In this paper, we propose a low-complexity and accurate noise suppression based on an a priori SNR (Speech to Noise Ratio) model for greater robustness w.r.t. short-term noise-fluctuation. The a priori SNR, the ratio of speech spectra and noise spectra in the spectral domain, represents the difference between speech features and noise features in the feature domain, including the mel-cepstral domain and the logarithmic power spectral domain. This is because logarithmic operations are used for domain conversions. Therefore, an a priori SNR model can easily be expressed in terms of the difference between the speech model and the noise model, which are modeled by the Gaussian mixture models, and it can be generated with low computational cost. By using a priori SNRs accurately estimated on the basis of an a priori SNR model, it is possible to calculate accurate coefficients of noise suppression filters taking into account the variance of noise, without serious increase in computational cost over that of a conventional model-based Wiener filter (MBW). We have conducted in-car speech recognition evaluation using the CENSREC-2 database, and a comparison of the proposed method with a conventional MBW showed that the recognition error rate for all noise environments was reduced by 9%, and that, notably, that for audio-noise environments was reduced by 11%. We show that the proposed method can be processed with low levels of computational and memory resources through implementation on a digital signal processor.

Machine learning (ML) has been used for various tasks in network operations in recent years. However, since the scale of networks has grown and the amount of data generated has increased, it has been increasingly difficult for network operators to conduct their tasks with a single server using ML. Thus, ML with edge-cloud cooperation has been attracting attention for efficiently processing and analyzing a large amount of data. In the edge-cloud cooperation setting, although transmission latency, bandwidth congestion, and accuracy of tasks using ML depend on the load balance of processing data with edge servers and a cloud server in edge-cloud cooperation, the relationship is too complex to estimate. In this paper, we focus on monitoring anomalous traffic as an example of ML tasks for network operations and formulate transmission latency, bandwidth congestion, and the accuracy of the task with edge-cloud cooperation considering the ratio of the amount of data preprocessed in edge servers to that in a cloud server. Moreover, we formulate an optimization problem under constraints for transmission latency and bandwidth congestion to select the proper ratio by using our formulation. By solving our optimization problem, the optimal load balance between edge servers and a cloud server can be selected, and the accuracy of anomalous traffic monitoring can be estimated. Our formulation and optimization framework can be used for other ML tasks by considering the generating distribution of data and the type of an ML model. In accordance with our formulation, we simulated the optimal load balance of edge-cloud cooperation in a topology that mimicked a Japanese network and conducted an anomalous traffic detection experiment by using real traffic data to compare the estimated accuracy based on our formulation and the actual accuracy based on the experiment.

To enhance safety and efficiency in the traffic environment, developing intelligent transportation systems (ITSs) is of paramount importance. In ITSs, roadside units (RSUs) are critical components that enable the environment awareness and connectivity via using radar sensing and communications. In this paper, we focus on RSUs with multiple radar systems. Specifically, we propose a parameter selection method of multiple radar systems to enhance the overall sensing performance. Furthermore, since different radars provide different sensing and tracking results, to benefit from multiple radars, we propose fusion algorithms to integrate the tracking results of different radars. We use two commercial frequency-modulated continuous wave (FMCW) radars to conduct experiments at Hsinchu city in Taiwan. The experimental results validate that our proposed approaches can improve the overall sensing performance.

Theoretically secure cryptosystems, digital signatures may not be secure after being implemented on Internet of Things (IoT) devices and PCs because of side-channel attacks (SCA). Because RSA key generation and ECDSA require GCD computations or modular inversions, which are often computed using the binary Euclidean algorithm (BEA) or binary extended Euclidean algorithm (BEEA), the SCA weaknesses of BEA and BEEA become a serious concern. Constant-time GCD (CT-GCD) and constant-time modular inversion (CTMI) algorithms are effective countermeasures in such situations. Modular inversion based on Fermat's little theorem (FLT) can work in constant time, but it is not efficient for general inputs. Two CTMI algorithms, named BOS and BY in this paper, were proposed by Bos, Bernstein and Yang, respectively. Their algorithms are all based on the concept of BEA. However, one iteration of BOS has complicated computations, and BY requires more iterations. A small number of iterations and simple computations during one iteration are good characteristics of a constant-time algorithm. Based on this view, this study proposes new short-iteration CT-GCD and CTMI algorithms over Fp borrowing a simple concept from BEA. Our algorithms are evaluated from a theoretical perspective. Compared with BOS, BY, and the improved version of BY, our short-iteration algorithms are experimentally demonstrated to be faster.

