Search Results (1,660)

Stock-ranking prediction is an important task in quantitative finance because it directly influences portfolio construction and alpha generation. Recent Graph Neural Network (GNN) models provide a promising way to describe inter-stock dependencies, but many existing methods still have difficulty balancing rapidly changing market interactions with relatively stable structural relationships. They are also easily affected by financial micro-structure noise. To address these issues, this paper proposes USTGCN, a Unified Spatio-Temporal Graph Convolutional Network for stock-ranking prediction. USTGCN adopts a dual-stream temporal encoder based on ALSTM and GRU to capture short-term dynamic patterns and longer-horizon structural information, respectively. We further introduce a rolling-window correlation smoothing strategy to build a more stable dynamic graph, and then integrate the dynamic and structural graph views through a shared fusion layer. Skip connections are used to preserve original temporal information during spatial aggregation. Experiments on the CSI100 and CSI300 benchmark datasets show that USTGCN achieves IC values of 0.141 and 0.154, respectively, and exhibits improved drawdown control during stressed market periods, indicating its practical value for quantitative trading. Full article

To address the inherent limitations in the robustness of fully autonomous unmanned aerial vehicle (UAV) visual perception and the high cognitive workload associated with manual control, this paper proposes a human-in-the-loop brain–computer interface (BCI) control framework. The system integrates steady-state visual evoked potential (SSVEP) with deep learning techniques to create a spatio-temporally dynamic interaction paradigm, enabling real-time alignment between visual targets and frequency stimuli. At the perception level, an enhanced YOLOv11 network incorporating partial convolution (PConv) and shape intersection over union (Shape-IoU) loss is developed and coupled with the DeepSort multi-object tracking algorithm. This configuration ensures high-speed execution on edge computing platforms while maintaining stable stimulus coverage over dynamic targets, thus providing a robust visual induction environment for EEG decoding. At the neural decoding level, an enhanced task-discriminant component analysis (TDCA-V) algorithm is introduced to improve signal detection stability within non-stationary flight conditions. Experimental results demonstrate that within the predefined fixation task window, the system achieves 100% success in maintaining target identity (ID). The BCI system achieved an average command recognition accuracy of 91.48% within a 1.0 s time window, with the TDCA-V algorithm significantly outperforming traditional spatial filtering methods in dynamic scenarios. These findings demonstrate the system’s effectiveness in decoupling human cognitive intent from machine execution, providing a robust solution for human–machine collaborative control. Full article

Network Intrusion Detection Systems (NIDS) play a crucial role in protecting network environments against cyberattacks. However, traditional NIDS rely heavily on predefined attack signatures, which limits their ability to detect zero-day attacks. Although machine learning-based intrusion detection techniques have been widely adopted in Network Intrusion Prevention Systems (NIPS), publicly available network traffic datasets often suffer from severe class imbalance, leading to biased learning and degraded detection performance. To address this issue, this study proposes data augmentation framework based on a 3D-GAN (Three-Discriminator Generative Adversarial Network). The proposed architecture integrates an autoencoder, a CNN (Convolutional Neural Network), and an LSTM (Long Short-Term Memory) network as parallel discriminators to capture the statistical, spatial, and temporal characteristics of network traffic. By jointly optimizing multiple discriminator losses, the framework enhances training stability and generates high-quality synthetic samples. Experiments were conducted on the CIC-UNSW-NB15 dataset using Random Forest-, XGBoost (eXtreme Gradient Boosting)-, and BiGRU (Bidirectional Gated Recurrent Unit)-based classifiers. Two augmented datasets were constructed to address class imbalance, containing approximately 100,000 and 350,000 samples, respectively. Among them, Dataset 2, augmented using the proposed 3D-GAN, demonstrated the most significant performance improvement. Compared to the original imbalanced dataset, the XGBoost classifier trained on Dataset 2 achieved approximately a 4% increase in both accuracy and F1-score, while reducing the false positive rate and false negative rate by approximately 3.5%. Furthermore, the optimal configuration attained an F1-score of 0.9816, indicating superior capability in modeling complex network traffic patterns. Overall, this study highlights the potential of GAN-based data augmentation for alleviating class imbalance and improving the robustness and generalization of intrusion detection systems. Full article

