A significant challenge in signal recognition tasks is identifying classes not present in the dataset. Zero-shot learning-based signal recognition addresses the challenge by identifying previously unseen classes in a mixed signal space without supervision. However, most existing methodologies are limited to one-time recognition processes. We propose a zero-shot class incremental learning (ZSCIL) method to achieve continuous unseen classes identification. Our model employs an encoder-decoder architecture and incorporates a triplet loss function to train the classifier, thereby enhancing the model’s ability to recognize mixed signals through a metric learning paradigm. Additionally, we utilize class incremental learning, where the identified unseen signals are stored in a fixed-size buffer with a maximum diversity data replay mechanism. These signals are then used for incremental training. The framework’s effectiveness and generality of our method are demonstrated through a series of experiments on two datasets. For instance, we achieved a significant 14.4% accuracy improvement for seen classes and that of the unseen classes by 4.2% on the DeepSig 2016.04C dataset. To the best of our knowledge, ZSCIL is the first method to implement sustainable identification for unseen classes in the mixed signal space.

Many current visual odometry (VO) methods that utilize deep learning primarily concentrate on the constraints of motion relationships between adjacent frames, neglecting the modeling of temporal correlations within sequence data. Consequently, this paper introduces LoSeVO to effectively capture and model the temporal correlation features present in images. We design a Joint Feature Extraction component that not only performs joint feature extraction on adjacent frames but also extracts features from cross-frame images, which are called feature-guided maps. Then, we apply a Local Consistency Constraint component to the joint features between adjacent frames. It can adaptively constrain adjacent frames at different temporal positions within a sequence using different feature-guided maps. Extensive experiments based on the KITTI and Malaga datasets have shown that, compared to our previous DeepAVO model, LoSeVO can improve pose estimation performance by up to 23% and 9% in translation and rotation estimation, respectively.

Indoor positioning technologies are pivotal for achieving high-precision localization in GPS-denied environments. Wireless positioning methods based on angle of arrival (AOA) models leverage spatial diversity to mitigate indoor multipath challenges. Recent approaches combine the extended sparse reconstruction framework with direct positioning (DP) techniques to jointly extract location parameters at the raw signal level. However, the disadvantage is that they have limited utilization for structure information inherent in a sparse solution and overlook the low-rankness in array manifolds induced by redundant grid points. To overcome these problems, a novel structure-aware direct localization method namely SaDPD is proposed that incorporates comprehensive structural constraints of joint row plus element sparsity and low-rankness in the designed sparse framework. A new sparse reconstruction problem is formulated by decomposing the position weight matrix into two distinct feature matrices, in which they are optimized for correlated line-of-sight (LOS) and inconsistent non-line-of-sight (NLOS) components, respectively. In particular, it employs the Alternating Direction Method of Multipliers (ADMM) to effectively address the extended high-dimensional optimization and utilizes grid refinement to avoid quantization constraints. Finally, extensive simulations verify that SaDPD tremendously improves sparse reconstruction accuracy and localization performance. Experimental result further demonstrates its effectiveness and practical applicability against real-world interference. These advancements establish SaDPD as a robust solution for asset positioning and target tracking where localization accuracy beyond half-meter level under multipath interference is critical.

Global navigation satellite system (GNSS) has established strong connections with users worldwide. However, when propagating in complex urban environments, GNSS signals are susceptible to blockage and reflection from surrounding obstacles, resulting in multipath (MP) effects and non-line-of-sight (NLOS) reception, significantly degrading positioning precision. With the rapid development of artificial intelligence technology, numerous researchers have advocated employing machine learning algorithms to address this issue. To effectively mitigate MP and NLOS, this study firstly introduces a novel signal classification-based MP pseudorange error correction model by initially categorizing signals into line-of-sight (LOS), MP, and NLOS. Secondly, to enhance the prediction accuracy of the model, an innovative feature adaptive iteration algorithm is proposed to update feature values. Additionally, this study is the first to propose utilizing the more reliable differential receiver clock error non-excluded pseudorange error (DNEPE), obtained through differential techniques, as the label for pseudorange error prediction. The performance of the algorithm model was tested using dynamic GNSS raw data collected by the Google team in the San Francisco area of the United States. Experimental results demonstrate that the proposed method in this study significantly improves positioning precision compared to baseline and comparative methods. Specifically, in comparison to the baseline, the proposed method exhibits an enhancement of 54.50% and 66.10% in two-dimensional root mean square error (RMSE) of positioning errors on the testing sets 1 and 2, respectively. Overall, the methods proposed in this study offer novel insights and robust support for the mitigation of MP and NLOS in urban environments.

