.5% and 54.2%, respectively. In addition, results from an image processing application indicate that the quality of processed images can be controlled by the proposed adder. Good scalability of the proposed adder is demonstrated from the evaluation results using a 32-bit length.

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.

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.

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.

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.

In this paper, we describe a novel low-delay 4K 120-fps real-time HEVC decoder with a parallel processing architecture that conforms to the HEVC main 4:2:2 10 profile. It supports the hierarchical temporal scalable streams required for Ultra High Definition high-frame-rate broadcasting and also supports low-delay and high-bitrate decoding for video transmission uses. To achieve this support, the decoding processes are parallelized and pipelined at the frame level, slice level, and coding tree unit row level. The proposed decoder was implemented on three FPGAs operated at 133 and 150 MHz, and it achieved 300-Mbps stream decoding and 37-msec end-to-end delay with our concurrently developed 4K 120-fps encoder.

Heterogeneous networks (HetNets) technology is expected to be applied in next generation cellular networks to boost system capacity. However, applying HetNets introduces a significant amount of interference among different tiers within the same cell. In this paper, we propose a weighted rank constrained rank minimization (WRCRM) based interference alignment (IA) approach for three-tier HetNets. The concept of RCRM is applied in a different way to deal with the basic characteristic of different tiers: their different interference tolerance. In the proposed WRCRM approach, interference components at different tiers are weighted with different weighting factors (WFs) to reflect their vulnerability to interference. First, we derive an inner and a loose outer bound on the achievable degrees of freedom (DoF) for the three-tier system that is modeled as a three-user mutually interfering broadcast channel (MIBC). Then, the derived bounds along with the well-known IA feasibility conditions are used to show the effectiveness of the proposed WRCRM approach. Results show that there exist WF values that maximize the achievable interference-free dimensions. Moreover, adjusting the required number of DoF according to the derived bounds improves the performance of the WRCRM approach.

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.

The equivalent transmission-path model is a propagation-oriented channel model for predicting the bit error rate due to intersymbol interference in single-input single-output systems. We extend this model to develop a new calculation scheme for maximal-ratio combining diversity reception in single-input multiple-output configurations. A key part of the study is to derive a general formula expressing the joint probability density function of the amplitude ratio and phase difference of the two-path model. In this derivation, we mainly take a theoretical approach with the aid of Monte Carlo simulation. Then, very high-accuracy estimation of the average bit error rate due to intersymbol interference (ISI) for CQPSK calculated based on the model is confirmed by computer simulation. Finally, we propose a very simple calculation formula for the prediction of the BER due to ISI that is commonly applicable to various modulation/demodulation schemes, such as CQPSK, DQPSK, 16QAM, and CBPSK in maximal-ratio combining diversity reception.