In China, a majority of the proven crude oil reserves are found in clastic rock reservoirs, which typically exhibit low natural energy levels. Water injection has become the most widely adopted technique for maintaining reservoir pressure and enhancing oil recovery in such formations. However, conventional water injection strategies heavily rely on empirical knowledge, often failing to accurately characterize the dynamic inter-well connectivity between injection and production wells. This limitation hinders the effective management of fluid injection and production processes. To address this challenge, we propose an intelligent optimization method for water allocation in high-water cut, low-permeability reservoirs. Our approach employs a Bidirectional Long Short-Term Memory (BiLSTM) neural network to learn the complex patterns from historical injection data in a data-driven manner. Furthermore, we design a well distance and time joint attention mechanism, which is integrated after the dual BiLSTM layers to enhance the model’s ability to capture the critical dynamic relationships among wells. This mechanism decouples temporal pattern recognition and the spatial physical constraints, laying the foundation for interpretable injection strategy optimization. We name this architecture “AttBiLSTM”, which is designed for optimizing injection strategies for individual layers in separate-layer water injection wells (The layer refers to the basic geological unit or flow unit within a vertically heterogeneous reservoir that is delineated and requires independent water injection regulation). Using field data from the Xinjiang Oilfield, we validate the proposed method and compare its performance against traditional water injection schemes and mainstream data-driven models. The experimental results demonstrate that the AttBiLSTM model effectively establishes a nonlinear mapping between the injection volumes and oil production rates, showing strong performance in both production prediction and injection optimization. An independent numerical reservoir simulation verification confirms that the optimized scheme increases well group oil production by over 3.6%, with no premature water breakthrough risk in a 5-year development cycle. This study provides a novel and practical technical framework for efficiently developing low-porosity, low-permeability, and highly heterogeneous reservoirs. Full article

Motion sickness (MS) is a prevalent condition that can significantly degrade user comfort and immersion, particularly in virtual reality (VR) environments. Accurate prediction models are essential for early detection and mitigation of MS symptoms, thereby improving the overall VR experience. Most existing approaches rely on bio-physiological data acquired through body-mounted sensors, which may restrict user mobility and diminish immersion. This study proposes a less intrusive alternative, leveraging head and torso kinematic data for MS prediction. We introduce a hybrid Convolutional–Recurrent Neural Network (C-RNN) designed to capture both spatial and temporal features for enhanced classification accuracy. Using a dataset of 40 participants, the proposed C-RNN outperformed traditional machine learning models—including Support Vector Machines (SVMs), k-Nearest Neighbors (KNN), Decision Trees (DT), and a baseline Recurrent Neural Network (RNN)—across multiple evaluation metrics. The C-RNN achieved 85.63% accuracy, surpassing SVM (60%), KNN (73.75%), DT (74.38%), and RNN (81.88%), with corresponding gains in precision, recall, F1-score, and ROC AUC. These results demonstrate that head–torso motion patterns provide sufficient predictive signal for accurate MS detection, offering a non-intrusive, efficient alternative to physiological sensing that supports improved comfort and sustained immersion in VR. Full article

