Quantization is commonly used to reduce the inference time of convolutional neural networks (CNNs). To reduce the inference time without drastically reducing accuracy, optimal bit widths need to be allocated for each layer or filter of the CNN. In conventional methods, the optimal bit allocation is obtained by using the gradient descent algorithm while minimizing the model size. However, the model size has little to no correlation with the inference time. In this paper, we present a computational-complexity metric called MAC×bit that is strongly correlated with the inference time of quantized CNNs. We propose a gradient descent-based regularization method that uses this metric for optimal bit allocation of a quantized CNN to improve the recognition accuracy and reduce the inference time. In experiments, the proposed method reduced the inference time of a quantized ResNet-18 model by 21.0% compared with the conventional regularization method based on model size while maintaining comparable recognition accuracy.

The study of the spread of pandemics, including COVID-19, is an emerging concern to promote self-care management through social distancing, using state-of-the-art tools and technologies. Existing technologies provide many opportunities to acquire and process large volumes of data to monitor user activities from various perspectives. However, determining disease hotspots remains an open challenge considering user activities and interactions; providing related recommendations to susceptible individuals requires attention. In this article, we propose an approach to determine disease hotspots by modeling users’ activities from both cyber- and real-world spaces. Our approach uniquely connects cyber- and physical-world activities to predict hazardous regions. The availability of such an exciting data set is a non-trivial task; therefore, we produce the data set with much hard work and release it to the broader research community to facilitate further research findings. Once the data set is generated, we model it as a directed multi-attributed and weighted graph to apply classical machine learning and graph neural networks for prediction purposes. Our contribution includes mapping user events from cyber- and physical-world aspects, knowledge extraction, dataset generation, and reasoning at various levels. Within our unique graph model, numerous elements of lifestyle parameters are measured and processed to gain deep insight into a person’s status. As a result, the proposed solution enables the authorities of any pandemic, such as COVID-19, to monitor and take measurable actions to prevent the spread of such a disease and keep the public informed of the probability of catching it.

Deep networks are undergoing rapid development. However, as the depth of networks increases, the issue of how to fuse features from different layers becomes increasingly prominent. To address this challenge, we creatively propose a cross-layer feature fusion module based on neural dendrites, termed dendritic learning-based feature fusion (DFF). Compared to other fusion methods, DFF demonstrates superior biological interpretability due to the nonlinear capabilities of dendritic neurons. By integrating the classic ResNet architecture with DFF, we devise the ResNeFt. Benefiting from the unique structure and nonlinear processing capabilities of dendritic neurons, the fused features of ResNeFt exhibit enhanced representational power. Its effectiveness and superiority have been validated on multiple medical datasets.

In recent years, deep convolutional neural networks (CNN) have been widely used in synthetic aperture radar (SAR) image recognition. However, due to the difficulty in obtaining SAR image samples, training data is relatively few and overfitting is easy to occur when using traditional CNNS used in optical image recognition. In this paper, a CNN-based SAR image recognition algorithm is proposed, which can effectively reduce network parameters, avoid model overfitting and improve recognition accuracy. The algorithm first constructs a convolutional network feature extractor with a small size convolution kernel, then constructs a classifier based on the convolution layer, and designs a loss function based on distance measurement. The networks are trained in two stages: in the first stage, the distance measurement loss function is used to train the feature extraction network; in the second stage, cross-entropy is used to train the whole model. The public benchmark dataset MSTAR is used for experiments. Comparison experiments prove that the proposed method has higher accuracy than the state-of-the-art algorithms and the classical image recognition algorithms. The ablation experiment results prove the effectiveness of each part of the proposed algorithm.

This paper focuses on top-k query in cluster-based multi-hop wireless sensor networks (WSNs) employing wake-up receivers. We aim to design wake-up control that enables a sink to collect top-k data set, i.e., k highest readings of sensor nodes within a network, efficiently in terms of energy consumption and delay. Considering a tree-based clustered WSN, we propose a cluster-based wake-up control, which conducts activations and data collections of different clusters sequentially while the results of data collections at a cluster, i.e., the information on provisional top-k data set, are exploited for reducing unnecessary data transmissions at the other clusters. As a wake-up control employed in each cluster, we consider two different types of control: countdown content-based wake-up (CDCoWu) and identity-based wake-up (IDWu). CDCoWu selectively activates sensor nodes storing data belonging to top-k dataset while IDWu individually wakes up all sensor nodes within a cluster. Based on the observation that the best control depends on the number of cluster members, we introduce a hybrid mechanism of wake-up control, where a wake-up control employed at each cluster is selected between CDCoWu and IDWu based on its number of cluster members. Our simulation results show that the proposed hybrid wake-up control achieves smaller energy consumption and data collection delay than the control solely employing conventional CDCoWu or IDWu.

