Search

Accurate power load forecasting is crucial for the sustainable operation of smart grids. However, the complexity and uncertainty of load, along with the large-scale and high-dimensional energy information, present challenges in handling intricate dynamic features and long-term dependencies. This paper proposes a computational approach to address these challenges in short-term power load forecasting and energy information management, with the goal of accurately predicting future load demand. The study introduces a hybrid method that combines multiple deep learning models, the Gated Recurrent Unit (GRU) is employed to capture long-term dependencies in time series data, while the Temporal Convolutional Network (TCN) efficiently learns patterns and features in load data. Additionally, the attention mechanism is incorporated to automatically focus on the input components most relevant to the load prediction task, further enhancing model performance. According to the experimental evaluation conducted on four public datasets, including GEFCom2014, the proposed algorithm outperforms the baseline models on various metrics such as prediction accuracy, efficiency, and stability. Notably, on the GEFCom2014 dataset, FLOP is reduced by over 48.8%, inference time is shortened by more than 46.7%, and MAPE is improved by 39%. The proposed method significantly enhances the reliability, stability, and cost-effectiveness of smart grids, which facilitates risk assessment optimization and operational planning under the context of information management for smart grid systems. [ABSTRACT FROM AUTHOR]

Uncaria rhynchophylla is an important traditional herbal medicine in China, and the yield and quality of Uncaria rhynchophylla can be improved by suitable soil conditioners because of changing the soil properties. In this paper, Uncaria rhynchophylla associated alkaloids and soil microbial communities were investigated. The field experiment was set up with the following control group: (M1, no soil conditioner) and different soil conditioner treatment groups (M2, biomass ash; M3, water retention agent; M4, biochar; M5, lime powder and M6, malic acid). The results showed that M2 significantly increased the fresh and dry weight and the contents of isorhynchophylline, corynoxeine, isocorynoxeine, and total alkaloids. Acidobacteria, Proteobacteria, Actinobacteria, and Chloroflexi were major bacterial phyla. Correlation analysis showed that fresh and dry weight was significantly positively correlated with Acidobacteria, while alkali-hydrolyzable nitrogen, phosphatase activity, fresh and dry weight, corynoxeine, and isocorynoxeine were significantly negatively correlated with Chloroflexi. The application of soil conditioner M2 increased the abundance of Acidobacteria and decreased the abundance of Chloroflexi, which contributed to improving the soil nutrient content, yield, and quality of Uncaria rhynchophylla. In summary, biomass ash may be a better choice of soil conditioner in Uncaria rhynchophylla growing areas. [ABSTRACT FROM AUTHOR]

Generally, the recognition performance of lightweight models is often lower than that of large models. Knowledge distillation, by teaching a student model using a teacher model, can further enhance the recognition accuracy of lightweight models. In this paper, we approach knowledge distillation from the perspective of intermediate feature-level knowledge distillation. We combine a cross-stage feature fusion symmetric framework, an attention mechanism to enhance the fused features, and a contrastive loss function for teacher and student models at the same stage to comprehensively implement a multistage feature fusion knowledge distillation method. This approach addresses the problem of significant differences in the intermediate feature distributions between teacher and student models, making it difficult to effectively learn implicit knowledge and thus improving the recognition accuracy of the student model. Compared to existing knowledge distillation methods, our method performs at a superior level. On the CIFAR100 dataset, it boosts the recognition accuracy of ResNet20 from 69.06% to 71.34%, and on the TinyImagenet dataset, it increases the recognition accuracy of ResNet18 from 66.54% to 68.03%, demonstrating the effectiveness and generalizability of our approach. Furthermore, there is room for further optimization of the overall distillation structure and feature extraction methods in this approach, which requires further research and exploration. [ABSTRACT FROM AUTHOR]

In the food industry, the increasing use of automatic processes in the production line is contributing to the higher probability of finding contaminants inside food packages. Detecting these contaminants before sending the products to market has become a critical necessity. This paper presents a pioneering real-time system for detecting contaminants within food and beverage products by integrating microwave (MW) sensing technology with machine learning (ML) tools. Considering the prevalence of water and oil as primary components in many food and beverage items, the proposed technique is applied to both media. The approach involves a thorough examination of the MW sensing system, from selecting appropriate frequency bands to characterizing the antenna in its near-field region. The process culminates in the collection of scattering parameters to create the datasets, followed by classification using the Support Vector Machine (SVM) learning algorithm. Binary and multiclass classifications are performed on two types of datasets, including those with complex numbers and amplitude data only. High accuracy is achieved for both water-based and oil-based products. [ABSTRACT FROM AUTHOR]

This paper provides six metaheuristic algorithms, namely Fast Cuckoo Search (FCS), Salp Swarm Algorithm (SSA), Dynamic control Cuckoo search (DCCS), Gradient-Based Optimizer (GBO), Northern Goshawk Optimization (NGO), Opposition Flow Direction Algorithm (OFDA) to efficiently solve the optimal power flow (OPF) issue. Under standard and conservative operating settings, the OPF problem is modeled utilizing a range of objectives, constraints, and formulations. Five case studies have been conducted using IEEE 30-bus and IEEE 118-bus standard test systems to evaluate the effectiveness and robustness of the proposed algorithms. A performance evaluation procedure is suggested to compare the optimization techniques' strength and resilience. A fresh comparison methodology is created to compare the proposed methodologies with other well-known methodologies. Compared to previously reported optimization algorithms in the literature, the obtained results show the potential of GBO to solve various OPF problems efficiently. [ABSTRACT FROM AUTHOR]

Existing research rarely examines the subjective and objective built environment of river valley-type cities in relation to travel mode choice, particularly overlooking the heterogeneity among travelers in these cities. In this paper, based on questionnaire survey data and built environment data, terrain spatial perception (TSP) is introduced to expand the theory of planned behavior (TPB), and a Structural Equation Model (SEM) is established. Factor analysis and path analysis are conducted using SPSS and AMOS to estimate latent variables. An integrated model of SEM and random parameter Logit model (RPLM), which can not only analyze the psychological perception factors of commuters in river valley-type cities but also consider the heterogeneity of psychological perception, was constructed to analyze the impact of personal attributes, objective built environment factors, and psychological latent variables on the commuting mode choice behavior of public transport users in river valley-type cities. The results indicate that the five observation indicators corresponding to the proposed terrain spatial perception latent variables can better explain the terrain spatial perception of commuters in river valley-type cities. Different from plain cities, the subjective and objective built environment of river valley-type cities notably influence the travel behavior of commuters. Moreover, the parameters of terrain spatial perception follow a normal distribution, indicating that the sensitivity of different commuters to the terrain spatial perception of river valley-type cities is heterogeneous. The results of our study can provide a reference for alleviating traffic issues in valley cities. [ABSTRACT FROM AUTHOR]

