Since deep learning was introduced, a series of achievements has been published in the field of automatic machine translation (MT). However, Korean-Vietnamese MT systems face many challenges because of a lack of data, multiple meanings of individual words, and grammatical diversity that depends on context. Therefore, the quality of Korean-Vietnamese MT systems is still sub-optimal. This paper discusses a method for applying Named Entity Recognition (NER) and Part-of-Speech (POS) tagging to Vietnamese sentences to improve the performance of Korean-Vietnamese MT systems. In terms of implementation, we used a tool to tag NER and POS in Vietnamese sentences. In addition, we had access to a Korean-Vietnamese parallel corpus with more than 450K paired sentences from our previous research paper. The experimental results indicate that tagging NER and POS in Vietnamese sentences can improve the quality of Korean-Vietnamese Neural MT (NMT) in terms of the Bi-Lingual Evaluation Understudy (BLEU) and Translation Error Rate (TER) score. On average, our MT system improved by 1.21 BLEU points or 2.33 TER scores after applying both NER and POS tagging to the Vietnamese corpus. Due to the structural features of language, the MT systems in the Korean to Vietnamese direction always give better BLEU and TER results than translation machines in the reverse direction.

We propose an effective 2d image based end-to-end deep learning model for malware detection by introducing a black & white embedding to reserve bit information and adapting the convolution architecture. Experimental results show that our proposed scheme can achieve superior performance in both of training and testing data sets compared to well-known image recognition deep learning models (VGG and ResNet).

We propose a multi-targeted backdoor that misleads different models to different classes. The method trains multiple models with data that include specific triggers that will be misclassified by different models into different classes. For example, an attacker can use a single multi-targeted backdoor sample to make model A recognize it as a stop sign, model B as a left-turn sign, model C as a right-turn sign, and model D as a U-turn sign. We used MNIST and Fashion-MNIST as experimental datasets and Tensorflow as a machine learning library. Experimental results show that the proposed method with a trigger can cause misclassification as different classes by different models with a 100% attack success rate on MNIST and Fashion-MNIST while maintaining the 97.18% and 91.1% accuracy, respectively, on data without a trigger.

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.

Coexistence between ZigBee and Wi-Fi technologies, which operate within the same frequency band, is increasing with the widespread use of the IoT (Internet of Things). ZigBee devices suffer significant decreases in the sink arrival rate of packets in the presence of Wi-Fi interference. To overcome this problem, many channel control methods have been proposed. These methods switch only ZigBee channels to avoid interference with Wi-Fi. In contrast, we propose a cooperative channel control method for improving ZigBee packet arrival rate by controlling both the Wi-Fi and ZigBee channels. Specifically, the proposed method not only controls ZigBee devices and channels but also requests a temporary pause in the use of specific Wi-Fi channels. Finally, computer simulations show the effectiveness of the proposed method from the viewpoints of ZigBee's packet arrival rate and applications' satisfaction. In addition, the feasibility of the proposed method is also confirmed by experiments with prototyping.

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.

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.

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.

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.

A convolutional neural network (CNN) for broadband direction of arrival (DOA) estimation of far-field electromagnetic signals is presented. The proposed algorithm performs a nonlinear inverse mapping from received signal to angle of arrival. The signal model used for algorithm is based on the circular antenna array geometry, and the phase component extracted from the spatial covariance matrix is used as the input of the CNN network. A CNN model including three convolutional layers is then established to approximate the nonlinear mapping. The performance of the CNN model is evaluated in a noisy environment for various values of signal-to-noise ratio (SNR). The results demonstrate that the proposed CNN model with the phase component of the spatial covariance matrix as the input is able to achieve fast and accurate broadband DOA estimation and attains perfect performance at lower SNR values.

This paper presents the design, implementation, and evaluation of a time-aware shaper, which is a traffic shaper specifically designed for IEEE 802.1Qbv-compliant time-sensitive networks. The proposed design adopts a software-based approach rather than using a dedicated custom logic chip such as an ASIC or FPGA. In particular, the proposed approach includes a run-time scheduler and a network interface card (NIC) that supports a time-based transmission scheme (i.e., launch-time feature). The run-time scheduler prefetches information (i.e., gate control entry) ahead of time from a given gate control list. With the prefetched information, the scheduler determines a launch time for each frame, and the NIC controls the time at which the transmission of each frame is started in a highly punctual manner. Evaluation results show that the proposed shaper triggers transmission of multiple time-sensitive streams at their intended timings in accordance with a given gate control list, even in the presence of high-bandwidth background traffic. Furthermore, we compare the timing accuracy of frame transmission with and without use of the launch-time feature of the NIC. Results indicate that the proposed shaper significantly reduces jitter of time-sensitive streams (to less than 0.1 µs) unlike a baseline implementation that does not use the launch-time feature.

