Search Results (17)

The integration of Synthetic Aperture Radar (SAR) imaging technology with deep neural networks has experienced significant advancements in recent years. Yet, the scarcity of high-quality samples and the difficulty of extracting prior information from SAR data have experienced limited progress in this domain. This study introduces an innovative sparse SAR imaging approach using a self-supervised non-local asymmetric pixel-shuffle blind spot network. This strategy enables the network to be trained without labeled samples, thus solving the problem of the scarcity of high-quality samples. Through asymmetric pixel-shuffle downsampling (AP) operation, the spatial correlation between pixels is broken so that the blind spot network can adapt to the actual scene. The network also incorporates a non-local module (NLM) into its blind spot architecture, enhancing its capability to analyze a broader range of information and extract more comprehensive prior knowledge from SAR data. Subsequently, Plug and Play (PnP) technology is used to integrate the trained network into the sparse SAR imaging model to solve the regularization term problem. The optimization of the inverse problem is achieved through the Alternating Direction Method of Multipliers (ADMM) algorithm. The experimental results of the unlabeled samples demonstrate that our method significantly outperforms traditional techniques in reconstructing images across various regions. Full article

Aiming at the cooperative localization problem for the dynamic UAV swarm in an anchor-limited environment, an adaptive Wasserstein filter (AWF) with distance-constrained bare bones self-recovery particles (CBBP) is proposed. Firstly, to suppress the cumulative error from the inertial navigation system (INS), a position-prediction strategy based on transition particles is designed instead of using inertial measurements directly, which ensures that the generated prior particles can better cover the ground truth and provide the uncertainties of nonlinear estimation. Then, to effectively quantify the difference between the observed and the prior data, the Wasserstein measure based on slice segmentation is introduced to update the posterior weights of the particles, which makes the proposed algorithm robust against distance-measurement noise variance under the strongly nonlinear model. In addition, to solve the problem of particle impoverishment caused by traditional resampling, a diversity threshold based on Gini purity is designed, and a fast bare bones particle self-recovery algorithm with distance constraint is proposed to guide the outlier particles to the high-likelihood region, which effectively improves the accuracy and stability of the estimation. Finally, the simulation results show that the proposed algorithm is robust against cumulative error in an anchor-limited environment and achieves more competitive accuracy with fewer particles. Full article

Infrared small target detection plays a crucial role in both military and civilian systems. However, current detection methods face significant challenges in complex scenes, such as inaccurate background estimation, inability to distinguish targets from similar non-target points, and poor robustness across various scenes. To address these issues, this study presents a novel spatial–temporal tensor model for infrared small target detection. In our method, we introduce the tensor tree rank to capture global structure in a more balanced strategy, which helps achieve more accurate background estimation. Meanwhile, we design a novel self-adaptive local prior weight by evaluating the level of clutter and noise content in the image. It mitigates the imbalance between target enhancement and background suppression. Then, the spatial–temporal total variation (STTV) is used as a joint regularization term to help better remove noise and obtain better detection performance. Finally, the proposed model is efficiently solved by the alternating direction multiplier method (ADMM). Extensive experiments demonstrate that our method achieves superior detection performance when compared with other state-of-the-art methods in terms of target enhancement, background suppression, and robustness across various complex scenes. Furthermore, we conduct an ablation study to validate the effectiveness of each module in the proposed model. Full article