The ionosphere can be artificially modified by employing ground-based high-power high-frequency electromagnetic waves to irradiate the ionosphere. This modification is achieved through the nonlinear interaction between the electromagnetic waves and the ionospheric plasma, leading to changes in the physical properties and structure of the ionosphere. The degree of artificial modification of the ionosphere is closely related to the heating energy density of high-frequency pump waves. Due to the high density of neutral constituents in the lower ionosphere and the high frequency of electron-neutral collisions, the energy of heating pump waves will be absorbed and attenuated during the penetration of the low ionosphere, seriously affecting the heating effect. This paper proposes a method to reduce the absorption of ionospheric heating pump waves by releasing electron attachment chemicals into low ionosphere to form a large-scale electron density hole. A model for mitigating pump waves absorption based on SF6 release is established, and the absorption at different frequencies is quantitatively calculated. The propagation characteristics of high-frequency signals in ionospheric holes are studied using a three-dimensional ray tracing method, and the results demonstrate that the chemical release method not only reduces the absorption attenuation of heating pump waves but also forms spherical electron density holes, which exhibit a focusing effect on the heating beam and enhance the heating effect. The results are of great significance for understanding the nonlinear interaction between electromagnetic wave and ionospheric plasma and improving the ionospheric heating efficiency. [ABSTRACT FROM AUTHOR]

Spectroscopic techniques generate one-dimensional spectra with distinct peaks and specific widths in the frequency domain. These features act as unique identities for material characteristics. Deep neural networks (DNNs) has recently been considered a powerful tool for automatically categorizing experimental spectra data by supervised classification to evaluate material characteristics. However, most existing work assumes balanced spectral data among various classes in the training data, contrary to actual experiments, where the spectral data is usually imbalanced. The imbalanced training data deteriorates the supervised classification performance, hindering understanding of the phase behavior, specifically, sol-gel transition (gelation) of soft materials and glycomaterials. To address this issue, this paper applies a novel data augmentation method based on a generative adversarial network (GAN) proposed by the authors in their prior work. To demonstrate the effectiveness of the proposed method, the actual imbalanced spectral data from Pluronic F-127 hydrogel and Alpha-Cyclodextrin hydrogel are used to classify the phases of data. Specifically, our approach improves 8.8%, 6.4%, and 6.2% of the performance of the existing data augmentation methods regarding the classifier's F-score, Precision, and Recall on average, respectively. Specifically, our method consists of three DNNs: the generator, discriminator, and classifier. The method generates samples that are not only authentic but emphasize the differentiation between material characteristics to provide balanced training data, improving the classification results. Based on these validated results, we expect the method's broader applications in addressing imbalanced measurement data across diverse domains in materials science and chemical engineering. [ABSTRACT FROM AUTHOR]

In this paper, based on linear matrix inequality technique, a simple controller and a compensatory controller are designed. It can track arbitrary fixed points and any periodic orbits. In addition, a synchronization control method via Chebyshev neural network with external disturbances is proposed. An adaptive controller is given. The Chebyshev neural network is used to approximate the uncertain nonlinear function and the adaptive law is used to adjust the corresponding parameters in the system. Taking a 4D memristive chaotic system as examples, the results are in consistent with the simulations. From a framework and control theoretical point of view, the proposed synchronization approach via compensation controller and Chebyshev neural network is firstly presented. From an application point of view, the proposed scheme can simplify the complexity of controller design. It is promising in many applications for mem-systems as secure communications and neural networks. [ABSTRACT FROM AUTHOR]

Correlation diagnosis in multivariate process quality management is an important and challenging issue. In this paper, a new diagnostic method based on quality component grouping is proposed. Firstly, three theorems describing the properties of the covariance matrix of multivariate process quality are established based on the statistical viewpoint of product quality, to prove the correlation decomposition theorem, which decomposes the correlation of all the quality components into a series of correlations of components pairs, and then by using the factor analysis method, all quality components are grouped in order to maximize the correlations in the same groups and minimize the ones between different groups. Finally, on the basis of correlations between different groups are ignored, T2 control charts of component pairs in the same groups are established to form the diagnostic model. Theoretical analysis and practice prove that for the multivariate process quality whose the correlations between different components vary considerably, the grouping technique enables the size of the correlation diagnostic model to be drastically reduced, thus allowing the proposed method can be used as a generalized theoretical model for the correlation diagnosis. [ABSTRACT FROM AUTHOR]

Exploring the spatial coupling relationship and interaction mechanism between green urbanization (GU) and tourism competitiveness (TC) is of great significance for promoting urban sustainable development. However, the lack of research on the interaction mechanism between GU and TC limits the formulation of effective environmental management policy and urban planning. Taking 734 counties in the Yellow River Basin (YRB) as the study area, this paper analyzes the spatial coupling relationship between GU and TC on the basis of comprehensive evaluation of GU and TC. Then, the interactive mechanism between GU and TC is systematically discussed, and the synergistic development strategy of the two is proposed. The results show that the GU level presents a multicore circle structure, with provincial capitals, prefecture-level urban districts and economically developed counties in east-central regions as high-value centers. The TC at county scale presents a multi-center spatial structure. Additionally, there is a significant positive spatial coupling between GU and TC in the YRB. The analysis further reveals that green urbanization level, social progress, population development, infrastructure construction, economic development quality, and eco-environmental protection has a observably influence on TC. Tourism competitiveness, service competitiveness, location competitiveness, resource competitiveness, market competitiveness, environmental influence, and talent competitiveness has a observably influence on GU. TC can promote GU, and the improvement of green urbanization level can support the development of tourism competitiveness. According to the spatial zoning method, 734 counties are divided into 6 categories, and the coordinated development strategy of GU and TC for each type of district is proposed. [ABSTRACT FROM AUTHOR]

Wireless charging of Electric Vehicles (EVs) has been extensively researched in the realm of electric cars, offering a convenient method. Nonetheless, there has been a scarcity of experiments conducted on low-power electric vehicles. To establish a wireless power transfer system for an electric vehicle, optimal power and transmission efficiency necessitate arranging the coils coaxially. In wireless charging systems, coils often experience angular and lateral misalignments. In this paper, a new alignment strategy is introduced to tackle the misalignment problem between the transmitter and receiver coils in the wireless charging of Electric Vehicles (EVs). The study involves the design and analysis of a coil, considering factors such as mutual inductance and efficiency. Wireless coils with angular misalignment are modelled in Ansys Maxwell simulation software. The proposed practical EV system aims to align the coils using angular motion, effectively reducing misalignment during the parking of two-wheelers. This is achieved by tilting the transmitter coil in the desired direction. Furthermore, micro sensing coils are employed to identify misalignment and facilitate automatic alignment. Additionally, adopting a power control technique becomes essential to achieve both constant current (CC) and constant voltage (CV) modes during battery charging. Integrating CC and CV modes is crucial for efficiently charging lithium-ion batteries, ensuring prolonged lifespan and optimal capacity utilization. The developed system can improve the efficiency of the wireless charging system to 90.3% with a 24 V, 16 Ah Lithium Ion Phosphate (LiFePO4) battery at a 160 mm distance between the coils. [ABSTRACT FROM AUTHOR]

