alexandria engineering journal最新文献

With the growing popularity of fitness, the demand for real-time action recognition and feedback is increasing. Current research faces challenges in handling complex actions, real-time processing, and system integration. To address these issues, we propose a novel fitness action recognition model that integrates ResNet, Transformer, and transfer learning techniques. Specifically, ResNet is used for image feature extraction, Transformer handles time-series data processing, and transfer learning accelerates the model’s adaptation to new data. We evaluated our model on the NTU RGB+D action recognition dataset, achieving 48.5 ms latency, 29.1 fps throughput, and 93.7% accuracy, significantly outperforming other models. Our model achieved an accuracy improvement of 5% over existing methods, demonstrating significant potential for real-time fitness monitoring. By incorporating IoT technology, our system enables real-time data processing and action recognition, making it ideal for smart fitness monitoring. Although the model has high complexity and memory usage, its efficiency and accuracy demonstrate its potential for widespread adoption. Future work will focus on optimizing the model structure and training methods to enhance applicability in resource-constrained environments, ensuring broader usability and efficiency in various real-world applications.

Human pose estimation in sports training is a critical application within Internet of Things (IoT) environments, leveraging IoT devices to enhance performance analysis and injury prevention. Current methods struggle with real-time processing and accuracy in dynamic settings, especially with high-speed movements and diverse data. To address these challenges, we propose a novel dual-channel architecture combining Spatiotemporal Transformer and Temporal Convolutional Network (TCN), integrated into an IoT system. Our model collects real-time motion data through IoT devices, including videos, depth information, and sensor data, combining global spatiotemporal features with local temporal dependencies to enhance pose understanding and estimation accuracy. The Spatiotemporal Transformer uses multi-head self-attention to process global features, while the TCN captures local temporal dependencies across frames. A residual fusion mechanism integrates these features for comprehensive pose estimation. Extensive experiments on the Human3.6M and MPI-INF-3DHP datasets demonstrate that our model significantly outperforms existing methods, achieving Mean Per Joint Position Error (MPJPE) scores of 42.2 mm and 29.1 mm on Human3.6M. This research advances 3D human pose estimation and offers a practical tool for sports training through precise, efficient pose analysis, leveraging deep learning and IoT technologies to enhance athletic performance and prevent injuries.

In most practical applications, the feature space of the training datasets and the target domain datasets are inconsistent, or the data distribution between them is inconsistent, which leads to the problem of data starvation and makes it difficult for terminal devices to obtain high accurate results. Aiming at the problems of limited terminal device resources, low accuracy of data processing results, and unsatisfactory processing speed, a Heterogeneous Multi-access Edge Computing (MEC) Framework based on Transfer Learning (TL) is proposed, abbreviated as HMECF-TL. This framework adopts a cloud-edge-end three-layer architecture. It uses model transfer to optimize the Convolutional Neural Networks (CNN) model at each layer to achieve the goal of improving data processing speed and accuracy. Furthermore, a multi-agent Deep Reinforcement Learning Algorithm having Attention Mechanism (DRLAAM) is designed to further increase the timeliness performance of computation-intensive applications. The performance of HMECSF-TL framework is verified by simulation experiments, which not only reduces the delay by more than 24.66 %, but also improves the accuracy by more than 8.34 %. The framework not only increase the computing capacity to solve the shortage of terminal device resources, but also improve the quality of data processing to solve the problem of data starvation.

Present paper discusses the simulation of three desalination plants when linked to a nuclear power plant. The study assesses the various desalination techniques that can be employed in low carbon emissions power plants from a thermo-economic standpoint. Moreover, it draws a comparison between five different desalination systems including RO, MED, MSF, MED + RO and MSF + RO that are connected to a nuclear power plant. Via simulation, it became clear that using RO technology to produce fresh water is economically more advantageous than thermal methods. In addition, it is found that the overall water cost of various hybrid desalination technologies of MED + RO is significantly lower than those of MSF + RO desalination plants by 0.36 $/m³. The results show that supplying the desalination plant with warm water is more efficient than the direct use of sea water. The process of using warm water saves 0.01 $/m³ in case of using MED + RO and 0.02 $/m³ in case of using MSF + RO. Furthermore, the results show a significant reduction in CO₂ emissions by 0.771 kg/kWh when nuclear power plants are used in place of conventional power plants that use oil fuel.

