Search Results (43,899)

Radar-based gesture recognition technology has gained increasing attention in the context of contactless human–computer interaction (HCI). Micro gestures have smaller motion amplitudes and shorter duration compared with traditional gestures, which increases the difficulty of motion feature extraction. In addition, improving recognition accuracy while maintaining low computational and storage costs is also a challenge. In this paper, a micro gesture recognition method combining multi-dimensional feature fusion and a lightweight CQ-MobileNetV3 network is proposed. For feature extraction, the range–time map, velocity–time map, and angle–time map of gestures are first constructed. Then, normalization and adaptive filtering are performed to refine the three maps. Finally, the three refined maps are fused to form a range–velocity–angle–time map, which can accurately describe the motion characteristics of gestures. For recognition, a lightweight CQ-MobileNetV3 network is designed. First, the network structure of MobileNetV3 is optimized to reduce computational complexity. Then, the improved convolutional block attention module (CBAM) and the improved self-attention (SA) module are constructed and integrated into different bottleneck blocks to improve recognition accuracy. A series of experiments are conducted with a 77 GHz frequency-modulated continuous wave (FMCW) radar. The results indicate that CQ-MobileNetV3 achieves a recognition accuracy of 97.16% for 14 micro gestures, with a parameter count of 0.207 M and a computational complexity of 0.027 GFLOPs, surpassing several other deep neural networks. Full article

The performance of the Fractional-order Extended Kalman Filter (FEKF) is often constrained by the manual tuning of its fractional-order parameter. This paper proposes HO-FEKF, a novel framework that integrates the Hippopotamus Optimization (HO) algorithm to automate and intelligently determine this optimal parameter. Central to our approach is a hierarchical optimization strategy that efficiently minimizes attitude estimation error. In addition to this automated tuning, we enhance the core FEKF model by improving its handling of nonlinear system dynamics, including the effects of time discretization on the Jacobian, cross-factor interactions, and the use of a sliding residual window. We validated our method on both a public benchmark and a custom-collected dataset. Results show that our improved FEKF surpasses the traditional version, and the complete HO-FEKF framework significantly outperforms approaches based on other optimization algorithms (genetic algorithm GA, grey wolf optimizer GWO, Harris hawks optimizer HHO, and HiPPO-LegS algorithm) combined with FEKF. These findings confirm the practical potential of HO-FEKF for achieving adaptive, high-accuracy attitude estimation in real-world sensor fusion scenarios. Full article

This paper presents a simplified matching network using coupled transmission lines (CTLs) for broadband power amplifiers. The proposed structure consists of a CTL with an electrical length shorter than $\lambda$/4 and a single shunt component, exhibiting excellent frequency characteristics across a wide bandwidth at both the input and load networks of the transistor. The reactance variation of the non-Foster elements in the equivalent circuit of the CTL with respect to frequency was analyzed, and the external reactive components were accordingly optimized to extend the bandwidth of the matching network. The proposed network was applied to the input and load networks of a GaN HEMT-based power amplifier. It was designed to maintain required performances over a wide frequency range of 1.9–4.9 GHz, covering both LTE and sub-6 GHz 5G bands, thereby achieving a fractional bandwidth (FBW) of 88.2%. The CTLs were fabricated on a two-layer printed-circuit board (PCB), and the additional shunt components were designed using surface-mount devices (SMDs). The overall power-amplifier module occupied a small area of 40 × 35 mm². Using the continuous-wave (CW) signal, the proposed power amplifier exhibited a power gain of 10–14.8 dB and a drain efficiency (DE) of 47.5–60% at a saturated output power of 7.1–9.3 W across the entire operating frequency band. Using a 5G New Radio (NR) signal with a 100 MHz bandwidth and a peak-to-average power ratio (PAPR) of 7.8 dB, the amplifier achieved an average output power of 30 dBm, a DE of 20–27.5%, and an adjacent-channel leakage power ratio (ACLR) better than −30 dBc. Full article

In recent years, a new type of natural gas hydrate reservoir (designated as Class 1S reservoir) has been discovered in the Qiongdongnan Basin. Within this hydrate reservoir, free gas and hydrate coexist within the same stratum. The Class 1S reservoir is comprised of three distinct zones: the gas accumulation zone, the three-phase zone, and the hydrate-bearing zone. It exhibits significant commercial development potential. This paper analyzes the formation mechanism and geological context of Class 1S hydrates. A geological model was established and numerical simulation methods were employed to evaluate its production capacity, elucidating the evolutionary patterns of hydrate saturation distribution at different well locations. The simulation results indicate that production wells should be prioritised in gas accumulation zones in order to achieve the highest cumulative gas production. Additional production wells may be considered in later stages to enhance recovery rates. Secondary hydrate formation significantly impacts production in Hydrate-bearing zone and three-phase zone. Measures such as wellbore heating can be employed to minimize secondary hydrate formation around the wellbore. Full article

