Estimating human joint angles is a crucial task in motion analysis, gesture recognition, and motion intention prediction. This paper presents a novel model-based approach for generating reliable and accurate human joint angle estimation using a dual-branch network. The proposed network leverages combined features derived from encoded sEMG signals and RGB-D image data. To ensure the accuracy and reliability of the estimation algorithm, the proposed network employs a convolutional autoencoder to generate a high-level compression of sEMG features aimed at motion prediction. Considering the variability in the distribution of sEMG signals, the proposed network introduces a vision-based joint regression network to maintain the stability of combined features. Taking into account latency, occlusion, and shading issues with vision data acquisition, the feature fusion network utilizes high-frequency sEMG features as weights for specific features extracted from image data. The proposed method achieves effective human body joint angle estimation for motion analysis and motion intention prediction by mitigating the effects of non-stationary sEMG signals.

Wearable sensor-based human activity recognition (HAR) methods hold considerable promise for upper-level control in exoskeleton systems. However, such methods tend to overlook the critical role of data quality and still encounter challenges in cross-subject adaptation. To address this, we propose an active learning framework that integrates the relation network architecture with data sampling techniques. Initially, target data are used to fine tune two auxiliary classifiers of the pre-trained model, thereby establishing subject-specific classification boundaries. Subsequently, we assess the significance of the target data based on classifier discrepancy and partition the data into sample and template sets. Finally, the sampled data and a category clustering algorithm are employed to tune model parameters and optimize template data distribution, respectively. This approach facilitates the adaptation of the model to the target subject, enhancing both accuracy and generalizability. To evaluate the effectiveness of the proposed adaptation framework, we conducted evaluation experiments on a public dataset and a self-constructed electromyography (EMG) dataset. Experimental results demonstrate that our method outperforms the compared methods across all three statistical metrics. Furthermore, ablation experiments highlight the necessity of data screening. Our work underscores the practical feasibility of implementing user-independent HAR methods in exoskeleton control systems.

Accurate and reliable human pose estimation (HPE) is essential in interactive systems, particularly for applications requiring personalized adaptation, such as controlling cooperative robots and wearable exoskeletons, especially for healthcare monitoring equipment. However, continuously maintaining diverse datasets and frequently updating models for individual adaptation are both resource intensive and time-consuming. To address these challenges, we propose a meta-transfer learning framework that integrates multimodal inputs, including high-frequency surface electromyography (sEMG), visual-inertial odometry (VIO), and high-precision image data. This framework improves both accuracy and stability through a knowledge fusion strategy, resolving the data alignment issue, ensuring seamless integration of different modalities. To further enhance adaptability, we introduce a training and adaptation framework with few-shot learning, facilitating efficient updating of encoders and decoders for dynamic feature adjustment in real-time applications. Experimental results demonstrate that our framework provides accurate, high-frequency pose estimations, particularly for intra-subject adaptation. Our approach enables efficient adaptation to new individuals with only a few new samples, providing an effective solution for personalized motion analysis with minimal data.

Larch casebearer (Coleophora laricella) poses a serious threat to forest ecological security, and remote sensing object detection is essential for early warning and targeted intervention. However, existing detectors are hindered by insufficient feature extraction, limited self-attention inductive bias, and weak spatial localization, which collectively constrain their practical deployment. To address these issues, we propose DROMAL-Net, which integrates global feature enhancement and positional dynamic clustering for forest pest detection. Built upon the YOLOv11n baseline, our model incorporates three key innovations. First, we design the MALAPSA module by embedding a magnitude-aware linear attention (MALA) mechanism into the feature extraction pipeline, achieving linear computational complexity while preserving global contextual modeling. Second, to address the inductive bias deficiency of C2PSA and better preserve spatial topology, we introduce C3kDR (DCCC3k), a positional dynamic clustering module that combines dynamic clustering convolution with complex-domain positional compensation to enhance multi-scale localization accuracy. Third, we integrate 2D Rotary Position Embedding (2D-RoPE) to further mitigate spatial ambiguity in dynamic clustering.Extensive experiments on the public SLFPD dataset validate the effectiveness of each component. Under the standard random partition, DROMAL-Net achieves 77.98% mAP@0.5, outperforming YOLOv11n by 2.46 percentage points. Furthermore, under a strict leave-one-block-out protocol to prevent spatial leakage, DROMAL-Net consistently outperforms YOLOv11n across all five held-out blocks, achieving a macro-average mAP@0.5 of 69.12% vs. 65.94%, corresponding to a 3.18 percentage point improvement, which confirms its strong generalization capability to unseen geographic regions. Results across five random seeds yield consistently low standard deviations, confirming the stability of these gains. We further evaluate generalization on the TreeFinder dataset, which encompasses diverse tree species and complex canopy structures, where DROMAL-Net maintains robust performance, underscoring the effectiveness of MALAPSA and C3kDR for global feature enhancement and accurate localization in cross-regional applications.

Accurate and real-time evaluation of energy expenditure is crucial for optimizing exoskeleton control laws. Conventional regression-based prediction approaches are strongly affected by inter-individual variability in surface electromyography (sEMG) signals, limiting their generalization across subjects. To address this limitation, we reformulate the evaluation task as a comparative classification problem, instead of predicting absolute metabolic values, the proposed method directly judges which of two control strategies induces lower energy expenditure. We design a Control Laws Evaluation Network (CLEN) based on a Siamese architecture, which captures pairwise sEMG representations to compare assistance strategies. To further mitigate subject-specific variability, we introduce a Dual Adversarial Adaptive Optimization Strategy (DAAOS) that aligns feature distributions across domains using maximum classifier discrepancy and domain confusion. Experimental results on both public and local datasets demonstrate that the proposed domain-adaptive framework significantly outperforms regression-based approaches, achieving accuracies of $77.6\pm 3.1\%$ on the public dataset and $73.3\pm 4.7\%$ on the local dataset across unseen subjects. The findings indicate that the proposed framework provides an effective and generalizable metric for optimizing exoskeleton control, with potential applications in mobility assistance.