Search Results (12,625)

Monitoring sediment concentration in water bodies is crucial for assessing water quality, ecosystems, and environmental health. However, physical sampling and sensor-based approaches are labor-intensive and unsuitable for large-scale, continuous monitoring. This study employs machine learning models to estimate suspended sediment concentration using images captured in natural light, named RGB, and near-infrared (NIR) conditions. A controlled dataset of approximately 1300 images with SSC values ranging from 1000 mg/L to 150,000 mg/L was developed, incorporating temperature, time of image capture, and solar irradiance as additional features. Random forest regression and gradient boosting regression were trained on mean RGB values, red reflectance, time of captured, and temperature for natural light images, achieving up to 72.96% accuracy within a 30% relative error. In contrast, NIR images leveraged gray-level co-occurrence matrix texture features and temperature, reaching 83.08% accuracy. Comparative analysis showed that ensemble models outperformed deep learning models like Convolutional Neural Networks and Multi-Layer Perceptrons, which struggled with high-dimensional feature extraction. These findings suggest that using machine learning models and RGB and NIR imagery offers a scalable, non-invasive, and cost-effective way of sediment monitoring in support of water quality assessment and environmental management. Full article

Quantum machine learning (QML) has emerged as a promising approach for enhancing image classification by exploiting quantum computational principles such as superposition and entanglement. However, practical applications on complex datasets like CIFAR-100 remain limited due to the low expressivity of shallow circuits and challenges in circuit optimization. In this study, we propose HQCNN–REGA—a novel hybrid quantum–classical convolutional neural network architecture that integrates data re-uploading and genetic algorithm optimization for improved performance. The data re-uploading mechanism allows classical inputs to be encoded multiple times into quantum states, enhancing the model’s capacity to learn complex visual features. In parallel, a genetic algorithm is employed to evolve the quantum circuit architecture by optimizing gate sequences, entanglement patterns, and layer configurations. This combination enables automatic discovery of efficient parameterized quantum circuits without manual tuning. Experiments on the MNIST and CIFAR-100 datasets demonstrate state-of-the-art performance for quantum models, with HQCNN–REGA outperforming existing quantum neural networks and approaching the accuracy of advanced classical architectures. In particular, we compare our model with classical convolutional baselines such as ResNet-18 to validate its effectiveness in real-world image classification tasks. Our results demonstrate the feasibility of scalable, high-performing quantum–classical systems and offer a viable path toward practical deployment of QML in computer vision applications, especially on noisy intermediate-scale quantum (NISQ) hardware. Full article

Neural networks (NNs) achieve breakthroughs in computer vision and natural language processing,yet their “black box” nature persists. Traditional methods prioritise parameter optimisation and loss design, overlooking NNs’ fundamental structure as topologically organised nonlinear computational systems. This work proposes a complex network theory framework decoding structure–function coupling by mapping convolutional layers, fully connected layers, and Dropout modules into graph representations. To overcome limitations of heuristic compression techniques, we develop a topology-sensitive adaptive pruning algorithm that evaluates critical paths via node strength centrality, preserving structural–functional integrity. On CIFAR-10, our method achieves 55.5% parameter reduction with only 7.8% accuracy degradation—significantly outperforming traditional approaches. Crucially, retrained pruned networks exceed original model accuracy by up to 2.63%, demonstrating that topology optimisation unlocks latent model potential. This research establishes a paradigm shift from empirical to topologically rationalised neural architecture design, providing theoretical foundations for deep learning optimisation dynamics. Full article

The cross-sectional dimensions of structural elements in a structure are design elements that need to be carefully designed and are related to the stiffness of the structure. Various optimization processes are applied to determine the optimum cross-sectional dimensions of beams or columns in structures. By repeating the optimization processes for multiple load scenarios, it is possible to create a data set that shows the optimum design section properties. However, this step means repeating the same processes to produce the optimum cross-sectional dimensions. Artificial intelligence technology offers a short-cut solution to this by providing the opportunity to train itself with previously generated optimum cross-sectional dimensions and infer new cross-sectional dimensions. By processing the data, the artificial neural network can generate models that predict the cross-section for a new structural element. In this study, an optimization process is applied to a simple tubular column and an I-section beam, and the results are compiled to create a data set that presents the optimum section dimensions as a class. The harmony search (HS) algorithm, which is a metaheuristic method, was used in optimization. An artificial neural network (ANN) was created to predict the cross-sectional dimensions of the sample structural elements. The neural architecture search (NAS) method, which incorporates many metaheuristic algorithms designed to search for the best artificial neural network architecture, was applied. In this method, the best values of various parameters of the neural network, such as activation function, number of layers, and neurons, are searched for in the model with a tool called HyperNetExplorer. Model metrics were calculated to evaluate the prediction success of the developed model. An effective neural network architecture for column and beam elements is obtained. Full article