Fracturing horizontal well casing deformation has become very prominent, particularly in tectonic stress-concentrated shale gas fields, limiting the efficient development progress of shale gas. The main failure mode of casing shearing deformation had been attributed to fault slip caused by multi-fracturing. The current research did not provide a clear picture of the dynamic evolution relationship between hydraulic fracturing, fault slip, and casing deformation. In this paper, the dynamic model of fault slip induced by formation pressure change is established, incorporating the effects of stress drop, physical change of friction, and casing and cement-sheath resistance loads. The discontinuous displacement approach and explicit/implicit coupling iteration methods are used to reveal the relationships between the effective normal stress, shear stress, friction coefficient, and sliding velocity during the fault slip process. Furthermore, the microscopic process of casing deformation sheared by fault slip is investigated using static equilibrium theory, and a characterization method for determining the amount casing deformation caused by real-scale fault slip is proposed. The results show that three stages exist in the process of casing deformation sheared by fault slip, including trigger activation stage, accelerated slip stage, and deceleration slip stage. Fault slip is clearly influenced by fault strike. To reduce the amount of fault slip, the fault direction with the maximum in-situ stress should be avoided as much as possible. Serious casing deformation still occurs for large-scale activated faults even though the optimization measure of wellbore structure has been well taken. To fundamentally reduce the possibility of casing shear deformation, it is necessary to prevent fault slip through optimizing the design of hydraulic fracturing. This study lays the theoretical groundwork for the casing deformation control method in shale gas wells. [ABSTRACT FROM AUTHOR]

Customer churn remains a critical concern for businesses, highlighting the significance of retaining existing customers over acquiring new ones. Effective prediction of potential churners aids in devising robust retention policies and efficient customer management strategies. This study dives into the realm of machine learning algorithms for predictive analysis in churn prediction, addressing the inherent challenge posed by diverse and imbalanced customer churn data distributions. This paper introduces a novel approach—the Ratio-based data balancing technique, which addresses data skewness as a pre-processing step, ensuring improved accuracy in predictive modelling. This study fills gaps in existing literature by highlighting the effectiveness of ensemble algorithms and the critical role of data balancing techniques in optimizing churn prediction models. While our research contributes a novel approach, there remain avenues for further exploration. This work evaluates several machine learning algorithms—Perceptron, Multi-Layer Perceptron, Naive Bayes, Logistic Regression, K-Nearest Neighbour, Decision Tree, alongside Ensemble techniques such as Gradient Boosting and Extreme Gradient Boosting (XGBoost)—on balanced datasets achieved through our proposed Ratio-based data balancing technique and the commonly used Data Resampling. Results reveal that our proposed Ratio-based data balancing technique notably outperforms traditional Over-Sampling and Under-Sampling methods in churn prediction accuracy. Additionally, using combined algorithms like Gradient Boosting and XGBoost showed better results than using single methods. Our study looked at different aspects like Accuracy, Precision, Recall, and F-Score, finding that these combined methods are better for predicting customer churn. Specifically, when we used a 75:25 ratio with the XGBoost method, we got the most promising results for our analysis which are presented in this work. [ABSTRACT FROM AUTHOR]

This paper presents an innovative control scheme designed to significantly enhance the power factor of AC/DC boost rectifiers by integrating an adaptive neuro-fuzzy inference system (ANFIS) with predictive current control. The innovative control strategy addresses key challenges in power quality and energy efficiency, demonstrating exceptional performance under diverse operating conditions. Through rigorous simulation, the proposed system achieves precise input current shaping, resulting in a remarkably low total harmonic distortion (THD) of 3.5%, which is well below the IEEE-519 standard threshold of 5%. Moreover, the power factor reaches an outstanding 0.990, indicating highly efficient energy utilization and near-unity power factor operation. To validate the theoretical findings, a 500 W laboratory prototype was implemented using the dSPACE ds1104 digital controller. Steady-state analysis reveals sinusoidal input currents with minimal THD and a power factor approaching unity, thereby enhancing grid stability and energy efficiency. Transient response tests further demonstrate the system's robustness against load and voltage fluctuations, maintaining output voltage stability within an 18 V overshoot and a 20 V undershoot during load changes, and achieving rapid response times as low as 0.2 s. Comparative evaluations against conventional methods underscore the superiority of the proposed control strategy in terms of both performance and implementation simplicity. By harnessing the strengths of ANFIS-based voltage regulation and predictive current control, this scheme offers a robust solution to power quality issues in AC/DC boost rectifiers, promising substantial energy savings and improved grid stability. The results affirm the potential of the proposed system to set new benchmarks in power factor correction technology. [ABSTRACT FROM AUTHOR]

Due to the presence of non-line-of-sight (NLOS) obstacles, the localization accuracy in ultra-wideband (UWB) wireless indoor localization systems is typically substantially lower. To minimize the influence of these environmental factors and improve the accuracy of indoor wireless positioning, this paper proposes a density clustering with noise combined with particle swarm optimization (DCNPSO) to improve UWB positioning. Which exploits the advantages of the density-based spatial clustering algorithm with noise (DBSCAN) and particle swarm optimization (PSO) algorithm. The experimental results show that the DCNPSO algorithm achieves 45.25% and 36.14% higher average positioning accuracy than the DBSCAN and PSO algorithms, respectively. The positioning error of this algorithm remains stable within 3 cm in static positioning and can achieve high accuracy in NLOS environments. [ABSTRACT FROM AUTHOR]

Over the past decades, the software industry has expanded to include all industries. Since stakeholders tend to use it to get their work done, software houses seek to estimate the cost of the software, which includes calculating the effort, time, and resources required. Although many researchers have worked to estimate it, the prediction accuracy results are still inaccurate and unstable. Estimating it requires a lot of effort. Therefore, there is an urgent need for modern techniques that contribute to cost estimation. This paper seeks to present a model based on deep learning and machine learning techniques by combining convolutional neural networks (CNN) and the particle swarm algorithm (PSO) in the context of time series forecasting, which enables feature extraction and automatic tuning of hyperparameters, which reduces the manual effort of selecting parameters and contributes to fine-tuning. The use of PSO also enhances the robustness and generalization ability of the CNN model and its iterative nature allows for efficient discovery of hyperparameter similarity. The model was trained and tested on 13 different benchmark datasets and evaluated through six metrics: mean absolute error (MAE), mean square error (MSE), mean magnitude relative error (MMRE), root mean square error (RMSE), median magnitude relative error (MdMRE), and prediction accuracy (PRED). Comparative results reveal that the performance of the proposed model is better than other methods for all datasets and evaluation criteria. The results were very promising for predicting software cost estimation. [ABSTRACT FROM AUTHOR]

