Search Results (3,056)

Accurate prediction of soil properties is essential for sustainable land management and precision agriculture. This study presents an LSTM-CNN-Attention model that integrates temporal and spatial feature extraction with attention mechanisms to improve predictive accuracy. Utilizing the LUCAS soil dataset, the model analyzes spectral data to estimate key soil properties, including organic carbon (OC), nitrogen (N), calcium carbonate (CaCO₃), and pH (in H₂O). The Long Short-Term Memory (LSTM) component captures temporal dependencies, the Convolutional Neural Network (CNN) extracts spatial features, and the attention mechanism highlights critical information within the data. Experimental results show that the proposed model achieves excellent prediction performance, with coefficient of determination (R²) values of 0.949 (OC), 0.916 (N), 0.943 (CaCO₃), and 0.926 (pH), along with corresponding ratio of percent deviation (RPD) values of 3.940, 3.737, 5.377, and 3.352. Both R² and RPD values exceed those of traditional machine learning models, such as partial least squares regression (PLSR), support vector machine regression (SVR), and random forest (RF), as well as deep learning models like CNN-LSTM and Gated Recurrent Unit (GRU). Additionally, the proposed model outperforms S-AlexNet in effectively capturing temporal and spatial patterns. These findings emphasize the potential of the proposed model to significantly enhance the accuracy and reliability of soil property predictions by capturing both temporal and spatial patterns effectively. Full article

Software reliability is a crucial factor in determining software quality quantitatively. It is also used to estimate the software testing duration. In software reliability testing, traditional parametric software reliability growth models (SRGMs) are effectively used. Nevertheless, a single parametric model cannot provide accurate predictions in all cases. Moreover, non-parametric models have proven to be efficient for predicting software reliability as alternatives to parametric models. In this paper, we adopted a deep learning method for software reliability testing in computer vision systems. Also, we focused on critical computer vision applications that need high reliability. We propose a new deep learning-based model that is combined and based on the ensemble method to improve the performance of software reliability testing. The experimental results of the new model architecture present fairly accurate predictive capability compared to other existing single Neural Network (NN) based models. Full article

In this article, we examine whether incorporating complexity measures as features in deep learning (DL) algorithms enhances their accuracy in predicting forex market volatility. Our approach involved the gradual integration of complexity measures alongside traditional features to determine whether their inclusion would provide additional information that improved the model’s predictive accuracy. For our analyses, we employed recurrent neural networks (RNNs), long short-term memory (LSTM), and gated recurrent units (GRUs) as DL model architectures, while using the Hurst exponent and fuzzy entropy as complexity measures. All analyses were conducted on intraday data from four highly liquid currency pairs, with volatility estimated using the Range-Based estimator. Our findings indicated that the inclusion of complexity measures as features significantly enhanced the accuracy of DL models in predicting volatility. In achieving this, we contribute to a relatively unexplored area of research, as this is the first instance of such an approach being applied to the prediction of forex market volatility. Additionally, we conducted a comparative analysis of the three models’ performance, revealing that the LSTM and GRU models consistently demonstrated a superior accuracy. Finally, our findings also have practical implications, as they may assist risk managers and policymakers in forecasting volatility in the forex market. Full article

Rolling bearings are vital components in rotating machinery, and their reliable operation is crucial for maintaining the stability and efficiency of mechanical systems. However, fault detection in rolling bearings is often hindered by noise interference in complex industrial environments. To overcome this challenge, this paper presents a novel fault diagnosis method for rolling bearings, combining Convolutional Neural Networks (CNNs) and Gated Recurrent Units (GRUs), integrated with the envelope analysis and adaptive mean filtering techniques. Initially, envelope analysis and adaptive mean filtering are applied to suppress random noise in the bearing signals, thereby enhancing the visibility of fault features. Subsequently, a deep learning model that combines a CNN and a GRU is developed: the CNN extracts spatial features, while the GRU captures the temporal dependencies between these features. The integration of the CNN and GRU significantly improves the accuracy and robustness of fault diagnosis. The proposed method is validated using the CWRU dataset, with the experimental results achieving an average accuracy of 99.25%. Additionally, the method is compared to four classical fault diagnosis models, demonstrating superior performance in terms of both diagnostic accuracy and generalization ability. The results, supported by various visualization techniques, show that the proposed approach effectively addresses the challenges of fault detection in rolling bearings under complex industrial conditions. Full article