Deep neural network (DNN) hardware (HW) accelerators have achieved great success in improving DNNs’ performance and efficiency. One key reason is the dataflow in executing a DNN layer, including on-chip data partitioning, computation parallelism, and scheduling policy, which have large impacts on latency and energy consumption. Unlike prior works that required considerable efforts from HW engineers to design suitable dataflows for different DNNs, this work proposes an efficient data-centric approach, named Dataflow Code Propagation (DCP), to automatically find the optimal dataflow for DNN layers in seconds without human effort. It has several attractive benefits that prior studies lack, including the following: (i) We translate the HW dataflow configuration into a code representation in a unified dataflow coding space, which can be optimized by back-propagating gradients given a DNN layer or network. (ii) DCP learns a neural predictor to efficiently update the dataflow codes towards the desired gradient directions to minimize various optimization objectives, e.g., latency and energy. (iii) It can be easily generalized to unseen HW configurations in a zero-shot or few-shot learning manner. For example, without using additional training data, Extensive experiments on several representative models such as MobileNet, ResNet, and ViT show that DCP outperforms its counterparts in various settings. Full article

Porous materials are characterized by the pore surface area (S) and volume (V) accessible to a confined fluid. For mesoporous materials NMR measurements of diffusion are used to assess the S/V ratio, because at short times, only the diffusivity of molecules in the adsorbed layer is affected by confinement and the fractional population of these molecules is proportional to the S/V ratio. For materials with sub-nanometer pores, this might not be true, as the adsorbed layer can encompass the entire pore volume. Here, using molecular simulations, we explore the role played by S and S/V in determining the dynamical behavior of two carbon-bearing fluids—CO₂ and ethane—confined in sub-nanometer pores of silica. S and V in a silicalite model representing a sub-nanometer porous material are varied by selectively blocking a part of the pore network by immobile methane molecules. Three classes of adsorbents were thus obtained with either all of the straight (labeled ‘S-major’) or zigzag channels (‘Z-major’) remaining open or a mix of a fraction of both types of channel blocked, resulting in half of the total pore volume being blocked (‘Half’). While the adsorption layers from opposite surfaces overlap, encompassing the entire pore volume for all pores except the intersections, the diffusion coefficient is still found to be reduced at high S/V, especially for CO₂, albeit not so strongly as would be expected in the case of wider pores. This is because of the presence of channel intersections that provide a wider pore space with non-overlapping adsorption layers. Full article

Landslides are among the most hazardous natural phenomena affecting Greater Abidjan, causing significant economic and social damage. Strategic planning supported by geographic information systems (GIS) can help mitigate potential losses and enhance disaster resilience. This study evaluates landslide susceptibility using logistic regression and frequency ratio models. The analysis is based on a dataset comprising 54 mapped landslide scarps collected from June 2015 to July 2023, along with 16 thematic predictor variables, including altitude, slope, aspect, profile curvature, plan curvature, drainage area, distance to the drainage network, normalized difference vegetation index (NDVI), and an urban-related layer. A high-resolution (5-m) digital elevation model (DEM), derived from multiple data sources, supports the spatial analysis. The landslide inventory was randomly divided into two subsets: 80% for model calibration and 20% for validation. After optimization and statistical testing, the selected thematic layers were integrated to produce a susceptibility map. The results indicate that 6.3% (0.7 km²) of the study area is classified as very highly susceptible. The proportion of the sample (61.2%) in this class had a frequency ratio estimated to be 20.2. Among the predictive indicators, altitude, slope, SE, S, NW, and NDVI were found to have a positive impact on landslide occurrence. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), demonstrating strong predictive capability. These findings can support informed land-use planning and risk reduction strategies in urban areas. Furthermore, the prediction model should be communicated to and understood by local authorities to facilitate disaster management. The cost function was adopted as a novel approach to delineate hazardous zones. Considering the landslide inventory period, the increasing hazard due to climate change, and the intensification of human activities, a reasoned choice of sample size was made. This informed decision enabled the production of an updated prediction map. Optimal thresholds were then derived to classify areas into high- and low-susceptibility categories. The prediction map will be useful to planners in helping them make decisions and implement protective measures. Full article