Loop Closure Detection (LCD) is an essential part of minimizing drift due to the accumulation of previously pose errors in Simultaneous Localization and Mapping (SLAM). The existing loop detection methods are limited by the changes of external conditions such as illumination, viewpoint and appearance. Previous work has mainly focused on the feature descriptor matching methods, which usually only consider the keypoints themselves. Here, we propose a fusion method GraSS, which uses the Graph Neural Network (GNN) based on visual features, and introduces semantics and depth, so as to enhance the spatial characteristics of the keypoints and the information correlation between them in the graph. Furthermore, a learnable parameter is added when two keypoints share the same semantic labels, their matching scores are increased, mitigating to some extent the issue of mismatch caused by significant differences in external conditions between two keypoints that should ideally be paired. Our findings show that GraSS has better performance than other state-of-the-art LCD methods when facing obvious illumination, appearance changes and slight viewpoint changes.

In the field of autonomous driving, semantic segmentation is crucial for scene understanding. Currently, there are two main methods: camera-based and Lidar-based approaches. To address the issues of Lidar segmentation lacking texture features and image segmentation lacking distance information, this paper proposes a fusion of camera and Lidar to achieve 3D semantic segmentation. The method utilizes a dual-stream encoder-decoder network to process camera images and Lidar point cloud and incorporates a specially designed attention mechanism module for feature fusion. To avoid expensive manual annotation of 3D point clouds, the study also introduces a cross-dataset and cross-modal self-supervised training approach. Experimental results show a 2.4% improvement compared to the Lidar-only mode baseline results on the SemanticKITTI dataset and a 6% improvement on the nuScenes dataset.

Abstract Detecting taxi passengers is crucial for assessing taxi driver behavior, which plays a significant role in regulating the taxi industry. Despite the advancements in deep learning, object detection algorithms have not been extensively applied to this domain. In this article, an innovative taxi passenger detection algorithm is introduced based on YOLOv8, a lightweight and highly accurate method designed to automatically monitor driver behavior and regulate the taxi industry. To address the challenge of deploying complex object detection models on mobile devices, the ghost module is incorporated in place of standard convolutions within the C2f module, thereby making the model more lightweight. Furthermore, the model's performance is enhanced by integrating an improved version of Frequency Channel Attention (FCA), termed Parallel Frequency Channel Attention (PFCA), which boosts detection accuracy with minimal additional parameters and computational overhead. Experimental results on a specific taxi passenger dataset demonstrate that the proposed method significantly outperforms the baseline YOLOv8n model. Specifically, the model reduces the number of parameters and floating point operations by 12.96% and 8.18%, respectively, while achieving increases in mAP50 and mAP50‐95 by 0.27 and 0.73 percentage points, respectively.

The estimation accuracy of conventional parameter estimation methods, including the maximum likelihood (ML) estimator and subspace-based estimation methods, diverges from the Cramer–Rao lower bound (CRLB) under low- signal-to-noise ratio (SNR) conditions. Conventional stochastic resonance (SR) technique has shown appealing weak signal improvement advantages under low SNR, but it still needs a priori information, such as the probability density functions (pdfs) of weak signal and channel noise. In this study, to address the channel parameter estimation for weak signal conditions, a novel channel parameter estimation algorithm based on dynamic stochastic resonance networks (SRNs) is introduced. Since the signal statistical properties are altered by the SRN processing, the CRLB of the wireless channel parameter estimation employing the SRN-enhanced signal is derived, and then the corresponding ML estimator is presented. Theoretical analyses show that the CRLB is lower than those from the original signal and SR-enhanced signal. Computer simulations are performed to verify the effectiveness of the theoretical CRLB expressions. Both simulation and real experimental results indicate that the proposed SRN processing approach outperforms the conventional SR processing through achieving the CRLB improvement, the ML estimation performance enhancement under low- SNR conditions, and the hardware complexity reduction.

Precise positioning is critical in autonomous driving, indoor navigation, and intelligent logistics. With the development of mobile communication technology, indoor base stations (BSs) have been utilized and installed to match indoor signal coverage better. Thus for indoor positioning, cellular signals have emerged as a new option. Ranging through the time of arrival (TOA) is achieved by capturing cellular signals as a signal of opportunity for localization. This approach can only estimate the user equipment (UE) to BS distance when there is just one BS and cannot obtain the two-dimensional (2D) coordinates. In this paper, we combine the fingerprint positioning approach with the signal parameters acquired via cellular signal of opportunity. TOA and one-reflection path are employed as fingerprint features, and 2D localization with a single BS is achieved. A complete signal processing flow is constructed, and the ray tracing method is performed to generate the channel parameters to evaluate the proposed positioning algorithm's performance and match the practical application as closely as feasible. Using the$100\ GHz$carrier frequency that conforms to the sixth generation (6G) communication for simulation, the mean positioning error is$0.312 m$when the fingerprint interval is$0.5 m$. This method provides a feasible solution for 6G indoor positioning scenarios.

