Recent self-supervised pre-training methods for object detection often rely on generic object proposals for localization and semantic feature learning for classification, but they yield limited improvements when applied to Detection Transformers (DETR) due to a lack of architectural alignment. Hence, we propose an elegant and versatile self-supervised framework tailored for DETR-like models called Distance-aware Multi-view Contrastive Learning (DisCo DETR). DisCo DETR enhances localization and semantic features through two core components. (i) Distance-aware Multi-view Object Query Fusion explicitly guides object queries to focus on spatially close objects across views, stabilizing training and improving localization accuracy. (ii) Contrastive Learning for DETR uses native bipartite matching to identify positive output pairs across views and pull them closer, enhancing semantic features discrimination with no extra matching. DisCo DETR can be seamlessly integrated into DETR-like models and achieves SOTA transfer performance on PASCAL VOC and COCO benchmarks across multiple variants.

The research on home energy management systems (HEMSs) has attracted wide attention because of the development trend of urban smart buildings. However, coordinating various homes is a nontrivial task due to uncertainties regarding renewable energy, user behavior, and the concern of privacy disclosure. The complex properties of household appliances further put forward requirements for the decision-making procedure. To solve these, this article proposes a novel federated transfer framework based on a teacher–student learning paradigm for the energy optimization process. The pretrained model based on an open-source building environment is introduced to assist the learning procedure under a cross-domain adaption mechanism, which avoids the time-consuming learning process from scratch. Considering household appliance discrepancies, a hybrid proximal policy optimization method with discrete-continuous action space is proposed to schedule these devices optimally. Extensive experiments have demonstrated the effectiveness of our proposed method in terms of training performance, cost efficiency, and comfort level.

Nonintrusive load monitoring (NILM) aims to accurately identify appliance-level power consumption patterns solely based on the total household power signal, facilitating fine-grained management of smart grid demands. Previous monitoring methods have often focused on classifying time domain power signals or identifying appliance signatures in the frequency domain, lacking sufficient analysis of diverse, sparsely labeled data across different households in the time-frequency domain. We propose a novel model named frequency-division fusion scattering time-series transformer (FFSTT). Specifically, in addition to NILM task-driven token embedding, self-attention, and feed forward blocks, we innovatively employ dual-tree complex wavelet transform for time-frequency transformation of tokens. Distinct feature extraction methods are applied to low- and high-frequency components, respectively, to efficiently separate and learn the power consumption patterns of different appliances. Furthermore, to achieve effective domain transfer among households in different regions, we utilize a small amount of labeled data to perform low-rank fine-tuning on the pretrained FFSTT. Experiments conducted on the REDD and U.K.-DALE datasets confirm that the proposed model achieves state-of-the-art performance across distinct scenarios of available labeled data.

本文概述了基于基础模型和并行智能开发基础、基础设施机器人、机器人技术的初始步骤和基本框架,以及新型人工智能技术(如AlphaGO、ChatGPT和Sora)的潜在应用。

The intermittency and randomness of wind power output have a negative impact on the stable operation of the power grid. Accurately modeling the uncertainty of wind power output is essential, and the primary method to achieve this is through scenario generation. Traditional scenario generation methods suffer from limitations such as low accuracy and high computational complexity. In this paper, a novel generation framework based on the denoising diffusion probabilistic model is presented and proposed for scenario generation of wind power. This method can overcome the limitations of traditional methods and learn the distribution of real data to generate reliable wind power scenarios. Compared to a homogeneous generative model, the proposed method shows improved performance in precisely capturing features of wind power scenarios.

Network alignment (NA) that identifies equivalent nodes across networks is an effective tool for integrating knowledge from multiple networks. The state-of-the-art NA methods learn inter-network node similarities based on labeled anchor links, which are costly, time-consuming, and difficult to acquire. Therefore, a few unsupervised network alignment (UNA) methods propose solving NA problems without anchor links. However, most existing UNA methods rely on discriminative attributes to capture nodes’ similarities and are hard to obtain optimal one-to-one alignments. Toward these issues, this article proposes a novel method named HackGAN to solve the UNA problem solely based on the structural information. Specifically, HackGAN represents nodes with embeddings based on an unsupervised graph neural network (GNN) to capture their global and local structural features. After that, it initializes mapping functions to transform the embedding spaces of different networks into the same vector space by iteratively solving the Wasserstein–Procrustes problem. The mapping functions are then refined by an adversarial model with cycle-consistency and Sinkhorn distance losses to obtain optimized one-to-one mappings. Based on the distances between mapped embeddings, accurate and robust results are obtained with a collective alignment algorithm. Experimental comparisons on both synthetic and real-world datasets demonstrate the superiority of HackGAN.

