Extended object detection and tracking (EODT) is becoming a promising alternative for autonomous perception, which provides not only common motion states but also accurate spatial extent information, such as shape and size estimations. However, due to uncoordinated radar transmissions in zero-trust autonomous driving scenarios, radar-based EODT systems suffer from mutual radio frequency (RF) interference launched by attackers, leading to ghost targets and increased noise. On this account, a novel joint anti-interference detection and tracking system for weak extended targets is presented in this paper. In contrast to pioneering works that treat object detection and tracking as two separate steps, the proposed method handles them jointly by integrating a continuous detection process into tracking, improving the detectability of weak targets. More specifically, to accommodate the time-varying number and extended size of radar reflections, an adaptive spatial distribution model representing the deformable extents is incorporated to capture the contour evolution over time. The key insight is that by accumulating the reflected power, all backscattered points are regarded as one entity to match the real target so that the intractable data association problem can be circumvented in the proposed method. Unlike the prominent random matrix model-based approaches that split motion and extent states into independent parts, this study explores the interdependencies between the states and updates them simultaneously. In addition, the proposed system has been deployed on a low-cost automotive radar platform. Experimental results confirm that the proposed approach can achieve accurate and resilient EODT against RF interference attacks, especially in occlusion, dynamic motion switching, and complex multiple extended target tracking scenarios. A demonstration video with EODT results is available in the supplementary materials.

Due to the small radar cross section (RCS), pedestrians are typical low-observable traffic participants for radar-based automotive perception systems. The early detection and understanding of pedestrians’ activities are of great significance to automotive safety. To this end, this paper presents an end-to-end joint tracking and activity estimation (RETA) system based on 4D automotive radar, which deals in particular with pedestrian activity identification under cluttered real-world scenes. Firstly, a novel integrated detection and tracking algorithm is proposed to guarantee positioning accuracy, in which all unthresholded 4D radar measurements are incorporated to explore the spatial coherent information across multiple frames, avoiding weak target information loss. After that, to discriminate continuous activities with varying durations in sequential trajectories, this paper innovatively presents a decomposed connectionist recurrent convolutional neural network, which facilitates fused temporal-spatial motion feature extraction. Especially, the labor-consuming activity pre-segmentation problem is circumvented with the help of a connectionist temporal classification algorithm in the proposed neural network. At last, RETA can be implemented for real end-to-end perception applications. Extensive experiment results highlight its superiority and effectiveness by attaining a continuous recognition accuracy of 94.8%. To the best of our knowledge, this is the first end-to-end activity recognition system specific for low-observable pedestrians. A demonstration video recorded in challenging practical traffic scenarios has been uploaded in the supplementary materials.

Unmanned aerial vehicle (UAV) communications and networks are promising technologies in the forthcoming 5G/6G wireless communications. However, they have challenges for realizing secure communications. In this paper, we consider to construct a virtual antenna array consists UAV elements and use collaborative beamforming (CB) to achieve the UAV secure communications with different base stations (BSs), subject to the known and unknown eavesdroppers on the ground. To achieve a better secure performance, the UAV elements can fly to optimal positions with optimal excitation current weights for performing CB transmissions. However, this leads to extra motion energy consumption. We formulate a physical layer secure communication multi-objective optimization problem (MOP) of UAV networks to simultaneously improve the total secrecy rates, total maximum sidelobe level (SLL) and total motion energy consumption of UAVs by jointly optimizing the positions and excitation current weights of UAVs, and the order of communicating with different BSs. Due to the complexity and NP-hardness of the formulated MOP, we propose an improved multi-objective dragonfly algorithm with chaotic solution initialization and hybrid solution update operators (IMODACH) and a parallel-IMODACH (P-IMODACH) to solve the problem. Simulation results verify that the proposed approaches can effectively solve the formulated MOP and it has better performance than some other benchmark algorithms and approaches. Moreover, some unexpected circumstances are considered and discussed.

