Search Results (854)

The emotional response of robotics is crucial for promoting the socially intelligent level of human–robot interaction (HRI). The development of machine learning has extensively stimulated research on emotional recognition for robots. Our research focuses on emotional gaits, a type of simple modality that stores a series of joint coordinates and is easy for humanoid robots to execute. However, a limited amount of research investigates emotional HRI systems based on gaits, indicating an existing gap in human emotion gait recognition and robotic emotional gait response. To address this challenge, we propose a Gait-to-Gait Emotional HRI system, emphasizing the development of an innovative emotion classification model. In our system, the humanoid robot NAO can recognize emotions from human gaits through our Trajectories-Aware and Skeleton-Graph-Aware Spatial–Temporal Transformer (TS-ST) and respond with pre-set emotional gaits that reflect the same emotion as the human presented. Our TS-ST outperforms the current state-of-the-art human-gait emotion recognition model applied to robots on the Emotion-Gait dataset. Full article

The identification of ongoing evolutionary trajectories, the prediction of future changes in the functioning of riverine habitats, and the assessment of flood-related risks to human populations all depend on regular hydro-morphological monitoring of fluvial settings. This paper focuses on the satellite monitoring of river macro-morphological units (assemblages of water, sediment, and vegetation units) and their temporal evolution. In particular, we develop a deep-learning semantic segmentation method using Synthetic Aperture Radar (SAR) Sentinel-1 dual-polarized data. The methodology is executed and tested on the Po River, located in Italy. The training of a relatively deep convolutional neural network requires a large amount of ground-truth data, which is often limited and challenging to acquire. To address this limitation, the dataset is augmented using a random forest (RF) classification algorithm. RF parameters are trained with both Sentinel-1 (S1) and Sentinel-2 (S2) data. The RF classification algorithm is very robust and achieves excellent performance. To overcome the limitation linked with the scarce availability of contemporary acquisition by S1 and S2 sensors, the deep learning (DL) model is trained by using only the Sentinel-1 input data and the ground truth from the RF result. The proposed approach achieves promising results in the classification of water, sediments, and vegetation along rivers such as the Italian Po River with low computational costs and no concurrency constraints between S1 and S2. Full article

Achieving accurate and efficient ship-type recognition is crucial for the development and management of modern maritime traffic systems. To overcome the limitations of existing methods that rely solely on AIS time series data or navigation trajectory images as single-modal approaches, this study introduces TrackAISNet, a multimodal ship classification model that seamlessly integrates ship trajectory images with AIS time series data for improved performance. The model employs a parallel structure, utilizing a lightweight neural network to extract features from trajectory images, and a specially designed TCN-GA (Temporal Convolutional Network with Global Attention) to capture the temporal dependencies and long-range relationships in the AIS time series data. The extracted image features and temporal features are then fused, and the combined features are fed into a classification network for final classification. We conducted experiments on a self-constructed dataset of variable-length AIS time series data comprising four types of ships. The results show that the proposed model achieved an accuracy of 81.38%, recall of 81.11%, precision of 80.95%, and an F1 score of 81.38%, outperforming the benchmark single-modal algorithms. Additionally, on a publicly available dataset containing three types of fishing vessel operations, the model demonstrated improvements in accuracy, recall, and F1 scores by 5.5%, 4.88%, and 5.88%, respectively. Full article

Pathological alterations in Alzheimer’s disease (AD) begin several years prior to symptom onset. Cortical mean diffusivity (cMD) may be used as a measure of early grey matter damage in AD as it reflects the breakdown of microstructural barriers preceding volumetric changes and affecting cognitive function. We investigated cMD changes early in the disease trajectory and evaluated the influence of amyloid-β (Aβ) and tau deposition. In this cross-sectional study, we analysed multimodal PET, DTI, and MRI data of 87 participants, and stratified them into Aβ-negative and -positive, cognitively normal, mildly cognitively impaired, and AD patients. cMD was significantly increased in Aβ-positive MCI and AD compared with CN in the frontal, parietal, temporal cortex, hippocampus, and medial temporal lobe. cMD was significantly correlated with cortical thickness only in patients without Aβ deposition but not in Aβ-positive patients. Our results suggest that cMD is an early marker of neuronal damage since it is observed simultaneously with Aβ deposition and is correlated with cortical thickness only in subjects without Aβ deposition. cMD changes may be driven by Aβ but not tau, suggesting that direct Aβ toxicity or associated inflammation causes damage to neurons. cMD may provide information about early microstructural changes before macrostructural changes. Full article