With the increasing frequency of extreme weather events, heavy rainfall and flooding pose significant pressure on the flood discharge systems of tailings dams. Simple discharge systems are insufficient to meet the flood discharge requirements of tailings dams, while complex discharge systems, with their greater flood discharge capacity, are gradually being promoted. Although complex discharge systems can increase the flood discharge capacity of tailings dams, the flow patterns within the discharge systems become more complex. As a new type of discharge system layout, existing research lacks systematic analysis, and its complex flow characteristics are not clear. This paper relies on the flood discharge system of a large tailings dam to carry out theoretical calculations and derivations of the hydraulic characteristics of the complex flood discharge system. Hydraulic characteristics are observed through hydraulic model tests and verified using numerical simulations. Based on these three methods, a basis for further research on the hydraulic characteristics of complex flood discharge systems is provided. The main results are as follows: (1) The formulas for calculating the discharge flow rate Q under different flow states in the tailings dam design manual are not applicable to complex discharge systems; (2) Formulas for calculating the discharge flow rate Q under different flow states in complex discharge systems are proposed; by comparing model test values and numerical simulation values, the accuracy of the formulas for calculating the discharge flow rate Q in complex discharge systems is verified; (3) If the traditional mode is used to calculate the discharge flow rate Q in complex discharge systems, it is recommended to take the reduction coefficient as 0.55–0.56, and the model test values should also be referred to during flow state transitions.

Alzheimer disease is a neurological disorder that affects the elderly, caused by abnormal protein buildup in the brain. It leads to difficulties such as financial mismanagement, disorientation, behavioral changes, and repetitive speech. The existing methods use traditional features to detect the early signs of AD with low detection accuracy. The potential features have to be identified that represent best the patterns associated with alzheimers. Feature selection using ant lion optimization resolves the issue by using complementary information from hybrid features. The proposed HybridOpt pipeling for AD diagnosis combines the high level and low level features for early stage detection The objective of this work is to select efficient features from different deep networks, such as AlexNet, Googlenet, VGG16, ResNet, Efficient, DenseNet, and traditional texture features. Ant Lion Optimization is used to select the best feature among the deep network and traditional texture feature groups. Extensive experimentation on two highly challenging datasets called the Alzheimer’s disease neuroimage dataset and KAGGLE reveals that the proposed HybridOpt pipeline achieves an accuracy of 99% and 98.1% respectively.

In energy-harvesting wireless body area networks (EH-WBAN), the self-sustainability of body sensor nodes without compromising the service quality criteria is very important. In remote vital signs monitoring applications, the sampling rate of body nodes in each period should be determined to achieve this goal. There are two fundamental challenges in determining the sampling rate: 1) In EH-WBAN, the rate of the harvestable energy is time-dependent and unpredictable. 2) The vital signs of the patient have different change rates relevant to the time. Therefore, a technique is required that can learn the changes of the harvestable energy and the change rates of vital signs simultaneously and specify the proper sampling rate for BNs. The reinforcement learning algorithms are among the efficient solutions for this problem because they are capable of learning environmental uncertainties. Previous RL-based methods for determining the BN's sampling rate have three fundamental problems: 1) focus on the optimization of the transmission energy and ignore the sensing energy, 2) only affect one of the two aspects of energy or sensed data in determining the sampling rate and 3) discretization of the problem space does not ensure the determination of the optimal sampling rate. Therefore, this paper proposes a method named “deep reinforcement learning-based dynamic sampling” (DRDS) which first formulates the sampling rate determination problem as a Markov decision process (MDP) and proposes a deep deterministic policy gradient algorithm (DDPG) to solve it. The proposed method considers both energy and data variability aspects in determining the sampling rate. Two parameters, the super-capacitor’s voltage level, and ambient light intensity, are considered for the energy aspect; for the data variability aspect, the long short-term memory (LSTM) algorithm is developed to predict the change rate of data in the next round. Simulations indicate that by preserving the data integrity, the proposed method can decrease the sampling rate and unnecessary data transmission by about 49.95 % and 89.7 %, respectively, compared with state-of-the-art methods, and allow the sensor to achieve self-sustainability.

