The continuous expansion of network data presents a pressing challenge for conventional routing algorithms. As the demand escalates, these algorithms are struggling to cope. In this context, reinforcement learning (RL) and multi-agent reinforcement learning (MARL) algorithms emerge as promising solutions. However, the urgency and importance of the problem are clear, as existing RL/MARL-based routing approaches lack effective communication in run time among routers, making it challenging for individual routers to adapt to complex and dynamic changing networks. More importantly, they lack the ability to deal with dynamically changing network topology, especially the addition of the router, due to the non-scalability of their neural networks. This paper proposes a novel dynamic routing algorithm, DRAMA, incorporating emergent communication in multi-agent reinforcement learning. Through emergent communication, routers could learn how to communicate effectively to maximize the optimization objectives. Meanwhile, a new Q-network and graph-based emergent communication are introduced to dynamically adapt to the changing network topology without retraining while ensuring robust performance. Experimental results showcase DRAMA’s superior performance over the traditional routing algorithm and other RL/MARL-based algorithms, achieving a higher delivery rate and lower latency in diverse network scenarios, including dynamic network load and topology. Moreover, an ablation experiment validates the prospect of emergent communication in facilitating packet routing.

This paper introduces a novel spectrum resource sharing framework in Vehicle-to-Everything (V2X) communication networks based on multi-agent reinforcement learning with graph emergent communication (MARLGEC). We formulate resource sharing as a distributed multi-agent reinforcement learning (MARL) problem, where each vehicle acts as an agent, interacting with the environment to optimize spectrum allocation strategies. The introduction of the emergent communication mechanism enhances cooperation among agents in the distributed framework. Meanwhile, the graph attention mechanism effectively reduces the communication overhead incurred by emergent communication. This enables reliable vehicle-to-vehicle (V2V) payload transmission and improves system performance under varying network conditions. The experimental results validate the method’s effectiveness, demonstrating its ability to adapt to the dynamic environment and outperform existing MARL approaches that lack communication mechanisms.

Chinese SLU suffers from unclear word boundaries. Previous works were either missing the word information or afflicted by word segmentation errors. In this paper, we propose a novel Word and Local feature Aware Network (WLAN), which incorporates both word information and local features for Chinese SLU while avoiding word segmentation. In addition, in our knowledge we first time use the potential slots likely to co-occur with the predicted intent as specific guidance. Experimental results on two Chinese SLU datasets show that our model gets very competitive performance.

The development of the Industrial Internet of Things (IIoT) is impeded by the lack of unknown protocol specifications. Protocol Reverse Engineering (PRE) plays a crucial role in inferring unpublished protocol specifications by analyzing traffic messages. Since different types within a protocol often have distinct formats, inferring the protocol type is essential for subsequent reverse analysis. Natural Language Processing (NLP) models have demonstrated remarkable capabilities in various sequence tasks, and traffic messages of unknown protocols can be analyzed as sequences. In this paper, we propose a framework for clustering unknown industrial control protocol types. Our framework utilizes a transformer-based auto-encoder network to train corresponding request and response messages, leveraging intermediate layer embedding vectors learned by the network for clustering. The clustering results are employed to extract candidate keywords and establish empirical rules. Subsequently, rule-based re-clustering is performed, and its effectiveness is evaluated based on previous clustering results. Through this re-clustering process, we identify the most effective combination of keywords that define the type. We evaluate the proposed framework using three general protocols that have different type rules and successfully separate the protocol internal types completely.

The rapid expansion of the Internet of Things (IoT) has raised increasing concern about targeted cyber attacks. Previous research primarily focused on static Intrusion Detection Systems (IDSs), which employ offline training to safeguard IoT systems. However, such static IDSs struggle with real-world scenarios where IoT system behaviors and attack strategies can undergo rapid evolution, necessitating dynamic and adaptable IDSs. In response to this challenge, we propose AOC-IDS, a novel online IDS that features an autonomous anomaly detection module (ADM) and a labor-free online framework for continual adaptation. In order to enhance data comprehension, the ADM employs an Autoencoder (AE) with a tailored Cluster Repelling Contrastive (CRC) loss function to generate distinctive representation from limited or incrementally incoming data in the online setting. Moreover, to reduce the burden of manual labeling, our online framework leverages pseudo-labels automatically generated from the decision-making process in the ADM to facilitate periodic updates of the ADM. The elimination of human intervention for labeling and decision-making boosts the system’s compatibility and adaptability in the online setting to remain synchronized with dynamic environments. Experimental validation using the NSL-KDD and UNSW-NB15 datasets demonstrates the superior performance and adaptability of AOC-IDS, surpassing the state-of-the-art solutions. The code is released at https://github.com/xinchen930/AOC-IDS.

Anomaly detection in time series data is fundamental to the design, deployment, and evaluation of industrial control systems. Temporal modeling has been the natural focus of anomaly detection approaches for time series data. However, the focus on temporal modeling can obscure or dilute the spatial information that can be used to capture complex interactions in multivariate time series. In this paper, we propose SARAD, an approach that leverages spatial information beyond data autoencoding errors to improve the detection and diagnosis of anomalies. SARAD trains a Transformer to learn the spatial associations, the pairwise inter-feature relationships which ubiquitously characterize such feedback-controlled systems. As new associations form and old ones dissolve, SARAD applies subseries division to capture their changes over time. Anomalies exhibit association descending patterns, a key phenomenon we exclusively observe and attribute to the disruptive nature of anomalies detaching anomalous features from others. To exploit the phenomenon and yet dismiss non-anomalous descent, SARAD performs anomaly detection via autoencoding in the association space. We present experimental results to demonstrate that SARAD achieves state-of-the-art performance, providing robust anomaly detection and a nuanced understanding of anomalous events.

