Gait and balance disorders pose significant risks of injury and negatively impact quality of life. Precise coordination and control of body movement are crucial for bodily-kinesthetic intelligence (BKI). In this work, we propose a fall risk feature mining method (FRFMM) that utilizes foot pressure sensor data and is based on a non-parametric walking model (NPWM). Our approach generates time-spatial features, including raw features, balance features, ratio features, and gait energy expenditure features. We employ three sorted metrics—correlation coefficient in features (CCF), Bayes Factor (BF), and self-information index (SII)—to refine body schema awareness and body image knowledge. This refinement aims to enhance goal-oriented BKI and reduce fall risk. We introduce three threshold rules based on the sorted metrics, enabling the selection of three discriminative fall risk features (the support base of center and two novel ratio features) from 64 generated features derived from plantar pressure sensors. Our framework integrates BKI and FRFMM across four levels: physical observation, feature extraction, decision-making, and multimodal data analysis. Experimental results using a fall risk dataset demonstrate that the FRFMM improves fall risk prediction accuracy by 10% compared to FRFMM with any single metric. Additionally, it outperforms well-known feature selection methods, achieving an accuracy improvement of 7% to 34%. Comparisons with clinical methods further highlight the effectiveness of our approach for analyzing and assessing fall risk.

In this paper propose a method of normalization in thickness of the contour lines based on the analysis by mask of the local orientations of fragments. Comparison of the proposed method with known methods of thinning is held. It is shown that the proposed method is superior to the known methods of thinning on speed and quality.

Gait impairment is a common motor manifestation of Parkinson’s disease (PD), which is also frequently accompanied by other motor abnormalities such as bradykinesia, rigidity, postural instability, and movement asymmetry. These motor impairments are closely associated with reduced mobility and increased fall risk. Although wearable plantar insole sensing provides a promising basis for objective gait assessment, existing studies have mainly focused on conventional time- or frequency-domain descriptors, whereas the nonlinear complexity of gait, laterality-related imbalance, and deviation from normal gait patterns remain insufficiently characterized in an integrated manner. To address this gap, this paper proposes FID-Gait, which is a three-domain fusion framework for PD identification using instrumented insole data. The framework combines automated gait-cycle segmentation with multidomain feature modeling, including a fractal domain for nonlinear gait complexity, a plantar-loading–phase imbalance (PLPI) domain for loading asymmetry and temporal disturbance, and a covariance-adjusted deviation (CAD) domain for measuring deviation from normal gait patterns. Experiments on the PhysioNet Gait in Parkinson’s Disease dataset showed that FID-Gait achieved strong discriminative performance under multiple evaluation protocols. At the gait-cycle level, the selected MLP classifier achieved an accuracy of 99.11% and an F1-score of 99.47%. At the subject level, the selected AdaBoost classifier achieved the highest accuracy of 90.22% and the best F1-score reached 93.02%. Five-fold cross-validation further supported the robustness of the proposed representation, and leave-one-subject-out evaluation provided preliminary evidence of subject-independent generalization. Overall, FID-Gait provides an effective and interpretable framework for PD gait characterization and identification in offline experimental settings.

Several recent scientific papers have been proposed on power consumption in Wireless Sensor Networks (WSN). Still, the work focused on control topologies of WSN in the field of increasing and prolonging the whole network is limited. This results from their function as routers that send data from edge nodes to the sink. The nodes around the sink node quickly die while delivering much data through intermediate nodes from one node to the sink node. The network lifetime was reduced because the sensor nodes adjacent to the sink consume twice as much power as the others. This problem is not recognized and addressed in more visual detail by the authors. The nodes closest to the sink node will die first. Therefore, this paper proposed a mathematical model to represent packet energy consumption with control topology for WSN. Due to the simulation, more than 90% of sensors are still operational and optimally arranged. The overall battery power remaining in the sensors was greater than 70%.

Ship detection in Synthetic Aperture Radar (SAR) images remains challenging due to coherent speckle noise, complex inshore clutter, and large variations in target scale, especially for tiny ships. To address these issues, this paper proposes a lightweight SAR ship detection network based on YOLOv11n. The proposed model introduces a high-resolution P2 detection branch to preserve fine spatial details that may be weakened during repeated downsampling. To improve multi-scale feature representation, a Four-Head Adaptive Spatial Feature Fusion (FASFF) structure is adopted to adaptively combine features from P2, P3, P4, and P5. In addition, the Squeeze-and-Excitation (SE) attention module is inserted into the high-resolution branches of the Neck to recalibrate channel responses and suppress clutter-dominant features during feature aggregation. Experiments on a fixed subset of the SAR-Ship-Dataset show that the proposed YOLOv11n-SE-FASFF model improves Recall and mAP50-95 compared with the YOLOv11n baseline. Specifically, Recall increases from 0.898 to 0.926, and mAP50-95 increases from 0.614 to 0.632. The model contains 3.01 M parameters and achieves an inference speed of 196 FPS with 640 × 640 input images on an NVIDIA GeForce RTX 5060Ti GPU. Additional cross-dataset evaluation on SSDD and HRSID without fine-tuning further suggests that the proposed model has a certain degree of transferability under different SAR data conditions.