Intelligent reflecting surface (IRS) is an effective technology to improve the energy and spectral efficiency of wireless powered communication network (WPCN). Under user cooperation, we propose an IRS-assisted WPCN system where the wireless devices (WDs) collect wireless energy in the downlink (DL) and then share data. The adjacent single-antenna WDs cooperate to form a virtual antenna array so that their information can be simultaneously transmitted to the multi-antenna common hybrid access point (HAP) through the uplink (UL) using multiple-input multiple-output (MIMO) technology. By jointly optimizing the passive beamforming at the IRS, the active beamforming in the DL and the UL, the energy consumed by data sharing, and the time allocation of each phase, we formulate an UL throughput maximization problem. However, this optimization problem is non-convex since the optimization variables are highly coupled. In this study, we apply the alternating optimization (AO) technology to decouple the optimization variables and propose an efficient algorithm to avoid the difficulty of directly solving the problem. Numerical results indicate that the joint optimization method significantly improves the UL throughput performance in multi-user WPCN compared with various baseline methods.

This paper proposes an anomaly-detection method using the Fast xFlow Proxy, which enables fine-grained measurement of communication traffic. When a fault occurs in services or networks, communication traffic changes from its normal behavior. Therefore, anomalies can be detected by analyzing their autocorrelations. However, in large-scale carrier networks, packets are generally encapsulated and observed as aggregate values, making it difficult to detect minute changes in individual communication flows. Therefore, we developed the Fast xFlow Proxy, which analyzes encapsulated packets in real time and enables flows to be measured at an arbitrary granularity. In this paper, we propose an algorithm that utilizes the Fast xFlow Proxy to detect not only the anomaly occurrence but also its cause, that is, the location of the fault at the end-to-end. The idea is not only to analyze the autocorrelation of a specific flow but also to apply spatial analysis to estimate the fault location by comparing the behavior of multiple flows. Through extensive simulations, we demonstrate that base station, network, and service faults can be detected without any false negative detections.

Using deep learning (DL) to achieve direction-of-arrival (DOA) estimation is an open and meaningful exploration. Existing DL-based methods achieve DOA estimation by spectrum regression or multi-label classification task. While, both of them face the problem of off-grid errors. In this paper, we proposed a cascaded deep neural network (DNN) framework named as off-grid network (OGNet) to provide accurate DOA estimation in the case of off-grid. The OGNet is composed of an autoencoder consisted by fully connected (FC) layers and a deep convolutional neural network (CNN) with 2-dimensional convolutional layers. In the proposed OGNet, the off-grid error is modeled into labels to achieve off-grid DOA estimation based on its sparsity. As compared to the state-of-the-art grid-based methods, the OGNet shows advantages in terms of precision and resolution. The effectiveness and superiority of the OGNet are demonstrated by extensive simulation experiments in different experimental conditions.

In this paper, we delve into wireless communications in the 300 GHz band, focusing in particular on the continuous bandwidth of 44 GHz from 252 GHz to 296 GHz, positioning it as a pivotal element in the trajectory toward 6G communications. While terahertz communications have traditionally been praised for the high speeds they can achieve using their wide bandwidth, focusing the beam has also shown the potential to achieve high energy efficiency and support numerous simultaneous connectivity. To this end, new performance metrics, EIRPλ and EINFλ, are introduced as important benchmarks for transmitter and receiver performance, and their consistency is discussed. We then show that, assuming conventional bandwidth and communication capacity, the communication distance is independent of carrier frequency. Located between radio waves and light in the electromagnetic spectrum, terahertz waves promise to usher in a new era of wireless communications characterized not only by high-speed communication, but also by convenience and efficiency. Improvements in antenna gain, beam focusing, and precise beam steering are essential to its realization. As these technologies advance, the paradigm of wireless communications is expected to be transformed. The synergistic effects of antenna gain enhancement, beam focusing, and steering will not only push high-speed communications to unprecedented levels, but also lay the foundation for a wireless communications landscape defined by unparalleled convenience and efficiency. This paper will discuss a future in which terahertz communications will reshape the contours of wireless communications as the realization of such technological breakthroughs draws near.

