Search Results (76)

Local feature matching plays a critical role in robotic SLAM and visual localization. However, in weakly textured indoor industrial environments, lightweight appearance-based methods often struggle to learn discriminative and stable local features. To address this challenge, this paper proposes GAEFeat, short for Geometry-Aware Efficient Feature, a lightweight vision–geometric feature learning network. To address the scarcity of specialized training data, we integrated robotic arm pose priors with depth information to automatically generate cross-view supervision signals and surface-normal labels. Based on this strategy, we constructed two complementary datasets, including a simulated dataset and a real-world dataset, to support feature learning and evaluation in weakly textured indoor industrial environments. For feature extraction, we design a dual enhancement mechanism consisting of a geometric auxiliary branch and a geometry-aware enhancement (GAE) module. The former guides the network to perceive local surface structures through surface normal supervision, while the latter utilizes a gating mechanism to achieve deep fusion between geometric priors and 2D texture descriptors. Experimental results demonstrate that GAEFeat achieves strong robustness and high inference efficiency in relative pose estimation, homography estimation, and visual localization tasks, with particularly notable advantages in near-field, weakly textured industrial scenes. The framework achieves an inference latency of only 3.9 ms on the NVIDIA Jetson AGX Orin edge platform, demonstrating its real-time capability and practical potential for deployment in edge computing environments. Full article

Automatic detection of sensitive fields in structured data is a critical prerequisite for privacy compliance and data governance. However, existing approaches face severe cross-domain generalization challenges. Hand-crafted pattern rules often fail under highly heterogeneous naming conventions, while single statistical models tend to overfit and degrade sharply under distribution shifts between training and deployment domains. These limitations stem from the weak semantic signals and distributional heterogeneity of structured data, which make it difficult to simultaneously capture explicit rules and latent, variant-sensitive attributes. To address these challenges, we propose a detection framework based on multi-view complementary features and a Hierarchical Gated Residual Network (HGRN). The framework first constructs a full-spectrum feature system that integrates explicit rules and implicit statistical fingerprints (e.g., entropy and character texture) to fill the semantic gap. It then introduces a decision mechanism combining robust priors with dynamic residual calibration: a random forest provides a stable probabilistic anchor, which is further nonlinearly corrected by a learnable gating-and-expert network. This design explicitly resolves the cognitive conflict between rule-dominated regions and complex distributional regions. Experiments on multiple real-world datasets—including DeSSI, CMS Open Payments and Home Credit—show that the proposed method achieves a Macro-F1 of 0.9408 on DeSSI and exhibits strong in-domain performance. Under strict frozen-model cross-domain transfer, HGRN mitigates the catastrophic collapse observed in pure neural baselines and maintains moderate detection capability, offering interpretable trust allocation between rule-based priors and data-driven correction in both financial and healthcare scenarios. Full article

Gearbox fault diagnosis under controlled bench-test conditions with known speed variations and noise interference remains challenging because nonstationarity, background noise, and operating-condition fluctuations can easily submerge weak localized fault features. To address this issue, this study proposes a fault diagnosis method based on a fractional-order-enhanced dual-view representation and VibrMamba–VMamba collaborative modeling. First, this study introduces a Grünwald–Letnikov fractional-order differential enhancement module with a fractional order of $\alpha =0.6$ to strengthen fault-sensitive impulsive components and improve the representation of nonstationary vibration signals. The framework then uses the enhanced signal to construct dual-view inputs: a fractional-order-enhanced one-dimensional vibration sequence and a fractional-order-enhanced synchrosqueezing transform (SST) time–frequency image. Subsequently, the framework constructs a VibrMamba temporal branch and a VMamba visual branch to extract dynamic temporal features and global structural features, respectively. Instead of using simple feature concatenation, this study designs a sample-adaptive collaborative fusion mechanism with gated weighting and cross-branch residual enhancement to integrate complementary temporal–visual representations. Bench-level experiments show that the proposed method achieves 98.90% diagnostic accuracy under clean test conditions and maintains 91.52% accuracy at −5 dB signal-to-noise ratio (SNR). These results should be interpreted as bench-level validation under controlled laboratory conditions rather than as direct evidence of field-level generalization. This framework provides a methodological solution that integrates fractional-order signal enhancement, dual-view representation, and Mamba-style collaborative state-space modeling for gearbox fault classification under controlled laboratory conditions with known speed variations and noise disturbances. Full article