Reinforcement learning (RL) methods can be used to develop a controller for the heating, ventilation, and air conditioning (HVAC) systems that both saves energy and ensures high occupants’ thermal comfort levels. However, the existing works typically require on-policy data to train an RL agent, and the occupants’ personalized thermal preferences are not considered, which is limited in the real-world scenarios. This paper designs a high-performance model-based offline RL algorithm for personalized HVAC systems. The proposed algorithm can quickly adapt to different occupants’ thermal preferences with a few thermal feedbacks, guaranteeing the high occupants’ personalized thermal comfort levels efficiently. First, we use a meta-supervised learning algorithm to train an occupant's thermal preference model. Then, we train an ensemble neural network to predict the thermal states of the considered zone. In addition, the obtained ensemble networks can indicate the regions in the state and action spaces covered by the offline dataset. With the personalized thermal preference model updated via meta-testing, model-based RL is used to derive the optimal HVAC controller. Since the proposed algorithm only requires offline datasets and a few online thermal feedbacks for training, it contributes to a more practical deployment of the RL algorithm to HVAC systems. We use the ASHRAE database II to verify the effectiveness and advantage of the meta-learning algorithm for modeling different occupants’ thermal preferences. Numerical simulations on the EnergyPlus environment demonstrate that the proposed algorithm can guarantee personalized thermal preferences with a slight increase of power consumption of 1.91% compared with the model-based RL algorithm with on-policy data aggregation.

This article proposes a novel learning-based control strategy, named MBRL-MC, for the heating, ventilation, and air conditioning (HVAC) system by combining model-based deep reinforcement learning (DRL) and model predictive control (MPC). First, a thermal dynamic model of the zone is learned by a supervised learning algorithm. Based on the learned model, a neural network (NN) planning framework is designed which leverages the ideas of both reinforcement learning (RL) and MPC. The proposed planning algorithm is directly obtained without imitating the results of MPC random shooting, which avoids the compounding error during the learning procedure. In addition, the bootstrapping technique is not employed by our algorithm when constructing the update target of the critic network, which improves the learning stability. The cross-entropy method is further used to augment the RL algorithm in order to avoid potential divergence. Finally, simulation experiments in the EnergyPlus environment demonstrate the effectiveness of the proposed algorithm. The comparisons with the existing algorithms show the advantages of MBRL-MC.

Unmanned aerial vehicle (UAV) communications and networks are promising technologies in the forthcoming fifth-generation wireless communications. However, they have the challenges for realizing secure communications. In this paper, we consider to construct a virtual antenna array consists UAV elements and use collaborative beamforming (CB) to achieve the UAV secure communications with different base stations (BSs), subject to the known and unknown eavesdroppers on the ground. To achieve a better secure performance, the UAV elements can fly to optimal positions with optimal excitation current weights for performing CB transmissions. However, this leads to extra motion energy consumptions. We formulate a secure communication multi-objective optimization problem (MOP) of UAV networks to simultaneously improve the total secrecy rates, total maximum sidelobe levels (SLLs) and total motion energy consumptions of UAVs by jointly optimizing the positions and excitation current weights of UAVs, and the order of communicating with different BSs. Due to the complexity and NP-hardness of the formulated MOP, we propose an improved multi-objective dragonfly algorithm with chaotic solution initialization and hybrid solution update operators (IMODACH) to solve the problem. Simulation results verify that the proposed IMODACH can effectively solve the formulated MOP and it has better performance than some other benchmark approaches.

Objective: Non-contact sensing of seismocardiogram (SCG) signals through a microwave Doppler radar is promising for biomedical applications. However, the delineation of fiducial points for radar SCG still relies on concurrent ECG which requires a contact sensor and limits the complete non-contact detection of SCG. Methods: Instead of ECG, a new reference signal, the radar displacement signal of heartbeat (RDH), was derived through the complex Fourier transform and the band pass filtering of the radar signal. The RDH signal was used to locate each cardiac cycle and mask the systolic profile, which was further used to detect an important fiducial point, aortic valve opening (AO). The beat-to-beat interval was estimated from AO-AO interval and compared with the gold standard, ECG R-to-R interval. Results: For the 22 subjects in the study, the evaluation of the AOs detected by RDH (AORDH) shows the average detection ratio can reach 90%, indicating a high ratio of the AORDHthat are exactly the same as AO detected using the ECG R-wave (AOECG). Additionally, the left ventricular ejection time (LVET) values estimated from the ensemble averaged radar waveform through AORDHsegmentation are within 2 ms of those through AOECGsegmentation, for all the detected subjects. Further analysis demonstrates that the beat-to-beat intervals calculated from AORDHhave an average root-mean-square-deviation (RMSD) of 53.73 ms when compared with ECG R-to-R intervals, and have an average RMSD of 23.47 ms after removing the beats in which AO cannot be identified. Conclusions: Radar signal RDH can be used as a reference signal to delineate fiducial points for non-contact radar SCG signals. Significance: This study can be applied to develop complete non-contact sensing of SCG and monitoring of vital signs, where contact-based SCG is not feasible.

