Suboptimal Performance Research Articles

Improving cross-regional model transfer performance in crop classification by crop time series correction

ABSTRACT Cross-Regional Model Transfer (CRMT) provides a solution to crop classification challenges in target regions with limited labeled samples. However, when the source region (source domain) and the target region (target domain) are spatially distant, a shift in crop Satellite Image Time Series (SITS) occurs, resulting in suboptimal performance of SITS-based classification models in the target domain. To address this issue, we propose a novel domain adaptation method, named SITS Correction. This method mitigates the SITS shift by introducing correction factors to improve the classification performance of CRMT. The correction factors consist of source domain correction units and target domain correction units, which are from variables associated with the SITS shift. In cases where labeled samples are available in the target domain, the SITS have calculated Barycenter (i.e. SitsB) as the correction units, which then combine the source domain and the target domain’s SitsB to form a SITS-based correction factor. When no labeled samples are available, the correction units are substituted by Barycenter of the temperature variables time series (i.e. temperature indicator) influencing crop growth, and the correction factors are composed of temperature indicators from both the source and target domains. We validate SITS Correction through transfer experiments conducted in four regions, encompassing various years, crops, and classification methods. Experimental results demonstrate a significant improvement in crop classification performance with SITS Correction in both scenarios – target domain with labeled samples (accuracy increased by 39.1%) and target domain without labeled samples (accuracy increased by 14.8%). This research provides a practical option for crop classification in target regions with either limited or no labeled samples.

UAV Trajectory Tracking Using Proportional-Integral-Derivative-Type-2 Fuzzy Logic Controller with Genetic Algorithm Parameter Tuning.

Unmanned Aerial Vehicle (UAV)-type Quadrotors are highly nonlinear systems that are difficult to control and stabilize outdoors, especially in a windy environment. Many algorithms have been proposed to solve the problem of trajectory tracking using UAVs. However, current control systems face significant hurdles, such as parameter uncertainties, modeling errors, and challenges in windy environments. Sensitivity to parameter variations may lead to performance degradation or instability. Modeling errors arise from simplifications, causing disparities between assumed and actual behavior. Classical controls may lack adaptability to dynamic changes, necessitating adaptive strategies. Limited robustness in handling uncertainties can result in suboptimal performance. Windy environments introduce disturbances, impacting system dynamics and precision. The complexity of wind modeling demands advanced estimation and compensation strategies. Tuning challenges may necessitate frequent adjustments, posing practical limitations. Researchers have explored advanced control paradigms, including robust, adaptive, and predictive control, aiming to enhance system performance amidst uncertainties in a scientifically rigorous manner. Our approach does not require knowledge of UAVs and noise models. Furthermore, the use of the Type-2 controller makes our approach robust in the face of uncertainties. The effectiveness of the proposed approach is clear from the obtained results. In this paper, robust and optimal controllers are proposed, validated, and compared on a quadrotor navigating an outdoor environment. First, a Type-2 Fuzzy Logic Controller (FLC) combined with a PID is compared to a Type-1 FLC and Backstepping controller. Second, a Genetic Algorithm (GA) is proposed to provide the optimal PID-Type-2 FLC tuning. The Backstepping, PID-Type-1 FLC, and PID-Type-2 FLC with GA optimization are validated and evaluated with real scenarios in a windy environment. Deep robustness analysis, including error modeling, parameter uncertainties, and actuator faults, is considered. The obtained results clearly show the robustness of the optimal PID-Type-2 FLC compared to the Backstepping and PID-Type-1 FLC controllers. These results are confirmed by the numerical index of each controller compared to the PID-type-2 FLC, with 12% for the Backstepping controller and 51% for the PID-Type-1 FLC.