In machine learning, data augmentation (DA) is a technique for improving the generalization performance of models. In this paper, we mainly consider gradient descent of linear regression under DA using noisy copies of datasets, in which noise is injected into inputs. We analyze the situation where noisy copies are newly generated and injected into inputs at each epoch, i.e., the case of using on-line noisy copies. Therefore, this article can also be viewed as an analysis on a method using noise injection into a training process by DA. We considered the training process under three training situations which are the full-batch training under the sum of squared errors, and full-batch and mini-batch training under the mean squared error. We showed that, in all cases, training for DA with on-line copies is approximately equivalent to the l2 regularization training for which variance of injected noise is important, whereas the number of copies is not. Moreover, we showed that DA with on-line copies apparently leads to an increase of learning rate in full-batch condition under the sum of squared errors and the mini-batch condition under the mean squared error. The apparent increase in learning rate and regularization effect can be attributed to the original input and additive noise in noisy copies, respectively. These results are confirmed in a numerical experiment in which we found that our result can be applied to usual off-line DA in an under-parameterization scenario and can not in an over-parametrization scenario. Moreover, we experimentally investigated the training process of neural networks under DA with off-line noisy copies and found that our analysis on linear regression can be qualitatively applied to neural networks.

Modern large scale distributed storage systems play a central role in data center and cloud storage, while node failure in data center is common. The lost data in failure node must be recovered efficiently. Locally repairable codes (LRCs) are designed to solve this problem. The locality of an LRC is the number of nodes that participate in recovering the lost data from node failure, which characterizes the repair efficiency. An LRC is called optimal if its minimum distance attains Singleton-type upper bound [1]. In this paper, using basic techniques of linear algebra over finite field, infinite optimal LRCs over extension fields are derived from a given optimal LRC over base field(or small field). Next, this paper investigates the relation between near-MDS codes with some constraints and LRCs, further, proposes an algorithm to determine locality of dual of a given linear code. Finally, based on near-MDS codes and the proposed algorithm, those obtained optimal LRCs are shown.

In frequency hopping communication, time delay and Doppler shift incur interference. With the escalating upgrading of complicated interference, in this paper, the time-frequency two-dimensional (TFTD) partial Hamming correlation (PHC) properties of wide-gap frequency-hopping sequences (WGFHSs) with frequency shift are discussed. A bound on the maximum TFTD partial Hamming auto-correlation (PHAC) and two bounds on the maximum TFTD PHC of WGFHSs are got. Li-Fan-Yang bounds are the particular cases of new bounds for frequency shift is zero.

Internet of Things (IoT) devices are widely used in various fields. However, their limited computing resources make them extremely vulnerable and difficult to be effectively protected. Traditional intrusion detection systems (IDS) focus on high accuracy and low false alarm rate (FAR), making them often have too high spatiotemporal complexity to be deployed in IoT devices. In response to the above problems, this paper proposes an intrusion detection model of IoT based on the light gradient boosting machine (LightGBM). Firstly, the one-dimensional convolutional neural network (CNN) is used to extract features from network traffic to reduce the feature dimensions. Then, the LightGBM is used for classification to detect the type of network traffic belongs. The LightGBM is more lightweight on the basis of inheriting the advantages of the gradient boosting tree. The LightGBM has a faster decision tree construction process. Experiments on the TON-IoT and BoT-IoT datasets show that the proposed model has stronger performance and more lightweight than the comparison models. The proposed model can shorten the prediction time by 90.66% and is better than the comparison models in accuracy and other performance metrics. The proposed model has strong detection capability for denial of service (DoS) and distributed denial of service (DDoS) attacks. Experimental results on the testbed built with IoT devices such as Raspberry Pi show that the proposed model can perform effective and real-time intrusion detection on IoT devices.

This study numerically investigates the symbol-level allocation of four-level pulse-amplitude modulation (PAM4) signals for optically pre-amplified receiver systems. Three level-allocation schemes are examined: intensity-equispaced, amplitude-equispaced, and numerically optimized. Numerical simulations are conducted to comprehensively compare the receiver sensitivities for these level-allocation schemes under various system conditions. The results show that the superiority or inferiority between the level allocations is significantly dependent on the system conditions of the bandwidth of amplified spontaneous emission light, modulation bandwidth, and signal extinction ratio (ER). The mechanisms underlying these dependencies are also discussed.