Efficient management of hospital evacuations and pharmaceutical supply chains is a critical challenge in modern healthcare, particularly during emergencies. This study addresses these challenges by proposing a novel bi-objective optimization framework. The model integrates a Mixed-Integer Linear Programming (MILP) approach with advanced machine learning techniques to simultaneously minimize total costs and maximize patient satisfaction. A key contribution is the incorporation of a Gated Recurrent Unit (GRU) neural network for accurate drug demand forecasting, enabling dynamic resource allocation in crisis scenarios. The model also accounts for two distinct patient destinations—receiving hospitals and temporary care centers (TCCs)—and includes a specialized pharmaceutical supply chain to prevent medicine shortages. To enhance system robustness, probabilistic demand patterns and disruption risks are considered, ensuring supply chain reliability. The solution methodology combines the Grasshopper Optimization Algorithm (GOA) and the ɛ-constraint method, efficiently addressing the multi-objective nature of the problem. Results demonstrate significant improvements in cost reduction, resource allocation, and service levels, highlighting the model’s practical applicability in real-world scenarios. This research provides valuable insights for optimizing healthcare logistics during critical events, contributing to both operational efficiency and patient welfare. Full article

Coastal litter is a severe environmental issue impacting marine ecosystems and coastal communities in Thailand, with plastic pollution posing one of the most urgent challenges. Every month, millions of tons of plastic waste enter the ocean, where items such as bottles, cans, and other plastics can take hundreds of years to degrade, threatening marine life through ingestion, entanglement, and habitat destruction. To address this issue, we deploy drones equipped with high-resolution cameras and sensors to capture detailed coastal imagery for assessing litter distribution. This study presents the development of an AI-driven coastal litter detection system using edge computing and 5G communication networks. The AI edge server utilizes YOLOv8 and a recurrent neural network (RNN) to enable the drone to detect and classify various types of litter, such as bottles, cans, and plastics, in real-time. High-speed 5G communication supports seamless data transmission, allowing efficient monitoring. We evaluated drone performance under optimal flying heights above ground of 5 m, 7 m, and 10 m, analyzing accuracy, precision, recall, and F1-score. Results indicate that the system achieves optimal detection at an altitude of 5 m with a ground sampling distance (GSD) of 0.98 cm/pixel, yielding an F1-score of 98% for cans, 96% for plastics, and 95% for bottles. This approach facilitates real-time monitoring of coastal areas, contributing to marine ecosystem conservation and environmental sustainability. Full article

Interval prediction is to predict the range of power prediction intervals, which can guide electricity production and usage better. To improve further improve the performance of the prediction interval, this paper aims to investigate he wind power interval prediction method based on the lower and upper bound evaluation (LUBE). Firstly, an improved loss function is proposed, which transforms multi-objective optimization problems into single-objective optimization with guidance of mathematical derivation. Afterward, the interval prediction results can be further improved through a combination of graph convolutional network (GCN) and gate recurrent unit (GRU). Then, the tree-structured Parzen estimator (TPE) optimization algorithm optimizes the GCN cell to find the optimal parameter configuration and maximize the performance of the model. Finally, in the experimental part, the proposed GCN-GRU with improved loss function is compared with some current mainstream neural networks. The results show that for any type of network, the improved loss function can obtain prediction intervals with better performance. Especially for the prediction interval based on GCN-GRU, the prediction interval normalized average width (PINAW) and prediction interval relative deviation (PIRD) can reach 6.75% and 46.99%, respectively, while ensuring the given prediction interval nominal confidence (PINC). Full article

