With the advent of the Internet of Things (IoT), short packet transmissions will dominate the future wireless communication. However, traditional coherent demodulation and channel estimation schemes require large pilot overhead, which may be highly inefficient for short packets in multipath fading scenarios. This paper proposes a novel pilot-free short packet structure based on the association of modulation on conjugate-reciprocal zeros (MOCZ) and tail-biting convolutional codes (TBCC), where a noncoherent demodulation and decoding scheme is designed without the channel state information (CSI) at the transceivers. We provide a construction method of constellation sets and demodulation rule for M-ary MOCZ. By deriving low complexity log-likelihood ratios (LLR) for M-ary MOCZ, we offer a reasonable balance between energy and bandwidth efficiency for joint coding and modulation scheme. Simulation results show that our proposed scheme can attain significant performance and throughput gains compared to the pilot-based coherent modulation scheme over multipath fading channels.

The reliability of deep neural networks (DNN) against hardware errors is essential as DNNs are increasingly employed in safety-critical applications such as automatic driving. Transient errors in memory, such as radiation-induced soft error, may propagate through the inference computation, resulting in unexpected output, which can adversely trigger catastrophic system failures. As a first step to tackle this problem, this paper proposes constructing a vulnerability model (VM) with a small number of fault injections to identify vulnerable model parameters in DNN. We reduce the number of bit locations for fault injection significantly and develop a flow to incrementally collect the training data, i.e., the fault injection results, for VM accuracy improvement. We enumerate key features (KF) that characterize the vulnerability of the parameters and use KF and the collected training data to construct VM. Experimental results show that VM can estimate vulnerabilities of all DNN model parameters only with 1/3490 computations compared with traditional fault injection-based vulnerability estimation.

Aiming at the problem of non-line of sight (NLOS) signal recognition for Ultra Wide Band (UWB) positioning, we utilize the concepts of Neural Network Clustering and Neural Network Pattern Recognition. We propose a classification algorithm based on self-organizing feature mapping (SOM) neural network batch processing, and a recognition algorithm based on convolutional neural network (CNN). By assigning different weights to learning, training and testing parts in the data set of UWB location signals with given known patterns, a strong NLOS signal recognizer is trained to minimize the recognition error rate. Finally, the proposed NLOS signal recognition algorithm is verified using data sets from real scenarios. The test results show that the proposed algorithm can solve the problem of UWB NLOS signal recognition under strong signal interference. The simulation results illustrate that the proposed algorithm is significantly more effective compared with other algorithms.

Currently, NDN-based VANETs protocols have several problems with packet overhead of rebroadcasting, control packet, and the accuracy of next-hop selection due to the dynamic topology. To deal with these problems in this paper, we propose a robust and lightweight forwarding protocol in Vehicular ad-hoc Named Data Networking. The concept of our forwarding protocol is adopting a packet-free approach. A vehicle collects its neighbor's visual identification by a pair of cameras (front and rear) to assign a unique visual ID for each node. Based on these IDs, we construct a hop-by-hop FIB-based forwarding strategy effectively. Furthermore, the Face duplication [1] in the wireless environment causes an all-broadcast problem. We add the visual information to Face to distinguish the incoming and outgoing Face to prevent broadcast-storm and make FIB and PIT work more accurate and efficiently. The performance evaluation results focusing on the communication overhead show that our proposal has better results in overall network traffic costs and Interest satisfaction ratio than previous works.

When a disaster hits a network, network service disruptions can occur even if the network facilities have survived and battery and power generators are provided. This is because in the event of a disaster, the power supply will not be restarted within the lifetime of the battery or oil transportation will not be restarted before running out of oil and power will be running out. Therefore, taking a power grid into account is important. This paper proposes a polynomial-time algorithm to identify the critical location C*D of a communications network Nc when a disaster hits. Electrical power grid Np supplies power to the nodes of Nc, and a link in Nc is disconnected when a node or a link in Nc or Np fails. Here, the disaster area is modeled as co-centric disks and the failure probability is higher in the inner disk than the outer one. The location of the center of the disaster with the greatest expected number of disconnected links in Nc is taken as the critical location C*D.