Learning Robust Sequential Recommenders through Confident Soft Labels

Sequential recommenders that are trained on implicit feedback are usually learned as a multi-class classification task through softmax-based loss functions on one-hot class labels. However, one-hot training labels are sparse and may lead to biased training and sub-optimal performance. Dense, soft labels have been shown to help improve recommendation performance. However, how to generate high-quality and confident soft labels from noisy sequential interactions between users and items is still an open question. We propose a new learning framework for sequential recommenders, CSRec, which introduces c onfident s oft labels to provide robust guidance when learning from user-item interactions. CSRec contains a teacher module that generates high-quality and confident soft labels and a student module that acts as the target recommender and is trained on the combination of dense, soft labels and sparse, one-hot labels. We propose and compare three approaches to constructing the teacher module: (i) model-level, (ii) data-level, and (iii) training-level. To evaluate the effectiveness and generalization ability of CSRec, we conduct experiments using various state-of-the-art sequential recommendation models as the target student module on four benchmark datasets. Our experimental results demonstrate that CSRec is effective in training better-performing sequential recommenders.

Category-Based Interactive Attention and Perception Fusion Network for Semantic Segmentation of Remote Sensing Images

With the development of CNNs and the application of transformers, the segmentation performance of high-resolution remote sensing image semantic segmentation models has been significantly improved. However, the issue of category imbalance in remote sensing images often leads to the model’s segmentation ability being biased towards categories with more samples, resulting in suboptimal performance for categories with fewer samples. To make the network’s learning and representation capabilities more balanced across different classes, in this paper we propose a category-based interactive attention and perception fusion network (CIAPNet), where the network divides the feature space by category to ensure the fairness of learning and representation for each category. Specifically, the category grouping attention (CGA) module utilizes self-attention to reconstruct the features of each category in a grouped manner, and optimize the foreground–background relationship and its feature representation for each category through the interactive foreground–background relationship optimization (IFBRO) module therein. Additionally, we introduce a detail-aware fusion (DAF) module, which uses shallow detail features to complete the semantic information of deep features. Finally, a multi-scale representation (MSR) module is deployed for each class in the CGA and DAF modules to enhance the description capability of different scale information for each category. Our proposed CIAPNet achieves mIoUs of 54.44%, 85.71%, and 87.88% on the LoveDA urban–rural dataset, and the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam urban datasets, respectively. Compared with current popular methods, our network not only achieves excellent performance but also demonstrates outstanding class balance.

Multiparametric MRI Radiomics With Machine Learning for Differentiating HER2-Zero, -Low, and -Positive Breast Cancer: Model Development, Testing, and Interpretability Analysis.

BACKGROUND: MRI radiomics has been explored for three-tiered classification of breast cancer HER2 expression (i.e., HER2-zero, HER2-low, or HER2-positive), although understanding of how such models reach their predictions is lacking. OBJECTIVE: To develop and test multiparametric MRI radiomics machine-learning models for differentiating three-tiered HER2 expression levels in patients with breast cancer, and to explain the contributions of model features through local and global interpretations using SHapley Additive exPlanation (SHAP) analysis. METHODS: This retrospective study included 737 patients (mean age, 54.1±10.6 years) with breast cancer from two centers (center 1: n=578; center 2: n=159), who underwent breast MRI and had HER2 expression determined after excisional biopsy. Analysis entailed two tasks: differentiating HER2-negative (i.e., HER2-zero or HER2-low) from HER2-positive tumors (task 1), and differentiating HER2-zero from HER2-low tumors (task 2). For each task, patients from center 1 were randomly assigned in 7:3 ratio to training (task 1: n=405; task 2: n=284) or internal test (task 1: n=173; task 2: n=122) sets; those from center 2 formed an external test set (task 1: n=159; task 2: n=105). Radiomics features were extracted from early-phase dynamic contrast-enhanced images (DCE), T2-weighted images (T2WI), and DWI. For each task, a support vector machine (SVM) was used for feature selection; a multiparametric radiomics score (radscore) was computed using feature weights from SVM correlation coefficients; conventional MRI and combined models were constructed; and model performances were evaluated. SHAP analysis was used to provide local and global interpretations for model outputs. RESULTS: In the external test set, for task 1, AUCs for the conventional MRI model, radscore, and combined model were 0.624, 0.757, and 0.762, respectively; for task 2, AUC for radscore was 0.754, and no conventional MRI model or combined model could be constructed. SHAP analysis identified early-phase DCE features as having the strongest influence for both tasks; T2WI features also had a prominent role for task 2. CONCLUSION: The findings indicate suboptimal performance of MRI radiomics models for noninvasive characterization of HER2 expression. CLINICAL IMPACT: The study provides an example of the use of SHAP interpretation analysis to better understand predictions of imaging-based machine learning models.

