Gradient leakage attacks pose significant privacy risks in federated learning by exploiting transmitted gradients to reconstruct sensitive data. While existing defense mechanisms typically apply uniform perturbation across all gradients, we identify a critical oversight: privacy information in gradients exhibits inherent layer-wise heterogeneity. Through systematic analysis, we establish that different neural network layers contain varying amounts of reconstructable private information due to differential accumulation of nonlinear effects during gradient formation. This fundamental discovery enables our key innovation—Layer-Specific Gradient Protection (LSGP)—which pioneers surgical defense mechanisms that adapt protection intensity to each layer’s inherent privacy exposure level. Experimental results validate that LSGP achieves superior defense efficacy with comparable model utility compared to uniform protection baselines, establishing a new paradigm for efficient privacy-preserving machine learning through principled vulnerability analysis of gradient formation mechanics.

The increasing parameters and expansive dataset of large lan- guage models (LLMs) highlight the urgent demand for a technical solution to audit the underlying privacy risks and copyright issues associated with LLMs. Existing studies have partially addressed this need through an exploration of the pre-training data detection problem, which is an instance of a membership inference attack (MIA). This problem involves determining whether a given piece of text has been used during the pre-training phase of the target LLM. Although existing methods have designed various sophisticated MIA score functions to achieve considerable detection performance in pre-trained LLMs, how to achieve high-confidence detection and how to perform MIA on aligned LLMs remain challenging. In this paper, we propose MIA-Tuner, a novel instruction-based MIA method, which instructs LLMs themselves to serve as a more precise pre-training data detector internally, rather than design an external MIA score function. Furthermore, we design two instruction-based safeguards to respectively mitigate the privacy risks brought by the existing methods and MIA-Tuner. To comprehensively evaluate the most recent state-of-the-art LLMs, we collect a more up-to-date MIA benchmark dataset, named WIKIMIA-24, to replace the widely adopted benchmark WIKIMIA. We conduct extensive experiments across various aligned and unaligned LLMs over the two benchmark datasets. The results demonstrate that MIA-Tuner increases the AUC of MIAs from 0.7 to a significantly high level of 0.9.

MmWave imaging assisted by metasurfaces is a burgeoning technique attributed to its fine-grained imaging ability by time-varying phase coding, which produces a large virtual aperture. To obtain stereoscopic 3D perception, multiple metasurfaces can be utilized for virtual multiview fusion, allowing for the capture of features that are not visible from a single viewpoint. However, the multipath imaging fusion faces huge data burden and the environment clutter especially reflection from the direct path will cause disturbance. To address these issues, this paper introduces Bayesian compressive sensing to focus on the region of interest (ROI) and design a double sparse prior for high-resolution multiview image reconstruction. First, multiple metasurfaces are utilized to generate virtual multiview imaging results. Then, the Bayesian inference method is leveraged to resist environmental noise and achieve autofocusing imaging with undersampled data. The expectation propagation (EP) is introduced to estimate the statistical parameter iteratively. Further, a double sparse prior is designed based on spike-and-slab to promote inter-sparsity and intra-sparsity simultaneously. Simulation results show that our proposed system demonstrates superior performance by fusing sparse images from multiple metasurfaces arrangements.

Metasurface-aided near-field radio imaging is emerging as an essential part of the future mmWave communication systems. Adjusting the metasurface phase shift to generate multiple measurements can significantly increase the system imaging aperture and enhance the resolution. However, this imaging technique relies heavily on precise measurements, and high-precision sampling leads to expensive hardware costs and memory burdens. To address this issue, this paper draws inspiration from binary compressive sensing and proposes a method for imaging under one-bit quantization. First, we propose a dynamic metasurface-aided mmWave imaging system with one-bit sampling, which simplifies the received signal acquisition process and significantly reduces the hardware and storage requirements. Then, a fused binary compressive sensing model is developed with an additional total-variation norm penalty to promote target continuity and suppress artifacts in mmWave images. Subsequently, we employ the proximal binary iterative hard thresholding algorithm to optimize the joint sparsity and the total variation (TV) constraints. In addition, the hybrid ℓ1-TV constraint is introduced to solve the problem of unknown a priori sparsity of image, and the alternating direction multiplication method is designed for effective reconstruction. Finally, the simulation results show that the proposed algorithms can utilize the target features under binary measurements and achieve better imaging accuracy and focusing performance than the sparsity constraint-only methods.