Network-on-Chips (NoCs) are important components for scalable many-core processors. Because the performance of parallel applications is usually sensitive to the latency of NoCs, reducing it is a primary requirement. In this study, a compression router that hides the (de)compression-operation delay is proposed. The compression router (de)compresses the contents of the incoming packet before the switch arbitration is completed, thus shortening the packet length without latency penalty and reducing the network injection-and-ejection latency. Evaluation results show that the compression router improves up to 33% of the parallel application performance (conjugate gradients (CG), fast Fourier transform (FT), integer sort (IS), and traveling salesman problem (TSP)) and 63% of the effective network throughput by 1.8 compression ratio on NoC. The cost is an increase in router area and its energy consumption by 0.22mm2 and 1.6 times compared to the conventional virtual-channel router. Another finding is that off-loading the decompressor onto a network interface decreases the compression-router area by 57% at the expense of the moderate increase in communication latency.

This paper proposes multi-input physical layer network coding (multi-input PLNC) for high speed wireless communication in two-dimensional wireless multihop networks. In the proposed PLNC, all the terminals send their packets simultaneously for the neighboring relays to maximize the network throughput in the first slot, and all the relays also do the same to the neighboring terminals in the second slot. Those simultaneous signal transmissions cause multiple signals to be received at the relays and the terminals. Signal reception in the multi-input PLNC uses multichannel filtering to mitigate the difficulties caused by the multiple signal reception, which enables the two-input PLNC to be applied. In addition, a non-linear precoding is proposed to reduce the computational complexity of the signal detection at the relays and the terminals. The proposed multi-input PLNC makes all the terminals exchange their packets with the neighboring terminals in only two time slots. The performance of the proposed multi-input PLNC is confirmed by computer simulation. The proposed multi-input physical layer network coding achieves much higher network throughput than conventional techniques in a two-dimensional multihop wireless network with 7 terminals. The proposed multi-input physical layer network coding attains superior transmission performance in wireless hexagonal multihop networks, as long as more than 6 antennas are placed on the terminals and the relays.

On an overlay network where a number of nodes work autonomously in a decentralized way, the efficiency of broadcasts has a significant impact on the performance of distributed systems built on the network. While a broadcast method using a spanning tree produces a small number of messages, the routing path lengths are prone to be relatively large. Moreover, when multiple nodes can be source nodes, inefficient broadcasts often occur because the efficient tree topology differs for each node. To address this problem, we propose a novel protocol in which a source node selects an efficient tree from multiple spanning trees when broadcasting. Our method shortens routing paths while maintaining a small number of messages. We examined path lengths and the number of messages for broadcasts on various topologies. As a result, especially for a random graph, our proposed method shortened path lengths by approximately 28% compared with a method using a spanning tree, with almost the same number of messages.

With the continued innovation of deep neural networks, spiking neural networks (SNNs) that more closely resemble biological brain synapses have attracted attention because of their low power consumption. Unlike artificial neural networks (ANNs), for continuous data values, they must employ an encoding process to convert the values to spike trains, suppressing the SNN's performance. To avoid this degradation, the incoming analog signal must be regulated prior to the encoding process, which is also realized in living things eg, the basement membranes of humans mechanically perform the Fourier transform. To this end, we combine an ANN and an SNN to build ANN-to-SNN hybrid neural networks (HNNs) that improve the concerned performance. To qualify this performance and robustness, MNIST and CIFAR-10 image datasets are used for various classification tasks in which the training and encoding methods changes. In addition, we present simultaneous and separate training methods for the artificial and spiking layers, considering the encoding methods of each. We find that increasing the number of artificial layers at the expense of spiking layers improves the HNN performance. For straightforward datasets such as MNIST, similar performances as ANN's are achieved by using duplicate coding and separate learning. However, for more complex tasks, the use of Gaussian coding and simultaneous learning is found to improve the accuracy of the HNN while lower power consumption.