Millimeter-wave radar and optical cameras are one of the primary sensing combinations for autonomous platforms such as self-driving vehicles and disaster monitoring robots. The millimeter-wave radar odometry can perform self-pose estimation and environmental mapping. However, cumulative errors can arise during extended measurement periods. In particular scenes where loop closure conditions are absent and visual geometric features are discontinuous, existing loop detection methods based on back-end optimization face challenges. To address this issue, this study introduces a correlative scan matching (CSM) pose estimation method that integrates visual and radar line features (VRL-SLAM). By making use of the pose output and the occupied grid map generated by the front end of the millimeter-wave radar’s simultaneous localization and mapping (SLAM), it compensates for accumulated errors by matching discontinuous visual line features and radar line features. Firstly, a pose estimation framework that integrates visual and radar line features was proposed to reduce the accumulated errors generated by the odometer. Secondly, an adaptive Hough transform line detection method (A-Hough) based on the projection of the prior radar grid map was introduced, eliminating interference from non-matching lines, enhancing the accuracy of line feature matching, and establishing a collection of visual line features. Furthermore, a Gaussian mixture model clustering method based on radar cross-section (RCS) was proposed, reducing the impact of radar clutter points online feature matching. Lastly, actual data from two scenes were collected to compare the algorithm proposed in this study with the CSM algorithm and RI-SLAM.. The results demonstrated a reduction in long-term accumulated errors, verifying the effectiveness of the method. Full article

Harris Hawk Optimization (HHO) is a well-known nature-inspired metaheuristic model inspired by the distinctive foraging strategy and cooperative behavior of Harris Hawks. As with numerous other algorithms, HHO is susceptible to getting stuck in local optima and has a sluggish convergence rate. Several techniques have been proposed in the literature to improve the performance of metaheuristic algorithms (MAs) and to tackle their limitations. Chaos optimization strategies have been proposed for many years to enhance MAs. There are four distinct categories of Chaos strategies, including chaotic mapped initialization, randomness, iterations, and controlled parameters. This paper introduces SHHOIRC, a novel hybrid algorithm designed to enhance the efficiency of HHO. Self-adaptive Harris Hawk Optimization using three chaotic optimization methods (SHHOIRC) is the proposed algorithm. On 16 well-known benchmark functions, the proposed hybrid algorithm, authentic HHO, and five HHO variants are evaluated. The computational results and statistical analysis demonstrate that SHHOIRC exhibits notable similarities to other previously published algorithms. The proposed algorithm outperformed the other algorithms by 81.25%, compared to 18.75% for the prior algorithms, by obtaining the best average solutions for 13 benchmark functions. Furthermore, the proposed algorithm is tested on a real-life problem, which is the maximum coverage problem of Wireless Sensor Networks (WSNs), and compared with pure HHO, and two well-known algorithms, Grey Wolf Optimization (GWO) and Whale Optimization Algorithm (WOA). For the maximum coverage experiments, the proposed algorithm demonstrated superior performance, surpassing other algorithms by obtaining the best coverage rates of 95.4375% and 97.125% for experiments 1 and 2, respectively. Full article

Background: There is an established evidence-base for dialectical behaviour therapy for adolescents (DBT-A) in the treatment of young people with severe emotion dysregulation and related problems, including repeated self-harm and suicidal behaviours. However, few studies have reported on parental involvement in such treatments. This study aims to explore the outcomes and experiences of participants of a dedicated skills group for parents and carers embedded within an adapted DBT-A programme in the United Kingdom. Method: This study was conducted within a specialist outpatient Child and Adolescent Mental Health Services (CAMHS) DBT programme in the National Health Service (NHS) in London. Participants were parents and carers of adolescents engaged in the DBT-A programme. Participants attended a 6-month parent and carer skills group intervention and completed self-report measures relating to carer distress, communication and family functioning, at pre-intervention and post-intervention. Following the intervention, semi-structured interviews were also completed with a subgroup of participants to explore their experiences of the skills group and how they perceived its effectiveness. Quantitative and qualitative methods were used to analyse the data collected from participants. Results: Forty-one parents and carers completed the intervention. Participants reported a number of statistically significant changes from pre- to post-intervention: general levels of distress and problems in family communication decreased, while perceived openness of family communication and strengths and adaptability in family functioning increased. A thematic analysis of post-intervention interviews examining participant experiences identified six themes: (1) experiences prior to DBT; (2) safety in DBT; (3) experiences with other parents and carers; (4) new understandings; (5) changes in behaviours; and (6) future suggestions. Discussion: Parents and carers who attended a dedicated DBT skills groups, adapted for local needs, reported improvements in their wellbeing, as well as interactions with their adolescents and more general family functioning, by the end of the intervention. Further studies are needed which report on caregiver involvement in DBT. Full article