As a key infrastructural technology, Industrial Internet of Things (IIoT) and its related techniques have emerged in the age of Industrial Internet. Among them, an increasing popular and attractive federated edge learning (FEL) mechanism, which performs data analysis and inference at the edge devices distributedly, and aggregates local FEL units at a centralized controller, is introduced to meet the stringent data privacy and low-latency requirements for high-stake IIoT devices. Due to the bandwidth limitation, only parts of the IIoT devices can be selected to transmit their local FEL models to the centralized controller at each learning step. However, the centralized controller prefers to collect all the local FEL models to generate the global FL model since each IIoT device has a differential data set. Existing works mainly focus on selecting an appropriate subset of IIoT devices through advanced scheduling mechanisms without extending the resource bandwidth. However, the new radio in unlicensed spectrum (NR-U) technology in the 5G network opens up new possibilities for FEL since it is a privately owned network with fruitful bandwidth resources. We thus propose a novel communication-efficient FEL mechanism for NR-U-based IIoT networks, which aims to select data importance IIoT devices for local training under relatively sufficient unlicensed resources. The objective function is formulated as a tradeoff between total FEL data importance and the transmission latency via joint learning, device selection, and resource management scheduling, which is a mixed-integer nonlinear programming (MINLP). To deal with this problem, an alternating direction method of multipliers and block coordinate update (ADMM-BCU) algorithm with low computational complexity has been used. Closed-form expressions for both optimal device selection and resource management are derived, which highlighted significant insights. Numerical results demonstrate the algorithmic advantages and structural benefits of the proposed strategies.

In this paper, we aim to illustrate the concept of mutually trustworthy human-machine knowledge automation (HM-KA) as the technical mechanism of hybrid augmented intelligence (HAI) based complex system cognition, management, and control (CMC). We describe the historical development of complex system science and analyze the limitations of human intelligence and machine intelligence. The need for using human-machine HAI in complex systems is then explained in detail. The concept of “mutually trustworthy HM-KA” mechanism is proposed to tackle the CMC challenge, and its technical procedure and pathway are demonstrated using an example of corrective control in bulk power grid dispatch. It is expected that the proposed mutually trustworthy HM-KA concept can provide a novel and canonical mechanism and benefit real-world practices of complex system CMC.

Artificial intelligence (AI) technology has become an important trend to support the analysis and control of complex and time-varying power systems. Although deep reinforcement learning (DRL) has been utilized in the power system field, most of these DRL models are regarded as black boxes, which are difficult to explain and cannot be used on occasions when human operators need to participate. Using the explainable AI (XAI) technology to explain why power system models make certain decisions is as important as the accuracy of the decisions themselves because it ensures trust and transparency in the model decision-making process. The interpretability issue in DRL models in power system emergency control is discussed in this article. The proposed interpretable method is a backpropagation deep explainer based on Shapley additive explanations (SHAPs), which is named the Deep-SHAP method. The Deep-SHAP method is adopted to provide a reasonable interpretable model for a DRL-based emergency control application. For the DRL model, the importance of input features has been quantified to obtain contributions for the outcome of the model. Further, feature classification of the inputs and probabilistic analysis of the outputs in the XAI model is added to interpretability results for better clarity.