Reliable estimation of extreme rainfall is essential for hydraulic design and flood risk mitigation, particularly in arid regions where rainfall exhibits strong temporal and spatial variability. This study presents a statistical framework for developing rainfall intensity-duration-frequency (IDF) curves, complemented by a machine learning-based assessment of model bias and performance. The analysis was conducted using data from ten rainfall stations located within or near the Wadi Al-Rummah Basin. Annual maximum series (AMS) from 1969 to 2024 were first reconstructed to address missing years using a modified normal ratio method (NRM) combined with nearest-station selection, ensuring spatial consistency while preserving station-specific rainfall characteristics. Six probability distributions (Weibull, Gumbel, gamma, lognormal, generalized extreme value (GEV), and generalized Pareto) were fitted to each station, and the best-fit distribution was identified using multiple goodness-of-fit (GOF) criteria, including the Kolmogorov–Smirnov (K-S) test, Anderson–Darling (A-D) test, root mean square error (RMSE), chi-square (χ²) statistic, Akaike information criterion (AIC), Bayesian information criterion (BIC), and the coefficient of determination (R²). Statistical IDF curves were then developed for durations ranging from 5 to 1440 min and return periods from 2 to 1000 years. To evaluate the robustness of the statistically derived IDF curves, three machine learning (ML) models, multiple linear regression (MLR), regression random forest (RRF), and multilayer feed-forward neural network (MFFNN), were trained as surrogate models using duration, return period, and station geographic attributes as predictor variables. Model performance was evaluated using RMSE, MAE, and mean bias metrics across stations and return periods. The lognormal distribution emerged as the best-fit model for four stations, while the Gumbel and gamma distributions were selected for two stations each. Overall, no single probability distribution consistently outperformed others, indicating station-dependent behavior. Among the machine learning models, the MFFNN achieved the closest agreement with statistical IDF estimates ($RMSE\approx 0.97$, $MAE\approx 0.65$, $bias\approx -0.02$), followed by RRF and MLR based on global average performance across all stations and return periods. The proposed framework offers a reliable approach for rainfall IDF development and evaluation in arid region watersheds. Full article

Mini-LED local dimming systems commonly suffer from luminance discontinuity, halo artifacts, and temporal instability in dynamic scenes. Traditional heuristic-based methods and standard convolutional neural networks often fail to capture long-range spatial dependencies and struggle to balance spatial smoothness, content fidelity, and real-time performance under hardware constraints. To address these challenges, this paper proposes SwinLightNet, an efficient adaptive backlight optimization network tailored for Mini-LED displays. Built upon a Swin Transformer framework tailored for Mini-LED backlight optimization, SwinLightNet integrates five hardware-aware design strategies: (i) a lightweight Swin variant (window size = 8, MLP ratio = 2.0) for efficient global context modeling; (ii) CNN encoder–decoder integration for multi-scale feature extraction; (iii) a partition-level alignment module ensuring spatial consistency; (iv) a backlight constraint module enforcing local luminance consistency and contrast preservation; (v) a change-aware temporal decision framework stabilizing dynamic sequences. These components synergistically resolve core limitations: global modeling suppresses halo artifacts while preserving content fidelity; alignment and constraint modules eliminate luminance discontinuity without compromising contrast; and the temporal framework guarantees flicker-free output under motion. Evaluated on DIV2K (static images) and a custom 2K-resolution video dataset (dynamic scenes), SwinLightNet demonstrates robust reconstruction quality while maintaining only 1.18 million parameters and 0.088 GFLOPs (Computational Cost). The results confirm SwinLightNet’s effectiveness in holistically addressing spatial, temporal, and hardware constraints, demonstrating strong potential for practical deployment in resource-constrained Mini-LED backlight control systems. Full article