The three-leg 50-Years Roundabout at King Abdulaziz University (KAU) is known for its vibrance and important location as it is located at the center of several major buildings and hospitals. In recent years, the roundabout is witnessing a huge demand that influences the university road networks’ level of service, “LOS”, which in return, has negative impacts on students and faculties in terms of delay and travel time. Several treatments can be implemented along the roundabout. One of those treatments is applying restrictions during morning peak hours such as blocking and restricting specific lanes. This treatment has the advantage of reducing conflict points that cause sudden and frequent stops at the roundabout; as a result, delay and congestion occur. By reducing conflict points, traffic flow can be improved, in addition to enhancing safety and promoting sustainability. This paper examines the base condition of the 50-Years Roundabout in terms of traffic flow, LOS, delay, capacity, and toxic emissions, and proposes traffic system management (TSM) strategies through applying restricted and designated lanes to improve traffic condition. The study employs PTV Vissim, SIDRA Intersection, and Surrogate Safety Assessment Model “SSAM” to examine the base and proposed conditions. The results show a significant improvement through the reduction in conflict points, so that reflects the positive impacts on sustainability, congestion, delay, travel time, LOS, and overall toxic emissions. Full article

Cooperative path planning is recognized as a critical technology for Autonomous Underwater Vehicle (AUV) clusters to execute complex marine operations. Through multi-AUV cooperative decision-making, perception limitations of individual robots can be mitigated, thereby significantly enhancing the efficiency of tasks such as deep-sea resource exploration and submarine infrastructure maintenance. However, the underwater environment is characterized by severe disturbances and limited communication, making cooperative path planning for AUV clusters particularly challenging. Currently, this field is still in its early research stage, and there exists an urgent need for the integration of scattered technical achievements to provide theoretical references and directional guidance for relevant researchers. Based on representative studies published in recent years, this paper provides a review of the research progress in three major technical domains: heuristic optimization, reinforcement and deep learning, and graph neural networks integrated with distributed control. The advantages and limitations of different technical approaches are elucidated. In addition to cooperative path planning algorithms, the evolutionary logic and applicable scenarios of each technical school are analyzed. Furthermore, the lack of realism in algorithm training environments has been recognized as a major bottleneck in cooperative path planning for AUV clusters, which significantly limits the transferability of algorithms from simulation-based validation to real-sea applications. This paper aims to comprehensively outline the current research status and development context of the field of AUV cluster cooperative path planning and propose potential future research directions. Full article

This paper applies a hybrid multi-criteria decision-making (MCDM) model that integrates the Analytic Hierarchy Process (AHP) for structured weighting of evaluation criteria with the Net Worth Analysis (NWA) method for value-based aggregation of scores. The proposed framework was employed to evaluate Learning Management Systems (LMS) in higher education, involving two independent expert panels representing management and IT perspectives. Results of the AHP analysis show that cost (28%), security (22%), and usability (17%) are the most influential criteria in the decision-making process, reflecting institutional priorities for financial efficiency, safety and ease of use. Based on the combined AHP-NWA model, Moodle 4.3 emerged as the most sustainable choice (0.586), followed by Atutor 2.2.1 (0.541) and Blackboard (SaaS edition) (0.490). The inclusion of sensitivity and scenario analyses confirmed the robustness of the model, demonstrating that the ranking of alternatives remains stable under variations in weighting factors and different strategic priorities. By framing LMS evaluation within the context of sustainable digital transformation, the study emphasizes how transparent and systematic decision-making supports long-term institutional resilience and aligns with the principles of Education for Sustainable Development (ESD). In addition, the framework contributes to the achievement of Sustainable Development Goal 4 (Quality Education), by guiding higher education institutions toward inclusive, resilient and cost-effective digital solutions. Full article