Lightning is a hazardous weather phenomenon, characterized by sudden occurrences and complex local distributions. It poses significant challenges for accurate forecasting, which is crucial for public safety and economic stability. Deep learning methods are often better than traditional numerical weather prediction (NWP) models at capturing the spatiotemporal predictors of lightning events. However, these methods struggle to integrate predictors from diverse data sources, which leads to lower accuracy and interpretability. To address these challenges, the Multi-Scale Spatial–Channel-Enhanced Recurrent Convolutional Neural Network (SCE-RCNN) is proposed to improve forecasting accuracy and timeliness by utilizing multi-source data and enhanced attention mechanisms. The proposed model incorporates a multi-scale spatial–channel attention module and a cross-scale fusion module, which facilitates the integration of data from diverse sources. The multi-scale spatial–channel attention module utilizes a multi-scale convolutional network to extract spatial features at different spatial scales and employs a spatial–channel attention mechanism to focus on the most relevant regions for lightning prediction. Experimental results show that the SCE-RCNN model achieved a critical success index (CSI) of 0.83, a probability of detection (POD) of 0.991, and a false alarm rate (FAR) reduced to 0.351, outperforming conventional deep learning models across multiple prediction metrics. This research provides reliable lightning forecasts to support real-time decision-making, making significant contributions to aviation safety, outdoor event planning, and disaster risk management. The model’s high accuracy and low false alarm rate highlight its value in both academic research and practical applications. Full article

Red-light running at signalised intersections poses a significant safety risk, necessitating advanced predictive technologies to predict red-light violation behaviour, especially for advanced red-light warning (ARLW) systems. This research leverages Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models to forecast the red-light running and stopping behaviours of drivers in connected vehicles. We utilised data from the Ipswich Connected Vehicle Pilot (ICVP) in Queensland, Australia, which gathered naturalistic driving data from 355 connected vehicles at 29 signalised intersections. These vehicles broadcast Cooperative Awareness Messages (CAM) within the Cooperative Intelligent Transport Systems (C-ITS), providing kinematic inputs such as vehicle speed, speed limits, longitudinal and lateral accelerations, and yaw rate. These variables were monitored at 100-millisecond intervals for durations from 1 to 4 s before reaching various distances from the stop line. Our results indicate that the LSTM model outperforms the GRU in predicting both red-light running and stopping behaviours with high accuracy. However, the pre-trained GRU model performs better in predicting red-light running specifically, making it valuable in applications requiring early violation prediction. Implementing these models can enhance red-light violation countermeasures, such as dynamic all-red extension (DARE), decreasing the likelihood of severe collisions and enhancing road users’ safety. Full article

In order for cognitive radios to identify and take advantage of unused frequency bands, spectrum sensing is essential. Conventional techniques for spectrum sensing rely on extracting features from received signals at specific locations. However, convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have recently demonstrated promise in improving the precision and efficacy of spectrum sensing. Our research introduces a groundbreaking approach to spectrum sensing by leveraging convolutional neural networks (CNNs) to significantly advance the precision and effectiveness of identifying unused frequency bands. We treat spectrum sensing as a classification task and train our model with diverse signal types and noise data, enabling unparalleled adaptability to novel signals. Our method surpasses traditional techniques such as the maximum–minimum eigenvalue ratio-based and frequency domain entropy-based methods, showcasing superior performance and adaptability. In particular, our CNN-based approach demonstrates exceptional accuracy, even outperforming established methods when faced with additive white Gaussian noise (AWGN). Full article

Vibration is a major problem that can cause structures to wear out prematurely and even fail. Smart structures are a promising solution to this problem because they can be equipped with actuators, sensors, and controllers to reduce or eliminate vibration. The primary objective of this paper is to explore and compare two deep learning-based approaches for vibration control in cantilever beams. The first approach involves the direct application of deep learning techniques, specifically multi-layer neural networks and RNNs, to control the beam’s dynamic behavior. The second approach integrates deep learning into the tuning process of a PID controller, optimizing its parameters for improved control performance. To activate the structure, two different input signals are used, an impulse signal at time zero and a random one. Through this comparative analysis, the paper aims to evaluate the effectiveness, strengths, and limitations of each method, offering insights into their potential applications in the field of smart structure control. Full article

This paper presents a varying-parameter finite-time recurrent neural network, called a varying-factor finite-time recurrent neural network (VFFTRNN), which is able to solve the solution of the time-varying Sylvester equation online. The proposed neural network makes the matrix coefficients vary with time and can achieve convergence in a finite time. Apart from this, the performance of the network is better than traditional networks in terms of robustness. It is theoretically proved that the proposed neural network has super-exponential convergence performance. Simulation results demonstrate that this neural network has faster convergence speed and better robustness than the return to zero neural networks and can track the theoretical solution of the time-varying Sylvester equation effectively. Full article