Assessing the relative importance of vitamin D deficiency in cardiovascular health.

Previous research has suggested a potential link between vitamin D (VD) deficiency and adverse cardiovascular health outcomes, although the findings have been inconsistent. This study investigates the association between VD deficiency and cardiovascular disease (CVD) within the context of established CVD risk factors. We utilized a Random Forest model to predict both CVD and VD deficiency risks, using a dataset of 1,078 observations from a rural Chinese population. Feature importance was evaluated using SHapley Additive exPlanations (SHAP) to discern the impact of various risk factors on the model's output. The results showed that the model for CVD prediction achieved a high accuracy of 87%, demonstrating robust performance across precision, recall, and F1 score metrics. Conversely, the VD deficiency prediction model exhibited suboptimal performance, with an accuracy of 52% and lower precision, recall, and F1 scores. Feature importance analysis indicated that traditional risk factors such as systolic blood pressure, diastolic blood pressure, age, body mass index, and waist-to-hip ratio significantly influenced CVD risk, collectively contributing to 70% of the model's predictive power. Although VD deficiency was associated with an increased risk of CVD, its importance in predicting CVD risk was notably low. Similarly, for VD deficiency prediction, CVD risk factors such as systolic blood pressure, glucose levels, diastolic blood pressure, and body mass index emerged as influential features. However, the overall predictive performance of the VD deficiency prediction model was weak (52%), indicating the absence of VD deficiency-related risk factors. Ablation experiments confirmed the relatively lower importance of VD deficiency in predicting CVD risk. Furthermore, the SHAP partial dependence plot revealed a nonlinear relationship between VD levels and CVD risk. In conclusion, while VD deficiency appears directly or indirectly associated with increased CVD risk, its relative importance within predictive models is considerably lower when compared to other risk factors. These findings suggest that VD deficiency may not warrant primary focus in CVD risk assessment and prevention strategies, however, further research is needed to explore the causal relationship between VD deficiency and CVD risk.

Optimizing Kernel Transformations to Handle Binary Class Imbalanced Dataset Classification

ABSTRACT Imbalanced class distributions pose a prevalent challenge in numerous classification problems, requiring effective strategies for learning from such skewed data. Traditional machine learning algorithms often struggle with imbalanced datasets, as they tend to bias their classification functions toward the majority class, resulting in suboptimal performance for minority classes. In our research, we propose a novel approach to address this challenge specifically tailored for Support Vector Machines (SVM), a well-established family of learning algorithms. Our method leverages a kernel trick to enhance the SVM’s classification capabilities on imbalanced datasets named KTI. It aims to streamline the classification process by incorporating adaptive data transformations within the algorithm itself, offering a more efficient and integrated solution for handling imbalanced data. Experimental evaluations conducted on diverse real-world datasets demonstrate the superior performance of our proposed strategy compared to existing methods, showcasing its potential for practical applications in classification tasks with skewed class distributions.

Bounded professionalism nexus: HR professionalism within and across organizational boundaries

AbstractEven though the field of human resources is rife with tensions and contradictions, little is known about how HR practitioners experience and navigate these challenges. The impact of these tensions and ambiguities on HR professionalism remains understudied. Using the framework of “bounded professionalism”, this study explores how HR practitioners in business organizations (RBOs) and staffing agencies (RSAs) navigate professional and organizational tensions. Through a qualitative methodology, we conducted 60 semi‐structured interviews with HR practitioners from a variety of organizational settings. By examining the complicated experiences of HR practitioners, we highlight the nuanced ways in which they manage and mitigate professional and organizational tensions. This paper introduces and further develops the concept of “bounded professionalism nexus,” which implies that collaboration between professionals across organizational boundaries may exacerbate the experience of bounded professionalism. Specifically, we identify the triggers and implications of “bounded professionalism nexus”, demonstrating how cross‐border organizational relations contribute to suboptimal performance in both RSAs and RBOs. According to our findings, these tensions are not only prevalent, but also have significant implications for HR professionalism. This study concludes by examining the broader implications of the “bounded professionalism nexus” for HR professionals and offering suggestions for mitigating these tensions.