Minimally Invasive Surgery is often limited by the lack of tactile feedback. Indeed, surgeons have traditionally relied heavily on tactile feedback to estimate tissue stiffness - a critical factor in both diagnostics and treatment. With this in mind we present in this paper a flexible sensor foil, based on polymer optical waveguide. This sensor has been applied for real-time contact force measurement, material stiffness differentiation and surface texture reconstruction. Interrogated by a commercially available optoelectronic device, the sensor foil offers precise and reproducible feedback of contact forces up to 5 N, with a minimal detectable limit of 0.1 N. It also demonstrates distinct optical attenuation responses when indenting silicone samples of varying stiffnesses under controlled displacement. When integrated onto a 3D-printed module resembling an endoscopic camera and manipulated by a robotic arm, the sensor successfully generated spatial stiffness mapsof a phantom. Moreover, by sliding over structures with varying surface textures, the sensor foil was able to reconstruct surface profiles based on the light attenuation responses. The results demonstrate that the presented sensor foil possesses great potential for surgical applications by providing additional haptic information to surgeons. Full article

For classification problems, an imbalanced dataset can seriously reduce the learning efficiency in machine learning. In order to solve this problem, many scholars have proposed a series of methods mainly from the data and algorithm levels. At the data level, SMOTE is one of the most effective methods; it creates new minority samples through linearly interpolating between existing minority samples. This paper proposes an improved SMOTE-based data-level oversampling method that leverages a symmetrical cube scoring mechanism. This algorithm first exploits the symmetry properties of cubes to construct a new scoring rule based on different symmetric neighboring cubes, thereby dynamically selecting sample points. It then maps back to the original dimensional space, and generates new samples through multiple linear interpolations. This is equivalent to reducing the data to three dimensions, selecting points in that three-dimensional space, and synthesizing new samples by mapping those points back to the corresponding high-dimensional space. Compared to existing SMOTE variants, the proposed method delivers more targeted performance in regions of varying densities and boundary areas. In the experimental section, the proposed method selects several datasets to synthesize samples under different oversampling methods, and then compare the performances of these methods by calculating some evaluation indicators. In addition, to avoid accidental results caused by relying on a single classifier, the performance of each oversampling method is tested in the experimental section using three commonly used classifiers (SVM, ELM, and MLP). The experimental results show that, compared with other oversampling methods, CS-SMOTE achieves the first place in average ranking. Based on 33 datasets, 3 classifiers, and 3 performance metrics, a total of 297 rankings were obtained, and CS-SMOTE ranked first in 179 of them, accounting for 60.27%, which clearly demonstrates its strong capability in addressing class-imbalanced problems. Full article

Welding is one of the most common machining methods in the industrial field, and weld grinding is a key task in the industrial manufacturing process. Although several weld-image datasets exist, most provide only coarse annotations and have limited scale and diversity. To address this gap, we constructed INWELD, a comprehensive multi-category weld dataset captured under real-world production conditions, providing both single-label and multi-label annotations. The dataset covers various types of welds and is evenly divided according to production needs. The proposed multi-category annotation method can predict the weld geometry and welding method without additional calculation and is applied to object detection and instance segmentation tasks. To evaluate the applicability of this dataset, we utilized the mainstream algorithms CenterNet and YOLOv7 for object detection, as well as Mask R-CNN, Deep Snake, and YOLACT for instance segmentation. The experimental results show that in single-category annotation, the AP50 of CenterNet and YOLOv7 is close to 90%, and the AP50 of Mask R-CNN and Deep Snake is greater than 80%. In multi-category annotation, the AP50 of CenterNet and YOLOv7 is greater than 80%, and the AP50 of Deep Snake and YOLACT is nearly 70%. The INWELD dataset constructed in this paper fills the gap in industrial weld surface images, lays the theoretical foundation for the intelligent research of welds, and provides data support and research direction for the development of automatic grinding and polishing of welds. Full article

In this paper we present a brief review of extended general relativity in four dimensions and solve versions of the extended equations for the case of static spherical symmetry in various contexts, for a previously studied Lagrangian. The exterior vacuum yields a Schwarzschild solution with an additional scalar field potential that falls off logarithmically, the latter essentially an inverse square force. That is probably not adequate as a dark matter force, but might contribute. When a constant density field of ions holds sway in the exterior, a solution identical to the cosmological constant extension of Schwarzschild occurs, together with a scalar field potential declining as $r^{-3/2}$, however it is not asymptotically flat. An inverse square declining distribution of ionic material, according to perturbation theory, results in an additional linear gravity potential that would provide further attraction in the gravity term. A limited exact solution in the same case yields a cubic equation with a Schwarzschild solution, corresponding to $A=0$, and two MOND-like possible potentials, one vanishing at infinity, but a better solution must be found. The approximate solution is complex (one of many) and the system requires further study. Ionic matter is ubiquitous in the universe and provides a source for the scalar field, which suggests that the extended Einstein equations could be of utility in the dark matter problem, provided such an electromagnetic scalar force could be found and differentiated from the usual, far stronger electromagnetic forces. Further, it’s possible that the strong photon flux outside stars might have an influence, and is under current investigation. These calculations show that extending the concept of curvature and working in four dimensions with larger operators may bring new tools to the study of physics and unified field theories. Full article