Hyperspectral anomaly detection is a popular research direction for hyperspectral images; however, it is problematic because it separates the background and anomaly without prior target information. Currently, deep neural networks are used as an extractor to mine intrinsic features in hyperspectral images, which can be fed into separate anomaly detection methods to improve their performances. However, this hybrid approach is suboptimal because the subsequent detector is unable to drive the data representation in hidden layers, which makes it a challenge to maximize the capabilities of deep neural networks when extracting the underlying features customized for anomaly detection. To address this issue, a novel unsupervised, self-attention-based, one-class neural network (SAOCNN) is proposed in this paper. SAOCNN consists of two components: a novel feature extraction network and a one-class SVM (OC-SVM) anomaly detection method, which are interconnected and jointly trained by the OC-SVM-like loss function. The adoption of co-training updates the feature extraction network together with the anomaly detector, thus improving the whole network’s detection performance. Considering that the prominent feature of an anomaly lies in its difference from the background, we designed a deep neural extraction network to learn more comprehensive hyperspectral image features, including spectral, global correlation, and local spatial features. To accomplish this goal, we adopted an adversarial autoencoder to produce the residual image with highlighted anomaly targets and a suppressed background, which is input into an improved non-local module to adaptively select the useful global information in the whole deep feature space. In addition, we incorporated a two-layer convolutional network to obtain local features. SAOCNN maps the original hyperspectral data to a learned feature space with better anomaly separation from the background, making it possible for the hyperplane to separate them. Our experiments on six public hyperspectral datasets demonstrate the state-of-the-art performance and superiority of our proposed SAOCNN when extracting deep potential features, which are more conducive to anomaly detection. Full article

Completing point clouds from partial terrestrial laser scannings (TLS) is a fundamental step for many 3D visual applications, such as remote sensing, digital city and autonomous driving. However, existing methods mainly followed an ordinary auto-encoder architecture with only partial point clouds as inputs, and adopted K-Nearest Neighbors (KNN) operations to extract local geometric features, which takes insufficient advantage of input point clouds and has limited ability to extract features from long-range geometric relationships, respectively. In this paper, we propose a keypoints-aligned siamese (KASiam) network for the completion of partial TLS point clouds. The network follows a novel siamese auto-encoder architecture, to learn prior geometric information of complete shapes by aligning keypoints of complete-partial pairs during the stage of training. Moreover, we propose two essential blocks cross-attention perception (CAP) and self-attention augment (SAA), which replace KNN operations with attention mechanisms and are able to establish long-range geometric relationships among points by selecting neighborhoods adaptively at the global level. Experiments are conducted on widely used benchmarks and several TLS data, which demonstrate that our method outperforms other state-of-the-art methods by a 4.72% reduction of the average Chamfer Distance of categories in PCN dataset at least, and can generate finer shapes of point clouds on partial TLS data. Full article

Space-time adaptive processing (STAP) encounters severe performance degradation with insufficient training samples in inhomogeneous environments. Sparse Bayesian learning (SBL) algorithms have attracted extensive attention because of their robust and self-regularizing nature. In this study, a computationally efficient SBL STAP algorithm with adaptive Laplace prior is developed. Firstly, a hierarchical Bayesian model with adaptive Laplace prior for complex-value space-time snapshots (CALM-SBL) is formulated. Laplace prior enforces the sparsity more heavily than Gaussian, which achieves a better reconstruction of the clutter plus noise covariance matrix (CNCM). However, similar to other SBL-based algorithms, a large degree of freedom will bring a heavy burden to the real-time processing system. To overcome this drawback, an efficient localized reduced-dimension sparse recovery-based space-time adaptive processing (LRDSR-STAP) framework is proposed in this paper. By using a set of deeply weighted Doppler filters and exploiting prior knowledge of the clutter ridge, a novel localized reduced-dimension dictionary is constructed, and the computational load can be considerably reduced. Numerical experiments validate that the proposed method achieves better performance with significantly reduced computational complexity in limited snapshots scenarios. It can be found that the proposed LRDSR-CALM-STAP algorithm has the potential to be implemented in practical real-time processing systems. Full article