Underground wireless communication technique facilitates various emerging applications such as infrastructure health monitoring and collapse rescue, which is suffering in the significant attenuation and reliability problem. Magnetic induction (MI) thus was introduced to enhance underground wireless transmission, as it can provide high penetration capability and low path loss in underground endogenous environment. However, due to the complex signal propagation mechanism and the neglection of coil antenna detailed structure, the receive signal strength indicator (RSSI) prediction is a great challenge in the underground environment. This paper develops an end-to-end numerical model considering the geometric configuration of the coil antenna and the complex soil dielectric behavior. The developed model is validated using the numerical analysis and finite element simulation in different underground endogenous environments. Compared to other models, the developed end-to-end numerical model provides considerable improvement in accuracy of RSSI in underground endogenous environment.

Magnetic antennas, due to their unique operating mechanism, have demonstrated excellent anti-interference capability and signal penetration in complex environments, leading to their rapid development in recent years. However, its inherent narrow-band characteristics limit the data transmission rate and affect the practical application range. Based on the frequency splitting phenomenon, this paper proposes a method for expanding the bandwidth of magnetic antennas by using parasitic structures and presents the equivalent circuit at the transmitting end. By introducing parasitic coil at the transmitter (TX) side and optimizing the system characteristics, the transmission bandwidth is increased by about 3 times, while the peak power is decreased by only 2.1 dB. In this paper, the influence of parasitic coil layout on the bandwidth of magnetic antenna is systematically discussed by combining the theoretical analysis, simulation calculations and experimental verification. The results show that the reasonable adjustment of the parasitic separation can effectively control the degree of frequency splitting and realize the broadband characteristics of the magnetic antenna, which provides a new idea for its application in high-efficiency wireless communication.

We study the problem of Non-line-of-sight (NLOS) mmWave imaging under inaccurate knowledge of multiangle relay surfaces. To this end, we propose a novel double sparse structure-enhanced Bayesian compressive sensing framework with dictionary parameters updating. First, the hierarchical probabilistic model with a parametric multipath dictionary is constructed, where the angles of multiple relay surface are considered as an unknown parameter. Then, a double sparse spike-and-slab (DS-SS) prior is introduced to model the intra-group and inter-group sparsity of multipath image, where the expectation propagation method is employed for posterior inference (dubbed as DS-SSEP). Moreover, the maximum likelihood solutions of the dictionary parameters are estimated iteratively by coupling the expectation maximization framework with DS-SSEP. Several experiments demonstrate the superiority of our proposed method, which significantly reduces image reconstruction errors in imprecise layout scenarios.

Utilizing device mobility to form virtual large-scale antenna arrays can provide accurate angle-of-arrival (AoA) information for robots. However, existing wireless localization systems that exploit device mobility are designed based on far-field channel assumptions and cannot directly provide range estimates. To address this problem, in this paper, we develop a novel near-field localization architecture for mobile robots by fusing the robot’s motion trajectory and channel state information (CSI) of a single antenna. Specifically, we first utilize channel reciprocity to multiply the uplink CSI and downlink CSI to eliminate the phase offset. Second, we further propose a two-stage localization algorithm that separates the line-of-sight (LoS) path from the multipath, and a multi-scale iterative scheme is employed to refine the estimation of AoA and distance of the LoS path. In addition, the range and AoA profiles for different trajectory shapes and the Cramer-Rao bounds for localization accuracy under squared channels are derived. Finally, the effectiveness of the proposed system is verified in a real environment. The simulation and experimental test results show that the proposed near-field localization system can operate in complex channel environments, and its localization accuracy outperforms the existing schemes.