Inspired by the concept of antennas in electromagnetics, this study proposes a novel acoustic metamaterial using Archimedean spiral structures. Unlike traditional resonant absorption structures, the present structure does not rely on resonant cavities but consists of multiple channels bent according to specific geometric parameters. The absorption mechanism is attributed to the combination of Fabry–Pérot (FP) resonance and viscous loss effects at waveguide boundaries. A theoretical model based on the transfer matrix method has been established and validated through numerical methods. Furthermore, the present study investigated the relationship between absorption performance and geometric parameters through theoretical analysis and numerical simulations, achieving efficient absorption across a wide frequency range and at low frequencies by adjusting these parameters. Additionally, samples have been fabricated using additive manufacturing techniques and experimental validation confirmed the accuracy of the theoretical and numerical simulations. The structure designed in this paper is expected to be applied to the engineering field with the need of broadband sound absorption. Full article

Ensembling techniques are viewed as a promising machine learning tool to resolve issues arising from the monolithic nature of deep neural networks. In this paper, we consider pairwise coupling models built from neural networks, which is a special kind of ensemble. These models promise to provide much needed modularity in classification models employing deep networks. In order to be practical, pairwise coupling models have to have comparable memory and speed requirements to commonly used architectures. In this paper, we propose novel architectures that address this key problem of pairwise coupling models. We show that the classification accuracy of the resulting pairwise coupling models matches the original network, while exceeding the original network’s pairwise accuracy. The introduction of these pairwise models brings additional benefits. First, they allow for much less expensive uncertainty predictions. Secondly, their modularity allows for the fine-tuning of classification accuracy. Both of these benefits can be viewed as relating to the larger topic of improving the explainability as well as the modularity of deep neural networks. Full article

In this study, we used the hydrophobic-polar (HP) two-dimensional square and three-dimensional cubic lattice models for the problem of protein structure prediction (PSP). This kind of lattice reduces computational time and calculations, the conformational space from $9^n$ to $3^{n-2}$ for the 2D square lattice and $5^{n-2}$ for the 3D cubic lattice. Even within this context, it remains challenging for genetic algorithms or other metaheuristics to identify the optimal solutions. The contributions of the paper consist of: (1) implementation of a high-performing novel genetic algorithm (GA); instead of considering only the self-avoiding walk (SAW) conformations approached in other work, we decided to allow any conformation to appear in the population at all stages of the proposed all conformations biomimetic genetic algorithm (ACGA). This increases the probability of achieving good conformations (self avoiding walk ones), with the lowest energy. In addition to classical crossover and mutation operators, (2) we introduced specific translation operators for these two operations. We have proposed and implemented an HP Protein Visualizer tool which offers interpretability, a hybrid approach in that the visualizer gives some insight to the algorithm, that analyse and optimise protein structures HP model. The program resulted based on performed research, provides a molecular modeling tool for studying protein folding using technologies such as Node.js, Express and p5js for 3D rendering, and includes optimization algorithms to simulate protein folding. Full article

Low-cost missions are ideal for applications that require spacecraft formation flying. The use of GNSS signals provides an economical solution to determine the orbital status of the formation. This paper facilitates the development of such missions by simulating spacecraft orbital formation conditions through the use of software-defined radio to generate the GNSS signals being received by each spacecraft. The simulation environment integrates low-cost commercial GNSSs, one for each member of the formation, to capture the signals generated. The analysis of the recorded raw signals shows that the instrumental error of the receivers is predominant because they have not been designed to work in orbital conditions. In addition to noise, the bias errors introduced must be taken into account by the mathematical trilateration methods, which can be very sensitive to these errors. This paper shows how sensitivity can be quantified using the condition number for matrix inversion. A condition number analysis determines that the optimal solution for trilaterating the orbital position of a spacecraft should use as few GNSS satellites as possible. The paper also introduces how to use the condition number to evaluate different methods for determining the state of the spacecraft formation: the independent trilateration method, the difference method, and the double difference method. The comparison of the methods shows that the difference and double difference methods are more sensitive to instrumental errors, because they are worse conditioned, but can be improved by reducing their order. Despite the limitations shown, at best, errors in the relative positions of the spacecrafts of the order of metres are obtained, demonstrating the feasibility of this type of mission and the usefulness of the condition number analysis method presented. Full article