Collaborative beamforming (CB) in wireless sensor networks (WSNs) based on a virtual node antenna array (VNAA) can increase the transmission distance and enhance the energy efficiency of sensor nodes. However, a VNAA cannot be pre-designed like the conventional antenna arrays due to the randomly deployed sensor nodes, thereby causing a high sidelobe level (SLL) which increases the interferences. In this article, we formulate a hybrid discrete and continuous optimization problem (HDCOP) for reducing the maximum SLL. HDCOP requires to solve both the discrete and the continuous problems simultaneously, and we propose both centralized and consensus-based distributed CB strategies for solving HDCOP. For the centralized strategy, we convert HDCOP into two sub-optimization problems, and propose a discrete cuckoo search (CS) algorithm for the node location selection optimization and a continuous CS algorithm to optimize the excitation current weights of the selected nodes. For the distributed strategy, we propose a parallel distributed CS algorithm to solve the discrete and continuous parts of HDCOP simultaneously. Moreover, we propose two operating mechanisms based on these two algorithms. Simulation results verify the effectiveness of the proposed strategies for reducing the maximum SLL of CB in WSNs. Moreover, the proposed CB strategies have better performance in terms of the energy efficiency compared with other approaches such as the cross-entropy optimization-based method.

Mobile wireless sensor networks (MWSNs) are resource constrained, and have limited energy and transmission range. Distributed collaborative beamforming (DCB) in MWSNs based on a virtual node antenna array (VNAA) can increase the transmission distance and enhance the energy efficiency of a single sensor node. To achieve a lower maximum sidelobe level (SLL), sensor nodes can move to optimal locations with optimal excitation current weights for DCB. However, this leads to an extra motion energy consumption. In this article, we construct a multiobjective optimization framework (MOF) to jointly optimize the maximum SLL, transmission power, and motion energy consumption of the DCB nodes in MWSNs. Moreover, an improved nondominated sorting genetic algorithm-II (INSGA-II) and a distributed parallel INSGA-II (DPINSGA-II) are proposed for solving the formulated MOF. In addition, a simple but practical DCB scheduling mechanism is proposed. The simulation results show that the maximum SLL, transmission power, and motion energy consumption of the VNAA can be effectively optimized by the proposed algorithms.

In this article, the self-aware power management framework is investigated for maintaining event detection probability of supercapacitor-powered cyber-physical systems, with a radar network system as an example. Maintaining the event detection probability of the radar network is decomposed as a problem of controlling the quality of service of each network node. Then a power management method based on model predictive control and particle swarm optimization is proposed for tracking the reference quality of service of each node while satisfying the operation constraints. The effectiveness of the proposed method is demonstrated through three simulation studies that cover both single node and network scenarios. In addition, to support the proposed power management method, an online state of charge prediction method is developed for the supercapacitor. The online prediction method adopts a supercapacitor model that describes both the ohmic leakage and charge redistribution phenomena and uses online model updating to more accurately capture the supercapacitor behavior and estimate the stored energy.

Conventional collaborative beamforming with virtual node antenna array often results in high maximum sidelobe level (SLL) due to the unexpected node positions. In this paper, a hybrid optimization approach (HOA) for the SLL suppression and transmission power reduction is proposed. The proposed HOA organizes the node locations according to the concentric circular antenna array for location optimization. Then, a novel algorithm called variation particle chicken swarm optimization (VPCSO) is proposed to further optimize the transmission power weight of the selected array nodes. Simulations are conducted and the results show that the proposed location optimization approach is effective, and the maximum SLL of the beam patterns obtained by VPCSO is lower than that of other algorithms. Moreover, the overall transmission power weights obtained by the proposed VPCSO is the lowest among all the comparison methods.