This paper introduces a biomimetic framework and novel brain-inspired AI (BIAI) models based on spiking neural networks (SNNs) for emotional state recognition from audio (speech), visual (face), and integrated multimodal audio–visual data. The developed framework, named eXCube2, uses a three-dimensional SNN architecture NeuCube that is spatially structured according to a human brain template. The BIAI models developed in eXCube2 are trainable on spatio- and spectro-temporal data using brain-inspired learning rules. Such models are explainable in terms of revealing patterns in data and are adaptable to new data. The eXCube2 models are implemented as software systems and tested on speech and video data of subjects expressing emotional states. The use of a brain template for the SNN structure enables brain-inspired tonotopic and stereo mapping of audio inputs, topographic mapping of visual data, and the combined use of both modalities. This novel approach brings AI-based emotional state recognition closer to human perception, provides a better explainability and adaptability than existing AI systems. It also results in a higher or competitive accuracy, even though this was not the main goal here. This is demonstrated through experiments on benchmark datasets, achieving classification accuracy above 80% on single-modality data and 88.9% when multimodal audio–visual data are used, and a “don’t know” output is introduced. The paper further discusses possible applications of the proposed eXCube2 framework to other audio, visual, and audio–visual data for solving challenging problems, such as recognizing emotional states of people from different origins; brain state diagnosis (e.g., Parkinson’s disease, Alzheimer’s disease, ADHD, dementia); measuring response to treatment over time; evaluating satisfaction responses from online clients; cognitive robotics; human–robot interaction; chatbots; and interactive computer games. The SNN-based implementation of BIAI also enables the use of neuromorphic chips and platforms, leading to reduced power consumption, smaller device size, higher performance accuracy, and improved adaptability and explainability. This research shows a step toward building brain-inspired AI systems. Full article

In recent years, radar-based gesture recognition technology has been widely applied in industrial and daily life scenarios. However, increasingly complex application scenarios have imposed higher demands on the accuracy and robustness of gesture recognition algorithms, and challenges such as clutter interference, inter-gesture similarity, and spatial–temporal feature ambiguity limit recognition performance. To address these challenges, a novel framework named CECL, which incorporates the Convolutional Block Attention Module (CBAM) into a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architecture, is proposed for high-accuracy radar-based gesture recognition. The CBAM adaptively highlights discriminative spatial regions and suppresses irrelevant background, and the CNN-LSTM network captures temporal dynamics across gesture sequences. During gesture signal processing, the Blackman window is applied to suppress spectral leakage. Additionally, a combination of wavelet thresholding and dynamic energy nulling is employed to effectively suppress clutter and enhance feature representation. Furthermore, an improved Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm further eliminates isolated sparse noise while preserving dense and valid target signal regions. Experimental results demonstrate that the proposed algorithm achieves 98.33% average accuracy in gesture classification, outperforming other baseline models. It exhibits excellent recognition performance across various distances and angles, demonstrating significantly enhanced robustness. Full article

Predicting the motion of ships and floating structures is essential for ensuring economical and environmentally friendly operations in the ocean. In this study, we propose a hybrid encoder–decoder Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) architecture to predict motions of a moored Floating Production Storage and Offloading (FPSO) vessel under varying sea conditions. The model integrates a CNN for spatial wave-field feature extraction and an LSTM encoder–decoder to capture temporal dependencies in vessel motion. Synthetic datasets were generated using mid-fidelity dynamics simulations of a coupled FPSO–mooring–riser system subjected to wave excitations. Five sea states ranging from calm to severe were considered to evaluate the model’s robustness. A key preprocessing step involved determining the optimal spatial domain for wave field input, and a wave field size of 600 m × 600 m was identified as the most cost-effective configuration while maintaining accuracy. The model was validated using the Root Mean Square Error (RMSE) or relative RMSE (RRMSE). Despite low RRMSE values in low sea states, predictions were noisier due to high-frequency, low-amplitude responses. In contrast, higher sea states yielded more stable predictions despite higher RRMSE values. The proposed method offers high-resolution motion forecasting capability, which can enhance operational safety and energy efficiency of offshore platforms, particularly when integrated with stereo camera-based wave monitoring systems. Full article