Real-time and accurate crop row extraction is a fundamental requirement for vision-based perception in autonomous agricultural machinery. In maize fields, however, row detection is easily affected by variable illumination, leaf occlusion, weed interference, and uneven soil backgrounds, which can reduce the reliability of both GNSS- and image-based navigation methods. To address these challenges, this study proposes a plant-oriented crop row perception framework that reconstructs row structures from individual maize plant detections. A lightweight detection model, named Maize–YOLO, was developed based on YOLOv11n for maize seedling detection. Three key improvements were introduced to enhance the balance between accuracy and efficiency. First, the C3k2_Faster_CGLU module replaces the original C3k2 block to reduce redundant convolutional computation while improving selective feature representation through convolutional gated linear units, thereby enhancing robustness under complex field backgrounds. Second, a lightweight shared detection head, Detect_LSH, was designed to share convolutional parameters across multi-scale feature maps and adaptively adjust feature amplitudes, reducing detection-head redundancy while maintaining multi-scale prediction capability. Third, a Layer-Adaptive Magnitude-Based Pruning strategy was applied to remove low-contribution channels and further improve computational efficiency for CPU-based deployment. Experimental results on field-collected maize seedling images showed that Maize–YOLO achieved an mAP@0.5 of 97.6%, reduced GFLOPs by 61.9%, and maintained a CPU inference speed of 84.4 FPS. After plant detection, row centerlines were estimated using an IPM–DBSCAN–LSM pipeline, which transformed detected plant centers into a quasi-top-view space, clustered them into crop rows, and fitted continuous centerlines. The extracted crop rows reached a positional accuracy of 98.6%, with a mean angular deviation of 0.44°. These results demonstrate that the proposed method can provide accurate, lightweight, and real-time crop row perception for autonomous agricultural navigation and precision field operations. Full article

Cotton, a globally significant crop grown in over 100 countries, sustains a $40 billion market and provides employment for over 350 million people worldwide. However, plastic contamination remains a persistent challenge within the industry, degrading cotton fiber quality and disrupting ginning. Manual inspection and optical machine-vision systems struggle when plastic fragments are concealed by fibers or lack sufficient color contrast. To address these challenges, we developed an ultrasonic phased-array imaging system operating at 40 kHz under field-programmable gate array (FPGA) control. Transmitter elements emit pulsed ultrasound along radial paths, separate reflection receivers record echo amplitudes to form acoustic images, and a set of transmission receivers captures signal attenuation, which is overlaid onto the reflection-based image to highlight potential contaminants. In preliminary laboratory-based tests on both seed cotton and lint samples, the system successfully detected visually obscured plastic fragments as small as $2\mathrm{cm}\times 2\mathrm{cm}$ with an angular resolution limit of $\pm 3°$. Distinct reflection peaks and corresponding attenuation overlays were produced across the field of view, validating the system’s detection capabilities. These results demonstrate the feasibility of using ultrasonic imaging to reveal concealed plastics in cotton processing. Integrating this approach with existing optical methods could enhance contaminant-removal workflows and improve overall fiber quality and processing efficiency. Full article

Multistep-ahead prediction of critical states in the iron ore sintering process is essential for maintaining production stability, enhancing energy efficiency, and reducing industrial emissions. However, large time delays, strong coupling, and condition drifts challenge existing spatiotemporal graph neural networks (STGNNs). This paper proposes Process-aware Mixed Dynamic Graph Network (ProMix-DGNet), which integrates a Decoupled Two-Stream Topology Learning mechanism—fusing Adaptive Static Graph with a Radial Basis Function (RBF)-driven Dynamic Graph Constructor—to ensure robust spatial modeling under high-noise conditions. Furthermore, Process-View Global Mixer explicitly captures long-range process coupling across the entire sintering strand, overcoming the receptive field limitations of traditional graph convolutions. In the decoding phase, a future control-informed module utilizes a bidirectional Long Short-Term Memory (BiLSTM) and a global mixer to align known future control setpoints with the system’s spatial topology. These features are integrated via a gated residual mechanism that dynamically modulates the interaction between control intents and historical representations. Extensive experiments conducted on two real-world industrial datasets, Sinter-A and Sinter-B, demonstrate that ProMix-DGNet consistently outperforms mainstream baselines across multiple metrics, including Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results verify the model’s higher accuracy and robustness in complex large-time-delay systems, offering a reliable framework for the intelligent monitoring and closed-loop optimization of sintering process. Full article