Mobile communication systems are not only the core of the Information and Communication Technology (ICT) infrastructure but also that of our social infrastructure. The 5th generation mobile communication system (5G) has already started and is in use. 5G is expected for various use cases in industry and society. Thus, many companies and research institutes are now trying to improve the performance of 5G, that is, 5G Enhancement and the next generation of mobile communication systems (Beyond 5G (6G)). 6G is expected to meet various highly demanding requirements even compared with 5G, such as extremely high data rate, extremely large coverage, extremely low latency, extremely low energy, extremely high reliability, extreme massive connectivity, and so on. Artificial intelligence (AI) and machine learning (ML), AI/ML, will have more important roles than ever in 6G wireless communications with the above extreme high requirements for a diversity of applications, including new combinations of the requirements for new use cases. We can say that AI/ML will be essential for 6G wireless communications. This paper introduces some ML techniques and applications in 6G wireless communications, mainly focusing on the physical layer.

Deep neural networks (DNNs) perform well for image recognition, speech recognition, and pattern analysis. However, such neural networks are vulnerable to adversarial examples. An adversarial example is a data sample created by adding a small amount of noise to an original sample in such a way that it is difficult for humans to identify but that will cause the sample to be misclassified by a target model. In a military environment, adversarial examples that are correctly classified by a friendly model while deceiving an enemy model may be useful. In this paper, we propose a method for generating a selective adversarial example that is correctly classified by a friendly gait recognition system and misclassified by an enemy gait recognition system. The proposed scheme generates the selective adversarial example by combining the loss for correct classification by the friendly gait recognition system with the loss for misclassification by the enemy gait recognition system. In our experiments, we used the CASIA Gait Database as the dataset and TensorFlow as the machine learning library. The results show that the proposed method can generate selective adversarial examples that have a 98.5% attack success rate against an enemy gait recognition system and are classified with 87.3% accuracy by a friendly gait recognition system.

In this letter, we propose an energy beamforming empowered relaying scheme for a batteryless IoT network, where wireless-powered relays are deployed between the hybrid access point (HAP) and batteryless IoT devices to assist the uplink information transmission from the devices to the HAP. In particular, the HAP first exploits energy beamforming to efficiently transmit radio frequency (RF) signals to transfer energy to the relays and as the incident signals to enable the information backscattering of batteryless IoT devices. Then, each relay uses the harvested energy to forward the decoded signals from its corresponding batteryless IoT device to the HAP, where the maximum-ratio combing is used for further performance improvement. To maximize the network sum-rate, the joint optimization of energy beamforming vectors at the HAP, network time scheduling, power allocation at the relays, and relection coefficient at the users is investigated. As the formulated problem is non-convex, we propose an alternating optimization algorithm with the variable substitution and semi-definite relaxation (SDR) techniques to solve it efficiently. Specifically, we prove that the obtained energy beamforming matrices are always rank-one. Numerical results show that compared to the benchmark schemes, the proposed scheme can achieve a significant sum-rate gain.

Recently, the face hallucination method based on deep learning understands the mapping between low-resolution (LR) and high-resolution (HR) facial patterns by exploring the priors of facial structure. However, how to maintain the face structure consistency after the reconstruction of face images at different scales is still a challenging problem. In this letter, we propose a novel multi-scale structure prior learning (MSPL) for face hallucination. First, we propose a multi-scale structure prior block (MSPB). Considering the loss of high-frequency information in the LR space, we mainly process the input image in three different scale ascending dimensional spaces, and map the image to the high dimensional space to extract multi-scale structural prior information. Then the size of feature maps is recovered by downsampling, and finally the multi-scale information is fused to restore the feature channels. On this basis, we propose a local detail attention module (LDAM) to focus on the local texture information of faces. We conduct extensive face hallucination reconstruction experiments on a public face dataset (LFW) to verify the effectiveness of our method.