Concerning the good description of arbitrarily shaped clusters, collecting accurate support vectors (SVs) is critical yet resource-consuming for support vector clustering (SVC). Even though SVs can be extracted from the boundaries for efficiency, boundary patterns with too much noise and inappropriate parameter settings, such as the kernel width, also confuse the connectivity analysis. Thus, we propose an improved boundary SVC (IBSVC) with self-adaption support for reasonable boundaries and comfortable parameters. The first self-adaption is in the movable edge selection (MES). By introducing a divide-and-conquer strategy with the k-means++ support, it collects local, informative, and reasonable edges for the minimal hypersphere construction while rejecting pseudo-borders and outliers. Rather than the execution of model learning with repetitive training and evaluation, we fuse the second self-adaption with the flexible parameter selection (FPS) for direct model construction. FPS automatically selects the kernel width to meet a conformity constraint, which is defined by measuring the difference between the data description drawn by the model and the actual pattern. Finally, IBSVC adopts a convex decomposition-based strategy to finish cluster checking and labeling even though there is no prior knowledge of the cluster number. Theoretical analysis and experimental results confirm that IBSVC can discover clusters with high computational efficiency and applicability. Full article

Individual tree modeling for terrestrial LiDAR point clouds always involves heavy computation burden and low accuracy toward a complex tree structure. To solve these problems, this paper proposed a self-adaptive optimization individual tree modeling method. In this paper, we first proposed a joint neighboring growing method to segment wood points into object primitives. Subsequently, local object primitives were optimized to alleviate the computation burden. To build the topology relation among branches, branches were separated based on spatial connectivity analysis. And then the nodes corresponding to each object primitive were adopted to construct the graph structure of the tree. Furthermore, each object primitive was fitted as a cylinder. To revise the local abnormal cylinder, a self-adaptive optimization method based on the constructed graph structure was proposed. Finally, the constructed tree model was further optimized globally based on prior knowledge. Twenty-nine field datasets obtained from three forest sites were adopted to evaluate the performance of the proposed method. The experimental results show that the proposed method can achieve satisfying individual tree modeling accuracy. The mean volume deviation of the proposed method is 1.427 m³. In the comparison with two other famous tree modeling methods, the proposed method can achieve the best individual tree modeling result no matter which accuracy indicator is selected. Full article

The human brain is a complex network whose ensemble time evolution is directed by the cumulative interactions of its cellular components, such as neurons and glia cells. Coupled through chemical neurotransmission and receptor activation, these individuals interact with one another to varying degrees by triggering a variety of cellular activity from internal biological reconfigurations to external interactions with other network agents. Consequently, such local dynamic connections mediating the magnitude and direction of influence cells have on one another are highly nonlinear and facilitate, respectively, nonlinear and potentially chaotic multicellular higher-order collaborations. Thus, as a statistical physical system, the nonlinear culmination of local interactions produces complex global emergent network behaviors, enabling the highly dynamical, adaptive, and efficient response of a macroscopic brain network. Microstate reconfigurations are typically facilitated through synaptic and structural plasticity mechanisms that alter the degree of coupling (magnitude of influence) neurons have upon each other, dictating the type of coordinated macrostate emergence in populations of neural cells. These can emerge in the form of local regions of synchronized clusters about a center frequency composed of individual neural cell collaborations as a fundamental form of collective organization. A single mode of synchronization is insufficient for the computational needs of the brain. Thus, as neural components influence one another (cellular components, multiple clusters of synchronous populations, brain nuclei, and even brain regions), different patterns of neural behavior interact with one another to produce an emergent spatiotemporal spectral bandwidth of neural activity corresponding to the dynamical state of the brain network. Furthermore, hierarchical and self-similar structures support these network properties to operate effectively and efficiently. Neuroscience has come a long way since its inception; however, a comprehensive and intuitive understanding of how the brain works is still amiss. It is becoming evident that any singular perspective upon the grandiose biophysical complexity within the brain is inadequate. It is the purpose of this paper to provide an outlook through a multitude of perspectives, including the fundamental biological mechanisms and how these operate within the physical constraints of nature. Upon assessing the state of prior research efforts, in this paper, we identify the path future research effort should pursue to inspire progress in neuroscience. Full article