Efficient leak detection and localization in water distribution networks (WDNs) are essential for mitigating disastrous losses from leak incidents. Current unsupervised learning-based methods excel in detecting single leaks but struggle with multi-leak scenarios, limiting their practical applicability. Additionally, leak localization methods relying on simulation optimization can be computationally intensive for large-scale WDNs. Meanwhile, purely data-driven approaches struggle to leverage network topology and hydraulic characteristics, hinde ring accurate leak localization. To address these challenges, we propose a leak detection and localization framework that employs online change-point detection and leak sensitivity modeling to achieve real-time detection and localization in multi-leak scenarios. For leak detection, the framework utilizes an unsupervised One-dimensional Convolutional Auto-encoder (1D-CAE) to reconstruct the pressure data collected from sensors deployed over a WDN. The residuals between the reconstructed values and the observed values, also known as reconstruction errors, are then analyzed using a Sequentially Discounting Normalized Maximum Likelihood (SDNML) change-point detector. Equipped with a customized scoring function designed for robust multi-leak detection, this detector computes anomaly scores in real-time at each time step, facilitating effective leak detection. Furthermore, we simulate leaks at different nodes of the WDN to quantify their impact on the sensor nodes using pressure residuals-based leak characteristic factors. By comparing reconstruction errors with these factors, we identify the nodes that best match the current leak event, achieving precise leak localization. An evaluation on the L-Town dataset demonstrates the superior performance of our method for multi-leak detection and localization.

Legal Judgment Prediction (LJP) aims to form legal judgments based on the criminal fact description. However, researchers struggle to classify confusing criminal cases, such as robbery and theft, which requires LJP models to distinguish the nuances between similar crimes. Existing methods usually design handcrafted features to pick up necessary semantic legal clues to make more accurate legal judgment predictions. In this paper, we propose a Semantic-Aware Dual Encoder Model (SEMDR), which designs a novel legal clue tracing mechanism to conduct fine-grained semantic reasoning between criminal facts and instruments. Our legal clue tracing mechanism is built from three reasoning levels: 1) Lexicon-Tracing, which aims to extract criminal facts from criminal descriptions; 2) Sentence Representation Learning, which contrastively trains language models to better represent confusing criminal facts; 3) Multi-Fact Reasoning, which builds a reasons graph to propagate semantic clues among fact nodes to capture the subtle difference among criminal facts. Our legal clue tracing mechanism helps SEMDR achieve state-of-the-art on the CAIL2018 dataset and shows its advance in few-shot scenarios. Our experiments show that SEMDR has a strong ability to learn more uniform and distinguished representations for criminal facts, which helps to make more accurate predictions on confusing criminal cases and reduces the model uncertainty during making judgments. All codes will be released via GitHub.

Optimal control of stochastic systems involves finding control strategies that optimize certain performance criteria while accounting for the parametric uncertainties and stochastic additive disturbances involved in the system dynamics. Model predictive control (MPC) solves an open-loop constrained stochastic optimal control problem repeatedly in a receding-horizon manner, resulting in large computation sometimes. Alternatively, the proposed stochastic self-optimizing control (SOC) selects optimal nonlinear controlled variables (CVs) offline by minimizing the expectation of the weighted closed-loop loss function based on neural network training. The nonlinear self-optimizing CVs are simply kept constant online so that the satisfactory control performance can be achieved. The proposed stochastic SOC requires much less online computation time compared with MPC, which is demonstrated by a two-mass spring simulation model.

An increasing number of factories are transitioning to industrial cyber-physical systems (iCPSs), which pose the threat of cyberattacks. To simulate and analyze the dynamic behavior of iCPS under cyber attacks, a unified iCPS model that integrates cyber and physical systems with profound interactions is indispensable. On the basis of a generic CPS architecture, we systematically model cyber and physical systems as discrete state-space equations, and simulate packet loss and delay in communication using Markov chains. Models for denial-of-service (DoS) attacks and false data injection (FDI) attacks have been delineated and applied to the unified iCPS model. Ultimately, the experimental results corroborate the feasibility and efficacy of the unified iCPS model. Furthermore, recommendations and guidelines are proposed to bolster the cybersecurity of bilateral control iCPSs.

Recent achievements in deep learning (DL) have demonstrated its potential in predicting traffic flows. Such predictions are beneficial for understanding the situation and making traffic control decisions. However, most state-of-the-art DL models are considered “black boxes” with little to no transparency of the underlying mechanisms for end users. Some previous studies attempted to “open the black box” and increase the interpretability of generated predictions. However, handling complex models on large-scale spatiotemporal data and discovering salient spatial and temporal patterns that significantly influence traffic flow remain challenging. To overcome these challenges, we present TrafPS , a visual analytics approach for interpreting traffic prediction outcomes to support decision-making in traffic management and urban planning. The measurements region SHAP and trajectory SHAP are proposed to quantify the impact of flow patterns on urban traffic at different levels. Based on the task requirements from domain experts, we employed an interactive visual interface for the multi-aspect exploration and analysis of significant flow patterns. Two real-world case studies demonstrate the effectiveness of TrafPS in identifying key routes and providing decision-making support for urban planning.