In this paper, we propose an end-to-end two-branch feature attention network. The network is mainly used for single image dehazing. The network consists of two branches, we call it CAA-Net: 1) A U-NET network composed of different-level feature fusion based on attention (FEPA) structure and residual dense block (RDB). In order to make full use of all the hierarchical features of the image, we use RDB. RDB contains dense connected layers and local feature fusion with local residual learning. We also propose a structure which called FEPA.FEPA structure could retain the information of shallow layer and transfer it to the deep layer. FEPA is composed of serveral feature attention modules (FPA). FPA combines local residual learning with channel attention mechanism and pixel attention mechanism, and could extract features from different channels and image pixels. 2) A network composed of several different levels of FEPA structures. The network could make feature weights learn from FPA adaptively, and give more weight to important features. The final output result of CAA-Net is the combination of all branch prediction results. Experimental results show that the CAA-Net proposed by us surpasses the most advanced algorithms before for single image dehazing.

Recently, deep learning for image generation with a guide for the generation has been progressing. Many methods have been proposed to generate the animation of facial expression change from a single face image by transferring some facial expression information to the face image. In particular, the method of using facial landmarks as facial expression information can generate a variety of facial expressions. However, most methods do not focus on anime characters but humans. Moreover, we attempted to apply several existing methods to anime characters by training the methods on an anime character face dataset; however, they generated images with noise, even in regions where there was no change. The first order motion model (FOMM) is an image generation method that takes two images as input and transfers one facial expression or pose to the other. By explicitly calculating the difference between the two images based on optical flow, FOMM can generate images with low noise in the unchanged regions. In the following, we focus on the aspect of the face image generation in FOMM. When we think about the employment of facial landmarks as targets, the performance of FOMM is not enough because FOMM cannot use a facial landmark as a facial expression target because the appearances of a face image and a facial landmark are quite different. Therefore, we propose an advanced FOMM method to use facial landmarks as a facial expression target. In the proposed method, we change the input data and data flow to use facial landmarks. Additionally, to generate face images with expressions that follow the target landmarks more closely, we introduce the landmark estimation loss, which is computed by comparing the landmark detected from the generated image with the target landmark. Our experiments on an anime character face image dataset demonstrated that our method is effective for landmark-guided face image generation for anime characters. Furthermore, our method outperformed other methods quantitatively and generated face images with less noise.

For a long time, the compensation effect of hearing aid is mainly evaluated subjectively, and there are fewer studies of objective evaluation. Furthermore, a pure speech signal is generally required as a reference in the existing objective evaluation methods, which restricts the practicality in a real-world environment. Therefore, this paper presents a non-intrusive speech quality evaluation method for hearing aid, which combines the audiogram and weighted frequency information. The proposed model mainly includes an audiogram information extraction network, a frequency information extraction network, and a quality score mapping network. The audiogram is the input of the audiogram information extraction network, which helps the system capture the information related to hearing loss. In addition, the low-frequency bands of speech contain loudness information and the medium and high-frequency components contribute to semantic comprehension. The information of two frequency bands is input to the frequency information extraction network to obtain time-frequency information. When obtaining the high-level features of different frequency bands and audiograms, they are fused into two groups of tensors that distinguish the information of different frequency bands and used as the input of the attention layer to calculate the corresponding weight distribution. Finally, a dense layer is employed to predict the score of speech quality. The experimental results show that it is reasonable to combine the audiogram and the weight of the information from two frequency bands, which can effectively realize the evaluation of the speech quality of the hearing aid.