Current electric vehicle (EV) charging systems have limited smart functionality, and most research focuses on load-balancing the national or regional grid. In this article, we focus on supporting the early design of a smart charging system that can effectively and efficiently charge a company’s EV fleet, maximizing the use of self-generated Photo-Voltaic energy. The support takes place in the form of the Vehicle Charging Simulation (VeCS) model. System performance is determined by operational costs, CO₂ emissions and employee satisfaction. Two impactful smart charging functions concern adaptive charging speeds and charging point management. Simulation algorithms for these functions are developed. The VeCS model is developed to simulate implementation of a smart charging system incorporating both charging infrastructure and local Photo-Voltaics input, using a company’s travel and energy data, prior to having the EVs in place. The model takes into account travel behaviour, energy input and energy consumption on a daily basis. The model shows the number of charged vehicles, whether incomplete charges occur, and energy flow during the day. The model also facilitates simulation of an entire year to determine overall cost and emission benefits. It also estimates charging costs and CO₂ emissions that can be compared to the non-EV situation. With the VeCS model, the impact of various system design and implementation choices can be explored before EVs are used. Two system designs are proposed for the case company; a short-term version with current technology and a future version with various smart functionalities. Overall, the model can contribute to substantiated advice for a company regarding implementation of charging infrastructure. Full article

Interventions to address climate adaptation have been on the rise over the past decade. Intervention programmes aim to build the resilience of local communities to climate shocks, and ultimately their wellbeing by helping them to better prepare, adapt and recover. Resilience, similar to human wellbeing, is a multidimensional construct grounded in local realities and lived experiences. Yet current evaluation frameworks used in resilience programming rarely consider what resilience means in local contexts prior to implementation. This means policy designs risk failing to improve resilience of communities and creating unintended negative consequences for communities’ wellbeing. Better processes and indicators for assessing resilience are needed. This paper explores the interplay between local predictors of resilience and wellbeing to assess the validity of self-assessed indicators as part of frameworks to measure resilience. We draw from research on the Devolved Climate Finance (DCF) mechanism implemented between 2014 and 2018 in Tanzania. We find that different factors explain resilience when compared to wellbeing; while resilience is primarily influenced by relationships, wellbeing is correlated with livelihoods. This shows that incentives to improve resilience differ from those of wellbeing. Climate and development practitioners must adopt locally grounded framings for resilience and wellbeing to ensure interventions track appropriate indicators, towards positive outcomes. Full article

Online detection of fatigued wear debris in the lubricants of aero-engines can provide warning of engine failure during flight, thus having great economic and social benefits. In this paper, we propose a capacitance array sensor and a hyper-heuristic partial differential equation (PDE) inversion method for detecting multiple micro-scale metal debris, combined with self-adaptive cellular genetic (SA-CGA) and morphological algorithms. Firstly, different from the traditional methods, which are limited in multi-induction-Dirac-boundary-inversion, a mathematical model with non-local boundary conditions is established. Furthermore, a hyper-heuristic method based on prior knowledge is also proposed to extract the wear character. Moreover, a 12-plate array circulating sensor and corresponding detection system are designed. The experimental results were compared with the optical microscopy. The results show that under the conditions of 1~3 wear debris with diameters of between 250–900 μm, the accuracy of the proposed method is 10–38% higher than those of the traditional methods. The recognition error of the wear debris counts decreases to 0. Full article