Smart cities aim to improve the quality of life of citizens and efficiency of city operations through utilization of 5G communication technology. Based on various technologies such as IoT, cloud computing, artificial intelligence, and big data, they provide smart services in terms of urban planning, development, and management for solving problems such as fine dust, traffic congestion and safety, energy efficiency, water shortage, and an aging population. However, as smart city has an open network structure, an adversary can easily try to gain illegal access and perform denial of service and sniffing attacks that can threaten the safety and privacy of citizens. In smart cities, the global mobility network (GLOMONET) supports mobile services between heterogeneous networks of mobile devices such as autonomous vehicles and drones. Recently, Chen et al. proposed a user authentication scheme for GLOMONET in smart cities. Nevertheless, we found some weaknesses in the scheme proposed by them. In this study, we propose a secure lightweight authentication for roaming services in a smart city, called SLARS, to enhance security. We proved that SLARS is more secure and efficient than the related authentication scheme for GLOMONET through security and performance analysis. Our analysis results show that SLARS satisfies all security requirements in GLOMONET and saves 72.7% of computation time compared to that of Chen et al.’s scheme.

Software refactoring is an important process in software development. During software refactoring, code smell is a popular research topic that refers to design or implementation flaws in the software. Large class is one of the most concerning code smells in software refactoring. Detecting and refactoring such problem has a profound impact on software quality. In past years, software metrics and clustering techniques have commonly been used for the large class detection. However, deep-learning-based approaches have also received considerable attention in recent studies. In this study, we apply graph neural networks (GNNs), an important division of deep learning, to address the problem of large class detection. First, to support the extensive data requirements of the deep learning task, we apply a semiautomatic approach to generate a substantial number of data samples. Next, we design a new type of directed heterogeneous graph (DHG) as an input graph using the methods similarity matrix and software metrics. We construct an input graph for each class sample and make the graph classification with GNNs to identify the smelly classes. In our experiments, we apply three typical GNN model architectures for large class detection and compare the results with those of previous studies. The results show that the proposed approach can achieve more accurate and stable detection performance.

Convolutional neural network (CNN) is widely used in acoustic scene classification (ASC) tasks. In most cases, local convolution is utilized to gather time-frequency information between spectrum nodes. It is challenging to adequately express the non-local link between frequency domains in a finite convolution region. In this paper, we propose a dual-path convolutional neural network based on band interaction block (DCNN-bi) for ASC, with mel-spectrogram as the model’s input. We build two parallel CNN paths to learn the high-frequency and low-frequency components of the input feature. Additionally, we have created three band interaction blocks (bi-blocks) to explore the pertinent nodes between various frequency bands, which are connected between two paths. Combining the time-frequency information from two paths, the bi-blocks with three distinct designs acquire non-local information and send it back to the respective paths. The experimental results indicate that the utilization of the bi-block has the potential to improve the initial performance of the CNN substantially. Specifically, when applied to the DCASE 2018 and DCASE 2020 datasets, the CNN exhibited performance improvements of 1.79% and 3.06%, respectively.

In recent years, the increasing complexity of deep network structures has hindered their application in small resource constrained hardware. Therefore, we urgently need to compress and accelerate deep network models. Channel pruning is an effective method to compress deep neural networks. However, most existing channel pruning methods are prone to falling into local optima. In this paper, we propose a channel pruning method via Improved Grey Wolf Optimizer Pruner which called IGWO-Pruner to prune redundant channels of convolutional neural networks. It identifies pruning ratio of each layer by using Improved Grey Wolf algorithm, and then fine-tuning the new pruned network model. In experimental section, we evaluate the proposed method in CIFAR datasets and ILSVRC-2012 with several classical networks, including VGGNet, GoogLeNet and ResNet-18/34/56/152, and experimental results demonstrate the proposed method is able to prune a large number of redundant channels and parameters with rare performance loss.

Cooperative Communication is one of the most effective techniques to improve the desired signal quality of the typical user. This paper studies an indoor cellular network system that deploys the Reconfigurable Intelligent Surfaces (RIS) at the position of BSs to enable the cooperative features. To evaluate the network performance, the coverage probability expression of the typical user in the indoor wireless environment with presence of walls and effects of Rayleigh fading is derived. The analytical results shows that the RIS-assisted system outperforms the regular one in terms of coverage probability.

Federated learning is a distributed machine learning approach in which clients train models locally with their own data and upload them to a server so that their trained results are shared between them without uploading raw data to the server. There are some challenges in federated learning, such as communication size reduction and client heterogeneity. The former can mitigate the communication overheads, and the latter can allow the clients to choose proper models depending on their available compute resources. To address these challenges, in this paper, we utilize Neural ODE based models for federated learning. The proposed flexible federated learning approach can reduce the communication size while aggregating models with different iteration counts or depths. Our contribution is that we experimentally demonstrate that the proposed federated learning can aggregate models with different iteration counts or depths. It is compared with a different federated learning approach in terms of the accuracy. Furthermore, we show that our approach can reduce communication size by up to 89.4% compared with a baseline ResNet model using CIFAR-10 dataset.