Deep learning has shown promise in tabular data modeling, yet challenges such as feature heterogeneity, sparse interactions, and expert prediction collapse remain unresolved. To address these issues, we propose DETTab (Diversity-Enhanced Tabular Experts), a framework that integrates feature gating, multi-expert fusion, and structure-aware regularization. DETTab first employs a Feature Gating Encoder to perform soft selection over input fields, enhanced by a Field Decorrelation Loss to promote embedding diversity. A Feature Interaction Encoder is then used to capture high-order dependencies among features via multi-head self-attention. Finally, a Multi-View Expert Fusion Module aggregates predictions from multiple experts through a soft routing mechanism, guided by an Expert Diversity Loss to mitigate prediction collapse and improve training stability. Extensive experiments on public tabular datasets demonstrate that DETTab achieves consistent improvements in predictive performance and training robustness across different settings, particularly in alleviating expert convergence collapse, thereby validating its effectiveness for tabular learning. Full article

This study aimed to establish the concurrent validity and agreement of the K-power (KINVENT Biomecanique, Montpellier, France) hybrid sensor system that combines Ultra-Wideband and Inertial Measurement Unit measures against criterion timing gates for recording 20-m sprint performance in adolescent athletes. Fifteen trained adolescent track and field sprinters (age: 15.2 ± 2.4 years) performed two maximal 20-m sprints. Sprint times were simultaneously recorded using timing gates and the K-power sensor. Validity and agreement were assessed using paired-samples t-tests, Intraclass Correlation Coefficients (ICCs), Coefficient of Variation (CV), and Bland–Altman analysis. Sensitivity was determined by comparing the Typical Error (TE) to the Smallest Worthwhile Change (SWC). No significant systematic bias was observed between the devices (p > 0.05). The K-power sensor demonstrated excellent absolute agreement (ICC = 0.96, [95% CI = 0.94–0.98) and a low relative error (CV = 1.07%). The device displayed high sensitivity, with a TE (0.034 s) smaller than SWC (0.040 s). In conclusion, the K-power sensor is a valid and reliable instrument for measuring 20-m sprint times, being a practical alternative to timing gates. While the system is sensitive (TE < SWC), the Minimal Detectable Change of 0.094 s likely reflects the inherent biological variability of adolescent mechanics; thus, coaches should view changes exceeding 0.09 s as meaningful for individual athletes. Full article

Sensor fusion is crucial in numerous imaging and sensing applications. Integrating data from multiple sensors with different field-of-view, resolution, and frame timing poses substantial computational overhead. Time-gated single-photon avalanche diode (SPAD) image sensors have been developed to support multiple sensing modalities and mitigate this issue, but mismatched frame timing remains a challenge. Dual-time-gated SPAD image sensors, which can capture dual images simultaneously, have also been developed. However, the reported sensors suffered from medium-to-large pixel pitch, limited resolution, and inability to independently control the exposure time of the dual images, which restricts their applicability. In this paper, we introduce a 5 µm-pitch, 3D-backside-illuminated (BSI) 1Megapixel dual-time-gated SPAD image sensor enabling a simultaneous output of dual images. The developed SPAD image sensor is verified to operate as an RGB-Depth (RGB-D) sensor without complex image alignment. In addition, a novel high dynamic range (HDR) technique, utilizing pileup effect with two parallel in-pixel memories, is validated for dynamic range extension in 2D imaging, achieving a dynamic range of 119.5 dB. The proposed architecture provides dual image output with the same field-of-view, resolution, and frame timing, and is promising for efficient sensor fusion. Full article