In the past few years, infectious diseases like COVID-19 have caused serious distress to the global society and the economy. To prevent its spread, the early detection and assessment of infectious diseases based on molecular tests or antigen testing of bodily have led to countless labor and material costs. Fortunately, with the rapid development of mobile localization and web techniques, the collected massive mobile trajectory data provide a promising solution for detecting positive cases. However, existing mobility data-driven infection case detection methods are limited in terms of modeling the complicated epidemic spreading processes and preserving user privacy of the mobility data. In this article, we propose a novel graph convolutional networks (GCN) model for detecting high-risk infection cases, where we incorporate a spatio-temporal hypergraph to model the complex interaction of individuals. Then, we elaborately design a privacy-preserving framework tightly coupled with the structure of the spatio-temporal hypergraph, which includes a mobility data obfuscation module to protect privacy and an accompanying confidence-aware mechanism to mitigate the consequent performance decline. Moreover, we introduce a causal propagation mechanism to further guarantee the temporal dependency and causal effect of the feature propagation in our spatio-temporal hypergraph, which introduces both the causal transform of node features and the causal gathering of edge features. Finally, extensive experiments on a large mobility dataset collected from location-based services (LBS) show that the proposed model improves the performance of infection case detection by at least 12.47% when compared with several widely adopted baselines. Besides, our code and datasets are available at the link ( https://github.com/wjfu99/EPI-HGNN ).

In order to prevent the re-emergence of an epidemic, predicting its trend while gaining insight into the intrinsic factors affecting it is a key issue in urban governance. Traditional SIR-like compartment models provide insight into the explanatory parameters of an outbreak, and the vast majority of existing deep learning models can predict the course of an outbreak well, but neither performs well in the other’s domain. Simultaneously, studying the commonalities and diversities in the causes of outbreaks among different countrywide regions is also a way to interrupt outbreaks. To address the issues of outbreak intrinsic relationships and prediction, we propose the Neural Compartmental Ordinary Differential Equations (NeuralCODE) model to study the relationship between population movements and outbreak development in different regions. Furthermore, to incorporate the commonalities and diversities in causes among different regions into the prediction and intrinsic inquiry problem, we propose an AutoML framework. Our results found that simply using the NeuralCODE algorithm could obtain better prediction and insight capabilities within different regions. With the introduction of AutoML, it became possible to explore the factors inherent in the epidemic’s development across regions and further improve the original algorithm’s predictive performance.

Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Existing MIAs designed for large language models (LLMs) can be bifurcated into two types: reference-free and reference-based attacks. Although reference-based attacks appear promising performance by calibrating the probability measured on the target model with reference models, this illusion of privacy risk heavily depends on a reference dataset that closely resembles the training set. Both two types of attacks are predicated on the hypothesis that training records consistently maintain a higher probability of being sampled. However, this hypothesis heavily relies on the overfitting of target models, which will be mitigated by multiple regularization methods and the generalization of LLMs. Thus, these reasons lead to high false-positive rates of MIAs in practical scenarios. We propose a Membership Inference Attack based on Self-calibrated Probabilistic Variation (SPV-MIA). Specifically, we introduce a self-prompt approach, which constructs the dataset to fine-tune the reference model by prompting the target LLM itself. In this manner, the adversary can collect a dataset with a similar distribution from public APIs. Furthermore, we introduce probabilistic variation, a more reliable membership signal based on LLM memorization rather than overfitting, from which we rediscover the neighbour attack with theoretical grounding. Comprehensive evaluation conducted on three datasets and four exemplary LLMs shows that SPV-MIA raises the AUC of MIAs from 0.7 to a significantly high level of 0.9. Our code and dataset are available at: https://github.com/tsinghua-fib-lab/NeurIPS2024_SPV-MIA

Non-line-of-sight (NLOS) sensing is essential for unmanned robots and intelligent transportation systems, as it enables the sensor to detect targets around street corners, reducing the collision risk. Existing NLOS millimeter-wave (mmWave) radar technologies are based on third-order bounce geometry and utilize a full specular reflection path on smooth relay surfaces to detect targets. However, these works primarily concentrate on ideal lab environments, which pose challenges in wild street scenarios with intricately rough-relay-surface (RRS), such as stone walls and rocks, where non-flat planar surfaces usually exist near a corner. In this article, we present an NLOS sensing system that employs a single commodity mmWave radar to recover a hidden target from multiple scattering paths caused by RRS. The core contribution of the NLOS system is a high-resolution hidden target recovery algorithm by leveraging the multiple scattering paths. Specifically, leveraging knowledge from stochastic geometry and electromagnetic roughness, a microfacets model is used to characterize the random RRS. To deduce the tensor signal model of NLOS mmWave radar sensing with multi-input–multi-output (MIMO) antennas, we first profile the nonlinear geometry relationship among the RRS scattering paths, then focus on the path reflected from each scattering point. Built upon the model, we design a novel stochastic geometry-aided three-stage recovery (SGTR) algorithm for NLOS sensing, which allows the use of estimated virtual ghost targets rather than considering them as a disturbance. We evaluate the effectiveness of the proposed NLOS sensing technique via both simulations and experimental tests.