This paper proposes a deep reinforcement learning (DRL) method that combines random network distillation (RND) and long short-term memory (LSTM) to address the tracking control problem, while leveraging the inherent symmetry in robotic arm movements to eliminate the need for learning or knowing the system’s dynamic model. In general, the complexity and strong coupling of robotic manipulators make trajectory tracking extremely challenging. Firstly, the prediction network and fixed network are jointly trained using the RND method. The difference in output values between the two networks acts as an internal reward for the robotic manipulator environment. This internal reward mechanism encourages the robotic arm agent to actively explore unpredictable and unknown environmental states, thereby consequently boosting the performance and efficiency of the tracking control for the robotic manipulator. Then, the Soft Actor-Critic (SAC) algorithm, the LSTM network, and the attention mechanism are integrated to resolve the instability problem during training and acquire a stable policy. The LSTM model effectively captures the symmetry and temporal changes in joint angles, while the attention mechanism dynamically prioritizes important features, thereby reducing the instability of the robotic manipulator during tracking tasks and enhancing feature extraction efficiency. The simulation outcomes demonstrate that the proposed method effectively performs the robot tracking task, confirming the efficacy and efficiency of the DRL algorithm. Full article

Location data collected from mobile devices via global positioning system often lack semantic information and can form sparse trajectories in space and time. This study investigates whether user age groups can be accurately classified solely from such sparse spatial–temporal trajectories. We propose a feature extraction method based on a Gaussian mixture model (GMM), which assigns representative points (RPs) by clustering the location data and aggregating user trajectories into these RPs. We then construct three machine learning (ML) models—support vector classifier (SVC), random forest (RF), and deep neural network (DNN)—using the GMM-based features and compare their performance with that of the improved DNN (IDNN), which is an existing feature extraction approach. In our experiments, we introduced a missing value ratio ${\theta }_{\mathrm{th}}$ to quantify trajectory sparsity and analyzed the effect of trajectory sparsity on the classification accuracy and generalizability performance of the ML models. The results indicate that GMM-based features outperform IDNN-based features in both classification accuracy and generalization performance. Notably, the RF model achieved the highest accuracy, whereas the SVC model displayed stable generalizability. As the missing value ratio ${\theta }_{\mathrm{th}}$ increases, the IDNN becomes more susceptible to overfitting, whereas the GMM-based approach preserves accuracy and robustness. These findings suggest that sparse trajectories can still offer meaningful classification performance with appropriate feature design and model selection even without semantic information. This approach holds promise for domains where large-scale, sparse trajectory data are common, including urban planning, marketing analysis, and public policy. Full article

The accurate prediction of marine shaft centerline trajectories is essential for ensuring the operational performance and safety of ships. In this study, we propose a novel Transformer-based model to forecast the lateral and longitudinal displacements of ship main shafts. A key challenge in this prediction task is capturing both short-term fluctuations and long-term dependencies in shaft displacement data, which traditional models struggle to address. Our Transformer-based model integrates Bidirectional Splitting–Agg Attention and Sequence Progressive Split–Aggregation mechanisms to efficiently process bidirectional temporal dependencies, decompose seasonal and trend components, and handle the inherent symmetry of the shafting system. The symmetrical nature of the shafting system, with left and right shafts experiencing similar dynamic conditions, aligns with the bidirectional attention mechanism, enabling the model to better capture the symmetric relationships in displacement data. Experimental results demonstrate that the proposed model significantly outperforms traditional methods, such as Autoformer and Informer, in terms of prediction accuracy. Specifically, for 96 steps ahead, the mean absolute error (MAE) of our model is 0.232, compared to 0.235 for Autoformer and 0.264 for Informer, while the mean squared error (MSE) of our model is 0.209, compared to 0.242 for Autoformer and 0.286 for Informer. These results underscore the effectiveness of Transformer-based models in accurately predicting long-term marine shaft centerline trajectories, leveraging both temporal dependencies and structural symmetry, thus contributing to maritime monitoring and performance optimization. Full article