Higher-order patterns reveal sequential multistep state transitions, which are usually superior to origin-destination analyses that depict only first-order geospatial movement patterns. Conventional methods for higher-order movement modeling first construct a directed acyclic graph (DAG) of movements and then extract higher-order patterns from the DAG. However, DAG-based methods rely heavily on identifying movement keypoints, which are challenging for sparse movements and fail to consider the temporal variants critical for movements in urban environments. To overcome these limitations, we propose HoLens, a novel approach for modeling and visualizing higher-order movement patterns in the context of an urban environment. HoLens mainly makes twofold contributions: First, we designed an auto-adaptive movement aggregation algorithm that self-organizes movements hierarchically by considering spatial proximity, contextual information, and temporal variability. Second, we developed an interactive visual analytics interface comprising well-established visualization techniques, including the H-Flow for visualizing the higher-order patterns on the map and the higher-order state sequence chart for representing the higher-order state transitions. Two real-world case studies demonstrate that the method can adaptively aggregate data and exhibit the process of exploring higher-order patterns using HoLens. We also demonstrate the feasibility, usability, and effectiveness of our approach through expert interviews with three domain experts.

Anomaly detection in the Industrial Internet of Things (IIoT) is a challenging task that relies heavily on the efficient learning of multivariate time series representations. We introduce Skip-patching and Spatial-Temporal discrepancy mechanisms to improve the efficiency of detecting anomalies. Traditional feature extraction is hindered by redundant information in limited datasets. The situation is that feature generation from stable operational processes results in low-quality representations. To address this challenge, we propose the Skip-Patching mechanism. This approach involves selectively extracting features from partial data patches, prompting the model to learn more meaningful knowledge through self-supervised learning. It also effectively doubles the training sample size by creating independent sub-groups of patches. Despite the complex spatial and temporal relationships in IIoT systems, existing methods mainly extracted features from a single domain, either temporal or spatial (sensor-wise), or simply cascaded two features, i.e., one after one, which limited anomaly detection capabilities. To address this, we introduce the Spatial-Temporal Association Discrepancy component, which leverages discrepancies between spatial and temporal features to enhance latent representation learning. Our Skip-Patching Spatial-Temporal Anomaly Detection (SSAD) framework combines these two components to provide a more diverse and comprehensive learning process. Tested across four multivariate time series anomaly detection benchmarks, SSAD demonstrates superior performance, confirming the efficacy of combining Skip-patching and Spatial-Temporal features to enhance anomaly detection in IIoT systems.

Industrial cyber–physical systems (iCPSs) are the backbone of the fourth industrial revolution, facing more safety and security (S&S) challenges compared to traditional industrial systems. One of the most critical challenges is the collaborative analysis of S&S. Considerable efforts have been made toward integrating S&S and resolving their contradictions. However, a significant research gap remains regarding the accurate definition of contradictions in S&S requirements, along with an identification methodology. This study presents a systematical methodology to address this challenge. We propose two sufficient conditions that result in contradictions and provide algorithms to help their identification. Additionally, three measures have been proposed to reduce the difficulty of contradictions identification, including a conceptual model for iCPSs with S&S objectives to constrain objects and interactions within the model, a method for unifying the elicitation of S&S requirements, and a requirements template for coordinating the representation of S&S requirements. To provide insight into the operations of the methodology, we demonstrate its application in a smart factory. The results show that this approach can effectively identify the hidden contradictions in S&S requirements.

Positioning services are often required in industrial and public applications. The requirements for positioning systems include sufficient positioning accuracy, appropriate anchor deployment in complex scenarios, stability, and precise clock synchronization between anchors. Therefore, algorithms designed for single-room and simple laboratory scenarios are not suitable. To address these challenges, this paper proposes a comprehensive solution that combines ultra-wideband (UWB) technology, time difference of arrival (TDoA)-based positioning, and a cascaded wireless clock synchronization algorithm. First, we introduce the cascaded wireless clock synchronization algorithm. Second, we discuss the control algorithm for transmitting clock calibration packets (CCP) through wireless broadcast. Finally, we define the time of arrival selection strategy for time difference of arrival calculation. For multi-room scenarios, we present a positioning boundary optimization method based on received signal strength power and the first path power. This method performs well in real-world experiments.

The number of natural gas users has been growing rapidly in China due to the promotion of clean energy and the economic benefits of natural gas, especially in businesses and industries. Though the infrastructures for gas supplies have been highly improved, gas providers are still suffering from various problems such as malfunctioning gas meters, gas leakage, gas theft etc. With the development of the Internet of Things, smart gas meters have been widely adopted by gas providers to collect real-time gas consumption data for billing purposes which can also serve as a basis for anomaly detection. One challenge of using such data for anomaly detection is that it is difficult to obtain sufficient labelled data for model training. To address this challenge, we propose DAE, a data distillation enhanced autoencoder for detecting anomalous gas consumption, which consists of three modules. The first module preprocesses the raw meter readings and carries out a rule-based anomaly detection. The second module extracts the normal gas usage patterns via an integration of correlation and clustering based consistency evaluation methods. The extracted normal usage patterns are then used in the third module to train an autoencoder for anomaly detection. DAE intends to provide a method to detect anomalous gas consumption induced by various causes such that manual inspection can be largely reduced. Moreover, DAE does not require user-specific information and can be applied to different types of gas users. Based on a real-world gas consumption dataset, we carry out a set of experiments and show that DAE outperforms the existing and improves the F1 score by an average of 7.4% for restaurant users and 5.7% for canteen users.

Crowd gathering events deeply affect public safety. To enhance city management and avoid potential risks, many algorithms are designed for crowd analysis and deployed on video surveillance. Widely applied deep learning models also can be trained for crowd analysis. However, there are still few works focusing on crowd gathering behavior. Furthermore, as a result of the lack of interpretability of deep learning models, which also brings potential risk of being rejected by the users. In this paper, we categorize crowd behaviors into wandering, merging, walking gathering, standing gathering, and dispersing. Also, we propose an interpretable framework for crowd gathering understanding based on crowd density estimation model and proposed crowd descriptors, named Irregularity, Sparsity, Randomness, and Volatility. The experiments on the PETS2009 dataset demonstrate our method has outperformed the previous works on the crowd gathering understanding task. Moreover, we further analyze the framework performance with different crowd feature extraction models and the relations between our descriptors and crowd behavior. Besides, an ablation study is conducted to investigate the effectiveness of the descriptors and differences between density estimation models. The results demonstrate the effectiveness and the much better interpretability of our framework. Our descriptors also show significant contributions to the quantification of crowd gathering behaviors.