A Novel YOLOv10-DECA Model for Real-Time Detection of Concrete Cracks

The You Only Look Once (YOLO) series algorithms have been widely adopted in concrete crack detection, with attention mechanisms frequently being incorporated to enhance recognition accuracy and efficiency. However, existing research is confronted by two primary challenges: the suboptimal performance of attention mechanism modules and the lack of explanation regarding how these mechanisms influence the model’s decision-making process to improve accuracy. To address these issues, a novel Dynamic Efficient Channel Attention (DECA) module is proposed in this study, which is designed to enhance the performance of the YOLOv10 model in concrete crack detection, and the effectiveness of this module is visually demonstrated through the application of interpretable analysis algorithms. In this paper, a concrete dataset with a complex background is used. Experimental results indicate that the DECA module significantly improves the model’s accuracy in crack localization and the detection of discontinuous cracks, outperforming the existing Efficient Channel Attention (ECA). When compared to the similarly sized YOLOv10n model, the proposed YOLOv10-DECA model demonstrates improvements of 4.40%, 3.06%, 4.48%, and 5.56% in precision, recall, mAP50, and mAP50-95 metrics, respectively. Moreover, even when compared with the larger YOLOv10s model, these performance indicators are increased by 2.00%, 0.04%, 2.27%, and 1.12%, respectively. In terms of speed evaluation, owing to the lightweight design of the DECA module, the YOLOv10-DECA model achieves an inference speed of 78 frames per second, which is 2.5 times faster than YOLOv10s, thereby fully meeting the requirements for real-time detection. These results demonstrate that an optimized balance between accuracy and speed in concrete crack detection tasks has been achieved by the YOLOv10-DECA model. Consequently, this study provides valuable insights for future research and applications in this field.

Vision-and-language navigation based on history-aware cross-modal feature fusion in indoor environment

Vision-and-language navigation (VLN) is a challenging task that requires an agent to navigate an indoor environment using natural language instructions. Traditional VLN employs cross-modal feature fusion, where visual and textual information are combined to guide the agent’s navigation. However, incomplete use of perceptual information, scarcity of domain-specific training data, and diverse image and language inputs result in suboptimal performance. Herein, we propose a cross-modal feature fusion VLN history-aware information, that leverages an agent’s past experiences to make more informed navigation decisions. The regretful model and self-monitoring models are added, and the advantage actor critic(A2C) reinforcement learning algorithm is employed to improve the navigation success rate, reduce action redundancy, and shorten navigation paths. Subsequently, a data augmentation method based on speaker data is introduced to improve the model generalizability. We evaluate the proposed algorithm on the room-to-room (R2R) and room-for-room (R4R) benchmarks, and the experimental results demonstrate that, by comparison, the proposed algorithm outperforms state-of-the-art methods.

Multi-Agent DRL for Air-to-Ground Communication Planning in UAV-Enabled IoT Networks.

In this paper, we present a novel method to enhance the sum-rate effectiveness in full-duplex unmanned aerial vehicle (UAV)-assisted communication networks. Existing approaches often couple uplink and downlink associations, resulting in suboptimal performance, particularly in dynamic environments where user demands and network conditions are unpredictable. To overcome these limitations, we propose a decoupling of uplink and downlink associations for ground-based users (GBUs), significantly improving network efficiency. We formulate a comprehensive optimization problem that integrates UAV trajectory design and user association, aiming to maximize the overall sum-rate efficiency of the network. Due to the problem's non-convexity, we reformulate it as a Partially Observable Markov Decision Process (POMDP), enabling UAVs to make real-time decisions based on local observations without requiring complete global information. Our framework employs multi-agent deep reinforcement learning (MADRL), specifically the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, which balances centralized training with distributed execution. This allows UAVs to efficiently learn optimal user associations and trajectory controls while dynamically adapting to local conditions. The proposed solution is particularly suited for critical applications such as disaster response and search and rescue missions, highlighting the practical significance of utilizing UAVs for rapid network deployment in emergencies. By addressing the limitations of existing centralized and distributed solutions, our hybrid model combines the benefits of centralized training with the adaptability of distributed inference, ensuring optimal UAV operations in real-time scenarios.