The goal of diagnosing the coronavirus disease 2019 (COVID-19) from suspected pneumonia cases, that is, recognizing COVID-19 from chest X-ray or computed tomography (CT) images, is to improve diagnostic accuracy, leading to faster intervention. The most important and challenging problem here is to design an effective and robust diagnosis model. To this end, there are three challenges to overcome: (1) The lack of training samples limits the success of existing deep-learning-based methods. (2) Many public COVID-19 data sets contain only a few images without fine-grained labels. (3) Due to the explosive growth of suspected cases, it is urgent and important to diagnose not only COVID-19 cases but also the cases of other types of pneumonia that are similar to the symptoms of COVID-19. To address these issues, we propose a novel framework called Unsupervised Meta-Learning with Self-Knowledge Distillation to address the problem of differentiating COVID-19 from pneumonia cases. During training, our model cannot use any true labels and aims to gain the ability of learning to learn by itself. In particular, we first present a deep diagnosis model based on a relation network to capture and memorize the relation among different images. Second, to enhance the performance of our model, we design a self-knowledge distillation mechanism that distills knowledge within our model itself. Our network is divided into several parts, and the knowledge in the deeper parts is squeezed into the shallow ones. The final results are derived from our model by learning to compare the features of images. Experimental results demonstrate that our approach achieves significantly higher performance than other state-of-the-art methods. Moreover, we construct a new COVID-19 pneumonia data set based on text mining, consisting of 2696 COVID-19 images (347 X-ray + 2349 CT), 10,155 images (9661 X-ray + 494 CT) about other types of pneumonia, and the fine-grained labels of all. Our data set considers not only a bacterial infection or viral infection which causes pneumonia but also a viral infection derived from the influenza virus or coronavirus.

Since early 2020, the COVID-19 global pandemic has significantly impacted almost every aspect of the human society throughout the world. Until now, middle of 2021, although with all the efforts on pandemic intervention and vaccination, COVID-19 is still hovering around the world, resulting in more than 177 million confirmed cases and 3.8 million deaths.

During the ongoing outbreak of coronavirus disease (COVID-19), people use social media to acquire and exchange various types of information at a historic and unprecedented scale. Only the situational information are valuable for the public and authorities to response to the epidemic. Therefore, it is important to identify such situational information and to understand how it is being propagated on social media, so that appropriate information publishing strategies can be informed for the COVID-19 epidemic. This article sought to fill this gap by harnessing Weibo data and natural language processing techniques to classify the COVID-19-related information into seven types of situational information. We found specific features in predicting the reposted amount of each type of information. The results provide data-driven insights into the information need and public attention.

Considering the distances to exits, exits' capacities, the sizes of queues at exits, distances to the nuclear power plant, as well as individual characteristics, the exit choice model for pedestrians in the plume planning area is established based on a random forest model. This model is trained and verified with the survey data of residents around the Daya Bay Nuclear Power Plant collected from a serious game-based questionnaire system. Combining the pedestrian choice with the agent-based pedestrian behavior simulation model, the evacuation process of a nuclear accident is simulated. Based on the detailed evacuation simulation model, a comparative experiment is performed to evaluate the staged evacuation strategy in such scenarios. Simulation results indicate that staged evacuation may not be the best strategy all the time, and the number of groups highly impacts its performance.

Blockchain, as an emerging decentralized architecture and distributed computing paradigm underlying Bitcoin and other cryptocurrencies, has attracted intensive attention in both research and applications recently. Blockchain, especially powered by chain-coded smart contracts, has the full potential of revolutionizing increasingly centralized cyber-physical-social systems (CPSSs) for constructions and applications, and reshaping traditional knowledge automation workflows. The key advantage of blockchain technology lies in the fact that it can enable the establishment of secured, trusted, and decentralized autonomous ecosystems for various scenarios, especially for better usage of the legacy devices, infrastructure, and resources.

Vehicular networks (VNs) have received great attention as one of the crucial supportive techniques for intelligent transportation systems (ITSs). However, the introduction of dynamic and complex human behaviors into VNs makes it a cyber-social-physical system. Thus, artificial systems, computational experiments, parallel executions-based parallel VNs (PVN) are proposed in this paper. The framework of PVN is then designed and presented, its characteristics and applications are demonstrated, and its related research challenges are discussed. PVN uses software-defined artificial VNs for modeling and representation, computational experiments for analysis and evaluation, and parallel execution for control and management. Thus, more reliable and efficient traffic status and ultrahigh data rate communications are obtained among vehicles and infrastructures, which is expected to achieve the descriptive intelligence, predictive intelligence, and prescription intelligence for VNs. The proposed PVN offers a competitive solution for achieving a smooth, safe, and efficient cooperation among connected vehicles in future ITSs.

The Internet of Things (IoT) is expected to connect a massive number of smart devices to the Internet. The existing centralized architecture for handling the huge volume of data created in the IoT is facing many research challenges, including security and privacy, trustworthiness, operational challenges, business models and the practical aspects, and legal and compliance issues. These challenges ask for new approaches to online identity, trustworthy transactions, and resilient networks.

