Localization Task Research Articles

Transfer-AE: A novel autoencoder-based impact detection model for structural digital twin

Accurately detecting the location and intensity of impacts is crucial for ensuring structural safety. Currently, AI-based structural impact detection methods are widely used for their excellent detection accuracy. However, their generalization capability is limited by the scenarios present in the training data. Many complex and dangerous impact scenarios are difficult to conduct real-world experiments on to collect sufficient samples. To capture all impact scenarios and fully leverage the advantages of AI-based detection technologies, advanced methods involve combining real-world structural monitoring data with corresponding numerical models to construct digital twins. These methods continuously refine the created numerical models with limited real-world data and provide diverse impact scenarios through numerical model simulations. However, there are inevitable differences between digital models and physical models that are challenging to correct through mechanical means. This discrepancy in data distribution between the two models significantly hinders the application of digital twin technology in impact/event identification tasks. To address this challenge, this study proposes a novel model based on autoencoders, named Transfer-AE. Transfer-AE encodes the common features of digital twins in the latent space to bridge the uncertainty gap at a macro scale between numerical models and physical models and synchronously fits the magnitude and location of the impact load in the decoder. This enables consistent detection results for the same impact event, whether the sample comes from the numerical model or the physical model. Transfer-AE includes two operating modes: Mode 1 has a fixed computational complexity with stable inference speed, but the training cost and difficulty increase with data distribution. Mode 2's computational complexity increases with data distribution, but it has a fixed training cost and speed. In both cases involving the geodesic dome structure simulating a deep space habitat and the IASC-ASCE benchmark structure, Transfer-AE demonstrated the best performance in impact localization and quantification tasks compared to mainstream domain-adaptive transfer models.

Neural populations in macaque anterior cingulate cortex encode social image identities

The anterior cingulate cortex gyrus (ACCg) has been implicated in prosocial behaviors and reasoning about social cues. While this indicates that ACCg is involved in social behavior, it remains unclear whether ACCg neurons also encode social information during goal-directed actions without social consequences. To address this, we assessed how social information is processed by ACCg neurons in a reward localization task. Here we show that neurons in the ACCg of female rhesus monkeys differentiate the identities of conspecifics in task images, even when identity was task-irrelevant. This was in contrast to the prearcuate cortex (PAC), which has not been strongly linked to social behavior, where neurons differentiated identities in both social and nonsocial images. Many neurons in the ACCg also categorically distinguished social from nonsocial trials, but this encoding was only slightly more common in ACCg compared to the PAC. Together, our results suggest that ACCg neurons are uniquely sensitive to social information that differentiates individuals, which may underlie its role in complex social reasoning.

VLR-BPP: An intelligent virtual location replacement based bilateral privacy-preserving architecture for edge cloud systems

Mobile Crowdsourcing (MCS) has emerged as a significant edge-cloud computing paradigm in which workers perceive data at the network edge and report it to cloud-based computing services for processing, enabling the construction of various applications. Consequently, it is imperative to achieve Bilateral Location Privacy-Preserving (BLPP) to protect the privacy of both Data Requester (DR) and workers, as disclosing location information entails many sensitive details that can result in losses for DR and workers alike. The Local Differential Privacy (LDP) approach is widely employed in Privacy-Preserving (PP) techniques due to its inherent advantages, wherein owners release data with added noise, allowing for proactive customization of privacy strength without relying on any third party. However, the current state of LDP methods presents a dilemma: when privacy protection is strong, introducing excessive location noise can lead to a decrease in the accuracy of task-worker matching, while a high rate of task-worker matching necessitates the compromise of privacy strength. In this paper, an intelligent Virtual Location Replacement based enhanced Bilateral Privacy-Preserving (VLR-BPP) architecture is proposed to improve privacy protection strength and matching accuracy in MCS simultaneously. Within the VLR-BPP architecture, a Bipartite-Graph-based Matrix Completion (BGMC) model is employed to establish the spatiotemporal correlations among data. Then, a Virtual Location Replacement (VLR) strategy is proposed to obfuscate the locations of tasks or workers to their highly correlated virtual location before publishing. Based on VLR, three preemptive location virtualization approaches are introduced: Only Task Location Virtual (OTLV), Only Workers Location Virtual (OWLV), and Both Task and Workers Location Virtual (BTWLV). For workers and DR, Randomized Response (RR) techniques and Random Matrix Multiplication Mechanism (RMM) are used to implement LDP independently. A greedy algorithm is adopted to recruit workers for tasks. In response to the data submitted by workers, BGMC imputation mechanism is utilized to enhance data quality. Finally, simulations based on real-world datasets demonstrate that the performance of our architecture surpasses existing state-of-the-art methods in privacy protection and data collection quality by 18.92∼38.17% and 15.49∼50.77%, respectively.