Deep learning (DL) has shown great potential in revolutionizing the traditional communications system. Many applications in communications have adopted DL techniques due to their powerful representation ability. However, the learning-based methods can be dependent on the training dataset and perform worse on unseen interference due to limited model generalizability and complexity. In this paper, we consider the semantic communication (SemCom) system with multiple users, where there is a limited number of training samples and unexpected interference. To improve the model generalization ability and reduce the model size, we propose a knowledge distillation (KD) based system where Transformer based encoder-decoder is implemented as the semantic encoder-decoder and fully connected neural networks are implemented as the channel encoder-decoder. Specifically, four types of knowledge transfer and model compression are analyzed. Important system and model parameters are considered, including the level of noise and interference, the number of interfering users and the size of the encoder and decoder. Numerical results demonstrate that KD significantly improves the robustness and the generalization ability when applied to unexpected interference, and it reduces the performance loss when compressing the model size.

LoRa technology is widely used to build wireless networks in various Internet of Things (IoT) applications. As the increased popularity of IoT, LoRa also gains tremendous attention in recent years. In most of the LoRa networks, the Aloha protocol is employed to send packets which may easily lead to collisions. Thanks to the orthogonality of spreading factor (SF) in modulate technique, a potential solution is obtained for this collision issue in the LoRa network. In this study, a reinforcement learning (RL)-based method called LR-RL is proposed to assign SF properly to alleviate collisions. The idea of LR-RL is mainly derived from the mathematical model of SF-channel traffic equilibrium, which indicates that SF with higher data rate must undertake more packet loads. Based on the system model, several similar methods, such as LR-opt-pro, LR-greedy, and LR-RL, are put forward successively. The LR-RL algorithm owns the best performance in terms of packet collision rate (PCR). In addition, we carry out simulations to evaluate the performance of LR-RL in both one-hop and LoRa-Mesh networks. Results show that LR-RL has lower PCR than other SF allocation methods. Moreover, practical experiments are also conducted to verify the performance. All the experiments exhibit that LR-RL is a desirable method to reduce packet collisions in the LoRa network.

Abnormality detection and identification is of great concern for complex processes monitoring. In chemical industrial parks (CIPs), the primary task is to identify abnormal (excess) sources when unexpected excess emissions occur. However, it is an ill-posed problem to detect, especially to identify them in dense industrial areas, where a vast number of emission sources are concentrated in limited space, challenging the relatively sparse wireless sensor networks (WSNs). Meanwhile, barely detecting the existence rather than identifying excess sources can hardly meet the requirements of fine management in CIPs. In this article, a QR decomposition-based method for excess sources identification (QR-ESI) has been proposed. By introducing equivalent sources (ES) as a substitute for real sources (RS), the semi-independent relation between ES and RS has been developed. By monitoring ES, excess sources can be inferred progressively through the iteration of logical judgments. The performance was evaluated with simulated data and then validated and compared with a state-of-the-art method in a case study in a real-world CIP.

Component-level heterogeneous redundancy is gaining popularity as an approach for preventing single-point security breaches in Industrial Control Systems (ICSs), especially with regard to core components such as Programmable Logic Controllers (PLCs). To take control of a system with component-level heterogeneous redundancy, an adversary must uncover and concurrently exploit vulnerabilities across multiple versions of hardened components. As such, attackers incur increased costs and delays when seeking to launch a successful attack. Existing approaches advocate attack resilience via pairwise comparison among outputs from multiple PLCs. These approaches incur increased resource costs due to them having a high degree of redundancy and do not address concurrent attacks. In this paper we address both issues, demonstrating a data-driven component selection approach that achieves a trade-off between resources cost and security. In particular, we propose (i) a novel dual-PLC ICS architecture with native pairwise comparison which can offer limited yet comparable defence against single-point breaches, (ii) a machine-learning based selection mechanisms which can deliver resilience against non-concurrent attacks under resource constraints, (iii) a scaled up variant of the proposed architecture to counteract concurrent attacks with modest resource implications.

Abstract Nowadays, the population has been overgrowing due to urbanization, yielding many severe problems in the urban area, including traffic congestion, unbalanced distribution of urban hotspots, air pollution and so on. Due to the uncertainty of the urban environment, it always needs to integrate experts' domain knowledge into solving these issues. In recent years, the visual analytics method has been widely used to assist domain experts in solving urban problems with its intuitiveness, interactivity and interpretability. In this survey, we first introduce the background of urban computing, present the motivation of visual analytics in the urban area and point out the characteristics of visual analytics methods. Second, we introduce the most frequently used urban data, analyse the main properties and provide an overview on how to use these data. Thereafter, we propose our taxonomy for visual analytics in the urban area and illustrate the taxonomy. The taxonomy provides four levels for visual analytics on urban data from a new perspective based on the four stages in data mining. Four levels from our taxonomy include: descriptive analytics, diagnostic analytics, predictive analytics and prescriptive analytics. Finally, we conclude this survey by discussing the limitations of the existing related works and the challenges to visual analytics in the urban area.