There have been lots of previous studies on fluency evaluation of spontaneous speech. However, most of them focus on lexical cues, and little emphasis is placed on how diverse acoustic features and deep end-to-end models contribute to improving the performance. In this paper, we describe multi-layer neural network to investigate not only lexical features extracted from transcription, but also consider utterance-level acoustic features from audio data. We also conduct the experiments to investigate the performance of end-to-end approaches with mel-spectrogram in this task. As the speech fluency evaluation task, we evaluate our proposed method in two binary classification tasks of fluent speech detection and disfluent speech detection. Speech data of around 10 seconds duration each with the annotation of the three classes of “fluent,” “neutral,” and “disfluent” is used for evaluation. According to the two way splits of those three classes, the task of fluent speech detection is defined as binary classification of fluent vs. neutral and disfluent, while that of disfluent speech detection is defined as binary classification of fluent and neutral vs. disfluent. We then conduct experiments with the purpose of comparative evaluation of multi-layer neural network with diverse features as well as end-to-end models. For the fluent speech detection, in the comparison of utterance-level disfluency-based, prosodic, and acoustic features with multi-layer neural network, disfluency-based and prosodic features only are better. More specifically, the performance improved a lot when removing all of the acoustic features from the full set of features, while the performance is damaged a lot if fillers related features are removed. Overall, however, the end-to-end Transformer+VGGNet model with mel-spectrogram achieves the best results. For the disfluent speech detection, the multi-layer neural network using disfluency-based, prosodic, and acoustic features without fillers achieves the best results. The end-to-end Transformer+VGGNet architecture also obtains high scores, whereas it is exceeded by the best results with the multi-layer neural network with significant difference. Thus, unlike in the fluent speech detection, disfluency-based and prosodic features other than fillers are still necessary in the disfluent speech detection.

Reducing the number of link crossings in a network drawn on the plane such as a wiring board is a well-known problem, and especially the calculation of the minimum number of such crossings: this is the crossing number problem. It has been shown that finding a general solution to the crossing number problem is NP-hard. So, this problem is addressed for particular classes of graphs and this is also our approach in this paper. More precisely, we focus hereinafter on the torus topology. First, we discuss an upper bound on cr(T(2, k)) the number of crossings in a 2-dimensional k-ary torus T(2, k) where k ≥ 2: the result cr(T(2, k)) ≤ k(k - 2) and the given constructive proof lay foundations for the rest of the paper. Second, we extend this discussion to derive an upper bound on the crossing number of a 3-dimensional k-ary torus: cr(T(3, k)) ≤ 2k4 - k3 - 4k2 - 2⌈k/2⌉⌊k/2⌋(k - (k mod 2)) is obtained. Third, an upper bound on the crossing number of an n-dimensional k-ary torus is derived from the previously established results, with the order of this upper bound additionally established for more clarity: cr(T(n, k)) is O(n2k2n-2) when n ≥ k and O(nk2n-1) otherwise.

A method of radar-based contactless vital-sign sensing and electrocardiogram (ECG) signal reconstruction using deep learning is proposed. A radar system is an effective tool for contactless vital-sign sensing because it can measure a small displacement of the body surface without contact. However, most of the conventional methods have limited evaluation indices and measurement conditions. A method of measuring body-surface-displacement signals by using frequency-modulated continuous-wave (FMCW) radar and reconstructing ECG signals using a convolutional neural network (CNN) is proposed. This study conducted two experiments. First, we trained a model using the data obtained from six subjects breathing in a seated condition. Second, we added sine wave noise to the data and trained the model again. The proposed model is evaluated with a correlation coefficient between the reconstructed and actual ECG signal. The results of first experiment show that their ECG signals are successfully reconstructed by using the proposed method. That of second experiment show that the proposed method can reconstruct signal waveforms even in an environment with low signal-to-noise ratio (SNR).

Recently, Linux Container has been the de-facto standard for a cloud system, enabling cloud providers to create a virtual environment in a much more scaled manner. However, configuring container networks remains immature and requires automatic verification for efficient cloud management. We propose Verikube, which utilizes a novel graph structure representing policies to reduce memory consumption and accelerate verification. Moreover, unlike existing works, Verikube is compatible with the complex semantics of Cilium Policy which a cloud adopts from its advantage of performance. Our evaluation results show that Verikube performs at least seven times better for memory efficiency, at least 1.5 times faster for data structure management, and 20K times better for verification.