Despite the historical position of the F-expansion method as a method for acquiring exact solutions to nonlinear partial differential equations (PDEs), this study highlights its superiority over alternative auxiliary equation methods. The efficacy of this method is demonstrated through its application to solve the convective–diffusive Cahn–Hilliard (cdCH) equation, describing the dynamic of the separation phase for ternary iron alloys (Fe–Cr–Mo) and (Fe–X–Cu). Significantly, this research introduces an extensive collection of exact solutions by the auxiliary equation, comprising fifty-two distinct types. Six of these are associated with Weierstrass-elliptic function solutions, while the remaining solutions are expressed in Jacobi-elliptic functions. I think it is important to emphasize that, exercising caution regarding the statement of the term 'new,' the solutions presented in this context are not entirely unprecedented. The paper examines numerous examples to substantiate this perspective. Furthermore, the study broadens its scope to include soliton-like and trigonometric-function solutions as special cases. This underscores that the antecedently obtained outcomes through the recently specific cases encompassed within the more comprehensive scope of the present findings. [ABSTRACT FROM AUTHOR]

Permanent magnet synchronous motor (PMSM) systems have gained popularity in various fields due to their advantages such as high speed, high accuracy, low maintenance, and high reliability. This paper presents the speed tracking control of a permanent magnet synchronous motor (PMSM) using a hybrid fractional order PI and type 2 fuzzy control with fractional order PD control (FOT2F-FOPD). The SRF-PLL observes the motor speed and estimates the rotor's position by interpreting the input voltages of the motor instead of using a sensor. Then, the controller parameters (gain, μ and λ) are tuned based on a novel optimization algorithm called Incomprehensible but Intelligible-in-time (IbI) Logics algorithm (ILA). The proposed controller enhances the performance of the system and regulates the speed of the motor under parameter variations such as the speed and the load. So, the proposed ILA (FOT2F-FOPD) controller is assessed using MATLAB/Simulink simulation and compared with other controller techniques. The proposed technique reduces the settling time, steady state error and overshoot by at least 65%, 54% and 53% respectively under load conditions compared with (PSO, optimized FOPD, FOPI and PI). While at no load condition, the settling time and the error are reduced by 31% and 12.5% respectively with no overshoot in output response. The results show a significant improvement in the performance of motors used with the application of the proposed controller and the employment of the (ILA) optimization compared with FOPI and PI controllers. [ABSTRACT FROM AUTHOR]

This paper provides a comprehensive analysis of linear regression models, focusing on addressing multicollinearity challenges in breast cancer patient data. Linear regression methodologies, including GAM, Beta, GAM Beta, Ridge, and Beta Ridge, are compared using two statistical criteria. The study, conducted with R software, showcases the Beta regression model's exceptional performance, achieving a BIC of − 5520.416. Furthermore, the Ridge regression model demonstrates remarkable results with the best AIC at − 8002.647. The findings underscore the practical application of these models in real-world scenarios and emphasize the Beta regression model's superior ability to handle multicollinearity challenges. The preference for AIC over BIC in Generalized Additive Models (GAMs) is rooted in the AIC's calculation framework, highlighting its effectiveness in capturing the complexity and flexibility inherent in GAMs. [ABSTRACT FROM AUTHOR]

This paper presents an innovative control scheme designed to significantly enhance the power factor of AC/DC boost rectifiers by integrating an adaptive neuro-fuzzy inference system (ANFIS) with predictive current control. The innovative control strategy addresses key challenges in power quality and energy efficiency, demonstrating exceptional performance under diverse operating conditions. Through rigorous simulation, the proposed system achieves precise input current shaping, resulting in a remarkably low total harmonic distortion (THD) of 3.5%, which is well below the IEEE-519 standard threshold of 5%. Moreover, the power factor reaches an outstanding 0.990, indicating highly efficient energy utilization and near-unity power factor operation. To validate the theoretical findings, a 500 W laboratory prototype was implemented using the dSPACE ds1104 digital controller. Steady-state analysis reveals sinusoidal input currents with minimal THD and a power factor approaching unity, thereby enhancing grid stability and energy efficiency. Transient response tests further demonstrate the system's robustness against load and voltage fluctuations, maintaining output voltage stability within an 18 V overshoot and a 20 V undershoot during load changes, and achieving rapid response times as low as 0.2 s. Comparative evaluations against conventional methods underscore the superiority of the proposed control strategy in terms of both performance and implementation simplicity. By harnessing the strengths of ANFIS-based voltage regulation and predictive current control, this scheme offers a robust solution to power quality issues in AC/DC boost rectifiers, promising substantial energy savings and improved grid stability. The results affirm the potential of the proposed system to set new benchmarks in power factor correction technology. [ABSTRACT FROM AUTHOR]

Tabular data analysis is a critical task in various domains, enabling us to uncover valuable insights from structured datasets. While traditional machine learning methods can be used for feature engineering and dimensionality reduction, they often struggle to capture the intricate relationships and dependencies within real-world datasets. In this paper, we present Multi-representation DeepInsight (MRep-DeepInsight), a novel extension of the DeepInsight method designed to enhance the analysis of tabular data. By generating multiple representations of samples using diverse feature extraction techniques, our approach is able to capture a broader range of features and reveal deeper insights. We demonstrate the effectiveness of MRep-DeepInsight on single-cell datasets, Alzheimer's data, and artificial data, showcasing an improved accuracy over the original DeepInsight approach and machine learning methods like random forest, XGBoost, LightGBM, FT-Transformer and L2-regularized logistic regression. Our results highlight the value of incorporating multiple representations for robust and accurate tabular data analysis. By leveraging the power of diverse representations, MRep-DeepInsight offers a promising new avenue for advancing decision-making and scientific discovery across a wide range of fields. [ABSTRACT FROM AUTHOR]

The concept, performance, and analyses of distinctive, miniaturized metamaterial (MTM) unit cell addressing the forthcoming Sub 6 GHz 5G applications are presented in this paper. Two circular split-ring resonators (CSRR) with two parallel rectangular copper elements in front of the design and a slotted square element in the background make up the suggested metamaterial. It has a line segment with tunable features that is positioned in the center of the little ring copper structure. The suggested design offers a significant operating frequency band of 220 MHz together with a resonance of transmission coefficient S21 at 3.5 GHz. Furthermore, in two (z & x) principal axes of wave propagation, wide-range achievement, single/double-negative (S/DNG) refractive index, negative permittivity, and near-zero permeability properties were demonstrated. Through varying central slotted-strip line length, resonance frequencies can be selectively altered. Moreover, the metamaterial has overall dimensions of 9 × 9 mm2 and is composed on a Rogers 5880 RT substrate. In order to create the suggested MTM's equivalent circuit, which shows similar coefficient of transmission (S21), a proposed design's numerical simulation is carried out in the CST micro-wave studio. This simulation is after that put to comparison with manufacturing of the design. [ABSTRACT FROM AUTHOR]