Welcome to the third issue of the IEEE Transactions on Computational Social Systems (TCSS) in 2019. Thanks to the efforts of the editors, reviewers, authors, and readers of TCSS, the influence of TCSS is rapidly increasing. According to the latest statistics released by Elsevier, the CiteScore of TCSS in 2018 reaches 4.00, and ranks eighth out of the 255 journals (top 3%) in the field of social sciences. This is a solid improvement compared with the corresponding data in 2017 (CiteScore: 2.36, Rank: 17/226, and top 8%). Thanks and congratulations to our authors, reviewers, and members of our editorial board. The current issue includes 20 regular papers and a brief discussion on social energy.

Time flies fast, it has been already one year since I was appointed as the Editor-in-Chief of this great publication, and thanks to the strong support and dedication of our associate editors, editorial staff, anonymous reviewers, and authors, we have made solid progress and I really enjoy my work and our achievement so far. At this point, significant improvements in the timeliness and quality of the review process, as well as the numbers of manuscripts submitted and articles published have been accomplished.

Welcome to the last issue of the IEEE Transactions on Computational Social Systems (IEEE TCSS) in 2018. Starting from the first issue next year, our Transactions will be a bimonthly publication, entering a new stage for the IEEE TCSS.

This paper is to discuss the state, trend, and frontiers of development of cyber-physical-social systems (CPSSs) in China. The demand for developing CPSS is discussed in detail, followed by the Artificial societies, Computational experiments, Parallel execution (ACP) approach for CPSS and knowledge automation. The development of ACP based on CPSS in transportation, energy, information, Internet of Things, and Internet of Minds (IoM) is discussed to demonstrate the cutting-edge applications in CPSS. Finally, the blockchainized IoM technology and the concepts of parallel society are described. This paper will contribute to the transition from the current social construct to a futuristic intelligent society.

In order to model and study the interactions between social on technical systems, a systemic method, namely the composite socio-technical systems (CSTS), is proposed to incorporate social systems, technical systems and the interaction mechanism between them. A case study on University of Denver (DU) campus grid is presented in paper to demonstrate the application of the proposed method. In the case study, the social system, technical system, and the interaction mechanism are defined and modelled within the framework of CSTS. Distributed and centralized control and management schemes are investigated, respectively, and numerical results verifies the feasibility and performance of the proposed composite system method.

Nonlinear frequency-modulated signals have been effectively applied in multiple-user communication schemes. In this paper, we propose to implement a multiple-user communication scheme using hyperbolic frequency-modulated(HFM) signals for underwater acoustic communications. We derive constraints on the HFM parameters to optimally reduce multiple access interference (MAI) at the transmission side. Additional constraints on the frequency-modulation (FM) rate reduce the underwater channel effects of multipath and scaling. The proposed signaling scheme is compared to an HFM-based code-division multiple-access (HFM-CDMA) scheme to demonstrate improved error performance.

Over-the-horizon radar (OTHR) systems provide wide-area surveillance capabilities to detect and track targets far beyond the range of conventional line-of-sight radars. Because of the narrowband waveforms, OTHR systems do not achieve reliable altitude estimation. In this paper, we develop a new technique to track the instantaneous altitude of maneuvering targets by exploiting the estimated multi-component Doppler signatures. The main contribution of this paper is to apply effective non-stationary signal analysis for estimating the time-varying Doppler signature of each individual multipath, which is then applied to an extended Kalman filter to reliably track the instantaneous target altitude.

This paper presents a method for proactive robot communication connectivity maintenance based on electromagnetic field (EMF) recognition and signal strength (SS) gradient estimation for mobile robots. To achieve these goals in an efficient manner, we combine EMF recognition method and gradient descent of SS measurements into a proactive robot motion control algorithm in a way that maintains connectivity among mobile robots in the presence of a radio frequency (RF) obstacle. The EMF recognition method utilizes hidden Markov models (HMMs) for learning EMF environments based on SS measurements. The proposed motion control algorithm uses the EMF recognition and gradient method results to drive the robots towards favorable locations in which robots can communicate. The numerical simulation demonstrates promising EMF recognition, robot motion control results and confirms their abilities in proactive robot motion control for connectivity maintenance.