A code change‐oriented approach to just‐in‐time defect prediction with multiple input semantic fusion

AbstractRecent research found that fine‐tuning pre‐trained models is superior to training models from scratch in just‐in‐time (JIT) defect prediction. However, existing approaches using pre‐trained models have their limitations. First, the input length is constrained by the pre‐trained models.Secondly, the inputs are change‐agnostic.To address these limitations, we propose JIT‐Block, a JIT defect prediction method that combines multiple input semantics using changed block as the fundamental unit. We restructure the JIT‐Defects4J dataset used in previous research. We then conducted a comprehensive comparison using eleven performance metrics, including both effort‐aware and effort‐agnostic measures, against six state‐of‐the‐art baseline models. The results demonstrate that on the JIT defect prediction task, our approach outperforms the baseline models in all six metrics, showing improvements ranging from 1.5% to 800% in effort‐agnostic metrics and 0.3% to 57% in effort‐aware metrics. For the JIT defect code line localization task, our approach outperforms the baseline models in three out of five metrics, showing improvements of 11% to 140%.

Assessment of Balance During a Single-Limb Stance Task in Healthy Adults: A Cross-Sectional Study.

Single-limb stance (SLS) is a demanding postural task, widely used for balance assessment in both research and clinical practice. Despite extensive data on elderly and clinical populations, less is known about younger and healthier adults. Our aim in this study was to assess balance during a SLS task among a cohort of healthy adults to determine whether there are age or sex group or testing condition differences in performances. In this cross-sectional study, we involved 120 participants aged 30-65 years and divided them into four age sub-groups with equal numbers of males and females in each. We assessed balance during a 45-s SLS task on a] the Delos Postural Proprioceptive System for both lower limbs in two conditions - open eyes (OE) and closed eyes (CE). We calculated stability (SI) and autonomy (AU) indices and used analysis of variance to determine that there was no significant effect of limb dominance or sex on balance parameters. However, there was a significant interaction effect between age group and testing condition for both SI and AU (p < .001 for both), with balance worsening as age increased only in the CE condition. These results highlight a pattern of balance decline with age when vision is eliminated from balance performance, underscoring the critical relationship between sensory input and postural control as people age.

Detection Method of Stator Coating Quality of Flat Wire Motor Based on Improved YOLOv8s.

The stator of a flat wire motor is the core component of new energy vehicles. However, detecting quality defects in the coating process in real-time is a challenge. Moreover, the number of defects is large, and the pixels of a single defect are very few, which make it difficult to distinguish the defect features and make accurate detection more difficult. To solve this problem, this article proposes the YOLOv8s-DFJA network. The network is based on YOLOv8s, which uses DSFI-HEAD to replace the original detection head, realizing task alignment. It enhances joint features between the classification task and localization task and improves the ability of network detection. The LEFG module replaces the C2f module in the backbone of the YOLOv8s network that reduces the redundant parameters brought by the traditional BottleNeck structure. It also enhances the feature extraction and gradient flow ability to achieve the lightweight of the network. For this research, we produced our own dataset of stator coating quality regarding flat wire motors. Data augmentation technology (Gaussian noise, adjusting brightness, etc.) enriches the dataset, to a certain extent, which improves the robustness and generalization ability of YOLOv8s-DFJA. The experimental results show that in the performance of YOLOv8s-DFJA compared with YOLOv8s, the mAP@.5 index increased by 6.4%, the precision index increased by 1.1%, the recall index increased by 8.1%, the FPS index increased by 9.8FPS/s, and the parameters decreased by 3 Mb. Therefore, YOLOv8s-DFJA can be better realize the fast and accurate detection of the stator coating quality of flat wire motors.

