Search Results (1,201)

This study proposes a hybrid approach combining threshold-based algorithm and deep learning to detect four major gait events—initial contact (IC), toe-off (TO), opposite initial contact (OIC), and opposite toe-off (OTO)—using only a smartphone’s built-in inertial sensor placed in the user’s pocket. The algorithm enables estimation of spatiotemporal gait parameters such as cadence, stride length, loading response (LR), pre-swing (PSw), single limb support (SLS), double limb support (DLS), and swing phase and symmetry. Gait data were collected from 20 healthy individuals and 13 hemiparetic stroke patients. To reduce sensitivity to sensor orientation and suppress noise, sum vector magnitude (SVM) features were extracted and filtered using a second-order Butterworth low-pass filter at 3 Hz. A deep learning model was further compressed using knowledge distillation, reducing model size by 96% while preserving accuracy. The proposed method achieved error rates in event detection below 2% of the gait cycle for healthy gait and a maximum of 4.4% for patient gait in event detection, with corresponding parameter estimation errors also within 4%. These results demonstrated the feasibility of accurate and real-time gait monitoring using a smartphone. In addition, statistical analysis of gait parameters such as symmetry and DLS revealed significant differences between the normal and patient groups. While this study is not intended to provide or guide rehabilitation treatment, it offers a practical means to regularly monitor patients’ gait status and observe gait recovery trends over time. Full article

The objective of this study was to improve measurement accuracy in the evaluation of autonomous agricultural tractor performance by addressing external disturbances, such as sensor installation errors, vibrations, and heading-induced bias that occur during the measurement of the conventional rear three-point hitch (Rear 3-Point) system. To mitigate these disturbances, the measurement point was relocated to the cab, where external interference is comparatively minimal. However, in compliance with the ISO 12188 standard, the Rear 3-Point system must be used as the reference measurement point. Therefore, its coordinates were indirectly estimated using an extended Kalman filter (EKF) and artificial intelligence (AI)-based techniques. A hybrid model was developed in which a transformer-based AI model was trained using the Rear 3-Point coordinates predicted by EKF as the ground truth. While traditional time-series models, such as LSTM and GRU, show limitations in predicting nonlinear data, the application of an attention mechanism was found to enhance prediction performance by effectively learning temporal dependencies and vibration patterns. The experimental results show that the EKF-based estimation achieved a precision of RMSE 1.6 mm, a maximum error of 12.6 mm, and a maximum standard deviation of 3.9 mm compared to actual measurements. From the perspective of experimental design, the proposed hybrid model was able to predict the trajectory of the autonomous agricultural tractor with significantly reduced external disturbances when compared to the actual measured Rear 3-Point coordinates, while also complying with the ISO 12188 standard. These findings suggest that the proposed approach provides an effective and integrated solution for developing high-precision autonomous agricultural systems. Full article

Accurate wind-speed prediction plays an important role in improving the operation stability of wind-power generation systems. However, the inherent complexity of meteorological dynamics poses a major challenge to forecasting accuracy. In order to overcome these limitations, we propose a new hybrid framework, which combines variational mode decomposition (VMD) for signal processing, enhanced quantum particle swarm optimization (e-QPSO), an improved walking optimization algorithm (IHOA) for feature selection and the long short-term memory (LSTM) network, and which finally establishes a reliable prediction architecture. The purpose of this paper is to optimize VMD by using the e-QPSO algorithm to improve the problems of excessive filtering or error filtering caused by parameter problems in VMD, as the noise signal cannot be filtered completely, and the number of sources cannot be accurately estimated. The IHOA algorithm is used to find the optimal hyperparameters of LSTM to improve the learning efficiency of neurons and improve the fitting ability of the model. The proposed e-QPSO-VMD-IHOA-LSTM model is compared with six established benchmark models to verify its predictive ability. The effectiveness of the model is verified by experiments using the hourly wind-speed data measured in four seasons in Changchun in 2023. The MAPE values of the four datasets were 0.0460, 0.0212, 0.0263, and 0.0371, respectively. The results show that e-QPSO-VMD effectively processes the data and avoids the problem of error filtering, while IHOA effectively optimizes the LSTM parameters and improves prediction performance. Full article