This letter proposes a deep-learning-based fingerprinting indoor positioning method, aiming to mitigate catastrophic forgetting in the process of depth transfer learning. Recently indoor positioning methods based on fingerprint have made great development. The deep transfer learning technique has been applied to transfer the positioning network among different scenarios. But catastrophic forgetting is a big challenge during the supervised transfer learning, which results in poor performance of fine-tuned network in source scenario. In order to solve this issue, the proposed method improves the fine-tuning learning procedure according to the importance of network parameters. It can adaptively control the ratio of network parameters by adding regularization factor to loss function. Simulation results show that the proposed method can effectively improve the positioning accuracy in source scenario without reducing the positioning accuracy in target scenario, especially for the transfer learning in multiple scenarios.

Path fading and non-line-of-sight (NLOS) signals constitute serious problems in the wireless localization process. These problems cause unpredictable degradation in the localization precision. In this paper, a novel wireless localization approach, which is based on twice receiving array signal spectra fusions and asymmetric second-order stochastic resonance (ASSR) networks, is proposed. By combining and repetitively processing the above two techniques, the receiving signal-to-noise ratio (SNR) can be enhanced. Additionally, the receiving array signal without the line-of-sight (LOS) component can be determined and removed from the spectra fusion process. The theoretical analyses presented verify the unbiasedness and asymptotic efficiency of the proposed twice receiving spectra fusion approach. Computer simulations demonstrate that the fused spectra can significantly improve the wireless localization precision compared with conventional and up-to-date localization methods, especially under low SNR conditions.

Nowadays the array signal processing has become a widely used technique in various applications. For example, it can be applied in the full-duplex jamming receiver and multiantenna jammer in wireless networks to improve the physical layer security 1, wireless signal localization in the near-field of an antenna array 2, phase enhancement for the low-angle estimation 3, direction-of-arrival (DoA) estimation in the nonuniform linear arrays 4, and so on. However, the theoretical and simulation performances in many applications using the array signal processing are seriously rely on the complexity or the antenna number of the signal receiving array. Here we show that the corresponding performance of the array signal processing can be enhanced by introducing the parallel stochastic resonance system (PSRS) in each branch or each antenna of the receiving array structure, especially under low signal-to-noise ratio (SNR) circumstance. We found that the output SNR of the receiving signal after the PSRS processing has been monotonically enhanced to a relatively high level with the increasing of number of parallel processing units in each antenna. And based on this result, it can be used to reduce the receiving array complexity. In other words, the array structure introducing the PSRS with small antenna number can also reach or even exceed the application performance of those array structures with more antenna number. Our results demonstrate an example of wireless signal DoA estimation error performance by using the proposed PSRS, which reveals that even a 4-antenna array structure with PSRS structure can outperformance a 48-antenna array structure without PSRS structure under very low SNR. We believe that this kind of technology could be applied very widely in many areas related to the array signal processing not only in reducing the array complexity, but also in signal quality or signal SNR enhancement, and so on.

The fifth generation mobile network(5G) is coming, and the base station network carries more and more pressure due to the higher rate demand of users. Load balancing traffic is crucial for high link utilization and low latency. Most of the research on load balancing algorithms focuses on data center scenarios and works based on TCP. Traditional algorithm used in 5G base station network is Equal Cost Multipath Routing(ECMP), which has poor performance due to its congestion agnostic nature. Other existing cogestion-aware algorithms work well in data center networks. However, the transport protocol and the traffic type is different in 5G base station network. It will change the performance of the original algorithms and cause the challenges to implement the schemes. In this paper, we propose RavenFlow, an effective load balancing algorithm working on layer 2 while using UDP. It makes use of different congestion information and eliminates the dependence on reverse packets. We evaluate the performance of RavenFlow in ns-3 simulator under typical 5G traffic. The result shows that RavenFlow achieves shorter Flow Completion Time(FCT) and smaller difference of utilization for different links.