Robust adaptive control for dynamic positioning vessels with actuator faults via the multiport event-triggered mechanism

This paper presents a robust adaptive neural control algorithm for dynamic positioning tasks of full-actuated vessels using a novel multiport event-triggered mechanism. The proposed mechanism only updates control signals and feedback error signals upon violation of the multiport event-triggered rule. Therefore, the communication loads between the sensors and controller, as well as between the controller and actuators, are significantly mitigated. Furthermore, a fault-adaptive method is adopted by estimating the uncertain actuator faults, based on the proposed event-triggered mechanism, the fault-adaptive parameters will be updated at the triggering instant, eliminating the destabilizing effects of the closed-loop system. Besides, the dynamic surface control (DSC) and the robust neural damping technique are employed to address the problems of “complexity explosion” and system uncertainties. Based on Lyapunov stability theory, the closed-loop system is proved to satisfy semi-globally uniform ultimate bounded (SGUUB). Finally, a simulation experiment validates the effectiveness of the proposed algorithm.

A Deep-Learning Based GNSS Scene Recognition Method for Detailed Urban Static Positioning Task via Low-Cost Receivers

A Deep-Learning Based GNSS Scene Recognition Method for Detailed Urban Static Positioning Task via Low-Cost Receivers

LettuceNet: A Novel Deep Learning Approach for Efficient Lettuce Localization and Counting

Traditional lettuce counting relies heavily on manual labor, which is laborious and time-consuming. In this study, a simple and efficient method for localization and counting lettuce is proposed, based only on lettuce field images acquired by an unmanned aerial vehicle (UAV) equipped with an RGB camera. In this method, a new lettuce counting model based on the weak supervised deep learning (DL) approach is developed, called LettuceNet. The LettuceNet network adopts a more lightweight design that relies only on point-level labeled images to train and accurately predict the number and location information of high-density lettuce (i.e., clusters of lettuce with small planting spacing, high leaf overlap, and unclear boundaries between adjacent plants). The proposed LettuceNet is thoroughly assessed in terms of localization and counting accuracy, model efficiency, and generalizability using the Shanghai Academy of Agricultural Sciences-Lettuce (SAAS-L) and the Global Wheat Head Detection (GWHD) datasets. The results demonstrate that LettuceNet achieves superior counting accuracy, localization, and efficiency when employing the enhanced MobileNetV2 as the backbone network. Specifically, the counting accuracy metrics, including mean absolute error (MAE), root mean square error (RMSE), normalized root mean square error (nRMSE), and coefficient of determination (R2), reach 2.4486, 4.0247, 0.0276, and 0.9933, respectively, and the F-Score for localization accuracy is an impressive 0.9791. Moreover, the LettuceNet is compared with other existing widely used plant counting methods including Multi-Column Convolutional Neural Network (MCNN), Dilated Convolutional Neural Networks (CSRNets), Scale Aggregation Network (SANet), TasselNet Version 2 (TasselNetV2), and Focal Inverse Distance Transform Maps (FIDTM). The results indicate that our proposed LettuceNet performs the best among all evaluated merits, with 13.27% higher R2 and 72.83% lower nRMSE compared to the second most accurate SANet in terms of counting accuracy. In summary, the proposed LettuceNet has demonstrated great performance in the tasks of localization and counting of high-density lettuce, showing great potential for field application.

Computer Vision Algorithms on a Raspberry Pi 4 for Automated Depalletizing

The primary objective of a depalletizing system is to automate the process of detecting and locating specific variable-shaped objects on a pallet, allowing a robotic system to accurately unstack them. Although many solutions exist for the problem in industrial and manufacturing settings, the application to small-scale scenarios such as retail vending machines and small warehouses has not received much attention so far. This paper presents a comparative analysis of four different computer vision algorithms for the depalletizing task, implemented on a Raspberry Pi 4, a very popular single-board computer with low computer power suitable for the IoT and edge computing. The algorithms evaluated include the following: pattern matching, scale-invariant feature transform, Oriented FAST and Rotated BRIEF, and Haar cascade classifier. Each technique is described and their implementations are outlined. Their evaluation is performed on the task of box detection and localization in the test images to assess their suitability in a depalletizing system. The performance of the algorithms is given in terms of accuracy, robustness to variability, computational speed, detection sensitivity, and resource consumption. The results reveal the strengths and limitations of each algorithm, providing valuable insights for selecting the most appropriate technique based on the specific requirements of a depalletizing system.