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.

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.

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.

In this letter, the performance of a state-of-the-art deep learning (DL) algorithm in [5] is analyzed and evaluated for orthogonal frequency-division multiplexing (OFDM) receivers, in the presence of harmonic spur interference. Moreover, a novel spur cancellation receiver structure and algorithm are proposed to enhance the traditional OFDM receivers, and serve as a performance benchmark for the DL algorithm. It is found that the DL algorithm outperforms the traditional algorithm and is much more robust to spur carrier frequency offset.

In this letter, we propose a novel deep domain-adaptive convolutional neural network (DDACNN) model to handle the challenging cross-corpus speech emotion recognition (SER) problem. The framework of the DDACNN model consists of two components: a feature extraction model based on a deep convolutional neural network (DCNN) and a domain-adaptive (DA) layer added in the DCNN utilizing the maximum mean discrepancy (MMD) criterion. We use labeled spectrograms from source speech corpus combined with unlabeled spectrograms from target speech corpus as the input of two classic DCNNs to extract the emotional features of speech, and train the model with a special mixed loss combined with a cross-entrophy loss and an MMD loss. Compared to other classic cross-corpus SER methods, the major advantage of the DDACNN model is that it can extract robust speech features which are time-frequency related by spectrograms and narrow the discrepancies between feature distribution of source corpus and target corpus to get better cross-corpus performance. Through several cross-corpus SER experiments, our DDACNN achieved the state-of-the-art performance on three public emotion speech corpora and is proved to handle the cross-corpus SER problem efficiently.

Recurrent Neural Network (RNN) has achieved many state-of-the-art performances on various complex tasks related to the temporal and sequential data. But most of these RNNs require much computational power and a huge number of parameters for both training and inference stage. Several tensor decomposition methods are included such as CANDECOMP/PARAFAC (CP), Tucker decomposition and Tensor Train (TT) to re-parameterize the Gated Recurrent Unit (GRU) RNN. First, we evaluate all tensor-based RNNs performance on sequence modeling tasks with a various number of parameters. Based on our experiment results, TT-GRU achieved the best results in a various number of parameters compared to other decomposition methods. Later, we evaluate our proposed TT-GRU with speech recognition task. We compressed the bidirectional GRU layers inside DeepSpeech2 architecture. Based on our experiment result, our proposed TT-format GRU are able to preserve the performance while reducing the number of GRU parameters significantly compared to the uncompressed GRU.

Unlike black-box cryptography, an adversary in a white-box security model has full access to the implementation of the cryptographic algorithm. Thus, white-box implementation of cryptographic algorithms is more practical. Nevertheless, in recent years, there is no white-box implementation for public key cryptography. In this paper, we propose the first white-box implementation of the identity-based signature scheme in the IEEE P1363 standard. Our main idea is to hide the private key to multiple lookup tables, so that the private key cannot be leaked during the algorithm executed in the untrusted environment. We prove its security in both black-box and white-box models. We also evaluate the performance of our white-box implementations, in order to demonstrate utility for real-world applications.

Research on adversarial examples for machine learning has received much attention in recent years. Most of previous approaches are white-box attacks; this means the attacker needs to obtain before-hand internal parameters of a target classifier to generate adversarial examples for it. This condition is hard to satisfy in practice. There is also research on black-box attacks, in which the attacker can only obtain partial information about target classifiers; however, it seems we can prevent these attacks, since they need to issue many suspicious queries to the target classifier. In this paper, we show that a naive defense strategy based on surveillance of number query will not suffice. More concretely, we propose to generate not pixel-wise but block-wise adversarial perturbations to reduce the number of queries. Our experiments show that such rough perturbations can confuse the target classifier. We succeed in reducing the number of queries to generate adversarial examples in most cases. Our simple method is an untargeted attack and may have low success rates compared to previous results of other black-box attacks, but needs in average fewer queries. Surprisingly, the minimum number of queries (one and three in MNIST and CIFAR-10 dataset, respectively) is enough to generate adversarial examples in some cases. Moreover, based on these results, we propose a detailed classification for black-box attackers and discuss countermeasures against the above attacks.