Species characterized by undetermined clade affiliations, limited research coverage, and deficient systematic investigation serve as enigmatic entities in plant and animal taxonomy, yet hold critical significance for exploring phylogenetic relationships and evolutionary trajectories. Subgenus Cyathophora (Allium, Amayllidaceae), a small taxon comprising approximately five species distributed in the Qinghai–Tibet Plateau (QTP) and adjacent regions might contain an enigmatic species that has long remained unexplored. In this study, we collected data on species from subgenus Cyathophora and its close relatives in subgenus Rhizirideum, as well as the enigmatic species Allium siphonanthum. Combining phylogenomic datasets and morphological evidence, we investigated species relationships and the underlying mechanism of phylogenetic discordance. A total of 1662 single-copy genes (SCGs) and 150 plastid loci were filtered and used for phylogenetic analyses based on concatenated and coalescent-based methods. Furthermore, to systematically evaluate phylogenetic discordance and decipher its underlying drivers, we implemented integrative analyses using multiple approaches, such as coalescent simulation, Quartet Sampling (QS), and MSCquartets. Our phylogenetic analyses robustly resolve A. siphonanthum as a member of subg. Cyathophora, forming a sister clade with A. spicatum. This relationship was further corroborated by their shared morphological characteristics. Despite the robust phylogenies inferred, extensive phylogenetic conflicts were detected not only among gene trees but also between SCGs and plastid-derived species trees. These significant phylogenetic incongruences in subg. Cyathophora predominantly stem from incomplete lineage sorting (ILS) and reticulate evolutionary processes, with historical hybridization events likely correlated with the past orogenic dynamics and paleoclimatic oscillations in the QTP and adjacent regions. Our findings not only provide new insights into the phylogeny of subg. Cyathophora but also significantly enhance our understanding of the evolution of species in this subgenus. Full article

Air purification is a key process aimed at removing harmful impurities and providing a safe and comfortable environment for human life and work. This study presents the results of an investigation into the composition, textural, and sorption properties of a multichannel carbon filtering material developed for air purification from biological (infectious) contaminants. The filtering block has a cylindrical shape and is manufactured by extrusion of a plastic composition based on carbonized rice husk with the addition of binding agents, followed by staged thermal treatment (calcination, activation, and demineralization). The filter’s effectiveness is based on the inactivation of pathogenic microorganisms as the air passes through the porous surface of the sorbent, which is modified with broad-spectrum antiseptic agents (active against bacteria, bacilli, fungi, and protozoa). X-ray diffraction analysis revealed the presence of amorphous carbon in a tubostratic structure, with a predominance of sp- and sp²-hybridized carbon atoms not incorporated into regular graphene lattices. IR spectroscopy demonstrated the presence of reactive functional groups characteristic of the developed porous structure of the material, which is capable of selective sorption of antiseptic molecules. SEM surface analysis revealed an amorphous texture with a loose structure and elements in the form of spherical semi-ring formations formed by overlapping carbon plates. An experimental setup was also developed using cylindrical multichannel carbon blocks with a diameter of 48 mm, a length of 120 mm, and 100–120 longitudinal channels with a cross-section of 1 mm². The obtained results confirm the potential of the proposed material for use in air purification and disinfection systems under conditions of elevated biological risk. Full article