Damage detection and localization in sealed spent nuclear fuel dry storage canisters using multi-task machine learning classifiers

Spent nuclear fuel (SNF) assemblies (FAs), composed of bundled radioactive fuel rods, are stored in stainless-steel canisters as an interim dry storage option until permanent storage solutions are available. Accidental damage to these canisters may occur during handling or transportation events. If such events occur, it is necessary to assess the integrity of FAs before long-term storage. Since the canisters are sealed shut and can only be opened in special handling facilities, non-destructive evaluation (NDE) is critical for detecting the FAs from the canister's exterior surface. In this study, two multi-task machine learning (ML) classifiers, a k-nearest neighbors (k-NN) and a convolutional neural network (CNN), are developed to simultaneously detect and localize internal FA damage. The classifiers were trained and tested on a dataset collected via experimental modal analysis on a 2/3-scale mock-up canister. The canister was excited from the bottom plate while accelerometers were also attached on the bottom plate at arbitrary locations to record the structural response. The differences in frequency response functions (FRFs) between an intact fully loaded canister basket (FLCB) system and the canister with simulated internal damage were calculated and used as input to the ML models. Results showed that both classifiers achieved high accuracy on the testing set. The k-NN classifier produced macro-F1 scores of 1.00 for the damage detection task and 0.996 for the localization task. The macro-F1 scores of the CNN were 0.991 for damage detection and 0.964 for damage localization. Additionally, dropout layers were added to the fully connected layers of the CNN to introduce model uncertainty. By testing the model 1,000 times, probability density functions (PDFs) were generated, and it was confirmed that the CNN produced confident predictions in both the damage detection and localization tasks. This multi-task ML method contributes to advancing NDE of SNF canisters and holds potential for field applications in inspecting actual SNF canisters.

Acoustic scene complexity affects motion behavior during speech perception in audio-visual multi-talker virtual environments

In real-world listening situations, individuals typically utilize head and eye movements to receive and enhance sensory information while exploring acoustic scenes. However, the specific patterns of such movements have not yet been fully characterized. Here, we studied how movement behavior is influenced by scene complexity, varied in terms of reverberation and the number of concurrent talkers. Thirteen normal-hearing participants engaged in a speech comprehension and localization task, requiring them to indicate the spatial location of a spoken story in the presence of other stories in virtual audio-visual scenes. We observed delayed initial head movements when more simultaneous talkers were present in the scene. Both reverberation and a higher number of talkers extended the search period, increased the number of fixated source locations, and resulted in more gaze jumps. The period preceding the participants’ responses was prolonged when more concurrent talkers were present, and listeners continued to move their eyes in the proximity of the target talker. In scenes with more reverberation, the final head position when making the decision was farther away from the target. These findings demonstrate that the complexity of the acoustic scene influences listener behavior during speech comprehension and localization in audio-visual scenes.

UAV Visual Tracking with Enhanced Feature Information

Unmanned aerial vehicles (UAVs) visual tracking is an important research direction. The tracking object is lost due to the problems of target occlusion, illumination variation, flight vibration and so on. Therefore, based on a Siamese network, this study proposes a UAVs visual tracker named SiamDFT++ to enhance the correlation of depth features. First, the network width of the three-layer convolution after the full convolution neural network is doubled, and the appearance information of the target is fully utilized to complete the feature extraction of the template frame and the detection frame. Then, the attention information fusion module and feature deep convolution module are proposed in the template branch and the detection branch, respectively. The feature correlation calculation methods of the two depths can effectively suppress the background information, enhance the correlation between pixel pairs, and efficiently complete the tasks of classification and regression. Furthermore, this study makes full use of shallow features to enhance the extraction of object features. Finally, this study uses the methods of deep cross-correlation operation and complete intersection over union to complete the matching and location tasks. The experimental results show that the tracker has strong robustness in UAVs short-term tracking scenes and long-term tracking scenes.