Virtual Reality (VR) laboratories are a new pedagogical approach to support psychomotor skills development in undergraduate programmes to achieve practical competency. VR laboratories are successfully used to carry out virtual experiments in science courses and for clinical skills training in professional courses. This paper describes the development and evaluation of a VR-based microbiology laboratory on Head-Mounted Display (HMD) for undergraduate students. Student and faculty perceptions and expectations were collected to incorporate into the laboratory design. An interactive 3-dimensional VR laboratory with a 360° view was developed simulating our physical laboratory setup. The laboratory environment was created using Unity with the (created) necessary assets and 3D models. The virtual laboratory was designed to replicate the physical laboratory environment as suggested by the students and faculty. In this VR laboratory, six microbiology experiments on Gram staining, bacterial streaking, bacterial motility, catalase test, oxidase test and biochemical tests were placed on the virtual platform. First-year biomedical science students were recruited to evaluate the VR laboratory. Students' perception of the virtual laboratory was positive and encouraging. About 70% of the students expressed they felt safe using the VR laboratory and that it was engaging. They felt that the VR laboratory provided an immersive learning experience. They appreciated that they could repeat each experiment multiple times without worrying about mistakes or mishaps. They could personalise their learning by concentrating on the specific experiments. Our in-house VR-based microbiology laboratory was later extended to other health professions programmes teaching microbiology. [ABSTRACT FROM AUTHOR]

The prevalence of cardiovascular disease (CVD) has surged in recent years, making it the foremost cause of mortality among humans. The Electrocardiogram (ECG), being one of the pivotal diagnostic tools for cardiovascular diseases, is increasingly gaining prominence in the field of machine learning. However, prevailing neural network models frequently disregard the spatial dimension features inherent in ECG signals. In this paper, we propose an ECG autoencoder network architecture incorporating low-rank attention (LRA-autoencoder). It is designed to capture potential spatial features of ECG signals by interpreting the signals from a spatial perspective and extracting correlations between different signal points. Additionally, the low-rank attention block (LRA-block) obtains spatial features of electrocardiogram signals through singular value decomposition, and then assigns these spatial features as weights to the electrocardiogram signals, thereby enhancing the differentiation of features among different categories. Finally, we utilize the ResNet-18 network classifier to assess the performance of the LRA-autoencoder on both the MIT-BIH Arrhythmia and PhysioNet Challenge 2017 datasets. The experimental results reveal that the proposed method demonstrates superior classification performance. The mean accuracy on the MIT-BIH Arrhythmia dataset is as high as 0.997, and the mean accuracy and F 1 -score on the PhysioNet Challenge 2017 dataset are 0.850 and 0.843. [ABSTRACT FROM AUTHOR]

This article investigates the impact of metal-organic frameworks (MOFs) on the performance and stability of perovskite solar cells (PSCs), specifically focusing on the type of metal and the morphology of the MOF. Two types of MOFs, copper-benzene-1,3,5-tricarboxylate (Cu-BTC MOF) with spherical morphology and cobalt-benzene-1,3,5-tricarboxylate (Co-BTC MOF) with rod morphology, are synthesized and spin-coated on TiO2 substrates to form FTO/TiO2/MOF/CH3NH3PbI3/C-paste PSCs. The morphology and size of the MOFs are characterized by scanning electron microscopy (SEM), and the crystallinity and residual PbI2 of the perovskite films are analyzed by X-ray diffraction (XRD). The results show that the Co-BTC MOF PSC exhibits the highest power conversion efficiency (PCE) of 10.4% and the best stability, retaining 82% of its initial PCE after 264 h of storage in ambient air. The improved performance and stability are attributed to the enhanced crystallinity and reduced residual PbI2 of the perovskite film after Co-BTC MOF modification. The paper showcases the immense potential of MOF-based interlayers to revolutionize PSC technology, offering a path toward next-generation solar cells with enhanced performance and longevity. [ABSTRACT FROM AUTHOR]

The initial Phase-I single centre, single dose, randomized, double-blind, cross-over study was planned to assess the pharmacokinetic and pharmacodynamic bioequivalence of the trastuzumab biosimilar (MYL-1401O) compared to the reference Herceptin®. Their respective immunomodulation profile presented in this paper involved healthy males receiving a single infusion of both monoclonals, separated by a washout period. Sixty parameters were assessed in total, including serum cytokines, peripheral mononuclear cell (PBMC) subsets, cell activation and response to recall antigens and mitogen, pre- and post- infusion, as well as a cytokine release assay (CRA) at baseline. Trastuzumab infusion induced a transient and weak peak of serum IL-6 at 6 h, and a modulation of mononuclear cell subset profile and activation level, notably CD16 + cells. Except for CD8 + T cells, there were no significant differences between Herceptin® and MYL-1401O. In CRA, PBMC stimulated with MYL-1401O or Herceptin® similarly secreted IL-6, TNF-α, IL-1β, GM-CSF, IFN-γ, and IL-10, but no or low level of IL-2. Interestingly, some observed adverse events correlated with IL-2 and IFN-γ in CRA. MYL-1401O exhibited a very similar immunomodulation profile to Herceptin®, strongly supporting its bioequivalence. This approach may thus be included in a proof-of-concept study. CRA may be used as a predictive assay for the evaluation of clinical monoclonals. [ABSTRACT FROM AUTHOR]

The concentration prediction of PM2.5 plays a vital role in controlling the air and improving the environment. This paper proposes a prediction model (namely EEMD-ALSTM) based on Ensemble Empirical Mode Decomposition (EEMD), Attention Mechanism and Long Short-Term Memory network (LSTM). Through the combination of decomposition and LSTM, attention mechanism is introduced to realize the prediction of PM2.5 concentration. The advantage of EEMD-ALSTM model is that it decomposes and combines the original data using the method of ensemble empirical mode decomposition, reduces the high nonlinearity of the original data, and Specially reintroduction the attention mechanism, which enhances the extraction and retention of data features by the model. Through experimental comparison, it was found that the EEMD-ALSTM model reduced its MAE and RMSE by about 15% while maintaining the same R2 correlation coefficient, and the stability of the model in the prediction process was also improved significantly. [ABSTRACT FROM AUTHOR]

This work addresses a critical issue: the deterioration of concrete structures due to fine-grained cracks, which compromises their strength and longevity. To tackle this problem, experts have turned to computer vision (CV) based automated strategies, incorporating object detection and image segmentation techniques. Recent efforts have integrated complex techniques such as deep convolutional neural networks (DCNNs) and transformers for this task. However, these techniques encounter challenges in localizing fine-grained cracks. This paper presents a self-supervised 'you only look once' (SS-YOLO) approach that utilizes a YOLOv8 model. The novel methodology amalgamates different attention approaches and pseudo-labeling techniques, effectively addressing challenges in fine-grained crack detection and segmentation in concrete structures. It utilizes convolution block attention (CBAM) and Gaussian adaptive weight distribution multi-head self-attention (GAWD-MHSA) modules to accurately identify and segment fine-grained cracks in concrete buildings. Additionally, the assimilation of curriculum learning-based self-supervised pseudo-labeling (CL-SSPL) enhances the model's ability when applied to limited-size data. The efficacy and viability of the proposed approach are demonstrated through experimentation, results, and ablation analysis. Experimental results indicate a mean average precision (mAP) of at least 90.01%, an F1 score of 87%, and an intersection over union threshold greater than 85%. It is evident from the results that the proposed method yielded at least 2.62% and 4.40% improvement in mAP and F1 values, respectively, when tested on three diverse datasets. Moreover, the inference time taken per image is 2 ms less than that of the compared methods. [ABSTRACT FROM AUTHOR]