Antenna arrays can enhance the directivity and save the transmission power of a communication system. Beam pattern optimization for reducing the maximum sidelobe level (SLL) is a classical electromagnetic problem in antenna arrays. In this paper, a novel improved chicken swarm optimization (ICSO) algorithm is proposed to suppress the maximum SLL of the linear antenna array (LAA), the circular antenna array (CAA) and the random antenna array (RAA). Three improved factors that are the global search, the weighting and the local search factors are introduced into the update method of the roosters, the hens and the chicks of the conventional chicken swarm optimization (CSO), respectively, to achieve better optimization results. Simulations are conducted to verify the performance of the proposed ICSO for suppressing the maximum SLL, and the results show that the proposed ICSO can obtain lower maximum SLL in LAA, CAA and RAA cases compared with several benchmark algorithms. Moreover, the stability of ICSO is evaluated and the results show that it outperforms the other algorithms.

Internet of Battery-less Things (IoBT) has recently emerged as a promising solution to enable prolonged lifetime for Internet of Things, by utilizing energy harvesting technology. With insufficient computational power reside in and time-varying energy availability for a single IoBT system, collaborative operation is desired to shorten the data processing time for IoBT networks. In this paper, we propose a novel collaborative in-network processing framework, combining feasibility check, latency-aware data partition (LDP), and joint computation and transmission optimization (JCTO). At the beginning of every slot, a capacity planning module provides an upper bound of the feasible input data size for the IoBT networks. LDP reduces the overall latency by providing efficient input data partition and considering the latency and remaining energy constraints. By jointly optimizing the micro control unit frequency and wireless transmit power, the proposed framework further reduces the overall data processing latency. The real world energy harvesting profiles are used to evaluate the performance of the proposed methodology. Compared with the existing strategies, the proposed framework achieves significantly lower overall latency of collaborative in-network processing. The simulation results also show that the overall latency is close to the minimal latency after three rounds of iterative optimizations of LDP and JCTO.

Mobile wireless sensor networks (MWSN) are resource constrained, and have limited energy and transmission range. Distributed collaborative beamforming (DCB) in MWSN based on a virtual node antenna array (VNAA) can increase the transmission distance and enhance energy efficiency of a single sensor node. To achieve a lower maximum sidelobe level (SLL), sensor nodes can move to optimal locations with optimal excitation currents for DCB. However, this leads to an extra motion energy consumption. In this paper, we construct a multi-objective optimization framework to jointly optimize the maximum SLL, the transmission power and the motion energy consumption of the DCB nodes in MWSN. Moreover, an improved non-dorminated sorting genetic algorithm-II (INSGAII) is proposed for solving the optimization problem. Simulation results show that the maximum SLL, the transmission power and the motion energy consumption of the VNAA can be effectively optimized by the proposed algorithms.

Recent advances in energy harvesting and green communication technologies give rise to the emerging Internet of Battery-less Things (IoBT). With prolonged lifetime and dense deployment, IoBT-operated networks contain huge computational power that is not fully utilized. With time-varying renewable energy, it is non-trivial to process latency-sensitive tasks in IoBT networks. In this paper, we propose a novel in-network computing framework to efficiently process latency-sensitive tasks. At the beginning of each time slot, the proposed framework first conducts task capacity check to derive the upper bound of the input data size that can be processed within the deadline. Then, a latency-aware data partition algorithm is developed to minimize the overall latency by jointly considering the energy budget and node position. The real world energy harvesting profiles are used to evaluate the proposed method. The simulation results demonstrate that the proposed method achieves significantly lower latency compared with the existing strategies for IoBT systems with varying ambient energy generation.