CEDNet: A cascade encoder–decoder network for dense prediction

The prevailing methods for dense prediction tasks typically utilize a heavy classification backbone to extract multi-scale features and then fuse these features using a lightweight module. However, these methods allocate most computational resources to the classification backbone, which delays the multi-scale feature fusion and potentially leads to inadequate feature fusion. Although some methods perform feature fusion from early stages, they either fail to fully leverage high-level features to guide low-level feature learning or have complex structures, resulting in sub-optimal performance. We propose a streamlined cascade encoder–decoder network, named CEDNet, tailored for dense prediction tasks. All stages in CEDNet share the same encoder–decoder structure and perform multi-scale feature fusion within each decoder, thereby enhancing the effectiveness of multi-scale feature fusion. We explored three well-known encoder–decoder structures: Hourglass, UNet, and FPN, all of which yielded promising results. Experiments on various dense prediction tasks demonstrated the effectiveness of our method.11Code: https://github.com/zhanggang001/CEDNet.

FROM PLANNING TO PERFORMANCE: ASSESSING THE ROLE OF MILESTONE SCHEDULING IN GARMENT ENTERPRISES IN ELDORET TOWN, KENYA

The performance of garment enterprise projects is a critical indicator of the economic progress and sustainability of any country. With respect to small garment enterprises in Eldoret town, data has shown suboptimal performance in the industry, resulting in some SMEs ceasing their operations. The aim of this paper is to assess the effect of scheduling milestones on the performance of small-scale garment enterprise projects in Eldoret town. The study was anchored on the Goal Setting Theory. An explanatory research design was used, and the target population consisted of 386 small-scale garment enterprise owners. A sample size of 196 small-scale garment enterprise projects in Eldoret town was selected. The respondents were selected using a stratified sampling method, and data was collected using questionnaires. The analysis was done using both descriptive and inferential statistics. With respect to findings, mapping risks was found to have a significant positive effect on the performance of garment enterprise projects (β 0.968, p<0.05). Milestone scheduling has a significant positive impact on the performance of garment enterprises in Eldoret town. The study recommends that small-scale garment enterprise projects prioritize the efficient use of their available resources and develop detailed production schedules.<p> </p><p><strong> Article visualizations:</strong></p><p><img src="/-counters-/soc/0773/a.php" alt="Hit counter" /></p>

Differential Neural Mechanisms of Feedback Processing in Children with Developmental Language Disorder: An Examination of Midfrontal Theta Connectivity.

Previous research indicates that children with Developmental Language Disorder (DLD) face challenges learning from feedback, resulting in suboptimal performance and learning outcomes. Feedback processing, a key developing executive function, involves cognitive processes critical for goal-directed behavior. This study examined the neural mechanisms underlying feedback processing in school-age children with DLD compared to typically developing (TD) peers, focusing on midfrontal theta band (4-8 Hz) oscillations as an index of cognitive control and error monitoring. We measured midfrontal theta inter-trial coherence (ITC) and inter-site coherence (ISC) at midfrontal (FCz), lateral prefrontal (F3/F4), and lateral central (C3/C4) sites in children with and without DLD (n = 33, age 8-13 years) in response to feedback provision within a Wisconsin Card Sorting Test (WCST) in two time windows (200-400 ms, which is associated with the Feedback-Related Negativity, or FRN, and 400-600 ms, which is associated with the P3a). Children with and without DLD showed elevated midfrontal theta oscillations in response to negative feedback that was followed by successful behavioral adjustments in the FRN time window. Activation in the P3a time window was only found in the TD group. Group differences were also noted in the inter-site coherence (ISC) associated with the effective processing of negative feedback. While in the TD group, effective processing of negative feedback was linked to high connectivity between midfrontal and right sensorimotor regions, in the DLD group, effective processing of negative feedback was associated with high connectivity between midfrontal and left sensorimotor sites. Differential ISC patterns in children with DLD may indicate that they employ alternative or compensatory neural strategies, possibly due to atypical right sensorimotor engagement.