Monitoring pH and acidity during yoghurt fermentation is essential for product quality and process efficiency. Conventional measurement methods, however, are invasive and labour-intensive. This study developed artificial neural network (ANN) models to predict pH and titratable acidity during yoghurt fermentation using CIELAB colour parameters (L, a*, b*). Reconstituted milk powder with 12% total solids was prepared with varying protein levels (4.2–4.8%), inoculum concentrations (1–3%), and fermentation temperatures (36–44 °C). Data were collected every 10 min until pH 4.6 was reached. Forty models were trained for each output variable, using 90% of the data for training and 10% for validation. The first two phases of the fermentation process were clearly distinguishable, lasting between 4.5 and 7 h and exceeding 0.6% lactic acid in all treatments evaluated. The best pH model used two hidden layers with 28 neurons (R² = 0.969; RMSE = 0.007), while the optimal acidity model had four hidden layers with 32 neurons (R² = 0.868; RMSE = 0.002). The strong correlation between colour and physicochemical changes confirms the feasibility of this non-destructive approach. Integrating ANN models and colourimetry offers a practical solution for real-time monitoring, helping improve process control in industrial yoghurt production. Full article

Background: Faced with the profound impact of major infectious diseases on public life and economic development, humans have long sought to understand disease transmission and intervention strategies. To better explore the impact of individuals’ different coping behaviors—triggered by changes in their psychological security due to public information and external environmental changes—on the spread to infectious diseases, the model will place greater emphasis on quantifying psychological factors to make it more aligned with real-world situations. Methods: To better understand the interplay between information dissemination and disease transmission, we propose a two-layer network model that incorporates psychological safety factors. Results: Our model reveals key insights into disease transmission dynamics: (1) active defense behaviors help reduce both disease spread and information diffusion; (2) passive resistance behaviors expand disease transmission and may trigger recurrence but enhance information spread; (3) high-timeliness, low-fuzziness information reduces the peak of the initial infection but does not significantly curb overall disease spread, and the rapid dissemination of disease-related information is most effective in limiting the early stages of transmission; and (4) community structures in information networks can effectively curb the spread of infectious diseases. Conclusions: These findings offer valuable theoretical support for public health strategies and disease prevention after government information release. Full article

In the era of smart agriculture, accurate identification of plant species is critical for effective crop management, biodiversity monitoring, and the sustainable use of medicinal resources. However, existing deep learning approaches often underperform when applied to fine-grained plant classification tasks due to the lack of domain-specific, high-quality datasets and the limited representational capacity of traditional architectures. This study addresses these challenges by introducing a novel, well-curated leaf image dataset consisting of 39 classes of medicinal and aromatic plants collected from the Aromatic and Medicinal Plant Research Station in Odakkali, Kerala, India. To overcome performance bottlenecks observed with a baseline Convolutional Neural Network (CNN) that achieved only 44.94% accuracy, we progressively enhanced model performance through a series of architectural innovations. These included the use of a pre-trained VGG16 network, data augmentation techniques, and fine-tuning of deeper convolutional layers, followed by the integration of Squeeze-and-Excitation (SE) attention blocks. Ultimately, we propose a hybrid deep learning architecture that combines VGG16 with Batch Normalization, Gated Recurrent Units (GRUs), Transformer modules, and Dilated Convolutions. This final model achieved a peak validation accuracy of 95.24%, significantly outperforming several baseline models, such as custom CNN (44.94%), VGG-19 (59.49%), VGG-16 before augmentation (71.52%), Xception (85.44%), Inception v3 (87.97%), VGG-16 after data augumentation (89.24%), VGG-16 after fine-tuning (90.51%), MobileNetV2 (93.67), and VGG16 with SE block (94.94%). These results demonstrate superior capability in capturing both local textures and global morphological features. The proposed solution not only advances the state of the art in plant classification but also contributes a valuable dataset to the research community. Its real-world applicability spans field-based plant identification, biodiversity conservation, and precision agriculture, offering a scalable tool for automated plant recognition in complex ecological and agricultural environments. Full article

Unmanned Aerial Vehicles (UAVs) face significant challenges in global path planning within complex terrains, as traditional algorithms (e.g., A*, PSO, APF) struggle to balance computational efficiency, path optimality, and safety. This study proposes a Voronoi–A* fusion algorithm, combining Voronoi-vertex-based rapid trajectory generation with A* supplementary expansion for enhanced performance. First, an adaptive DEM layering strategy divides the terrain into horizontal planes based on obstacle density, reducing computational complexity while preserving 3D flexibility. The Voronoi vertices within each layer serve as a sparse waypoint network, with greedy heuristic prioritizing vertices that ensure safety margins, directional coherence, and goal proximity. For unresolved segments, A* performs localized searches to ensure complete connectivity. Finally, a line-segment interpolation search further optimizes the path to minimize both length and turning maneuvers. Simulations in mountainous environments demonstrate superior performance over traditional methods in terms of path planning success rates, path optimality, and computation. Our framework excels in real-time scenarios, such as disaster rescue and logistics, although it assumes static environments and trades slight path elongation for robustness. Future research should integrate dynamic obstacle avoidance and weather impact analysis to enhance adaptability in real-world conditions. Full article