Introduction: The variability of cancers and medical big data can be addressed using artificial intelligence techniques. Artificial intelligence models can accept different input types, including images as well as other formats such as numerical data, predefined categories, and free text. Non-image sources are as important as images in clinical practice and the literature; nevertheless, the secondary literature tends to focus exclusively on image-based inputs. This article reviews such models, using non-image components as a use case in the context of rectal cancer. Methods: A literature search was conducted using PubMed and Scopus, without temporal limits and in English; for the secondary literature, appropriate filters were employed. Results and Discussion: We classified artificial intelligence models into three categories: image (image-based input), non-image (non-image input), and combined (hybrid input) models. Non-image models performed significantly well, supporting our hypothesis that disproportionate attention has been given to image-based models. Combined models frequently outperform their unimodal counterparts, in agreement with the literature. However, multicenter and externally validated studies assessing both non-image and combined models remain under-represented. Conclusions: To the best of our knowledge, no previous reviews have focused on non-image inputs, either alone or in combination with images. Non-image components require substantial attention in both research and clinical practice. The importance of multimodality—extending beyond images—is particularly relevant in the context of rectal cancer and potentially other pathologies. Full article

This study presents a multi-objective predictive energy management system (EMS) for optimizing hybrid renewable energy systems (HRES) in autonomous marine vessels. The objective is to minimize fuel consumption and emissions while maximizing renewable energy usage and pure-electric sailing durations. The EMS combines nonlinear model predictive control (NMPC) with metaheuristic optimizers—Grey Wolf Optimization (GWO) and Genetic Algorithm (GA)—and is benchmarked against a conventional rule-based (RB) method. The HRES architecture comprises photovoltaic arrays, vertical-axis wind turbines (VAWTs), diesel engines, generators, and a battery storage system. A ship dynamics model was used to represent propulsion power under realistic sea conditions. Simulations were conducted using real-world operational and environmental datasets, with state prediction enhanced by an Extended Kalman Filter (EKF). Performance is evaluated using marine-relevant indicators—fuel consumption; emissions; battery state of charge (SOC); and emission cost—and validated using standard regression metrics. The NMPC-GWO algorithm consistently outperformed both NMPC-GA and RB approaches, achieving high prediction accuracy and greater energy efficiency. These results confirm the reliability and optimization capability of predictive EMS frameworks in reducing emissions and operational costs in autonomous maritime operations. Full article

To address the need for intelligent scheduling and model integration under spatiotemporal variability and uncertainty in water systems, this study proposes a hybrid correction method for pump characteristic curves that integrates data-driven techniques with an affine modeling framework. Steady-state data are extracted through adaptive filtering and statistical testing, and representative operating conditions are identified via unsupervised clustering. An affine transformation is then applied to the factory-provided characteristic equation, followed by parameter optimization using the clustered dataset. Using the Hongze Pump Station along the eastern route of the South-to-North Water Diversion Project as a case study, the method reduced the mean blade angle prediction error from 1.73° to 0.51°, and the efficiency prediction error from 7.32% to 1.30%. The results demonstrate improved model accuracy under real-world conditions and highlight the method’s potential to support more robust and adaptive hydrodynamic scheduling models, contributing to the advancement of sustainable and smart water resource management. Full article

Photovoltaic (PV) power generation may vary with respect to several factors such as solar radiation, temperature, power conditioning units, environmental effects, and shading conditions. The partial shading of PV modules is one of the most crucial factors that causes the performance degradation of PV systems. The main reason for efficiency reduction under partial shading conditions is the creation of multiple local maximums and one global maximum operating point. The classical Maximum Power Point Tracking (MPPT) algorithm fails to determine the global maximum operating point to prevent power losses under partial shading conditions. In this study, a novel hybrid MPPT method based on Perturb & Observe and Particle Swarm Optimization that mainly aims to determine global operating point, is proposed. The proposed hybrid MPPT method is tested under different partial shading conditions and variable irradiance levels. In this manner, the dynamic response of the system is remarkably increased by the proposed MPPT method. To show the superiority of the developed method, a performance comparison is conducted with the P&O- and Kalman-Filter-based MPPT methods. The obtained results illustrate an improvement around 1.5 V in undershoot voltage and 0.2 ms in convergence speed. In addition, the overall system efficiency of the PV system is increased around 2% when compared to the P&O- and Kalman-Filter-based MPPT methods. Consequently, the proposed method seems to be an efficient method in terms of undershoot voltage, convergence time, tracking accuracy, and efficiency under partial shading conditions. Full article