In this paper, we propose an edge selective sharing architecture (ESSA) for massive mobile video streaming (MMVS) and develop cross-layer optimizations for joint user scheduling and power allocation (JUSPA) in ESSA. This work aims to ensure users' high quality of experience (QoE) by efficiently using network resources over mobile edge computing (MEC)-assisted massive multiple-input and multiple-output (MIMO) networks. Initially, by taking advantage of the analytical and empirical characteristics of video streaming, ESSA is able to maintain MMVS by activating only a portion of facilities in wireless access networks (WANs) without sacrificing video quality. Following this, a cross-layer optimization problem is formulated for JUSPA. We simplify the problem into a generalized assignment (GA) problem by discussing the peculiarities of MMSV, whose approximate solution can be obtained in polynomial time. Moreover, load balancing based on user density is integrated to reformulate a capacitated facility location (CFL) problem solvable with low overall time complexity, effectively mitigating the increased overheads of MEC units and enhancing the overall performance of MMVS. Numerical results indicate that our ESSA with JUSPA schemes for MMVS achieves better streaming fluency and transmission efficiency than alternative methods.

The application of Wireless Sensor Networks (WSNs) in extreme environments is becoming increasingly widespread. Within these extreme environments, communication links between WSN nodes become more fragile. We refer to such WSNs as Wireless Weak-link Sensor Networks (WWSNs). The characteristics of WWSNs make them more vulnerable to internal attacks. During the data transmission process from source nodes to destination nodes, intermediary nodes could act as malicious entities capable of intercepting or manipulating data. Therefore, detecting malicious nodes is of utmost importance. This paper proposes a malicious node detection strategy based on dynamic trust management to address these challenges. The dynamic trust management algorithm integrates type-2 fuzzy logic and considers various trust factors to comprehensively evaluate node trust within WWSNs. Additionally, a dynamic trust value updating mechanism is proposed to accommodate the dynamic environmental changes inherent to WWSNs. Experimental results emphasize the effectiveness of the proposed approach in dynamically adapting to the network environment while achieving a high level of performance in detecting malicious nodes.

By providing an immersive experience with panoramic views, 360-degree video streaming has gained increasing popularity recently. In many cases, videos are transmitted to mobile users over cellular networks. However, due to the high bandwidth requirement of 360-degree videos and the growing number of users, it is challenging to provide high-quality live streaming services to all users with limited bandwidth. Improving spectral efficiency and reducing bandwidth consumption are two major approaches to address this issue, which can be achieved with non-orthogonal multiple access (NOMA) and scalable video coding (SVC), respectively. In this paper, we apply NOMA and SVC to 360-degree video streaming over a cellular network and propose a multicast scheme called SVCast, aiming to maximize the sum quality of experience of users served by a base station. Such a problem is formulated as an NP-hard problem, and we decompose it into two levels of subproblems. The lower-level subproblem is inter-group spectrum allocation, which is solved by a knapsack approach. The higher-level subproblem is intra-group multicast scheduling, and we propose a recursive algorithm to solve it. Simulation results demonstrate that SVCast improves the system utility by 31.9% on average. Furthermore, SVCast eliminates the need for viewport prediction by aggregating the contents from the viewports of multiple users.