In this letter, a radio frequency (RF) precoding method is put forward for massive multiple-input multiple-output (MIMO) systems with limited RF chains on high altitude platform (HAP). In the proposed method, we formulate the RF precoder design as an average signal-to-leakage-plus-noise ratio (SLNR) maximization problem, where the RF precoder is composed of some columns of a specific discrete fourier transform (DFT) matrix. First, we obtain the lower bound of the average SLNR and transform it into a trace problem. Then, for ease of handling, signal-to-leakage ratio (SLR) is adopted to achieve the initial RF precoder. Finally, a greedy algorithm for RF precoding is proposed to update the initial RF precoder for better performance. Numerical simulations demonstrate that the design proposed in this letter has better performance than other RF precoding schemes.

We propose a novel direction-of-arrival (DOA) estimation method for hybrid millimeter-wave massive MIMO systems at low SNR. Unlike the existing hierarchical-search-based methods that directly estimate the DOA from the angular power, we investigate the angular power gradient based on beamforming with incremental gains. Then, we leverage the difference of beamforming gain among codebook levels and adopt a cumulative positive angular power gradient for estimation. Specifically, codewords for analog precoders are selected from different levels of a codebook that cover the same direction during every spatial sweep. Moreover, the power difference is proved to be a weak detector of source existence according to its sign, enabling the angular distribution estimation of the signal strength. Finally, the DOAs are estimated from peaks of the cumulative product of the previously measured signal strength. Simulation results show considerably enhancements of DOA performance at low SNR.

In the wireless positioning, the performances of most traditional methods are influenced by the low signal-to-noise (SNR) and none-line-of-sight (NLOS) problems seriously. So in this study, a kind of nonlinear stochastic-resonance (SR) signal enhancement technique combined with the distributed receiving array power spectrum fusion approach is proposed. By utilizing the signal power improvement property, the fitness of distributed SR system with the array structure, and the information fusion of the spectrum, the corresponding wireless positioning can be realized satisfactorily. Computer simulations also show the advantages over conventional methods in the direction of arrival (DoA) estimation and positioning estimation.

With the coming fifth generation (5G) network, effective congestion control mechanism is needed for increasing requirements of high quality of service (QoS). Quantized Congestion Notification (QCN) is a standard layer 2 congestion control mechanism providing low latency and preventing packet loss. However, it cannot provide fairness when several flows share one bottle link. Meanwhile, QCN performs poorly in rate convergence and queue occupancy stability under bursty traffic which is normal in 5G scenario. In this paper, we address these issues and propose an enhanced QCN congestion notification algorithm called stable and fair QCN (SFQCN). SFQCN senses congestion through joint queue occupancy and incoming traffic estimation, then feedbacks individual congestion notification message with information of expected share rate to each flow. We evaluate the performance of SFQCN in terms of rate convergence and queue occupancy under typical 5G traffic using NS3 simulator. The results of simulation validate that SFQCN achieves fast and fair rate allocation while ensuring a low and stable queue occupancy at congestion point.

In this study, we investigate a positioning-aided scheme using computer vision techniques for image sensor communication (ISC), generally referred to as a visible light communication (VLC) system that utilizes an image sensor (camera). The image sensor in ISC is frequently used as a typical receiver because it has the ability to measure light intensity and distinguish multiple light sources. Additionally, thanks to its ability to detect the angle of arrival of light, the image sensor can estimate its own position using computer vision techniques. The positioning accuracy of ISC is reported to be in sub-meter levels that render visible light positioning (VLP). VLP is one of the most excellent positioning applications in indoor settings as global positioning system cannot provide satisfying indoor positioning services. To apply this significant positioning performance of VLP to our visible light system, we propose a positioning-aided scheme for ISC using computer vision techniques here. In addition, we evaluate the demodulation performance and positioning accuracy of our proposed scheme.

In the computer network intrusion detection system, data objects, mapped from original space, are analyzed based on kernel clustering algorithm. During the process of kernel clustering, some representative points are introduced to represent a cluster. In just one iteration, the distance between a data object and representative points of a cluster is computed to partition the data objects. The clustering results contain normal data and abnormal data, which achieve the goal of intrusion detection. At the same time, KDD CUP 1999 dataset is used to make simulations. The results show that the proposed algorithm has higher detecting probability under the condition of low constant false alarm rate compared with K-Means clustering algorithm and SVM.

A kind of uplink power control approach of asynchronous code division multiple access (CDMA) mobile communication system based on the adaptive chaotic simulated annealing (CSA) is proposed. The particular influence of near-far effect can be solved by using the global optimal searching function of CSA method, and the multiple access interference (MAI) problem can be overcome by introducing adaptive MAI cancellation network in corresponding close loop control strategy. Computer simulations show the comparison results between proposed approach and conventional method with heterogeneous signal-to-interference ratio (SIR) threshold decision. It shows that this new approach can achieve higher channel capability and lower average outrage probability with some small increase of iteration steps, which can improve the performance of CDMA mobile communication system effectively.