We investigate and demonstrate the sparsity of electroencephalography (EEG) signals in the spatial domain by incorporating grid spacing in the area of the head enclosing the brain volume. We exploit this spatial sparsity and propose a new approach for tracking neural activity that is based on compressive particle filtering. Our approach results in reducing the number of EEG channels required to be stored and processed for neural tracking using particle filtering. Simulations using both synthetic and real EEG signals illustrate that the proposed algorithm has tracking performance comparable to existing methods while using only a reduced set of EEG channels.

We consider the particle probability hypothesis density filter (PPHDF) for tracking multiple targets in urban terrain. This is a filtering technique based on random finite sets, implemented using the particle filter. Unlike data association methods, the PPHDF can be modified to estimate both the number of targets and their corresponding tracking parameters. We propose a modified PPHDF algorithm that employs multipath-to-measurement association (PPHDF-MMA) to automatically and adaptively estimate the available types of measurements. By using the best matched measurement at each time step, the new algorithm results in improved radar coverage and scene visibility. Numerical simulations demonstrate the effectiveness of the PPHDF-MMA in improving the tracking performance of multiple targets and targets in clutter.

We consider the problem of tracking a maneuvering target in urban terrain with high clutter. Although multipath has been previously exploited to improve target tracking in complex urban environments, when the clutter is high, multipath returns can suffer from large losses in signal-to-noise ratio (SNR), reducing probability of detection (PD). Maneuvering, a common motion in urban terrain, can also affect PD as different multipaths occur at different times. We propose a waveform-agile probabilistic data association target tracker that allows for multiple interactive motion models. The new adaptive tracker computes the different PD values for the validated measurements of line-of-sight (LOS) and non-LOS (NLOS) returns from the target, while selecting the transmit waveform that minimizes the mean-squared error (MSE) at each time step. The proposed approach is demonstrated using simulations of a realistic high clutter urban environment.

We integrate multipath exploitation with adaptive waveform design in order to increase the tracking performance of a vehicle moving in urban terrain. Mitigation of both clutter and strong multipath returns can result in increased target detection. However, exploiting multiple bounces from obstacles such as buildings can be shown to increase radar coverage and scene visibility, especially in the absence of direct line-of-sight paths. For this purpose, we formulate the multipath propagation of an arbitrary number of specular bounces in urban terrain for three-dimensional motion. We then further exploit and optimize multipath returns by dynamically selecting the parameters of the transmitted waveform to minimize the predicted mean-squared tracking error. We demonstrate our proposed approach in a realistic urban environment by varying the type of measurement to include regions of obscuration and different number of multipath bounces.

We investigate two methods for estimating the matched signal transformations caused by time-varying underwater acoustic channels in orthogonal frequency division multiplexing (OFDM) communication systems. The underwater acoustic channel for this 12-20 kHz medium frequency range OFDM system is best modeled using multipath and wideband Doppler scale changes on the transmitted signal. As a result, our first channel estimation method is based on discretizing the wideband spreading function time-scale representation of the channel output using the Mellin transform. The second method is based on extracting the time-scale features of distinct ray paths in the received signal using a modified matching pursuit decomposition algorithm. We validate and discuss both methods using data from the recent Kauai Acomms MURI 2008 (KAM08) underwater acoustic communication experiment.

We investigated the joint multi-modal operation of the asymmetric character of the fields of view of radar and electro optical (EO) sensors for multi-target tracking applications. We proposed a joint multi-modal sensing mode based on using dynamic agility selection to optimize the tracking performance of multiple maneuvering targets. The proposed method jointly designs waveforms for radar sensing and resolution switching modes for EO sensing, when both sensor measurements experience high false alarm rates. Rao-Blackwellized particle filtering is used to track an unknown number of targets within an adaptive framework that yields the optimized joint sensor configuration. We demonstrated the performance of the proposed adaptive tracking system using numerical simulations.

In this paper, we investigate the application of compressive sensing and waveform design for estimating linear time-varying system characteristics. Based on the fact that the spreading function system representation is sparse in realistic system scenarios, we propose a new method for the identification of narrowband, wideband and dispersive systems using a small set of measurements. Through numerical simulations, we successfully demonstrate the feasibility of using compressive sensing to estimate the system spreading function.

In this paper, we propose a frequency-domain characterization of shallow water systems based on normal-mode acoustic processing that is applicable to a large class of signals. After studying the dispersive characteristics of this system, we propose a matched transmission waveform and receiver structure. The design uses a warping technique and the system characteristics to obtain time-dispersion diversity. Simulation results demonstrate that the system characterization and receiver schemes can improve processing performance.