This paper presents a flight control framework based on neural network Model Predictive Control (NN-MPC) to tackle the challenges of acceleration command tracking for supersonic vehicles (SVs) in complex flight environments, addressing the shortcomings of traditional methods in managing nonlinearity, random disturbances, and real-time performance requirements. Initially, a dynamic model is developed through a comprehensive analysis of the vehicle’s dynamic characteristics, incorporating strong cross-coupling effects and disturbance influences. Subsequently, a predictive mechanism is employed to forecast future states and generate virtual control commands, effectively resolving the issue of sluggish responses under rapidly changing commands. Furthermore, the approximation capability of neural networks is leveraged to optimize the control strategy in real time, ensuring that rudder deflection commands adapt to disturbance variations, thus overcoming the robustness limitations inherent in fixed-parameter control approaches. Within the proposed framework, the ultimate uniform bounded stability of the control system is rigorously established using the Lyapunov method. Simulation results demonstrate that the method exhibits exceptional performance under conditions of system state uncertainty and unknown external disturbances, confirming its effectiveness and reliability. Full article

The aim of this paper is to tailor the geometry and material parameters of a three-layer railway track model to achieve favorable properties for the circulation of high-speed trains at very high velocities. The three layers imply that the model should have three critical velocities for resonance. However, in many cases, some of these values are missing and must be replaced by pseudo-critical values. Since no resonance occurs at pseudo-critical velocities, even in the absence of damping, deflections never reach infinity. By using optimization techniques, it is possible to adjust the model’s parameters, so that the increase in vibrations remains minimal and does not pose a real danger. In this way, circulation velocities could be extended beyond the critical value, thereby increasing the network capacity and, consequently, improving the competitiveness of rail transport compared to other modes of transportation, thus contributing to decarbonization. The presented results are preliminary and require further analysis and validation. Several optimization techniques are implemented, leading to the establishment of designs that already have rather high pseudo-critical velocities. Further research will show how these theoretical findings can be utilized in practice.  Full article

Currently, the primary random access protocol for satellite communications is Irregular Repetition Slotted ALOHA (IRSA). This protocol leverages interference cancellation and burst repetition based on probabilistic distributions, achieving up to 80% channel utilization in practical use. However, it faces three significant issues: (1) low channel utilization with smaller frame sizes; (2) drastic performance degradation under heavy load, where channel utilization can be lower than that of traditional Slotted ALOHA; and (3) even under optimal load and frame sizes, up to 20% of the valuable satellite channel resources are still wasted despite reaching up to 80% channel utilization. In this paper, we propose the Separated Transmission and Control ALOHA (STCA) protocol, which introduces a space–air–ground layered network and separates the access control process from the satellite to an airborne platform, thus preventing collisions in satellite channels. Additionally, the airborne-platform estimates the load to ensure maximum access rates. Simulation results demonstrate that the STCA protocol significantly outperforms the IRSA protocol in terms of channel utilization. Full article

Cement-based batteries (CBBs) are an emerging category of multifunctional materials that combine structural load-bearing capacity with integrated electrochemical energy storage, enabling the development of self-powered infrastructure. Although previous reviews have explored selected aspects of CBB technology, a comprehensive synthesis encompassing system architectures, material strategies, and performance metrics remains insufficient. In this review, CBB systems are categorized into two representative configurations: probe-type galvanic cells and layered monolithic structures. Their structural characteristics and electrochemical behaviors are critically compared. Strategies to enhance performance include improving ionic conductivity through alkaline pore solutions, facilitating electron transport using carbon-based conductive networks, and incorporating redox-active materials such as zinc–manganese dioxide and nickel–iron couples. Early CBB prototypes demonstrated limited energy densities due to high internal resistance and inefficient utilization of active components. Recent advancements in electrode architecture, including nickel-coated carbon fiber meshes and three-dimensional nickel foam scaffolds, have achieved stable rechargeability across multiple cycles with energy densities surpassing 11 Wh/m². These findings demonstrate the practical potential of CBBs for both energy storage and additional functionalities, such as strain sensing enabled by conductive cement matrices. This review establishes a critical basis for future development of CBBs as multifunctional structural components in infrastructure applications. Full article