High aspect ratio (HAR) sample-induced aberrations seriously affect the topography measurement for the bottom of the microstructure by coherence scanning interferometry (CSI). Previous research proposed an aberration compensating method using deformable mirrors at the conjugate position of the pupil. However, it failed to compensate for the shift-variant aberrations introduced by the HAR hybrid trench array composed of multiple trenches with different parameters. Here, we propose a computational aberration correction method for measuring the topography of the HAR structure by the particle swarm optimization (PSO) algorithm without constructing a database and prior knowledge, and a phase filter in the spatial frequency domain is constructed to restore interference signals distorted by shift-variant aberrations. Since the aberrations of each sampling point are basically unchanged in the field of view corresponding to a single trench, each trench under test can be considered as a separate isoplanatic region. Therefore, a multi-channel aberration correction scheme utilizing the virtual phase filter based on isoplanatic region segmentation is established for hybrid trench array samples. The PSO algorithm is adopted to derive the optimal Zernike polynomial coefficients representing the filter, in which the interference fringe contrast is taken as the optimization criterion. Additionally, aberrations introduce phase distortion within the 3D transfer function (3D-TF), and the 3D-TF bandwidth remains unchanged. Accordingly, we set the non-zero part of the 3D-TF as a window function to preprocess the interferogram by filtering out the signals outside the window. Finally, experiments are performed in a single trench sample and two hybrid trench array samples with depths ranging from 100 to 300 μm and widths from 10 to 30 μm to verify the effectiveness and accuracy of the proposed method. Full article

Phishing attacks continue to pose serious challenges to cybersecurity, with attackers constantly refining their methods to bypass detection systems. One particularly evasive technique is Zero-Font phishing, which involves the insertion of invisible or zero-sized characters into email content to deceive both users and traditional email filters. Because these characters are not visible to human readers but still processed by email systems, they can be used to evade detection by traditional email filters, obscuring malicious intent in ways that bypass basic content inspection. This study introduces a proactive phishing detection tool capable of identifying both traditional and Zero-Font phishing attempts. The proposed tool leverages a multi-layered security framework, combining structural inspection and machine learning-based classification to detect both traditional and Zero-Font phishing attempts. At its core, the system incorporates an advanced machine learning model trained on a well-established dataset comprising both phishing and legitimate emails. The model alone achieves an accuracy rate of up to 98.8%, contributing significantly to the overall effectiveness of the tool. This hybrid approach enhances the system’s robustness and detection accuracy across diverse phishing scenarios. The findings underscore the importance of multi-faceted detection mechanisms and contribute to the development of more resilient defenses in the ever-evolving landscape of cybersecurity threats. Full article

Failures in gas path components pose significant risks to aeroengine performance and safety. Traditional fault diagnosis methods often require extensive data and struggle with real-time applications. This study addresses these critical limitations in traditional studies through physics-informed modeling and adaptive estimation. A nonlinear component-level model of the JT9D engine is developed through aero-thermodynamic governing equations, enhanced by a dual-loop iterative cycle combining Newton–Raphson steady-state resolution with integration-based dynamic convergence. An augmented state-space model that linearizes nonlinear dynamic models while incorporating gas path health characteristics as control inputs is novelly proposed, supported by similarity-criterion normalization to mitigate matrix ill-conditioning. A hybrid identification algorithm is proposed, synergizing partial derivative analysis with least squares fitting, which uniquely combines non-iterative perturbation advantages with high-precision least squares. This paper proposes a novel enhanced Kalman filter through integral compensation and three-dimensional interpolation, enabling real-time parameter updates across flight envelopes. The experimental results demonstrate a 0.714–2.953% RMSE in fault diagnosis performance, a 3.619% accuracy enhancement over traditional sliding mode observer algorithms, and 2.11 s reduction in settling time, eliminating noise accumulation. The model maintains dynamic trend consistency and steady-state accuracy with errors of 0.482–0.039%. This work shows marked improvements in temporal resolution, diagnostic accuracy, and flight envelope adaptability compared to conventional approaches. Full article