Over Over the past years, the field of Machine Learning (ML) and Deep Learning (DL) has seen strong developments both in terms of software and hardware, with the increase of specialized devices. One of the biggest challenges in this field is the inference phase, where the trained model makes predictions of unseen data. Although computationally powerful, traditional computing architectures face limitations in efficiently managing requests, especially from an energy point of view. For this reason, the need arose to find alternative hardware solutions, and among these, there are Field Programmable Gate Arrays (FPGAs): their key feature of being reconfigurable, combined with parallel processing capability, low latency and low power consumption, makes those devices uniquely suited to accelerating inference tasks. In this paper, we present a novel approach to accelerate the inference phase of a multi-layer perceptron (MLP) using BondMachine framework, an OpenSource framework for the design of hardware accelerators for FPGAs. Analysis of the latency, energy consumption, and resource usage, as well as comparisons with respect to standard architectures and other FPGA approaches, is presented, highlighting the strengths and critical points of the proposed solution. The present work represents an exploratory study to validate the proposed methodology on MLP architectures, establishing a crucial foundation for future work on scalability and the acceleration of more complex neural network models. Full article

Knee osteoarthritis (KOA) is a most prevalent chronic muscoloskeletal disorder causing pain and functional impairment. Accurate predictions of KOA evolution are important for early interventions and preventive treatment planning. In this paper, we propose a novel dynamic hypergraph-based risk model (DyHRM) which integrates the encoder–decoder (ED) architecture with hypergraph convolutional neural networks (HGCNs). The risk model is used to generate longitudinal forecasts of KOA incidence and progression based on the knee evolution at a historical stage. DyHRM comprises two main parts, namely the dynamic hypergraph gated recurrent unit (DyHGRU) and the multi-view HGCN (MHGCN) networks. The ED-based DyHGRU follows the sequence-to-sequence learning approach. The encoder first transforms a knee sequence at the historical stage into a sequence of hidden states in a latent space. The Attention-based Context Transformer (ACT) is designed to identify important temporal trends in the encoder’s state sequence, while the decoder is used to generate sequences of KOA progression, at the prediction stage. MHGCN conducts multi-view spatial HGCN convolutions of the original knee data at each step of the historic stage. The aim is to acquire more comprehensive feature representations of nodes by exploiting different hyperedges (views), including the global shape descriptors of the cartilage volume, the injury history, and the demographic risk factors. In addition to DyHRM, we also propose the HyGraphSMOTE method to confront the inherent class imbalance problem in KOA datasets, between the knee progressors (minority) and non-progressors (majority). Embedded in MHGCN, the HyGraphSMOTE algorithm tackles data balancing in a systematic way, by generating new synthetic node sequences of the minority class via interpolation. Extensive experiments are conducted using the Osteoarthritis Initiative (OAI) cohort to validate the accuracy of longitudinal predictions acquired by DyHRM under different definition criteria of KOA incidence and progression. The basic finding of the experiments is that the larger the historic depth, the higher the accuracy of the obtained forecasts ahead. Comparative results demonstrate the efficacy of DyHRM against other state-of-the-art methods in this field. Full article

Quantum computing, with its foundational principles of superposition and entanglement, has the potential to provide significant quantum advantages, addressing challenges that classical computing may struggle to overcome. As data generation continues to grow exponentially and technological advancements accelerate, classical machine learning algorithms increasingly face difficulties in solving complex real-world problems. The integration of classical machine learning with quantum information processing has led to the emergence of quantum machine learning, a promising interdisciplinary field. This work provides the reader with a bottom-up view of quantum circuits starting from quantum data representation, quantum gates, the fundamental quantum algorithms, and more complex quantum processes. Thoroughly studying the mathematics behind them is a powerful tool to guide scientists entering this domain and exploring their connection to quantum machine learning. Quantum algorithms such as Shor’s algorithm, Grover’s algorithm, and the Harrow–Hassidim–Lloyd (HHL) algorithm are discussed in detail. Furthermore, real-world implementations of quantum machine learning and quantum deep learning are presented in fields such as healthcare, bioinformatics and finance. These implementations aim to enhance time efficiency and reduce algorithmic complexity through the development of more effective quantum algorithms. Therefore, a comprehensive understanding of the fundamentals of these algorithms is crucial. Full article