LoRa is one of the most promising techniques for the Internet of Things (IoT), and it has attracted considerable attention. Most existing LoRa applications follow the LoRaWAN specification and adopt a star topology. However, LoRaWAN networks are typically limited by their scalability due to the use of a centralized control strategy. The recent development of LoRa-Mesh networks can be a potential solution to this limitation. In this article, we propose a hierarchical-based energy-efficient (HBEE) routing protocol as a desirable method for building LoRa-Mesh networks. The HBEE exhibits the following advantages: 1) it can quickly build the network structure during the network formation stage by using contention-free concurrent transmission; 2) during the routing exploration phase, end-device nodes (ENs) can locate parent ENs with a minimized overhead; and 3) at the data collection stage, packet collision is minimized using multipath and multichannel routing method. Simulations are conducted to evaluate the performance of HBEE, and the results show that HBEE outperforms conventional ad hoc on-demand distance vector routing (AODV) protocol in terms of energy efficiency and transmission delay. Finally, proof-of-concept experiments are implemented in the real world. The results show that the packet reception rate of 95.7% and 89.8% can be achieved during network formation and normal operation phases, respectively.

Abstract A study is conducted with the aim to reveal the relationship between the performance of moving object tracking algorithms and tracking anchor (station) deployment. The dilution of precision (DoP) for the time difference of arrival (TDoA) technique with respect to anchor deployment is studied. Linear and non‐linear estimators are used for TDoA algorithms. The research findings for the linear estimator indicate that the DoP attains a lower value when other anchors are scattered around a central anchor; for the non‐linear estimator, the DoP is optimal when the anchors are scattered around the target tag. Experiments on both algorithms are conducted that target location precision related to anchor deployment in practical situations for tracking moving objects integrated with a Kalman filter in an ultra‐wideband (UWB)‐based real‐time localization system. The work provides a guideline for deploying anchors in UWB‐based tracking systems.

Density map is an effective visualization technique for depicting the scalar field distribution in 2D space. Conventional methods for constructing density maps are mainly based on Euclidean distance, limiting their applicability in urban analysis that shall consider road network and urban traffic. In this work, we propose a new method named Topology Density Map, targeting for accurate and intuitive density maps in the context of urban environment. Based on the various constraints of road connections and traffic conditions, the method first constructs a directed acyclic graph (DAG) that propagates nonlinear scalar fields along 1D road networks. Next, the method extends the scalar fields to a 2D space by identifying key intersecting points in the DAG and calculating the scalar fields for every point, yielding a weighted Voronoi diagram like effect of space division. Two case studies demonstrate that the Topology Density Map supplies accurate information to users and provides an intuitive visualization for decision making. An interview with domain experts demonstrates the feasibility, usability, and effectiveness of our method.

Time Synchronisation is one of the fundamental technologies in Wireless Sensor Networks (WSNs). However, most of the existing research focuses on clock estimation and message exchange to increase the synchronisation accuracy without taking network performance as the primary consideration. To improve the network energy conservation while balancing the time synchronisation accuracy, this paper introduces a new clock offset and skew estimation system for WSNs including a system model, a clock offset estimation method and a skew estimation method. The system adopts a sparse mesh network structure for establishing sensor node connections. In particular, the clock offset estimation uses a data preprocessing procedure to deal with missing data and outliers. The offset estimation considers both start-up delays and clock drifts. Local clock offsets and skews are estimated by timestamps from previous transmissions, even the current state of the transceivers is off. By carrying out a set of simulation experiments based on Network Simulator 2 (NS2), we show that the energy consumption of the individual sensor nodes is decreased with an acceptable time error rate.

Industrial control systems (ICSs) in networked environments face severe cyber-security risks and challenges. A timely response to cyber-attacks is of paramount importance for mitigating risks. However, the security policy developed for an ICS may be conflicting with the ICS's safety policy, on which much attention has been paid for a long time in industrial control. An inappropriate enforcement of the security policy may deteriorate the ICS performance or even result in severe unexpected consequences. To tackle this problem, a risk-based security task scheduling approach is presented for ICSs with consideration of the safety policy. It ensures a timely response to cyber-attacks without compromising safety. More specifically, the approach reconciles security tasks and safety tasks according to a designed resolution policy, so as to acquire contradiction-free security and safety (S&S) tasks. Then, a real-time risk assessment method is developed to characterize the subtle change of the system risk with the implementation of the reconciled S&S tasks. After that, a task scheduling method is designed with the risk as the optimization objective, i.e., it searches the optimal task scheduling scheme by minimizing the risk posture. The resulting scheduling scheme ensures the smooth implementation of the S&S policy, which reflects the optimal recovery process against the risk. Finally, case studies on a hardware-in-the-loop testbed are conducted to demonstrate the effectiveness of the proposed approach.

On-demand query-based in-network processing sensor system is used to improve power efficiency being a limited resource in sensing devices. In order to reduce energy consumption, data is only sent when requested and irrelevant data is eliminated through aggregation within an intermediate node. This technique is referred to as the in-network data processing techniques. In order to achieve this, we proposed an On Demand Query Sensing (ODQS) approach, a query-based engine that transfers the sensed data into aggregation functions at both the routing and the sink aggregator. Finally, we evaluated our experiment, and the results showed an improvement in energy saving using the aggregated functions. We also found that the energy consumed at each query is reduced to a significant ratio compared to the static sensing approach.

The optimization of the network throughput and transmission range is one of the most important issues in cognitive relay networks (CRNs). Existing research has focused on the dual-hop network, which cannot be extended to a triple-hop network due to its shortcomings, including the limited transmission range and one-way communication. In this paper, a novel, triple-hop relay scheme is proposed to implement time-division duplex (TDD) transmission among secondary users (SUs) in a three-phase transmission. Moreover, a superposition coding (SC) method is adopted for handling two-receiver cases in triple-hop networks with a cognitive relay. We studied a joint optimization of time and power allocation in all three phases, which is formulated as a nonlinear and concave problem. Both analytical and numerical results show that the proposed scheme is able to improve the throughput of SUs, and enlarge the transmission range of primary users (PUs) without increasing the number of hops.