Accurately predicting individual-level infection state is of great value since its essential role in reducing the damage of the epidemic. However, there exists an inescapable risk of privacy leakage in the fine-grained user mobility trajectories required by individual-level infection prediction. In this article, we focus on developing a framework of privacy-preserving individual-level infection prediction based on federated learning (FL) and graph neural networks (GNN). We proposeFalcon, aFederated grAphLearning method for privacy-preserving individual-level infeCtion predictiON. It utilizes a novel hypergraph structure with spatio-temporal hyperedges to describe the complex interactions between individuals and locations in the contagion process. By organically combining the FL framework with hypergraph neural networks, the information propagation process of the graph machine learning is able to be divided into two stages distributed on the server and the clients, respectively, so as to effectively protect user privacy while transmitting high-level information. Furthermore, it elaborately designs a differential privacy perturbation mechanism as well as a plausible pseudo location generation approach to preserve user privacy in the graph structure. Besides, it introduces a cooperative coupling mechanism between the individual-level prediction model and an additional region-level model to mitigate the detrimental impacts caused by the injected obfuscation mechanisms. Extensive experimental results show that our methodology outperforms state-of-the-art algorithms and is able to protect user privacy against actual privacy attacks. Our code and datasets are available at the link: https://github.com/wjfu99/FL-epidemic .

Much exploration has been conducted to ensure the successful implementation of underground applications based on wireless underground sensor networks (WUSNs). However, most of them only focus on the communication aspect while neglecting location information. As a matter of fact, for scenarios such as earthquake and mine emergency rescue, it is necessary to achieve communication and positioning simultaneously. Nevertheless, accomplishing this goal is challenging, as the underground environment not only causes tremendous attenuation but also has limited hardware resources. Long range (LoRa) technology has high reception sensitivity and a simple structure, making it well suited for underground emergency rescue. Therefore, we propose a LoRa-based joint communication and localization system called LoRaAid. When a disaster occurs, the wearable LoRa device transmits sensing information to surrounding buried nodes. Through collaboration between nodes, diversity reception of signals and location acquisition of the target can be achieved simultaneously. Two different schemes are proposed to achieve correct demodulation, and the closed-form expression for bit error rate (BER) is also derived. While implementing communication, LoRaAid uses the mapping relationship between noise-reduced received signal strength indicator (RSSI) and distance to achieve trilateral localization. Numerous experimental results demonstrate that LoRaAid can enable long-range communication while achieving decimeter-level positioning accuracy.

Filter bank multicarrier (FBMC) is emerging as a promising approach to combat the orthogonal frequency division multiplexing (OFDM) sensitivity to synchronization errors for machine-type communication (MTC). However, related designs in FBMC-MTC fail to meet the requirements of transmitting diverse data between machines as well as eliminating the effects of FBMC’s inherent imaginary interference. To address this issue, in this paper, we propose an FBMC-MTC system with deep learning (DL) assistance. Specifically, we first construct a hybrid packet transmission architecture to meet the delay and throughput requirements of different packets. Second, we further present a DL-based receiver consists two modules driven by communication domain knowledge to enhance data reliability. The dense and convolutional layers are used in two different modules since the two types of packets have different pilot structures and propagation properties. Finally, we deploy the proposed FBMC-MTC system via universal software radio peripheral (USRP) and mobile robots and test the DL-based receiver over the air (OTA). Both simulation and OTA test results show that the proposed FBMC-MTC system can operate in various channel environments, and its receiver is better than the previously advanced OFDM and FBMC receivers.

This research investigates the digital-to-analog converter (DAC) free architecture for the digital reconfigurable intelligent surface (RIS) system, where the transmission lines are implemented for reflection coefficient (RC) control to reduce power consumption. In the proposed architecture, the radio frequency (RF) switch based phase shifter is considered. By using a single-pole four-throw (SP4T) switch to simultaneously control the RCs of a group of elements, a 2-bit phase shifter is realized for passive beam steering. A novel modulation scheme is developed to explore the cost effectiveness, which approaches the performance of traditional quadrature amplitude modulation (QAM). Specifically, to overcome the limitation of the phase shift bits, joint frequency-shift and phase-rotation operations are applied to the constellation points. The simulation and experimental results demonstrate that the proposed architecture is capable of providing an ideal transmission performance. Moreover, 64- and 256-QAM modulation schemes could be implemented by expanding the elements and phase bits.