Accurate dynamic model and response prediction of industrial robots (IRs) are prerequisites for production optimization before actual operation. In this study, a hybrid-driven dynamic position prediction (HDPP) approach integrating a parametric dynamic model (PDM) and learning-based residual error compensators (RECs) is developed to estimate the actual position of a robot end-effector based on the reference input trajectory. Firstly, a PDM consisting of a flexible dynamic model of the mechanical system and a servo system model is constructed as the primary predictor in HDPP. Meanwhile, a reinforcement learning (RL)-based parameter identification method is presented to obtain independent dynamic parameters, which integrates a CAD model, least squares estimation, and RL. Then, an REC based on the temporal convolutional network long short-term memory (TCN-LSTM) is proposed for each joint to compensate for the residual error after PDM prediction. A TCN is employed as the input of LSTM to extract and compress the discontinuous features, which can enhance the compensator’s accuracy and stability. Additionally, a dynamics-integrated (DI) dataset construction scheme is developed for network training to boost the prediction accuracy. Finally, a series of experiments and comparative analysis are preformed to validate the performance of HDPP in terms of prediction accuracy and stability. Full article

With advancements in autonomous driving technology, the coupling of spatial paths and temporal speeds in complex scenarios becomes increasingly significant. Traditional sequential decoupling methods for trajectory planning are no longer sufficient, emphasizing the need for spatio-temporal joint trajectory planning. The Constrained Iterative LQR (CILQR), based on the Iterative LQR (ILQR) method, shows obvious potential but faces challenges in computational efficiency and scenario adaptability. This paper introduces three key improvements: a segmented barrier function truncation strategy with dynamic relaxation factors to enhance stability, an adaptive weight parameter adjustment method for acceleration and curvature planning, and the integration of the hybrid A* algorithm to optimize the initial reference trajectory and improve iterative efficiency. The improved CILQR method is validated through simulations and real-vehicle tests, demonstrating substantial improvements in human-like driving performance, traffic efficiency improvement, and real-time performance while maintaining comfortable driving. The experiment’s results demonstrate a significant increase in human-like driving indicators by 16.35% and a 12.65% average increase in traffic efficiency, reducing computation time by 39.29%. Full article

This study investigates cyclone dynamics and impacts in the Southwestern Atlantic, with a focus on their effects on southern Brazil. As climate change intensifies coastal vulnerability, understanding cyclone behavior has become essential. Using the TRACK and cycloTRACK algorithms, we examined cyclone trajectories and cyclogenesis densities from 1979 to 2019 to analyze seasonal and spatial patterns shaped by large-scale atmospheric circulations, including the Antarctic Oscillation (AAO). The analysis explores trends in cyclone activity across various temporal and spatial scales, identifying key regions of cyclogenesis and trajectory density. Results indicate that the cycloTRACK algorithm is more effective at tracking more intense and consistent cyclones, excluding weaker systems. Seasonal patterns suggest variability in cyclone formation, likely associated with atmospheric instability and ocean–atmosphere interactions. While trends reveal an increase in cyclone passages in southern Brazil, these systems are strongly associated with extreme climatic events in the region, including coastal storms, intense precipitation, strong winds, and high waves. By clarifying cyclone dynamics and seasonal patterns, this study enhances our understanding of cyclone behavior and contributes to improved assessments of regional climate resilience in southern Brazil. Full article