The identification of the nonlinearity and coupling is crucial in nonlinear target tracking problem in collaborative sensor networks. According to the adaptive Kalman filtering (KF) method, the nonlinearity and coupling can be regarded as the model noise covariance, and estimated by minimizing the innovation or residual errors of the states. However, the method requires large time window of data to achieve reliable covariance measurement, making it impractical for nonlinear systems which are rapidly changing. To deal with the problem, a weighted optimization-based distributed KF algorithm (WODKF) is proposed in this paper. The algorithm enlarges the data size of each sensor by the received measurements and state estimates from its connected sensors instead of the time window. A new cost function is set as the weighted sum of the bias and oscillation of the state to estimate the "best" estimate of the model noise covariance. The bias and oscillation of the state of each sensor are estimated by polynomial fitting a time window of state estimates and measurements of the sensor and its neighbors weighted by the measurement noise covariance. The best estimate of the model noise covariance is computed by minimizing the weighted cost function using the exhaustive method. The sensor selection method is in addition to the algorithm to decrease the computation load of the filter and increase the scalability of the sensor network. The existence, suboptimality and stability analysis of the algorithm are given. The local probability data association method is used in the proposed algorithm for the multitarget tracking case. The algorithm is demonstrated in simulations on tracking examples for a random signal, one nonlinear target, and four nonlinear targets. Results show the feasibility and superiority of WODKF against other filtering algorithms for a large class of systems.

Intrusion response is a critical part of security protection. Compared with IT systems, industrial automation systems (IASs) have greater timeliness and availability demands. Real-time security policy enforcement of intrusion response is a challenge facing intrusion response for IASs. Inappropriate enforcement of the security policy can influence normal operation of the control system, and the loss caused by this security policy may even exceed that caused by cyberattacks. However, existing research about intrusion response focuses on security policy decisions and ignores security policy execution. This paper proposes a general, real-time control approach based on table-driven scheduling of intrusion response in IASs to address the problem of security policy execution. Security policy consists of a security service group, with each type of security service supported by a realization task set. Realization tasks from several task sets can be combined to form a response task set. In the proposed approach, first, a response task set is generated by a nondominated sorting genetic algorithm (GA) II with joint consideration of security performance and cost. Then, the system is reconfigured through an integrated scheduling scheme where system tasks and response tasks are mapped and scheduled together based on a GA. Furthermore, results from both numerical simulations and a real-application simulation show that the proposed method can implement the security policy in time with little effect on the system.

Industrial process automation is undergoing an increased use of information communication technologies due to high flexibility interoperability and easy administration. But it also induces new security risks to existing and future systems. Intrusion detection is a key technology for security protection. However, traditional intrusion detection systems for the IT domain are not entirely suitable for industrial process automation. In this paper, multiple models are constructed by comprehensively analyzing the multidomain knowledge of field control layers in industrial process automation, with consideration of two aspects: physics and information. And then, a novel multimodel-based anomaly intrusion detection system with embedded intelligence and resilient coordination for the field control system in industrial process automation is designed. In the system, an anomaly detection based on multimodel is proposed, and the corresponding intelligent detection algorithms are designed. Furthermore, to overcome the disadvantages of anomaly detection, a classifier based on an intelligent hidden Markov model, is designed to differentiate the actual attacks from faults. Finally, based on a combination simulation platform using optimized performance network engineering tool, the detection accuracy and the real-time performance of the proposed intrusion detection system are analyzed in detail. Experimental results clearly demonstrate that the proposed system has good performance in terms of high precision and good real-time capability.

The irrational use of limited network resources in conjunction with the unpredictable nature of traffic load injection in wireless multimedia sensor networks (WMSN) may lead to congestion. Traditional transmission schemes were not designed for supporting prioritized QoS, especially not for guaranteeing strict QoS required by real-time services such as voice and video. To overcome these deficiencies, an optimized rate control approach is proposed for multi-priority data transmission based on the extended Lotka-Volterra competitive model. The key idea is, when some new traffic flows are initialized and injected into the WMSN due to unexpected events, a novel bio-inspired rate control (Bio-RC) approach is designed to consider their effects on the system stability according to the limited network resources and competitions with others traffic flows, ensuring that the system will rapidly converge to a global and stable equilibrium point (EP) and all traffic flows are of peaceful coexistence and differentiated with QoS and priorities. At the same time, the network resources can be utilized adequately and congestion can be brought down or avoided effectively. Extensive simulations reveal that the proposed approach achieves adaptability and scalability to dynamic network traffic load, and coexistence with service differentiation for data flows.

A 2D localization system is constructed by using Wireless Sensor Nodes (WSN) to create a Virtual Fingerprint map. Linear and exponential taper functions are utilized with the received signal strength distributions between the fingerprint nodes to generate virtual fingerprint maps. Thus, a real and virtual combined fingerprint map is generated across the test area. k-NN and k-NN weighted algorithms have been implemented on virtual fingerprint maps to find the coordinates of the unknown objects. The system Localization accuracies of less than a grid space are obtained in calculations.

Recent developments in the field of home automation have shifted the technology away from the realms of research and into the homes of consumers. Together with the rapid adoption of the Internet, the ‘anywhere and anytime’ accessible home environment has been brought closer to a reality. Exciting as this prospect might be, significant security challenges arise from making the home environment accessible to anyone with Internet access. Hence, providing sufficient security to offer a reasonable level of protection for homeowner's privacy and safety is crucial for successful adoption of this technology. This study examines the security issues raised by the ‘anywhere and anytime’ accessible home environment. The existing approaches for addressing these security challenges and their weaknesses are reviewed. This study concludes with the proposal, implementation and evaluation of an improved approach for providing remote access security for the home environment.