In order to solve the problem of difficult deployment of existing deep learning-based defect detection models in terminal equipment with limited computational capacity, a lightweight steel surface defect testing model LSKA-YOLOv8 was proposed based on the YOLOv8n target detection framework. The model uses KernelWarehouse Conv (KWConv) with lower computational volumes, which significantly reduces the required computational resources. By updating the traditional Feature Pyramid Network (FPN) structure to Bi-directional Feature Pyramid Network (BiFPN), enhance the capture of contextual information and reduce the number of parameters of the model. In addition, the Spatial Pyramid Pooling Fast (SPPF) module was replaced with a more accurate Receptive Field Block (RFB) module, expanding the model’s sensory field and improving characteristic representation. At the same time, the Large Separable Kernel Attention (LSKAttention) module was introduced in the detection head, effectively enhancing the understanding and capture of the target characteristics, thus significantly improving the overall detection performance. Experiments on the NEU-DET dataset showed that the average accuracy of LSKA-YOLO increased by 4.4% on the [email protected] indicator compared to the benchmark model, while the number of parameters and calculations of the model decreased by 26.7% and 50%, respectively. Provides valuable references and practical applications for deployment of defect detection models on computing-resource-limited terminal devices.

The objective of the current study is analyze linear and nonlinear time–space fractional Black–Scholes models via modified homotopy perturbation method (m-HPM). In current investigation, memory effects in financial markets are explored through fractional derivative in Caputo sense. The effectiveness of proposed methodology is checked numerically by finding residual errors and presented in tables. These tables also provide a benchmark for the comparison with already existing results in literature. Furthermore, solutions are graphically analyzed via 3D and contour plots across a range of parameters under varying market conditions. Analysis confirms the efficiency of m-HPM for predicting solutions of time–space fractional Black–Scholes models. The current study can contribute in understanding the applications of fractional calculus in finance, and can be a valuable computational tool for pricing financial derivatives in fractional environments.

In this paper, we present a mathematical model to lower the probability of breast cancer risk of the Breast Imaging Reporting and Data Systems (BI-RADS) 4 subcategories with the fractal fractional operator. This method improves evaluation quality, creates straightforward concepts for the early detection of breast cancer, and outcomes can be tracked easily by using BI-RADS-4 subcategories data at the Near East University Hospital. It uses the Banach fixed point theorem for nonlinear functional analysis and confirms the boundedness and uniqueness of solutions. Sensitivity analysis was performed on model parameters, and advanced numerical techniques were used to develop solutions. Also, this reveals disease-free and endemic equilibrium points, indicating local and global asymptotic stability. Chaos control was used in the regulated for linear responses approach to bring the system to stabilize according to its points of equilibrium. The growing procedure yields more effective and similar outcomes than the rotting technique, which happens quickly in the lowest fractional orders. Using Lagrange polynomial insight into the fractal-fractional operator, we conducted simulations and presented a comparative analysis in graphical form with classical and non-integer derivatives. The comparison of integer and non-integer results highlighted the importance of accurate fractional parameters in simulation. Moreover, it suggests that fractional operator-included mathematical models can help reveal more significant decisions on managing such real-life problems. Numerical simulations reveal absorption features for the fractal-fractional derivative with a generalized Mittag-Leffler kernel. The approximation solution approach allows for different order and dimension between 0 and 1, with outcomes changing for different fractional and fractal orders. It was determined that early diagnosis, quitting smoking, higher lactation rates, and ongoing care can reduce cancer risk. Our findings are critical for researchers, policymakers, and health care practitioners in combating and preventing breast cancer, contributing to worldwide public health initiatives.