The sparse synthesis of the concentric circular antenna array (CCAA) is a very important technology because it is able to reduce the cost of the antenna array. In this paper, we first formulate a multi-objective optimization problem to jointly reduce the maximum sidelobe level (SLL) and the number of the switched-on elements of the CCAA. Then, we propose a novel enhanced non-dominated sorting genetic algorithm-II (ENSGA-II) to solve this problem. ENSGA-II introduces a hierarchy mechanism to improve the population utilization of the conventional non-dominated sorting genetic algorithm, thereby enhancing the accuracy and the convergence rate of the algorithm. Simulation results show that ENSGA-II obtains a lower maximum SLL with the similar number the switched-off elements compared with other algorithms. Moreover, ENSGA-II has a faster convergence rate.

A wireless rechargeable sensor network (WRSN) consists of sensor nodes that can harvest energy from the wireless charging nodes (WCNs) for prolonging the network lifetime. This study deals with the WCN deployment optimization problem in WRSNs. We present an optimization framework that simultaneously maximizes the coverage and the charging efficiency. Moreover, an improved firefly algorithm (IFA) is proposed for solving the WCN deployment optimization problem. IFA adopts a novel adaptive attractiveness factor and introduces a dynamic location update mechanism to enhance the performance of the normal firefly algorithm (FA). We compare the proposed IFA with several benchmark algorithms in two different scenarios. Simulation results show that the proposed algorithm outperforms other comparative algorithms in both accuracy and convergence rate.

Enabled by energy harvesting technology, Internet of Battery-less Things (IoBTs) have been attracting increasing attention, as lifetime and battery capacity throttle the performance of Internet of Things (IoTs). Due to the dynamism of ambient energy generation, it is non-trivial for IoBT nodes to work collaboratively and deliver information in high throughput. In this paper, we propose a novel adaptive clustering framework for IoBT systems, combining optimal Cluster Head (CH) selection and Lexicographic Rate Assignment. Using the remaining energy level of each IoBT node as the energy budget, the proposed framework assigns a lexicographic optimal rate vector that enables each node to fully utilize the scavenged energy and achieve high transmission rate. For each possible CH candidate, the proposed clustering framework evaluates the throughput it can provide, and then select the one with the highest rate as the CH node to optimize the performance of the cluster. Real world energy harvesting profile is used to validate the effectiveness of the proposed methodology. The simulation results demonstrate that the proposed framework achieves higher throughput when compared with the existing strategies and is robust to the varying ambient energy.

A novel approach to suppress the maximum sidelobe level (SLL) with specific half power beam width (HPBW) of concentric circular antenna array (CCAA) is proposed. The approach is based on the cuckoo search (CS) algorithm, which is an effective optimization method for continuous problems. However, the sparse array synthesis is a discrete problem, so an improved discrete cuckoo search algorithm (IDCSA) is presented by introducing the nest location coding discretization, mapping method based on jumping path, and improved egg elimination mechanism, thereby optimizing the beam pattern of the CCAA. Simulation results show that IDCSA can obtain a lower maximum SLL with the same HPBW compared with other algorithms. Moreover, IDCSA has a faster convergence rate. In addition, the thinning rate of the antenna array can reach more than 50%, thereby resulting in cost savings after optimization.

Empowered by energy harvesting technology, Internet of Batteryless Things (IoBT) is considered to be a promising solution for the lifetime constraint of Internet of Things. The varying ambient energy source makes it nontrivial for multiple IoBT nodes to work collaboratively and achieve high-throughput data collection. In this paper, we propose a novel clustered data collection framework for IoBT networks, combining cluster head (CH) selection and lexicographic rate assignment. Using the remaining energy level of the energy storage device as the energy budget, the proposed framework assigns a lexicographic optimal rate vector that enables each IoBT node to fully utilize the scavenged energy and at the same time achieve high and fair data collection rate. Two CH selection schemes are developed. One is optimal CH selection by traversing all the possible CH candidates in the cluster. The other is an approximation search based on the inherent energy consumption features of the lexicographic optimal rate assignment. The real world energy harvesting profile is used to validate the effectiveness of the proposed methodology. Compared with the existing strategies, the proposed framework achieves higher throughput over all range of the data aggregation ratio. The simulation results also demonstrate that the approximation-based CH selection scheme has similar data collection rate performance as that of the optimal CH selection scheme at a much lower computational cost.