Transmitting delay-sensitive video streaming over IEEE 802.11e wireless local area networks (WLANs) is becoming increasingly popular. However, the transmission of real-time video streaming is very challenging because of the time-varying wireless channels and video content characteristics. The authors propose an accurate model to assess the perceived quality of video streaming over WLANs with enhanced distributed coordination function (EDCF) mechanism. The analytical model considers not only the packet loss caused by wireless interference and channel fading, but also the effects of loss from channel access competition. Based on the Markov chain, the authors then present the discrete probability distribution of medium access control (MAC) layer packet service time by using the signal transfer function of the generalised state transition diagram. Moreover, the coding relation of lost video frames is also explored in the performance analysis of the proposed model. Simulations based on Network Simulator 2 (NS-2) are conducted to verify the performance of the analytical model. The results show that the proposed model provides superior accuracy for the perceived quality of MPEG-4 video streaming over IEEE 802.11e EDCF-based WLANs.

In this paper, immune systems and its relationships with multi-robot shepherding problems are discussed. The proposed algorithm is based on immune network theories that have many similarities with the multi-robot systems domain. The underlying immune-inspired cooperative mechanism of the algorithm is simulated and evaluated. The paper also describes a refinement of the memory-based immune network that enhances a robot's action-selection process. A refined model, which is based on the Immune Network T-cell-regulated — with Memory (INT-M) model, is applied to the dog–sheep scenario. The refinements involves the low-level behaviors of the robot dogs, namely shepherds' formation and shepherds' approach. These behaviors would make the shepherds form a line behind the group of sheep and also obey a safety zone of each flock, thus achieving better control of the flock and minimize flock separation occurrences. Simulation experiments are conducted on the Player/Stage robotics platform.

This paper aims to guarantee high-precision tracking of the desired optical path difference velocity for a Fourier transform spectrometer (FTS) in a space exploration system with time-varying parameters and nonlinear dynamics. A novel characteristic model-based adaptive discrete-time sliding mode control (ADSMC) scheme is proposed. The design of the ADSMC includes characteristic modeling, characteristic model-based discrete-time sliding mode control, and the estimator of the uncertain coefficients. The stability analysis of the ADSMC is also given in this paper. Simulation and experimental results demonstrate that the proposed characteristic model-based ADSMC can achieve high-precision control over a Michelson interferometer-based FTS. The significant advantages of the proposed ADSMC are its robustness and better control performance over the external disturbance and internal parameter uncertainty of the system.

Because of the recent developments in both wireless technologies and low power electronics, wireless devices consume less and less power and are promising the possibility to operate continuously by using energy harvesting technologies. The interest in Wireless Sensor Networks (WSNs), powered by environment energy harvesters, has been increasing over the last decade, especially those using thermal energy harvesting. In this paper, a low temperature thermal energy harvesting system, which can harvest heat energy from a temperature gradient and convert it into electrical energy, which can be used to power wireless electronics, is proposed. A prototype based on three subsystems is presented to extract heat energy from a radiator and use it to power ZigBee electronics. High efficiency and a long system lifetime are two of the main advantages of this design. The experimental results show that a maximum of 150mW power can be harvested by the prototype and the system can continue to operate normally when the harvesting voltage is as low as 0.45V. Theoretical calculations suggest that by placing the two AA batteries by proposed thermal energy harvesting system, a ZigBee Wireless Radiator Valve can operate for more than eight years.

Using wireless sensor network (WSN) to provide environmental data is becoming an increasingly important topic in the research area of building a smart house. As the standard designed for low data rate and low cost wireless personal area network, the IEEE 802.15.4 standard is widely employed in the construction of home sensor networks to assist the smart house application with a real-time environment information infrastructure. However, its working frequency (2.4 GHz ISM band) and low transmission power (typically 1 mW) make the system easily open to interference caused by other powerful wireless systems or signals which also work on the same frequency band, especially by Wi-Fi (IEEE 802.11b) systems. In this paper, we analyze the factors, which cause interference of the IEEE 802.15.4 system by Wi-Fi, and propose an interference mitigation strategy which utilizing the interferer's transmission interval to enable the IEEE 802.15.4 network to maintain communications during times of interference.

Random early detection (RED) can stabilize the queue within a given target range and simultaneously achieve high throughput in the routers. However, the average queue length is quite sensitive to the network scenarios and it is difficult to adapt RED parameters to the changing network traffic. This paper develops an algorithm for systematically adapting RED parameters to variable network conditions such as link capacity, round- trip time and the number of TCP flows. Simulations demonstrate that this algorithm can stabilize the queue length within a target range and maintain high link utilization in a wide variety of network traffic conditions.

This paper presents a Priority Checking Random Early Detection (PC-RED) gateway for ensuring the Quality of Service (QoS) of high priority dataflow in IPv6 networks. A bit in the IP header is used in PC-RED to label the current status of the QoS that the dataflow is being treated in, which is determined by the difference between the packet average-dropping rate and the fixed desired limit dropping rate of the dataflow. PC-RED would perform dissimilarly to every dataflow corresponding to the different QoS status throughout congestions. PC-RED has been modeled and the parameter setting has been studied. Simulation result shows remarkable contrast between the High-Priority and Non-Priority dataflow throughput under PC-RED mechanism.