In rice detection tasks, accurate identification of leaf streaks, pest and disease distribution, and spikelet hierarchies relies on high-quality images to distinguish between texture and hierarchy. However, existing images often suffer from texture blurring and contour shifting due to equipment and environment limitations, which affects the detection performance. In view of the fact that pests and diseases affect the whole situation and tiny details are mostly localized, we propose a rice image reconstruction method based on an adaptive two-branch heterogeneous structure. The method consists of a low-frequency branch (LFB) that recovers global features using orientation-aware extended receptive fields to capture streaky global features, such as pests and diseases, and a high-frequency branch (HFB) that enhances detail edges through an adaptive enhancement mechanism to boost the clarity of local detail regions. By introducing the dynamic weight fusion mechanism (CSDW) and lightweight gating network (LFFN), the problem of the unbalanced fusion of frequency information for rice images in traditional methods is solved. Experiments on the 4× downsampled rice test set demonstrate that the proposed method achieves a 62% reduction in parameters compared to EDSR, 41% lower computational cost (30 G) than MambaIR-light, and an average PSNR improvement of 0.68% over other methods in the study while balancing memory usage (227 M) and inference speed. In downstream task validation, rice panicle maturity detection achieves a 61.5% increase in mAP50 (0.480 → 0.775) compared to interpolation methods, and leaf pest detection shows a 2.7% improvement in average mAP50 (0.949 → 0.975). This research provides an effective solution for lightweight rice image enhancement, with its dual-branch collaborative mechanism and dynamic fusion strategy establishing a new paradigm in agricultural rice image processing. Full article

With the advancement of information technology, artificial intelligence (AI) has demonstrated significant potential in clinical prediction, helping to improve the level of intelligent medical care. Current clinical practice primarily relies on patients’ time series data and clinical notes to predict health status and makes predictions by simply concatenating cross-modal features. However, they not only ignore the inherent correlation between cross-modal features, but also fail to analyze the collaborative representation of multi-granularity features from diverse perspectives. To address these challenges, we propose a deep dynamic memory-driven cross-modal feature representation network for clinical outcome prediction. Specifically, we use a Bi-directional Gated Recurrent Unit (BiGRU) network to capture dynamic features in time series data and a dual-view feature encoding model with sentence-aware and entity-aware capabilities to extract clinical text features from global semantic and local concept perspectives, respectively. Furthermore, we introduce a memory-driven cross-modal attention mechanism, which dynamically establishes deep correlations between clinical text and time series features through learnable memory matrices. In addition, we also introduce a memory-aware constrained layer normalization to alleviate the challenges of multi-modal feature heterogeneity. Besides, we use gating mechanisms and dynamic memory components to enable the model to learn feature information of different historical-current patterns, further improving the model’s performance. Lastly, we combine the integrated gradients for feature attribution analysis to enhance the model’s interpretability. Finally, we evaluate the model’s performance on the MIMIC-III dataset, and the experimental results demonstrate that the model outperforms current advanced baselines in clinical outcome prediction tasks. Notably, our model maintains high predictive accuracy and robustness even when faced with imbalanced data. It can also provide a new perspective for researchers in the field of AI medicine. Full article

Finite Control Set Model Predictive Control emerges as a promising method for controlling power electronics inverters, outperforming traditional linear techniques. However, implementing Finite Control Set Model Predictive Control on conventional processors faces a significant computational burden due to its repetitive nature. This paper presents a novel approach that utilizes LabVIEW & Field Programmable Gate Arrays to address this computational bottleneck. By capitalizing on the inherent parallelism and suitability of Field Programmable Gate Arrays for discrete control problems, substantial computational advantages are achieved for Finite Control Set Model Predictive Control. The use of LabVIEW, a well-established platform in industrial and commercial solutions, ensures that this work is relevant not only academically but also for real-world industrial applications of FCS-MPC in power electronics and motor drives. This research successfully demonstrates the application of Finite Control Set Model Predictive Control for controlling the current of a motor-like load for a three-phase Voltage Source Inverter system in LabVIEW. To simplify the traditionally complex Field Programmable Gate Arrays programming process, user-friendly toolkits such as LabVIEW Control Design & Simulation, LabVIEW Real-Time, and LabVIEW FPGA Module are employed. This LabVIEW-based integration facilitates the execution of both concurrent and sequential Field Programmable Gate Arrays algorithms, leading to efficient Field Programmable Gate Arrays resource management and user-defined restrictions on maximum switching frequency, obviating the need for resource-intensive control methods for fast switches such as SiC and GaN IGBTs. The proposed controller is validated using an off-the-shelf computer turned into a real-time system but also on Field Programmable Gate Arrays for comparison purposes. Full article