The paper presents a fault region identification method for the active distribution network (ADN) with limited PMU. First, PMU configuration and region division strategies are proposed based on the network topology. Next, the difference in three-phase current variations between the normal and fault regions of the ADN is analyzed. A multi-dimensional state monitoring matrix is built using the measured current data. The spectral norm ratio coefficient is constructed based on the 2-norm to lower the complexity of the multi-dimensional state monitoring matrix and quantify the difference in state changes before and after the fault occurs in each region. Then, the fault region is identified by combining each region's spectral norm ratio coefficient and the change of the current phase. Finally, an IEEE 33-node simulation model is created to simulate faults under different working conditions. According to the simulation results, the suggested approach is less impacted by fault type, neutral point grounding mode, and transition resistance. Furthermore, even if the communication does not match the rigorous synchronization requirements, the proposed method can still complete the fault identification of the distribution network correctly and has high robustness. [ABSTRACT FROM AUTHOR]

Satellite navigation positioning has become an indispensable component of everyday life, where precise pinpointing and rapid convergence are crucial in delivering timely and accurate location information. However, due to the damping of integer ambiguities and system residual errors, the rapid convergence of Precise Point Positioning (PPP) implementation is a significant challenge. To address this, this paper proposes a novel Carrier Phase Zero-Baseline Self-Differencing Precise Point Positioning (CZS-PPP) technique and its ionosphere-free fusion model. By employing the proposed CZS-PPP approach in separate scenarios involving BDS-3, GPS, and dual-system settings, we systematically validate the efficacy of the method. The experimental results indicate that the convergence time of the method is less than 4 min in a single-system scenario. Furthermore, in a dual-system scenario, the method can achieve rapid convergence in less than 3 min. The CZS-PPP technique presented demonstrates the elimination of integer ambiguities and the effective suppression of system residuals, in comparison to the conventional method. The proposed approach has demonstrated remarkable performance across different systems, offering a promising new pathway for achieving PPP fast convergence in BDS/GNSS. [ABSTRACT FROM AUTHOR]

In remote sensing image fusion, the conventional Convolutional Neural Networks (CNNs) extract local features of the image through layered convolution, which is limited by the receptive field and struggles to capture global features. Transformer utilizes self-attention to capture long-distance dependencies in images, which has a global receptive field, but the computational cost for high-resolution images is excessively high. In response to the above issues, this paper draws inspiration from the FusionNet network, harnessing the local detail acquisition capability of CNNs and the global data procuring capacity of Transformer. It presents a novel method for remote sensing image sharpening named Guided Filtering-Cross Stage Partial Network-Transformer, abbreviated as GF-CSTNet. This solution unifies the strengths of Guided Filtering (GF), Cross Stage Partial Network (CSPNet), and Transformer. Firstly, this method utilizes GF to enhance the acquired remote sensing image data. The CSPNet and Transformer structures are then combined to further enhance fusion performance by leveraging their respective advantages. Subsequently, a Rep-Conv2Former method is designed to streamline attention and extract diverse receptive field features through a multi-scale convolution modulator block. Simultaneously, a reparameterization module is constructed to integrate the multiple branches generated during training into a unified branch during inference, thereby optimizing the model's inference speed. Finally, a residual learning module incorporating attention has been devised to augment the modeling and feature extraction capabilities of images. Experimental results obtained from the GaoFen-2 and WorldView-3 datasets demonstrate the effectiveness of the proposed GF-CSTNet approach. It effectively extracts detailed information from images while avoiding the problem of spectral distortion. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a theoretical framework for optical trapping that integrates nonlinear polarization within the dipole approximation. This theory represents the most comprehensive analytic model to date capable of resolving the discrepancies between the observed and simulated trapping of plasmonic nanoparticles. Our theory elucidates how two-photon absorption can account for the stable trapping of gold nanoparticles, including their longitudinal stability, especially near their plasmon resonance. Furthermore, the experimentally observed split potential wells in the transverse plane, which are attributed to two-photon absorption, are in close agreement with our model's predictions. Finally, this study provides new insights into the mechanism of optical trapping under conditions of intense light–matter interactions. [ABSTRACT FROM AUTHOR]

This study presents a dynamic Bayesian game model designed to improve predictions of ecological uncertainties leading to natural disasters. It incorporates historical signal data on ecological indicators. Participants, acting as decision-makers, receive signals about an unknown parameter-observations of a random variable's realization values before a specific time, offering insights into ecological uncertainties. The essence of the model lies in its dynamic Bayesian updating, where beliefs about unknown parameters are refined with each new signal, enhancing predictive accuracy. The main focus of our paper is to theoretically validate this approach, by presenting a number of theorems that prove its precision and efficiency in improving uncertainty estimations. Simulation results validate the model's effectiveness in various scenarios, highlighting its role in refining natural disaster forecasts. [ABSTRACT FROM AUTHOR]

Effective blood glucose management is crucial for people with diabetes to avoid acute complications. Predicting extreme values accurately and in a timely manner is of vital importance to them. People with diabetes are particularly concerned about suffering a hypoglycemia (low value) event and, moreover, that the event will be prolonged in time. It is crucial to predict hyperglycemia (high value) and hypoglycemia events that may cause health damages in the short term and potential permanent damages in the long term. This paper describes our research on predicting hypoglycemia events at 30, 60, 90, and 120 minutes using machine learning methods. We propose using structured Grammatical Evolution and dynamic structured Grammatical Evolution to produce interpretable mathematical expressions that predict a hypoglycemia event. Our proposal generates white-box models induced by a grammar based on if-then-else conditions using blood glucose, heart rate, number of steps, and burned calories as the inputs for the machine learning technique. We apply these techniques to create three types of models: individualized, cluster, and population-based. They all are then compared with the predictions of eleven machine learning techniques. We apply these techniques to a dataset of 24 real patients of the Hospital Universitario Principe de Asturias, Madrid, Spain. The resulting models, presented as if-then-else statements that incorporate numeric, relational, and logical operations between variables and constants, are inherently interpretable. The True Positive Rate and True Negative Rate metrics are above 0.90 for 30-minute predictions, 0.80 for 60 min, and 0.70 for 90 min and 120 min for the three types of models. Individualized models exhibit the best metrics, while cluster and population-based models perform similarly. Structured and dynamic structured grammatical evolution techniques perform similarly for all forecasting horizons. Regarding the comparison of different machine learning techniques, on the shorter forecasting horizons, our proposals have a high probability of winning, a probability that diminishes on the longer time horizons. Structured grammatical evolution provides advanced forecasting models that facilitate model explanation, modification, and retesting, offering flexibility for refining solutions post-creation and a deeper understanding of blood glucose behavior. These models have been integrated into the glUCModel application, designed to serve people with diabetes. [ABSTRACT FROM AUTHOR]