Internet-based control is a way of using the internet as a platform for remote monitoring and control operation. The obvious benefit is to enable remote monitoring and maintenance of process plants and to initiate global collaboration and data sharing between operators from geographically dispersed locations. However, connection to an open network and the use of universal technology present high safety and security risks to the new generations of control systems. Are we opening up our internet-enabled control systems for trouble since a number of malicious hackers continually attack web servers on the internet? The new type of control systems will never be accepted by industries if people do not have enough confidence in their safety and do not feel secure by using the system. This paper presents a framework of security and safety checking, used in the design of internet-based control systems. Based on the existing measures of physical and network securities, such as firewall and comprehensive user-authorised access control, the framework proposed in this paper focuses on the security of control commands transferred over the internet, responding actions to malicious attacks and system safety. An internet-based control system for a process rig is used as a case study to illustrate the implementation of the framework.

One of the major challenges in Internet-based control systems is how to overcome the Internet transmission delay. In this paper, we investigate the potential of using the multirate control scheme and the time-delay compensation to overcome the Internet transmission delay. A two-level hierarchy is used for the Internet-based control systems. At the lower level, a local controller is implemented to control the plant at a higher frequency. At the higher level, a remote controller is employed to remotely regulate the desirable set-point at a lower frequency for the local controller. A compensator located at the feedback channel is designed to overcome the time delay occurring in the transmission from the local site to a remote site. Another compensator in the feedforward channel is designed to compensate the time-delay occurring in the control action transmission. The simulation and experimental application results illustrate that the multirate control scheme with the time delay compensation offers a promising way to efficiently reduce the effect of Internet time delay on control performance

This paper investigates and improves a technique known as Nonlinear Dynamic Data Reconciliation (NDDR) for a real industrial process. NDDRS is a technique for data reconciliation that requires an objective function to be minimised subject to both algebraic and differential, equality and inequality constraints. These constraints are obtained from the mathematical description of the process and ensure that the measurement data can be optimised to conform as closely as possible to the true behaviour of the process. One of the difficulties of using the original NDDR is that a rigorous process dynamic model is required as a constraint. Unfortunately it is very hard to establish a rigorous dynamic model for a complex industrial process, particularly for data reconciliation purpose. A transfer function matrix model has been introduced in this new NDDR method. Therefore the rigorous dynamic model is avoided. The real industrial data from FCCU is used to illustrate the efficiency of the new NDDR method.

Intelligent home environments are one of the major application areas of pervasive computing. Safety and security are two most important issues in the remote monitoring and control of intelligent home environments. This article takes safety and security into consideration together and proposes a phone-out-only policy for ensuring security and virtual home environments for safety. A remote monitoring and control system for a security camera is used to illustrate the new methodologies for safety and security. By using the demonstration system people are able to easily monitor and control a security camera, central heating, microwave oven and washer from anywhere by using mobile phones. Our system distinguishes from the existing DTI (Department of Trade and Industry in the UK) next wave technologies and a few of on-going EU projects in the ways of dealing with safety and security and its simplicity. Remote monitoring and control of intelligent home environments can be of great benefits to the working families and holiday makers and has a great commercial potential.

Wireless sensor networks (WSN) are designed to collect and process sensory data from environments. Some environments are dangerous or un-reachable to human beings and it is difficult to replace sensor nodes when they are out of battery or even destroyed, i.e. wireless sensor nodes are in general prone to failure. This kind of characteristics require WSN to detect whether or not its next destination is still available (alive) and to maintain a transferring path if the next destination in the route does not exist (dead). In the normal state, nodes are in power-saving 'sleep' state. When a route is created for some purpose, all nodes in this route will be active and be ready to respond requests from its neighbors. Our approach is to maintain the routing table up-to-date by sending message from a last node to its next node and judging whether the next node is alive according to the response. If problems happen, node will self-organize and try to maintain transferring.

The paper focuses on the hardware architectures of wireless sensor nodes based on the IEEE 802.15.4/ZigBee protocol. It reviews the solutions provided by some main commonly used chip manufacturers, lists some of typical components and part of their parameters related to power consumption. The paper discusses the architecture of a canonical node and its subsystems, and analyzes the special requirements of wireless sensor nodes for building fire safety. A possible hardware architecture, centering routine transactions, of wireless sensor node, is presented.

Abstract This paper describes an approach for the integration of control system software design, testing, and implementation over the Internet using the Java and Jini technologies. Process models and control systems are remotely designed and tested in a virtual laboratory (also called the virtual world), and then implemented in a physical plant (also called the real world) through an integrated environment. Although control system and process model designers and real‐site operators are geographically dispersed they work together as a team over the Internet to provide the maintenance support to all the authorized industrial processes. As a consequence, time and money can both be saved because there is no need for an expert of the control software supplier to travel to the site of the real plant and conduct on‐site implementation. A generic control system life cycle model is presented first in this paper. Then three enabling technologies including Java, Jini and WWW are briefly introduced. Taking advantage of the Java, Jini and WWW technologies, an Internet‐based general infrastructure is proposed to remotely facilitate process modelling, control system design, simulation, validation and on‐site implementation. An integrated environment is established to implement the infrastructure. A water tank with a liquid level control system is refereed as a case study to illustrate how the prototype of the integrated environment works over the Internet. Further work and the conclusions are given at the end. Copyright © 2003 John Wiley & Sons, Ltd.

The Internet is playing an important role not only in information retrieval, but also in industrial process manipulation. This paper describes an approach to writing requirements specifications for Internet-based control systems and to deriving architecture for this new type of control system according to the requirements specification. Specification is described in terms of a functional model and then extended into information architecture. In contrast to the functional model, the information architecture gives an indication to the architecture of the Internet-based control systems. An integrated-distributed architecture has been derived from the functional model and the information architecture as a case study.