Collaborative optimization for scheduling manufacturing tasks and transport vehicles considering manufacturer’s time availability in cloud manufacturing

ABSTRACT As an advanced networked intelligent manufacturing model, cloud manufacturing (CMfg) effectively integrates available resources by strengthening the connection among various manufacturers to solve complex manufacturing problems. Due to the geographical dispersion of manufacturers and the cooperativity nature of the manufacturing process, logistic impacts are non-negligible in scheduling. This paper focuses on the collaborative scheduling of manufacturing and transportation services. To make full use of the manufacturer’s capacity without affecting his benefit, local tasks are scheduled with higher priority on a manufacturer while the service time for CMfg tasks is assumed to be fragmented and represented as a set of available time windows. Based on these considerations, a collaborative optimization model for CMfg on task and vehicle scheduling with manufacturing service windows is established, in which the completion time of all CMfg orders and the total idle traveling time of vehicles are minimized to ensure the efficiency of both manufacturing and logistic service. A dual-loop variable neighborhood search algorithm is designed to solve the problem. Comprehensive experiments are conducted, showing improvements of 2.41% to 29.57% in objective and fewer vehicles needed compared with some existing methods, which validate the efficacy of the proposed model and method.

Adapting the segment anything model for multi-modal retinal anomaly detection and localization

The fusion of optical coherence tomography (OCT) and fundus modality information can provide a comprehensive diagnosis for retinal artery occlusion (RAO) disease, where OCT provides the cross-sectional examination of the fundus image. Given multi-modal retinal images, an anomaly diagnosis model can discriminate RAO without the need for real diseased samples. Despite this, previous studies have only focused on single-modal diagnosis, because of: 1) the lack of paired modality samples; and 2) the significant imaging differences, which make the fusion difficult with small-scale medical data. In this paper, we describe how we first built a multi-modal RAO dataset including both OCT and fundus modalities, which supports both the anomaly detection and localization tasks with pixel-level annotation. Motivated by the powerful generalization ability of the recent visual foundation model known as the Segment Anything Model (SAM), we adapted it for our task considering the small-scale property of retinal samples. Specifically, a modality-shared decoder with task-specific tokens is introduced to make SAM support the multi-modal image setting, which includes a mask token for the anomaly localization task at the pixel level and a fusion token for the anomaly detection task at the case level. Since SAM has little medical knowledge and lacks the learning of the “normal” concept, it is infeasible to localize RAO anomalies in the zero-shot manner. To integrate expert retinal knowledge while keeping the general segmentation knowledge, general anomaly simulation for both modalities and a low-level prompt-tuning strategy are introduced. The experiments conducted in this study show that the adapted model can surpass the state-of-the-art model by a large margin. This study sets the first benchmark for the multi-modal anomaly detection and localization tasks in the medical community. The code is available at https://github.com/Jingtao-Li-CVer/MMRAD.

An Efficient Modified Black Widow Optimized Node Localization in Wireless Sensor Network

Wireless Sensor Network (WSN) is an encouraging technology in various applications like atmosphere monitoring, vehicular systems, and targeting devices. Localization in WSN is performed to identify the current position or coordinates of sensor nodes. The crucial task of localization is to find coordinates without manual configuration and expensive hardware like GPS. This work proposes a new localization algorithm using Modified Black Widow Optimization (MBWO). The proposed method involves an optimal selection of anchor nodes to reduce localization errors. Black Widow Optimization (BWO) is a naturally inspired optimization algorithm encouraged by the unique coupling behaviour of black widow spiders. The performance of black widow optimization is improved by levy flight distribution to escape from local minima. Experimental results show that the proposed MBWO-optimized localization achieves a higher localized node count with minimized localized error compared to other optimization algorithms.

To be global or personalized: Generalized federated learning with cooperative adaptation for data heterogeneity

As federated learning (FL) continues to advance, research has branched into two major directions: enhancing the individual global model and developing multiple personalized models. However, few studies took both orientations into consideration in parallel. The underlying reason lies in the objective heterogeneity between global and personalized models, where the former emphasizes generalization, while the latter focuses on specialization. The dilemma of sacrificing the personalized deviation in exchange for stable global enhancement, or forsaking the global model for personalization, is particularly acute in highly heterogeneous data scenarios (as a curse). To establish the coexistence of global and personalized models in highly heterogeneous data scenarios, we propose FedAKD, a generalized federated learning framework with adaptive knowledge distillation to optimizes both global and personalized models. Specifically, based on the similarity of predictive distributions over a reference dataset, two distinct adaptive weighting strategies are employed to match the divergent focuses of global and personalized optimization, leveraging data heterogeneity to foster cooperative adaptation and establish their coexistence (as a blessing). The client-side strategy through cluster-oriented optimization to facilitate the domain adaptation in local tasks. Meanwhile, the server-side strategy adjusts the global model to accommodate varying optimization directions from diverse implicit clusters. Experiments in label and feature shift settings demonstrate that our method outperforms state-of-the-art methods in both global and personalized performance with faster convergence [e.g. the accuracy improvements on the physical activity monitoring dataset (PAMAP2) for global and personalized models exceed 26.51% and 11.00%, respectively]. Furthermore, our method is equally applicable to real-world healthcare scenarios.