Wide deployment of artificial intelligence (AI) is inducing exponentially growing energy consumption. Traditional digital platforms are becoming difficult to fulfill such ever-growing demands on energy efficiency as well as computing latency, which necessitates the development of high efficiency analog hardware platforms for AI. Recently, optical and electrooptic hybrid computing is reactivated as a promising analog hardware alternative because it can accelerate the information processing in an energy-efficient way. Integrated photonic circuits offer such an analog hardware solution for implementing photonic AI and machine learning. For this purpose, we proposed a photonic analog of support vector machine and experimentally demonstrated low-latency and low-energy classification computing, which evidences the latency and energy advantages of optical analog computing over traditional digital computing. We also proposed an electrooptic Hopfield network for classifying and recognizing time-series data. This paper will review our work on implementing classification computing and Hopfield network by leveraging silicon photonic circuits.

In cyber-physical systems (CPSs) that interact between physical and information components, there are many sensors that are connected through a communication network. In such cases, the reduction of communication costs is important. Event-triggered control that the control input is updated only when the measured value is widely changed is well known as one of the control methods of CPSs. In this paper, we propose a design method of output feedback controllers with decentralized event-triggering mechanisms, where the notion of uniformly ultimate boundedness is utilized as a control specification. Using this notion, we can guarantee that the state stays within a certain set containing the origin after a certain time, which depends on the initial state. As a result, the number of times that the event occurs can be decreased. First, the design problem is formulated. Next, this problem is reduced to a BMI (bilinear matrix inequality) optimization problem, which can be solved by solving multiple LMI (linear matrix inequality) optimization problems. Finally, the effectiveness of the proposed method is presented by a numerical example.

In interdependent systems, such as electric power systems, entities or components mutually depend on each other. Due to these interdependencies, a small number of initial failures can propagate throughout the system, resulting in catastrophic system failures. This paper addresses the problem of finding the set of entities whose failures will have the worst effects on the system. To this end, a two-phase algorithm is developed. In the first phase, the tight bound on failure propagation steps is computed using a Boolean Satisfiablility (SAT) solver. In the second phase, the problem is formulated as an Integer Linear Programming (ILP) problem using the obtained step bound and solved with an ILP solver. Experimental results show that the algorithm scales to large problem instances and outperforms a single-phase algorithm that uses a loose step bound.

Control of complex networks such as gene regulatory networks is one of the fundamental problems in control theory. A Boolean network (BN) is one of the mathematical models in complex networks, and represents the dynamic behavior by Boolean functions. In this paper, a solution method for the finite-time control problem of BNs is proposed using a BDD (binary decision diagram). In this problem, we find all combinations of the initial state and the control input sequence such that a certain control specification is satisfied. The use of BDDs enables us to solve this problem for BNs such that the conventional method cannot be applied. First, after the outline of BNs and BDDs is explained, the problem studied in this paper is given. Next, a solution method using BDDs is proposed. Finally, a numerical example on a 67-node BN is presented.

Fault-tolerant aggregate signature (FT-AS) is a special type of aggregate signature that is equipped with the functionality for tracing signers who generated invalid signatures in the case an aggregate signature is detected as invalid. In existing FT-AS schemes (whose tracing functionality requires multi-rounds), a verifier needs to send a feedback to an aggregator for efficiently tracing the invalid signer(s). However, in practice, if this feedback is not responded to the aggregator in a sufficiently fast and timely manner, the tracing process will fail. Therefore, it is important to estimate whether this feedback can be responded and received in time on a real system. In this work, we measure the total processing time required for the feedback by implementing an existing FT-AS scheme, and evaluate whether the scheme works without problems in real systems. Our experimental results show that the time required for the feedback is 605.3 ms for a typical parameter setting, which indicates that if the acceptable feedback time is significantly larger than a few hundred ms, the existing FT-AS scheme would effectively work in such systems. However, there are situations where such feedback time is not acceptable, in which case the existing FT-AS scheme cannot be used. Therefore, we further propose a novel FT-AS scheme that does not require any feedback. We also implement our new scheme and show that a feedback in this scheme is completely eliminated but the size of its aggregate signature (affecting the communication cost from the aggregator to the verifier) is 144.9 times larger than that of the existing FT-AS scheme (with feedbacks) for a typical parameter setting, and thus has a trade-off between the feedback waiting time and the communication cost from the verifier to the aggregator with the existing FT-AS scheme.