In this paper, theoretical performance of optimal maximum likelihood (ML) detector and near-optimal simulated detectors are designed for massive multiple-input multiple-output (MIMO) aided grant-free (MM-GF) systems. Specifically, the approximated average bit error probability (ABEP) bounds are firstly derived by exploiting the relationship between the Hamming distance (HD) and the pairwise error probability (PEP), which are confirmed by the simulation results. Moreover, an extended alphabet based expectation propagation (EA-EP) and an adaptive subspace matching pursuit (ASMP) algorithm are devised for signal detection of MM-GF without the prior information (PI) of active users. Simulation results show that the proposed detectors are able to outperform the classic oracle least squares (OLS) benchmark and are capable of approaching the theoretical ABEP bounds of ML.

In this paper, generalized space-time block-coded (GSTBC) spatial modulation (SM)-assisted reconfigurable intelligent surface (RIS) structures are designed for three communication scenarios, where RIS works as a transmitter, passive relay as well as active relay. Specifically, the information bits are first mapped to an appropriate GSTBC-SM symbol according to the required transmit rate and diversity order. Then, the mapped GSTBC-SM symbol is transmitted by the based station or the RIS elements based on the communication scenario. Both the signal detector and the upper bounds of average bit error probability are derived for the three cases, which are verified by the simulation results. Simulation results show that the proposed GSTBC-SM-RIS scheme is capable of providing a significant performance gain over the existing SM-RIS scheme, as well as the conventional GSTBC-SM counterpart.

Massive Multiple-Input Multiple-Output (MIMO), with its spatial multiplexing and channel hardening, has the potential to provide high capacity and reliability for massive video services. In spite of this, massive MIMO in the physical layer does not fully showcase its abilities in video applications unless it is specifically designed to do so. In this paper, we consider a cell-free massive MIMO system as an edge node for scheduling massive streams, and thus the standard server-to-client transmission is split into server-to-edge and edge-to-client. When the server-to-edge transmission is ideal, edge schedules massive streams to alleviate user conflicts in cell-free massive MIMO. Moreover, we propose a novel edge-to-client grouping algorithm for assigning the streams with severe interference to different time slots. The proposed algorithm achieves an innovative.7-approximation ratio while keeping the group sizes within a certain range. When the server-to-edge transmission is non-ideal, we design a special transmission framework called Aggressive, wherein the server sends the next video chunk when the current chunk reaches the edge rather than the client. Thus, the proposed framework saves considerable server-to-edge latency compared with the traditional framework. Simulation results show that the proposed user grouping algorithm improves the achievable rate by around 18% and the Aggressive framework improves the average bitrate.

Abstract Recently, text-based anomaly detection methods have obtained impressive results in social network services, but their applications are limited to social texts provided by users. To propose a method for generalized evolving social networks that have limited structural information, this study proposes a novel structural evolution-based anomaly detection method ($SeaDM$), which mainly consists of an evolutional state construction algorithm ($ESCA$) and an optimized evolutional observation algorithm ($OEOA$). $ESCA$ characterizes the structural evolution of the evolving social network and constructs the evolutional state to represent the macroscopic evolution of the evolving social network. Subsequently, $OEOA$ reconstructs the quantum-inspired genetic algorithm to discover the optimized observation vector of the evolutional state, which maximally reflects the state change of the evolving social network. Finally, $SeaDM$ combines $ESCA$ and $OEOA$ to evaluate the state change degrees and detect anomalous changes to report anomalies. Experimental results on real-world evolving social networks with artificial and real anomalies show that our proposed $SeaDM$ outperforms the state-of-the-art anomaly detection methods.

In this paper, we investigate the two-hop active relaying for dynamic magnetic induction based underwater wireless sensor networks (MI-UWSNs). Specifically, we firstly propose the two-hop active relaying schemes with unidirectional (UD) and tri-directional (TD) active relays, respectively, by considering the angular misalignment in practical underwater MI environments. Then, the statistical properties of the received signal-to-noise ratio (SNR) for the proposed two-hop UD and TD active relaying schemes are rigorously analyzed and the corresponding closed-form expressions of the probability density functions are derived according to the distribution of the angular misalignment. Based on the statistical SNRs, we develop the analytical expressions of the ergodic achievable rate and the average bit-to-error rate for the two-hop UD and TD active relaying schemes employing the amplify-and-forward and decode-and-forward strategies. Extensive simulation results validate the effectiveness of our theoretical analyses and demonstrate that the proposed two-hop TD active relaying scheme performs the best among all comparative schemes.