We propose an efficient hybrid automatic repeat request (HARQ) method that simultaneously achieves packet combining and resolution of the collisions of random access identifiers (RAIDs) during retransmission in a non-orthogonal multiple access (NOMA)-based random access system. Here, the RAID functions as a separator for simultaneously received packets that use the same channel in NOMA. An example of this is a scrambling code used in 4G and 5G systems. Since users independently select a RAID from the candidate set prepared by the system, the decoding of received packets fails when multiple users select the same RAID. Random RAID reselection by each user when attempting retransmission can resolve a RAID collision; however, packet combining between the previous and retransmitted packets is not possible in this case because the base station receiver does not know the relationship between the RAID of the previously transmitted packet and that of the retransmitted packet. To address this problem, we propose a HARQ method that employs novel hierarchical tree-structured RAID groups in which the RAID for the previous packet transmission has a one-to-one relationship with the set of RAIDs for retransmission. The proposed method resolves RAID collisions at retransmission by randomly reselecting for each user a RAID from the dedicated RAID set from the previous transmission. Since the relationship between the RAIDs at the previous transmission and retransmission is known at the base station, packet combining is achieved simultaneously. Computer simulation results show the effectiveness of the proposed method.

Intelligent traffic monitoring provides information support for autonomous driving, which is widely used in intelligent transportation systems (ITSs). A method for estimating vehicle moving target parameters based on millimeter-wave radars is proposed to solve the problem of low detection accuracy due to velocity ambiguity and Doppler-angle coupling in the process of traffic monitoring. First of all, a MIMO antenna array with overlapping elements is constructed by introducing them into the typical design of MIMO radar array antennas. The motion-induced phase errors are eliminated by the phase difference among the overlapping elements. Then, the position errors among them are corrected through an iterative method, and the angle of multiple targets is estimated. Finally, velocity disambiguation is performed by adopting the error-corrected phase difference among the overlapping elements. An accurate estimation of vehicle moving target angle and velocity is achieved. Through Monte Carlo simulation experiments, the angle error is 0.1° and the velocity error is 0.1m/s. The simulation results show that the method can be used to effectively solve the problems related to velocity ambiguity and Doppler-angle coupling, meanwhile the accuracy of velocity and angle estimation can be improved. An improved algorithm is tested on the vehicle datasets that are gathered in the forward direction of ordinary public scenes of a city. The experimental results further verify the feasibility of the method, which meets the real-time and accuracy requirements of ITSs on vehicle information monitoring.

Previously, convolutional neural networks have made tremendous progress in target recognition based on micro-Doppler radar. However, these studies only considered the presence of one target at a time in the surveillance area. Simultaneous multi-targets recognition for surveillance radar remains a pretty challenging issue. To alleviate this issue, this letter develops a multi-instance multi-label (MIML) learning strategy, which can automatically locate the crucial input patterns that trigger the labels. Benefitting from its powerful target-label relation discovery ability, the proposed framework can be trained with limited supervision. We emphasize that only echoes from single targets are involved in training data, avoiding the preparation and annotation of multi-targets echo in the training stage. To verify the validity of the proposed method, we model two representative ground moving targets, i.e., person and wheeled vehicles, and carry out numerous comparative experiments. The result demonstrates that the developed framework can simultaneously recognize multiple targets and is also robust to variation of the signal-to-noise ratio (SNR), the initial position of targets, and the difference in scattering coefficient.

Video-based action recognition encompasses the recognition of appearance and the classification of action types. This work proposes a discrete-temporal-sequence-based motion tendency clustering framework to implement motion clustering by extracting motion tendencies and self-supervised learning. A published traffic intersection dataset (inD) and a self-produced gesture video set are used for evaluation and to validate the motion tendency action recognition hypothesis.

We propose Quality Enhancement via a Side bitstream Network (QESN) technique for lossy image compression. The proposed QESN utilizes the network architecture of deep image compression to produce a bitstream for enhancing the quality of conventional compression. We also present a loss function that directly optimizes the Bjontegaard delta bit rate (BD-BR) by using a differentiable model of a rate-distortion curve. Experimental results show that QESN improves the rate by 16.7% in the BD-BR compared to Better Portable Graphics.