The hybrid energy storage system of wind power involves the deep coupling of heterogeneous energy such as electricity and heat. Exergy as a dual physical quantity that takes into account both 'quantity' and 'quality, plays an important guiding role in the unification of heterogeneous energy. In this paper, the operation characteristics of the system are related to the energy quality, and the operation strategy of the wind power hybrid energy storage system is proposed based on the exergoeconomics. First, the mathematical model of wind power hybrid energy storage system is established based on exergoeconomics. Then, wind power experiments of three forms of thermal-electric hybrid energy storage are carried out, and RSM is used to analyze the power quality and exergoeconomic characteristics of the system, and the optimal working conditions of the experiment are obtained. Finally, an optimization strategy is proposed by combining experiment and simulation. The system efficiency, unit exergy cost and current harmonic distortion rate are multi-objective optimization functions. The three algorithms evaluate the optimal solution based on standard deviation. The results show that the exergoeconomics can effectively judge the production-storage-use characteristics of the new system of ' wind power + energy storage'. The thermal-electric hybrid energy storage system can absorb the internal exergy loss of the battery, increase the exergy efficiency by 10%, reduce the unit exergy cost by 0.03 yuan/KJ, and reduce the current harmonic distortion rate by 8%. It provides guidance for improving the power quality of wind power system, improving the exergy efficiency of thermal-electric hybrid energy storage wind power system and reducing the unit cost. [ABSTRACT FROM AUTHOR]

Scholars of color remain underrepresented in US institutions in academia. In this paper, we will examine one factor that contributes to their continued marginalization in psychology and management: the scientific method's commitment to traditional notions of objectivity. We argue that objectivity—defined as practices and policies rooted in the heightened value placed on a research process that is ostensibly free from bias—is central to the prominence of primarily White scholarship in psychology and management research and remains central to knowledge production. To investigate this, we employ a mixed-methods approach, integrating qualitative and quantitative data to codify how scholars of color experience objectivity interrogations, or written and verbal questioning in academic contexts that implicates their scientific rigor. We also identify how scholars of color engage in objectivity armoring, or self-presentational strategies (toning down and stepping up) to contend with these interrogations. Finally, we reveal these toning down processes in language use within publications on racial scholarship. Overall, these studies reveal the unique challenges scholars of color face to legitimize and validate their work on race and racism within predominantly White institutions and disciplines. [ABSTRACT FROM AUTHOR]

Accurate prediction of the remaining useful life (RUL) of lithium-ion batteries is advantageous for maintaining the stability of electrical systems. In this paper, an interpretable online method which can reflect capacity regeneration is proposed to accurately estimate the RUL. Firstly, four health indicators (HIs) are extracted from the charging and discharging process for online prediction. Then, the HIs model is trained using support vector regression to obtain future features. And the capacity model of Gaussian process regression (GPR) is trained and analyzed by Shapley additive explanation (SHAP). Meanwhile, the state space for capacity prediction is constructed with the addition of Gaussian non-white noise to simulate the capacity regeneration. And the modified predicted HIs and noise are obtained by unscented Kalman filter. Finally, according to SHAP explainer, the predicted HIs acting as the baseline and the modified HIs containing information on capacity regeneration are chosen to predict RUL. In addition, the bounds of confidence intervals (CIs) are calculated separately to reflect the regenerated capacity. The experimental results demonstrate that the proposed online method can achieve high accuracy and effectively capture the capacity regeneration. The absolute error of failure RUL is below 5 and the minimum confidence interval is only 2. [ABSTRACT FROM AUTHOR]

With the continuous development of the economy and society, along with the sustained population growth, the issue of water resources carrying capacity in China has attracted increasing attention. This paper constructs a model for evaluating the provincial water resources carrying capacity in China from four dimensions: water, economy, society, and ecology. Utilizing this model, we analyze the spatiotemporal variations in water resources carrying capacity among 31 provinces in China from 2005 to 2021. Additionally, we delve into the coupling coordination and influencing factors of water resources carrying capacity. The study reveals an overall increasing trend in China's water resources carrying capacity index, with the ecological indicator exhibiting the most significant growth while the water resources sub-indicator lags behind. There are notable regional differences, with higher water resources carrying capacity observed in the eastern coastal areas and relatively lower capacity in the western regions. The ecological criterion becomes a core factor constraining water resources carrying capacity from 2005 to 2015, gradually giving way to the prominence of the social criterion since 2015. The coordination degree is relatively higher in the eastern regions, more scattered in the western regions, and relatively stable in the central regions. Based on the research findings, a series of recommendations are proposed, including strengthening environmental protection policies, optimizing water resources management mechanisms, improving water use efficiency, and promoting economic structural diversification. These suggestions aim to facilitate the sustainable development of water resources carrying capacity in China. [ABSTRACT FROM AUTHOR]

In recent years, the growth spurt of medical imaging data has led to the development of various machine learning algorithms for various healthcare applications. The MedMNISTv2 dataset, a comprehensive benchmark for 2D biomedical image classification, encompasses diverse medical imaging modalities such as Fundus Camera, Breast Ultrasound, Colon Pathology, Blood Cell Microscope etc. Highly accurate classifications performed on these datasets is crucial for identification of various diseases and determining the course of treatment. This research paper presents a comprehensive analysis of four subsets within the MedMNISTv2 dataset: BloodMNIST, BreastMNIST, PathMNIST and RetinaMNIST. Each of these selected datasets is of diverse data modalities and comes with various sample sizes, and have been selected to analyze the efficiency of the model against diverse data modalities. The study explores the idea of assessing the Vision Transformer Model's ability to capture intricate patterns and features crucial for these medical image classification and thereby transcend the benchmark metrics substantially. The methodology includes pre-processing the input images which is followed by training the ViT-base-patch16-224 model on the mentioned datasets. The performance of the model is assessed using key metrices and by comparing the classification accuracies achieved with the benchmark accuracies. With the assistance of ViT, the new benchmarks achieved for BloodMNIST, BreastMNIST, PathMNIST and RetinaMNIST are 97.90%, 90.38%, 94.62% and 57%, respectively. The study highlights the promise of Vision transformer models in medical image analysis, preparing the way for their adoption and further exploration in healthcare applications, aiming to enhance diagnostic accuracy and assist medical professionals in clinical decision-making. [ABSTRACT FROM AUTHOR]