Given the distribution difference of the vehicle flow in different urban areas, coordinating the optimization priorities of crossroads in the dynamic control of traffic lights is vital. To reduce traffic congestion at crossroads, in this study, an intelligent diverse optimization priority method (IDOPM) was developed for dynamic traffic light control at crossroads, where diverse optimization priorities can be flexibly and efficiently assigned to different crossroads. The IDOPM mainly consists of a dynamic state constructor and an optimization priority assigner. The dynamic state constructor controls the transformation of the signal combinations of traffic lights. The signal combinations of traffic lights at crossroads are abstracted as cells to be controlled by formulated rules. By designing duration particles and enhancing particles, the optimization priority assigner reconstructs the quantum particle swarm algorithm to assign crossroads with different optimization priorities. The results obtained by comparison with state-of-the-art methods via extensive experiments confirmed the outstanding optimization performance of the proposed IDOPM in dynamic traffic light control.

The colorimetric method is usually used to test the concentration of substances. However, this method has a big error since different people have different sensitivities to colors. In this paper, in order to solve the identification problem of the color and the concentration of the test paper, firstly, we found out that the concentration of substance is correlated with the color reading by using the Pearson’s Chi-squared test method. And by the concentration coefficient of Pearson correlation analysis, the concentration of substance and color reading is highly correlated. Secondly, according to the RGB value of the paper image, the color moments of the image are calculated as the characteristics of the image, and the Levenberg–Marquardt (LM) neural network is established to classify the concentration of the substance. The accuracy of the training set model is 94.5%, and the accuracy of the test set model is 87.5%. The model precision is high, and the model has stronger generalization ability. Therefore, according to the RGB value of the test paper image, it is effective to establish the LM neural network model to identify the substance concentration.

We study the optimal resource allocation in the MIMO-based wireless powered underground sensor network (WPUSN) for throughput maximization. Compared to existing WPUSNs that rely on single-antenna wireless power transfer techniques to transmit geological data in real time, the MIMO-based WPUSN can be adaptively replenished by beamforming. Note that, WPUSN has two remarkable features: the severe wireless path loss and diverse data traffic demands from different underground sensors. Further, by considering the quality of service (QoS) with respect to diverse data traffic demands and communication reliability, the throughput of the network is considered as a crucial measure, which suffers from a significant loss since it has to encounter a seriously unreasonable energy scarcity under the strong-heterogeneity underground environment. To this end, the MIMO is used to eliminate the unreasonable distribution of harvested energy resources and improve effective throughput for WPUSNs. In this paper, we formulate a non-convex optimization problem to maximize the system throughput in MIMO-based WPUSNs with QoS assurance. Specifically, we find there exists no mutual forbearance between the time allocation and the beamforming weight, and transform this non-convex problem to a solvable convex-constrained problem with convex sub-problems. Finally, we give a closed-form solution and show its advantages by simulations.

We study the optimal resource allocation in the wireless powered underground sensor network (WPUSN) for throughput maximization. The WPUSN is a new networking paradigm where underground sensors can be replenished by a radio frequency energy harvesting technique and transmit geological data to the nearby aboveground access point in real time. In this paradigm, the underground portion of the wireless communication link suffers from severe path loss. Moreover, different underground sensors may have diverse data traffic demands. In this paper, we formulate an optimization problem to maximize the throughput in WPUSNs with the quality of service (QoS) consideration in terms of communication reliability and diverse data traffic demands. Specifically, we map the QoS requirements to signal-to-noise ratio thresholds and transform our problem into a convex optimization problem with linear constraints. We then present a closed-form solution for the transformed problem through a problem decomposition of the Karush-Kuhn-Tucker conditions. Our closed-form solution uncovers the insights that how the wireless channel states, reliability requirements, and data traffic demands affect the optimal resource allocation in the WPUSN. Finally, we demonstrate the effectiveness of the proposed scheme by running simulations.