Deep learning has demonstrated significant success in hyperspectral image (HSI) classification by effectively leveraging spatial–spectral feature learning. However, current approaches encounter three challenges: (1) high spectral redundancy and the presence of noisy bands, which impair the extraction of discriminative features; (2) limited spatial receptive fields inherent in convolutional operations; and (3) unidirectional context modeling that inadequately captures bidirectional dependencies in non-causal HSI data. To address these challenges, this paper proposes HG-Mamba, a novel hybrid geometry-aware bidirectional Mamba network for HSI classification. The proposed HG-Mamba synergistically integrates convolutional operations, geometry-aware filtering, and bidirectional state-space models (SSMs) to achieve robust spectral–spatial representation learning. The proposed framework comprises two stages. The first stage, termed spectral compression and discrimination enhancement, employs multi-scale spectral convolutions alongside a spectral bidirectional Mamba (SeBM) module to suppress redundant bands while modeling long-range spectral dependencies. The second stage, designated spatial structure perception and context modeling, incorporates a Gaussian Distance Decay (GDD) mechanism to adaptively reweight spatial neighbors based on geometric distances, coupled with a spatial bidirectional Mamba (SaBM) module for comprehensive global context modeling. The GDD mechanism facilitates boundary-aware feature extraction by prioritizing spatially proximate pixels, while the bidirectional SSMs mitigate unidirectional bias through parallel forward–backward state transitions. Extensiveexperiments on the Indian Pines, Houston2013, and WHU-Hi-LongKou datasets demonstrate the superior performance of HG-Mamba, achieving overall accuracies of 94.91%, 98.41%, and 98.67%, respectively. Full article

To address the issues of information redundancy, limited feature representation, and empirically set parameters in rolling bearing fault diagnosis, this paper proposes a Multi-Entropy Screening and Optimization Temporal Convolutional Network (MESO-TCN). The method integrates feature filtering, network modeling, and parameter optimization into a unified diagnostic framework. Specifically, ensemble empirical mode decomposition (EEMD) is combined with a hybrid entropy criterion to preprocess the raw vibration signals and suppress redundant noise. A kernel-extended temporal convolutional network (ETCN) is designed with multi-scale dilated convolution to extract diverse temporal fault patterns. Furthermore, an improved whale optimization algorithm incorporating a firefly-inspired mechanism is introduced to adaptively optimize key hyperparameters. Experimental results on datasets from Xi’an Jiaotong University and Southeast University demonstrate that MESO-TCN achieves average accuracies of 99.78% and 95.82%, respectively, outperforming mainstream baseline methods. These findings indicate the method’s strong generalization ability, feature discriminability, and engineering applicability in intelligent fault diagnosis of rotating machinery. Full article

Electromyography (EMG) has emerged as a vital tool in the development of wearable robotic exoskeletons, enabling intuitive and responsive control by capturing neuromuscular signals. This review presents a comprehensive analysis of the EMG signal processing pipeline tailored to exoskeleton applications, spanning signal acquisition, noise mitigation, data preprocessing, feature extraction, and control strategies. Various EMG acquisition methods, including surface, intramuscular, and high-density surface EMG, are evaluated for their applicability in real-time control. The review addresses prevalent signal quality challenges, such as motion artifacts, power-line interference, and crosstalk. It also highlights both traditional filtering techniques and advanced methods, such as wavelet transforms, empirical mode decomposition, and adaptive filtering. Feature extraction techniques are explored to support pattern recognition and motion classification. Machine learning approaches are examined for their roles in pattern recognition-based and hybrid control architectures. This article emphasizes muscle synergy analysis and adaptive control algorithms to enhance personalization and fatigue compensation, followed by the benefits of multimodal sensing and edge computing in addressing the limitations of EMG-only systems. By focusing on EMG-driven strategies through signal processing, machine learning, and sensor fusion innovations, this review bridges gaps in human–machine interaction, offering insights into improving the precision, adaptability, and robustness of next generation exoskeletons. Full article