Anxiety is a widespread mental health issue, and binaural beats have been explored as a potential non-invasive treatment. EEG data reveal changes in neural oscillation and connectivity linked to anxiety reduction; however, harmonics introduced during signal acquisition and processing often distort these findings. Existing methods struggle to effectively reduce harmonics and capture the fine-grained temporal dynamics of EEG signals, leading to inaccurate feature extraction. Hence, a novel Denoised Harmonic Subtraction and Transient Temporal Feature Extraction is proposed to improve the analysis of the impact of binaural beats on anxiety levels. Initially, a novel Wiener Fused Convo Filter is introduced to capture spatial features and eliminate linear noise in EEG signals. Next, an Intrinsic Harmonic Subtraction Network is employed, utilizing the Attentive Weighted Least Mean Square (AW-LMS) algorithm to capture nonlinear summation and resonant coupling effects, effectively eliminating the misinterpretation of brain rhythms. To address the challenge of fine-grained temporal dynamics, an Embedded Transfo XL Recurrent Network is introduced to detect and extract relevant parameters associated with transient events in EEG data. Finally, EEG data undergo harmonic reduction and temporal feature extraction before classification with a cross-correlated Markov Deep Q-Network (DQN). This facilitates anxiety level classification into normal, mild, moderate, and severe categories. The model demonstrated a high accuracy of 95.6%, precision of 90%, sensitivity of 93.2%, and specificity of 96% in classifying anxiety levels, outperforming previous models. This integrated approach enhances EEG signal processing, enabling reliable anxiety classification and offering valuable insights for therapeutic interventions. Full article

The dissolved oxygen (DO) content is one of the important water quality parameters; it is crucial for assessing water body quality and ensuring the healthy growth of aquatic organisms. To enhance the prediction accuracy of DO in aquaculture, we propose a fused neural network model integrating a convolutional neural network (CNN) and a gated recurrent unit (GRU). This model initially employs a CNN to extract primary features from water quality parameters. Subsequently, the GRU captures temporal information and long-term dependencies, while a temporal attention mechanism (TAM) is introduced to further pinpoint crucial information. By optimizing model parameters through an improved particle swarm optimization (IPSO) algorithm, we develop a comprehensive IPSO-CNN-GRU-TAM prediction model. Experiments conducted using water quality datasets collected from Eagle Mountain Lake demonstrate that our model achieves a root mean square error (RMSE) of 0.0249 and a coefficient of determination (R²) of 0.9682, outperforming other prediction models with high precision. The model exhibits stable performance across fivefold cross-validation and datasets of varying depths, showcasing robust generalization capabilities. In summary, this model allows aquaculturists to precisely regulate the DO content, ensuring fish health and growth while achieving energy conservation and carbon reduction, aligning with the practical demands of modern aquaculture. Full article

Advancements in 3D modelling technology have facilitated more immersive and efficient solutions in spatial planning and user-centred design. In healthcare systems, 3D modelling is beneficial in various applications, such as emergency evacuation, pathfinding, and localization. These models support the fast and efficient planning of evacuation routes, ensuring the safety of patients, staff, and visitors, and guiding them in cases of emergency. To improve urban modelling and planning, 3D representation and analysis are used. Considering the advantages of 3D modelling, this study proposes a framework for 3D indoor navigation and employs a multiphase methodology to enhance spatial planning and user experience. Our approach combines state-of-the art GIS technology with a 3D hybrid model. The proposed framework incorporates federated learning (FL) along with edge computing and Internet of Things (IoT) devices to achieve accurate floor-level localization and navigation. In the first phase of the methodology, Quantum Geographic Information System (QGIS) software was used to create a 3D model of the building’s architectural details, which are required for efficient indoor navigation during emergency evacuations in healthcare systems. In the second phase, the 3D model and an FL-based recurrent neural network (RNN) technique were utilized to achieve real-time indoor positioning. This method resulted in highly precise outcomes, attaining an accuracy rate over 99% at distances of no less than 10 metres. Continuous monitoring and effective pathfinding ensure that users can navigate safely and effectively during emergencies. IoT devices were connected with the building’s navigation software in Phase 3. As per the performed analysis, it was observed that the proposed framework provided 98.7% routing accuracy between different locations during emergency situations. By improving safety, building accessibility, and energy efficiency, this research addresses the health and environmental impacts of modern technologies. Full article