Optimizing Attention and Cognitive Control Costs Using Temporally Layered Architectures.

The current reinforcement learning framework focuses exclusively on performance, often at the expense of efficiency. In contrast, biological control achieves remarkable performance while also optimizing computational energy expenditure and decision frequency. We propose a decision-bounded Markov decision process (DB-MDP) that constrains the number of decisions and computational energy available to agents in reinforcement learning environments. Our experiments demonstrate that existing reinforcement learning algorithms struggle within this framework, leading to either failure or suboptimal performance. To address this, we introduce a biologically inspired, temporally layered architecture (TLA), enabling agents to manage computational costs through two layers with distinct timescales and energy requirements. TLA achieves optimal performance in decision-bounded environments and in continuous control environments, matching state-of-the-art performance while using a fraction of the computing cost. Compared to current reinforcement learning algorithms that solely prioritize performance, our approach significantly lowers computational energy expenditure while maintaining performance. These findings establish a benchmark and pave the way for future research on energy and time-aware control.

Heterogeneous graph contrastive learning with adaptive data augmentation for semi‐supervised short text classification

AbstractShort text classification has been widely used in many fields. Due to the scarcity of labelled data, implementing short text classification under semi‐supervised learning setting has become increasingly popular. Semi‐supervised short text classification methods based on graph neural networks can achieve state‐of‐the‐art classification performance by utilizing the expressive power of graph neural networks. However, these methods usually fail to mine the hidden patterns of a large amount of short text node data in the graph to optimize the short text node embeddings, which limits the semantic representation power of the short texts, thus leading to suboptimal classification performance. To overcome the limitation, this paper proposes a novel semi‐supervised short text classification method called the Heterogeneous Graph Contrastive Learning with Adaptive Data Augmentation (HGCLADA). In the knowledge bases guided soft prompt‐based data augmentation component, the related words of the tag words are used to optimize the soft prompts for generating diverse augmented samples. In the heterogeneous graph contrastive learning framework component, a heterogeneous graph that is constructed using short texts and keywords and an effective edge augmentation scheme based on a short text clustering algorithm are proposed. The optimized short text embeddings can be obtained to achieve the effective semi‐supervised short text classification. Extensive experiments on six benchmark datasets show that our HGCLADA method outperforms four classes of state‐of‐the‐art methods in terms of classification accuracy, especially with significant performance improvements of 8.74% on the TagMyNews dataset when each class only contains 20 labelled data.

Three-Dimensional Reconstruction of Partially Coherent Scatterers Using Iterative Sub-Network Generation Method

Synthetic aperture radar tomography (TomoSAR) has gained significant attention for three-dimensional (3D) imaging in urban environments. A notable limitation of traditional TomoSAR approaches is their primary focus on persistent scatterers (PSs), disregarding targets with temporal decorrelated characteristics. Temporal variations in coherence, especially in urban areas due to the dense population of buildings and artificial structures, can lead to a reduction in detectable PSs and suboptimal 3D reconstruction performance. The concept of partially coherent scatterers (PCSs) has been proven effective by capturing the partial temporal coherence of targets across the entire time baseline. In this study, an novel approach based on an iterative sub-network generation method is introduced to leverage PCSs for enhanced 3D reconstruction in dynamic environments. We propose a coherence constraint iterative variance analysis approach to determine the optimal temporal baseline range that accurately reflects the interferometric coherence of PCSs. Utilizing the selected PCSs, a 3D imaging technique that incorporates the iterative generation of sub-networks into the SAR tomography process is developed. By employing the PS reference network as a foundation, we accurately invert PCSs through the iterative generation of local star-shaped networks, ensuring a comprehensive coverage of PCSs in study areas. The effectiveness of this method for the height estimation of PCSs is validated using the TerraSAR-X dataset. Compared with traditional PS-based TomoSAR, the proposed approach demonstrates that PCS-based elevation results complement those from PSs, significantly improving 3D reconstruction in evolving urban settings.