This study addresses the critical need for accurate, continuous monitoring of surface water quality parameters (SWQPs) using remote sensing, overcoming limitations in existing models that often rely on pre-trained networks ill-suited for complex aquatic environments. We present a customized convolutional neural network (CNN) architecture, implemented in the MATLAB environment, designed to simultaneously predict optically active (Total Organic Carbon, TOC) and non-optically active (Dissolved Oxygen, DO) parameters from eighteen Sentinel-2 Level-2A satellite images, acquired between 2023 and 2024. Our approach integrates spatial and spectral data through a customized CNN with three convolutional layers and two dense layers, optimized via adaptive learning strategies, data augmentation, and rigorous regularization to enhance predictive performance and prevent overfitting. The models were trained and validated on fused datasets of satellite imagery and in situ measurements, organized into comprehensive four-dimensional arrays capturing spectral, spatial, and sample dimensions. The results demonstrated high accuracy, with coefficient of determination (R²) values exceeding 0.97 and low root mean square error (RMSE) across training, validation, and testing subsets. Spatial prediction maps generated at high resolution revealed realistic ecological and hydrological patterns consistent with known regional water quality dynamics in New Brunswick. Our contribution, accessible to users with MATLAB, lies in the development of a transparent, adaptable, and reproducible CNN framework tailored for multiparameter water quality estimation, which extends beyond traditional empirical, site-specific regression models by enabling non-invasive, cost-effective, and continuous monitoring from satellite platforms over a large, heterogeneous province-scale domain. Additionally, model interpretability was enhanced through SHapley Additive exPlanations (SHAP) analysis, which identified key spectral bands influencing predictions and provided ecological insights, offering guidance for future sensor design and data reduction strategies. This study addresses a significant research gap by providing a dual-parameter focused, end-to-end deep learning solution optimized for province-scale remote sensing data, facilitating more informed environmental management. This study can support water managers and agencies by providing province-wide DO and TOC maps derived from freely available Sentinel-2 imagery, reducing reliance on sparse field sampling alone and helping to identify areas of low oxygen or high organic carbon. Future work will extend this framework temporally and spatially and explore hybrid CNN architectures incorporating temporal dependencies for improved generalization and accuracy. Full article

Mycotoxin contamination of grains during storage and transportation represents a significant threat to global food security. Conventional detection methods exhibit limitations in terms of real-time monitoring. This study presents a compact smart gas sensing system for mycotoxins, facilitating non-destructive testing of corn infected with fungi by analyzing the volatile organic compounds (VOCs) emitted during fungal growth. It also facilitates the precise quantitative detection of Aflatoxin B₁ (AFB₁). Additionally, a dual-branch convolutional neural network (DB-CNN) model has been developed to conduct an in-depth analysis of the temporal and spatial characteristics of VOCs signals. The system achieves 100% accuracy in identifying grains (corn, peanuts, wheat, and rice) infected with Fusarium graminearum and Aspergillus flavus by extracting the characteristic fingerprint spectra of fungal VOCs. In the quantitative analysis, the DB-CNN exhibits good performance (RMSE = 1.0292 μg/kg, R² = 0.9994). In addition, the designed detection system supports wireless transmission and can be connected to a smartphone for data transfer, thereby facilitating data storage and remote monitoring. The entire detection process is completed within 4 min. This study provides an innovative technical foundation for dynamic real-time monitoring of fungal contamination in the food supply chain, contributing to early warning systems and quality control measures. Full article

In dynamic and complex real-world environments, artificial intelligence (AI) vision systems continue to face significant challenges in accurately detecting and tracking small objects. The core difficulty lies in the fact that small targets usually exhibit limited spatial and textural features, while dynamic backgrounds often generate numerous misleading motion cues, thereby interfering with reliable discrimination between targets and backgrounds. Inspired by the remarkable capability of the insect brain in detecting small moving objects, this study proposes a visual neural network model enhanced by a feedback mechanism. By adaptively responding to temporal variations, the proposed model is able to more precisely distinguish small targets from background-induced false targets. The network architecture consists of two main pathways: a motion detection pathway that extracts motion-related features from minute targets, and a feedback attention pathway that enhances the focus on true targets by leveraging the feature differences between real and false motion signals. In addition, a global inhibition module is incorporated to reduce the false alarm rate by filtering out background-induced false positives, thereby improving the overall detection performance of the model. Experimental results demonstrate that the proposed model achieves a detection rate of 0.81 in complex visual scenarios, whereas the compared models all achieve detection rates below 0.59, indicating a significant improvement in detection performance. Meanwhile, in terms of Precision and F1-score, the proposed model achieves values of 0.0648 and 0.12, respectively, while the compared models obtain values lower than 0.0077 and 0.015, further validating the superiority of the proposed method in detection accuracy and robustness. Full article