In this paper, a novel covariance spectrum sensing approach used in cognitive radio (CR) networks which is based on the dynamical stochastic resonance (SR) technique is proposed. When the optimal SR technique is introduced as the pre-processing method for the covariance-based detection and after it has been realized, it can increase the signal-to-noise ratio (SNR) of the primary user (PU) signal and accordingly increase the mean value of the decision statistic of the covariance-based detection, so that the detection probability of the proposed approach can be improved under constant false alarm rate (CFAR). Computer simulation results verify the effectiveness of the proposed approach compared with the traditional spectrum sensing methods.

A cooperative spectrum sensing technique in cognitive radio (CR) networks is proposed in this paper, which is based on the data fusion of different stochastic resonance (SR) energy detectors. Due to the noisy uncertainty in the unpredictable wireless communication channel, the detection performance of the traditional energy detector cannot be guaranteed. By introducing the SR system with different SR noise types, and with the fusion on these SR-based energy detectors, the detection probability can be improved even under low signal-to-noise ratio (SNR) circumstances. Computer simulation results validate the efficiency of the proposed novel cooperative spectrum sensing approach.

A new censoring cooperative spectrum sensing scheme in cognitive radio (CR) network is proposed in this paper, which is based on stochastic resonance (SR) technique and optimal censoring interval. The selection strategy for the optimal censoring interval is derived. The observations of the cooperative secondary users (SUs) whose statistics fall into the censoring interval are processed by SR system. Theoretical analyses and simulation results show that the proposed cooperative spectrum sensing scheme has the same detection performance and lower computational complexity compared with the method that each cooperative performs spectrum sensing using SR-based energy detection, and the detection performance of both above method is superior than that of the conventional method that each cooperative performs spectrum sensing using energy detection.

A novel computer network intrusion detection approach based on the relevance vector machine (RVM) classification is proposed, where a Chebyshev chaotic map is introduced as the inner training noise signal. According to the known distribution property of the Chebyshev map, the iteration process of RVM classifier can be derived and be realized easily. Compared with the support vector machine (SVM) classification method, it can be found from the simulation results that the proposed approach can reach higher detection probabilities under different kinds of intrusion signals, and the corresponding computational complexity can be reduced efficiently, which guarantee the reliability of this RVM-based approach with Chebyshev chaotic map.

This paper proposes an optimal stochastic resonance (SR) approach of the traditional quartic double-well bistable system, which is driven by a weak noisy single-frequency sinusoidal signal under low signal-to-noise ratio (SNR) circumstance. By introducing an external independent additive SR noise and optimizing the corresponding two driving parameters of the weak noisy sinusoidal signal and the external SR noise, a maximal output SNR of the SR system state variable can be reached together with SNR improvement. Simulation results verify the effectiveness of the approach. And it can certainly be applied to weak single-frequency target detection or identification problems and so on.

A novel spectrum sensing technique in cognitive radio (CR) networks based on chaotic stochastic resonance (CSR) is proposed in this paper. By introducing the received signal into the CSR system, the signal-to-noise ratio (SNR) of the signal can be improved, which can lead to the decrease of the SNR wall in the traditional energy detector and reduce the sample complexity needed to reach certain detection performance. Theoretical analyses and computer simulations validate the effectiveness of the proposed CSR-based spectrum sensing approach.

An optimal stochastic resonance approach is proposed in this paper to overcome the defects of traditional stochastic resonance system in real applications. By introducing the stochastic resonance noise with optimal variance when the driving parameter is selected within the region which ensures the maximal output signal-to-noise ratio (SNR), the improvement of SNR gain can be guaranteed. Simulation results show that the SNR gain can reach 7~8.5dB even when the SNR of the original signal is lower than 0dB.

In this paper, a novel approach for estimating signal parameter in clutter using chaos synchronization based on support vector machine (SVM) is proposed. Assuming that the clutter process is chaotic, chaos synchronization is found to be able to extract the weak signal even when the signal is totally embedded inside the clutter spectrum. When the dynamics of the chaotic system is unknown, an SVM-based chaos synchronization is proposed here to estimate the signal parameters. The unbiasedness of the proposed approach is evaluated theoretically. Computer simulations on estimating sinusoidal frequencies confirm that the weak target frequencies can be estimated accurately. Using mean square error (MSE) as the performance measure, the proposed method is shown to have a better performance than the conventional frequency estimation techniques including the fast Fourier transform (FFT) and multiple signal classification (MUSIC) algorithm.