MWIR image deep denoising reconstruction based on single-pixel imaging

Single-pixel imaging enables cost-effective and highly sensitive mid-wave infrared imaging, with the added convenience facilitated by deep learning algorithms. However, most networks train separate models depending on compression rates, frequently neglecting real-world infrared noise, leading to inconveniences and suboptimal reconstruction performance. To address these issues, we propose to integrate intrinsic and external deep denoising priors for the reconstruction of compressive mid-wave infrared images from single-pixel measurements. The generalized alternating projection is unfolded into a designed network to harness the benefits of robustness and internal priors. Furthermore, to mitigate real-world noise in measurements, a Swin Transformer U-shaped network that embeds noise variance is introduced to learn external denoise prior. A comparative analysis of simulated and real infrared single-pixel imaging in experiments highlights the promising performance of the proposed method.

Trajectory mapping through channel state information by triangulation method and fine-tuning

Trajectory mapping techniques have widespread applications in diverse fields, including robotics, localization, smart environments, gaming, and tracking systems. However, existing free devices encounter challenges in representing trajectories, thereby limiting the effectiveness of applications such as robotics, localization, and tracking systems. The imprecise mappings generated by these methods lead to suboptimal performance and unreliable results. The proposed approach leverages WiFi sensing through channel state information (CSI), triangulation techniques, and a fine-tuning mechanism to enhance trajectory precision within indoor environment trajectory mapping. The proposed solution employs a domain adapter fine-tuning technique to enable location-independent tracking via CSI, minimizing errors. The use of CSI MIMO signals for trajectory mapping offers enhanced spatial resolution, robust multipath handling, and improved accuracy in tracking movement by leveraging multiple antenna channels and exploiting the rich information embedded in signal reflections and scattering, while triangulation aids in accurately determining the location of objects or targets. Furthermore, incorporating a fine-tuning mechanism refines the generated trajectories. The findings demonstrate substantial enhancements in mapping precision, with an accuracy of 95.5% in tracking 13 paths within the new domain. These results underscore the effectiveness of the proposed approach in overcoming the limitations of existing methods and achieving highly accurate trajectory mapping.

Bi-Interfusion: A bidirectional cross-fusion framework with semantic-guided transformers in LiDAR-camera fusion

Multi-sensor modal fusion has shown significant advantages in 3D object detection tasks. However, existing methods for fusing multi-modal features into the bird’s eye view (BEV) space often encounter challenges such as feature misalignment, underutilization of semantic information, and inaccurate depth estimation on the Z-axis, resulting in suboptimal performance. To address these issues, we propose Bi-Interfusion, a novel multi-modal fusion framework based on transformers. Bi-Interfusion incorporates a bidirectional fusion architecture, including components such as Pixel-wise Semantic Painting, Gaussian Depth Prior Distribution module, and Semantic Guidance Align module, to overcome the limitations of traditional fusion methods. Specifically, Bi-Interfusion employs a bidirectional cross-fusion strategy to merge image and LiDAR features, enabling the generation of multi-sensor BEV features. This approach leverages a refined Gaussian Depth Prior Distribution generated from LiDAR points, thereby improving the precision of view transformation. Additionally, we apply a pixel-wise semantic painting technique to embed image semantic information into LiDAR point clouds, facilitating a more comprehensive scene understanding. Furthermore, a transformer-based model is utilized to establish soft correspondences among multi-sensor BEV features, capturing positional dependencies and fully exploiting semantic information for alignment. Through experiments on nuScenes benchmark dataset, Bi-Interfusion demonstrates notable performance improvements, achieving a competitive performance of 72.6% mAP and 75.4% NDS in the 3D object detection task.