Neuromodulation stands as a cutting-edge approach in the fields of neuroscience and therapeutic intervention typically involving the regulation of neural activity through physical and chemical stimuli. The purpose of this review is to provide an overview and evaluation of different neuromodulation techniques, anticipating a clearer understanding of the future developmental trajectories and the challenges faced within the domain of neuromodulation that can be achieved. This review categorizes neuromodulation techniques into genetic neuromodulation methods (including optogenetics, chemogenetics, sonogenetics, and magnetogenetics) and non-genetic neuromodulation methods (including deep brain stimulation, transcranial magnetic stimulation, transcranial direct current stimulation, transcranial ultrasound stimulation, photobiomodulation therapy, infrared neuromodulation, electromagnetic stimulation, sensory stimulation therapy, and multi-physical-factor stimulation techniques). By systematically evaluating the principles, mechanisms, advantages, limitations, and efficacy in modulating neuronal activity and the potential applications in interventions of neurological disorders of these neuromodulation techniques, a comprehensive picture is gradually emerging regarding the advantages and challenges of neuromodulation techniques, their developmental trajectory, and their potential clinical applications. This review highlights significant advancements in applying these techniques to treat neurological and psychiatric disorders. Genetic methods, such as sonogenetics and magnetogenetics, have demonstrated high specificity and temporal precision in targeting neuronal populations, while non-genetic methods, such as transcranial magnetic stimulation and photobiomodulation therapy, offer noninvasive and versatile clinical intervention options. The transformative potential of these neuromodulation techniques in neuroscience research and clinical practice is underscored, emphasizing the need for integration and innovation in technologies, the optimization of delivery methods, the improvement of mediums, and the evaluation of toxicity to fully harness their therapeutic potential. Full article

In light of the growing interest in the bidirectional relationship between epilepsy and dementia, this review aims to provide an overview of the role of hyperphosphorylated tau (pTau) in cognition in human epilepsy. A literature search identified five relevant studies. All of them examined pTau burden in surgical biopsy specimens from patients with temporal lobe epilepsy. The prevalence of pTau reported across the five studies, encompassing a total of 142 patients, ranged from 3.5% to 95%. Findings also varied regarding the location of pTau in the hippocampus and/or temporal cortex. Two of five studies (40%) demonstrated an inverse relationship between pTau burden and cognitive performance, one study with regard to executive functions and the other with regard to naming and verbal short-term memory. The only longitudinal study found a significant link between pTau and cognitive decline in verbal learning and memory, and in part also in naming, from the pre- to the postoperative assessment and from three to 12 months postoperatively. Given the heterogeneity of the study cohorts and the neuropsychological and neuropathological methodologies and findings, no clear picture emerges regarding the association between pTau and cognition in temporal lobe epilepsy. Added to this is the multifactorial etiology of cognitive impairment in epilepsy, including the active epilepsy, the underlying and sometimes dynamic pathology, and anti-seizure medication. Some of these factors may affect pTau expression. Further research should aim to investigate pTau longitudinally and noninvasively on a whole-brain level, using targeted neuropsychological outcome measures and controlling for age and other factors potentially influencing cognitive trajectories in epilepsy. Full article