Binary Decision Diagrams (BDDs) are an important data structure for the design of digital circuits using VLSI CAD tools. The ordering of variables affects the total number of nodes and path length in the BDDs. Finding a good variable ordering is an optimization problem and previously many optimization approaches have been implemented for BDDs in a number of research works. In this paper, an optimization approach based on Spider Monkey Optimization (SMO) algorithm is proposed for the BDD variable ordering problem targeting number of nodes and longest path length. SMO is a well-known swarm intelligence-based optimization approach based on spider monkeys foraging behavior. The proposed work has been compared with other latest BDD reordering approaches using Particle Swarm Optimization (PSO) algorithm. The results obtained show significant improvement over the Particle Swarm Optimization method. The proposed SMO-based method is applied to different benchmark digital circuits having different levels of complexities. The node count and longest path length for the maximum number of tested circuits are found to be better in SMO than PSO.

In this paper, user set selection in the allocation sequences of round-robin (RR) scheduling for distributed antenna transmission with block diagonalization (BD) pre-coding is proposed. In prior research, the initial phase selection of user equipment allocation sequences in RR scheduling has been investigated. The performance of the proposed RR scheduling is inferior to that of proportional fair (PF) scheduling under severe intra-cell interference. In this paper, the multi-input multi-output technology with BD pre-coding is applied. Furthermore, the user equipment (UE) sets in the allocation sequences are eliminated with reinforcement learning. After the modification of a RR allocation sequence, no estimated throughput calculation for UE set selection is required. Numerical results obtained through computer simulation show that the maximum selection, one of the criteria for initial phase selection, outperforms the weighted PF scheduling in a restricted realm in terms of the computational complexity, fairness, and throughput.

This study proposes a low-complexity permittivity estimation for ground penetrating radar applications based on a contrast source inversion (CSI) approach, assuming multilayered ground media. The homogeneity assumption for each background layer is used to address the ill-posed condition while maintaining accuracy for permittivity reconstruction, significantly reducing the number of unknowns. Using an appropriate initial guess for each layer, the post-CSI approach also provides the dielectric profile of a buried object. The finite difference time domain numerical tests show that the proposed approach significantly enhances reconstruction accuracy for buried objects compared with the traditional CSI approach.

Since the dark channel prior (DCP)-based dehazing method is ineffective in the sky area and will cause the problem of too dark and color distortion of the image, we propose a novel dehazing method based on sky area segmentation and image fusion. We first segment the image according to the characteristics of the sky area and non-sky area of the image, then estimate the atmospheric light and transmission map according to the DCP and correct them, and then fuse the original image after the contrast adaptive histogram equalization to improve the details information of the image. Experiments illustrate that our method performs well in dehazing and can reduce image distortion.

The application of time-series prediction is very extensive, and it is an important problem across many fields, such as stock prediction, sales prediction, and loan prediction and so on, which play a great value in production and life. It requires that the model can effectively capture the long-term feature dependence between the output and input. Recent studies show that Transformer can improve the prediction ability of time-series. However, Transformer has some problems that make it unable to be directly applied to time-series prediction, such as: (1) Local agnosticism: Self-attention in Transformer is not sensitive to short-term feature dependence, which leads to model anomalies in time-series; (2) Memory bottleneck: The spatial complexity of regular transformation increases twice with the sequence length, making direct modeling of long time-series infeasible. In order to solve these problems, this paper designs an efficient model for long time-series prediction. It is a double pyramid bidirectional feature fusion mechanism network with parallel Temporal Convolution Network (TCN) and FastFormer. This network structure can combine the time series fine-grained information captured by the Temporal Convolution Network with the global interactive information captured by FastFormer, it can well handle the time series prediction problem.

Uncovered muck truck detection aims to detect the muck truck and distinguish whether it is covered or not by dust-proof net to trace the source of pollution. Unlike traditional detection problem, recalling all uncovered trucks is more important than accurate locating for pollution traceability. When two objects are very close in an image, the occluded object may not be recalled because the non-maximum suppression (NMS) algorithm can remove the overlapped proposal. To address this issue, we propose a Location First NMS method to match the ground truth boxes and predicted boxes by position rather than class identifier (ID) in the training stage. Firstly, a box matching method is introduced to re-assign the predicted box ID using the closest ground truth one, which can avoid object missing when the IoU of two proposals is greater than the threshold. Secondly, we design a loss function to adapt the proposed algorithm. Thirdly, a uncovered muck truck detection system is designed using the method in a real scene. Experiment results show the effectiveness of the proposed method.