Examining the lateralization of electrophysiological correlates of auditory awareness.

The neurological basis for perceptual awareness remains unclear, and theories disagree as to whether sensory cortices per se generate awareness. Critically, neural activity in the sensory cortices is only a neural correlate of consciousness (NCC) if it closely matches the contents of perceptual awareness. Research in vision and touch suggest that contralateral activity in sensory cortices is an NCC. Similarly, research in hearing with two sound sources (left and right) presented over headphones also suggests that a candidate NCC called the auditory awareness negativity (AAN) matches perceived location of sound. The current study used 13 different sound sources presented over loudspeakers for natural localization cues and measured event-related potentials to a threshold stimulus in a sound localization task. Preregistered Bayesian mixed models provided moderate evidence against an overall AAN and very strong evidence against its lateralization. Because of issues regarding data quantity and quality, exploratory analyses with aggregated data from multiple loudspeakers were conducted. Results provided moderate evidence for an overall AAN and strong evidence against its lateralization. Nonetheless, the interpretations of these results remain inconclusive. Therefore, future research should reduce the number of conditions and/or test over several sessions to procure a sufficient amount of data. Taken at face value, the results may suggest issues with AAN as an NCC of auditory awareness, as it does not laterally map onto experiences in a free-field auditory environment, in contrast to the NCCs of vision and touch.

Facial feature point detection under large range of face deformations

Facial Feature Point Detection (FFPD) plays a significant role in several face analysis tasks such as feature extraction and classification. This paper presents a Fully Automatic FFPD system using the application of Random Forest Regression Voting in a Constrained Local Model (RFRV-CLM) framework. A global detector is used to find the approximate positions of the facial region and eye centers. A sequence of local RFRV-CLMs are used to locate a detailed set of points around the facial features. Both global and local models use Random Forest Regression to vote for optimal positions. The system is evaluated in the task of facial expression localization using five different facial expression databases of different characteristics including age, intensity, 6-basic expressions, 22 compound expressions, static and dynamic images, and deliberate and spontaneous expressions. Quantitative results of the evaluation of automatic point localization against manual points (ground truth) demonstrated that the results of the proposed approach are encouraging and outperform the results of alternative techniques tested on the same databases.

Federated Many-Task Bayesian Optimization

Bayesian optimization is a powerful surrogate-assisted algorithm for solving expensive black-box optimization problems. While Bayesian optimization was developed for centralized optimization, the availability of massive distributed data has attracted increased interests in exploring federated Bayesian optimization that can use data on multiple clients without leaking the raw data. However, existing federated Bayesian optimization (FBO) approaches assume that either all clients jointly solve the same optimization task, or only one client solves one target optimization task by transferring knowledge from others in a federated way, making them unsuited for many real-world applications. In this paper, we consider FBO for the scenario where multiple related local black-box tasks associated with different clients are jointly optimized by sharing knowledge between tasks without leaking the data privacy. An efficient federated many-task Bayesian optimization framework is proposed to address not independent and identically distributed (non-IID) data while protecting the data privacy in the federated setting. A novel federated knowledge transfer paradigm is developed for dynamic many-task model aggregation according to a dissimilarity matrix. The dissimilarity is measured based on the rank of the predictions and only the hyperparameters in the local Gaussian process models are shared. In addition, a federated ensemble acquisition function is constructed by integrating the predictions of two surrogates using the global and local hyperparameters, respectively, to effectively search for the optimal solution. Experimental results show that our proposed method has reliable performance on both benchmark problems and a real machine learning problem also in the presence of non-IID data.