Autism classification is challenging due to the subtle, heterogeneous, and overlapping neural activation profiles that occur in individuals with autism. Novel deep learning approaches, such as Convolutional Neural Networks (CNNs) and their variants, as well as Transformers, have shown moderate performance in discriminating between autism and normal cohorts; yet, they often struggle to jointly capture the spatial–structural and temporal–functional variations present in autistic brains. To overcome these shortcomings, we propose a novel hierarchical deep learning framework that extracts the inherent spatial dependencies from the dual-modal MRI scans. For sMRI, we develop a 3D Hierarchical Convolutional Neural Network to capture both fine and coarse anatomical structures via multi-view projections along the axial, sagittal, and coronal planes. For the fMRI case, we introduced a bidirectional LSTM-based temporal encoder to examine regional brain dynamics and functional connectivity. The sequential embeddings and correlations are combined into a unified spatiotemporal representation of functional imaging, which is then classified using a multilayer perceptron to ensure continuity in diagnostic predictions across the examined modalities. Finally, a cross-modality fusion scheme was employed to integrate feature representations of both modalities. Extensive evaluations on the ABIDE I dataset (NYU repository) demonstrate that our proposed framework outperforms existing baselines, including Vision/Swin Transformers and various newly developed CNN variants. For the sMRI branch, we achieved 90.19 ± 0.12% accuracy (precision: 90.85 ± 0.16%, recall: 89.27 ± 0.19%, F1-score: 90.05 ± 0.14%, and focal loss: 0.3982). For the fMRI branch, we achieved an accuracy of 88.93 ± 0.15% (precision: 89.78 ± 0.18%, recall: 88.29 ± 0.20%, F1-score: 89.03 ± 0.17%, and focal loss of 0.4437). These outcomes affirm the superior generalization and robustness of the proposed framework for integrating structural and functional brain representations to achieve accurate autism classification. Full article

The artificial lateral line sensing principle provides a promising approach for underwater target perception and the navigation of underwater vehicles in complex flow environments. However, the highly nonlinear hydrodynamic mechanisms in complex flow fields make it difficult to establish accurate analytical models, which limits the development of high-precision perception and localization methods for underwater moving targets. In this study, a high-fidelity simulation model is established to characterize the pressure field variations induced by a moving source on an artificial lateral line pressure array. The influences of source velocity and sensing distance on the sensitivity and discretization characteristics of the pressure array are systematically investigated. Simulation results indicate that the sensor density of the pressure array is strongly correlated with the spatial resolution of the acquired pressure data, and a resolution of 50 sensors per meter is selected as the best-performing configuration by balancing sensing accuracy and sensor quantity. Under this configuration, the pressure distribution induced by the moving source exhibits clear and distinguishable spatiotemporal features, making it suitable for deep learning-based modeling. Furthermore, a large-scale temporal pressure dataset is constructed based on high-fidelity simulations under multiple motion directions and velocity conditions, and a spatiotemporal neural network is employed to predict the position of the underwater moving source. Experimental results demonstrate that, for straight-line underwater motion scenarios, the average localization error is within 7 cm, and a classification accuracy of 71% is achieved in practical engineering experiments. These results indicate that the proposed artificial lateral line pressure array design and deep learning-based prediction framework provide a feasible and effective solution for underwater target perception and localization in complex flow environments. Full article