Rehabilitation of gait function in post-stroke hemiplegic patients is critical for improving mobility and quality of life, requiring a comprehensive understanding of individual gait patterns. Previous studies on gait analysis using unsupervised clustering often involve manual feature extraction, which introduces limitations such as low accuracy, low consistency, and potential bias due to human intervention. This cross-sectional study aimed to identify and cluster gait patterns using an end-to-end deep learning approach that autonomously extracts features from joint angle trajectories for a gait cycle, minimizing human intervention. A total of 74 sub-acute post-stroke hemiplegic patients with lower limb impairments were included in the analysis. The dataset comprised 219 sagittal plane joint angle and angular velocity trajectories from the hip, knee, and ankle joints during gait cycles. Deep temporal clustering was employed to cluster them in an end-to-end manner by simultaneously optimizing feature extraction and clustering, with hyperparameter tuning tailored for kinematic gait cycle data. Through this method, six optimal clusters were selected with a silhouette score of 0.2831, which is a relatively higher value compared to other clustering algorithms. To clarify the characteristics of the selected groups, in-depth statistics of spatiotemporal, kinematic, and clinical features are presented in the results. The results demonstrate the effectiveness of end-to-end deep learning-based clustering, yielding significant performance improvements without the need for manual feature extraction. While this study primarily utilizes sagittal plane data, future analysis incorporating coronal and transverse planes as well as muscle activity and gait symmetry could provide a more comprehensive understanding of gait patterns. Full article

Due to advances in sensor techniques and deep learning, autonomous vehicular technologies have become more reliable and practical. Trajectory prediction is a critical task to anticipate the future positions of surrounding vehicles. However, existing algorithms, such as LSTM-based and attention-based models, face challenges of high computational complexity, large parameter sizes, and limited ability to efficiently capture both temporal dependencies and spatial interactions in dynamic traffic scenarios. In this paper, we propose a parameter-efficient trajectory prediction model that integrates Liquid Time-Constant (LTC) networks with attention mechanisms, termed the Attn-LTC model. The key contributions of our work are threefold. First, we introduce a temporal attention-enhanced LTC encoder that effectively captures both long-term temporal dependencies and dynamic behaviors from historical trajectory data. Second, we incorporate a spatial attention-enhanced LTC decoder, which emphasizes the influence of neighboring vehicles and spatial interactions, thereby improving prediction accuracy. Third, we demonstrate the computational efficiency of the Attn-LTC model, which achieves high predictive accuracy with significantly fewer parameters compared to LSTM-based and Transformer-based counterparts. Extensive experiments conducted on the NGSIM dataset demonstrate the advantages of our proposed Attn-LTC model. Notably, it reduces computational complexity and model size while maintaining superior accuracy, making it well suited for deployment in resource-constrained systems. The results highlight the effectiveness of the Attn-LTC model in balancing precision and efficiency, paving the way for its application in real-time autonomous driving systems. Full article

Trajectory prediction is a critical component of autonomous driving, intelligent transportation systems, and human–robot interactions, particularly in complex environments like intersections, where diverse road constraints and multi-agent interactions significantly increase the risk of collisions. To address these challenges, a Heterogeneous Risk-Aware Graph Encoder with Continuous Parameterized Decoder for Trajectory Prediction (HRGC) is proposed. The architecture integrates a heterogeneous risk-aware local graph attention encoder, a low-rank temporal transformer, a fusion lane and global interaction encoder layer, and a continuous parameterized decoder. First, a heterogeneous risk-aware edge-enhanced local attention encoder is proposed, which enhances edge features using risk metrics, constructs graph structures through graph optimization and spectral clustering, maps these enhanced edge features to corresponding graph structure indices, and enriches node features with local agent-to-agent attention. Risk-aware edge attention is aggregated to update node features, capturing spatial and collision-aware representations, embedding crucial risk information into agents’ features. Next, the low-rank temporal transformer is employed to reduce computational complexity while preserving accuracy. By modeling agent-to-lane relationships, it captures critical map context, enhancing the understanding of agent behavior. Global interaction further refines node-to-node interactions via attention mechanisms, integrating risk and spatial information for improved trajectory encoding. Finally, a trajectory decoder utilizes the aforementioned encoder to generate control points for continuous parameterized curves. These control points are multiplied by dynamically adjusted basis functions, which are determined by an adaptive knot vector that adjusts based on velocity and curvature. This mechanism ensures precise local control and the superior handling of sharp turns and speed variations, resulting in more accurate real-time predictions in complex scenarios. The HRGC network achieves superior performance on the Argoverse 1 benchmark, outperforming state-of-the-art methods in complex urban intersections. Full article