The textile dyeing and manufacturing industry is the major producer of significant amounts of wastewater that contain persistent substances such as azo dyes that require adequate remediation measures. Far ultraviolet at 222 nm light may provide an advantage for contaminants degradation as compared to conventional UV sources (254 nm). In this paper, the degradation of reactive black 5 (RB5) in artificial wastewater has been performed using a 222 nm Kr/Cl2 excimer source under direct photolysis and an advanced oxidation process using TiO2/H2O2. The solution pH, catalyst concentration, 222 nm intensity, initial concentration of dye, and addition of H2O2 influence the degradation rate constant. The molar absorption coefficient, quantum yield of RB5 at 222 nm and the electrical energy per order (EEO) from different treatment methods have been reported. RB5 shows 1.26 times higher molar absorption at 222 nm than at 254 nm. The EEO for excimer-222/H2O2 (∼ 13 kWh/m3) is five times lower than that of the excimer-222/TiO2 process, which makes the process energy efficient. The degradation of wastewater has been carried out at three distinct pH values (2, 6, and 10), and the pH level of 10 exhibited the highest degree of degradation. The degradation rate in the alkaline medium is 8.27 and 2.05 times higher than in the acidic or ambient medium. Since textile effluent is highly alkaline, this result is significant, as no neutralization of the wastewater is required, and direct treatment is possible. A possible degradation pathway has been established based on Fourier transform infrared spectroscopy (FTIR) and high resolution mass spectroscopy (HRMS) analysis. The phytotoxicity of the treated wastewater has also been evaluated for its suitability for reuse in agriculture. The study reveals that the excimer-222/H2O2 treated wastewater significantly enhanced the germination percentage of Raphanus sativus seed (97%) compared to dye wastewater-grown seeds (75%). This work offers crucial information for future studies on the direct and indirect photolysis of azo dyes, as well as insight into the process of RB5 degradation under Kr/Cl2 excimer radiation. [ABSTRACT FROM AUTHOR]

This paper presents an analysis and prediction of the shear strength of wide-shallow reinforced concrete beams, utilizing Finite Element Analysis (FEA) and machine learning techniques. The methodology involves validating a detailed Finite Element Model (FEM) against experimental results, conducting a parametric study, and developing three Machine Learning prediction equations. The FEM captures concrete and steel behaviors, including cracking and crushing for concrete and linear isotropic properties for steel reinforcement. Loading and boundary conditions are defined for accuracy and validated against 13 experimental specimens, exhibiting a maximum 8% and 12% difference in loads and deflections, respectively. A parametric study generates a dataset of 77 wide beam configurations, exploring variations in beam widths, concrete strengths, compression rebars, and shear reinforcement. This dataset is used to develop machine learning models, including "Genetic Programming (GP)", "Evolutionary Polynomial Regression (EPR)", and "Artificial Neural Network (ANN)". Comparative analysis reveals GP and EPR models with over 95% correlation, while the ANN model outperforms with 99% accuracy. Sensitivity analysis underscores the significant influence of concrete strength and beam aspect ratio on shear strength. In conclusion, the study demonstrates the potential of FEA and machine learning models to predict shear strength in wide-shallow reinforced concrete beams, providing valuable insights for architectural design and engineering practices and emphasizing the role of concrete strength and beam geometry in shear behavior. [ABSTRACT FROM AUTHOR]

Speech is produced by a nonlinear, dynamical Vocal Tract (VT) system, and is transmitted through multiple (air, bone and skin conduction) modes, as captured by the air, bone and throat microphones respectively. Speaker specific characteristics that capture this nonlinearity are rarely used as stand-alone features for speaker modeling, and at best have been used in tandem with well known linear spectral features to produce tangible results. This paper proposes Recurrent Plot (RP) embeddings as stand-alone, non-linear speaker-discriminating features. Two datasets, the continuous multimodal TIMIT speech corpus and the consonant-vowel unimodal syllable dataset, are used in this study for conducting closed-set speaker identification experiments. Experiments with unimodal speaker recognition systems show that RP embeddings capture the nonlinear dynamics of the VT system which are unique to every speaker, in all the modes of speech. The Air (A), Bone (B) and Throat (T) microphone systems, trained purely on RP embeddings perform with an accuracy of 95.81%, 98.18% and 99.74%, respectively. Experiments using the joint feature space of combined RP embeddings for bimodal (A–T, A–B, B–T) and trimodal (A–B–T) systems show that the best trimodal system (99.84% accuracy) performs on par with trimodal systems using spectrogram (99.45%) and MFCC (99.98%). The 98.84% performance of the B–T bimodal system shows the efficacy of a speaker recognition system based entirely on alternate (bone and throat) speech, in the absence of the standard (air) speech. The results underscore the significance of the RP embedding, as a nonlinear feature representation of the dynamical VT system that can act independently for speaker recognition. It is envisaged that speech recognition too will benefit from this nonlinear feature. [ABSTRACT FROM AUTHOR]

This paper aims to estimate the permeability of concrete by replacing the laboratory tests with robust machine learning (ML)-based models. For this purpose, the potential of twelve well-known ML techniques was investigated in estimating the water penetration depth (WPD) of nano natural pozzolana (NNP)-reinforced concrete based on 840 data points. The preparation of concrete specimens was based on the different combinations of NNP content, water-to-cement (W/C) ratio, median particle size (MPS) of NNP, and curing time (CT). Comparing the results estimated by the ML models with the laboratory results revealed that the hist-gradient boosting regressor (HGBR) and K-nearest neighbors (KNN) algorithms were the most and least robust models to estimate the WPD of NNP-reinforced concrete, respectively. Both laboratory and ML results showed that the WPD of NNP-reinforced concrete decreased with the increase of the NNP content from 1 to 4%, the decrease of the W/C ratio and the MPS, and the increase of the CT. To further aid in the estimation of concrete's WPD for engineering challenges, a graphical user interface for the ML-based models was developed. Proposing such a model may be effectively employed in the management of concrete quality. [ABSTRACT FROM AUTHOR]

Knowledge distillation is an effective approach for training robust multi-modal machine learning models when synchronous multimodal data are unavailable. However, traditional knowledge distillation techniques have limitations in comprehensively transferring knowledge across modalities and models. This paper proposes a multiscale knowledge distillation framework to address these limitations. Specifically, we introduce a multiscale semantic graph mapping (SGM) loss function to enable more comprehensive knowledge transfer between teacher and student networks at multiple feature scales. We also design a fusion and tuning (FT) module to fully utilize correlations within and between different data types of the same modality when training teacher networks. Furthermore, we adopt transformer-based backbones to improve feature learning compared to traditional convolutional neural networks. We apply the proposed techniques to multimodal human activity recognition and compared with the baseline method, it improved by 2.31% and 0.29% on the MMAct and UTD-MHAD datasets. Ablation studies validate the necessity of each component. [ABSTRACT FROM AUTHOR]

Effective management of dementia requires the timely detection of mild cognitive impairment (MCI). This paper introduces a multi-objective optimization approach for selecting EEG channels (and features) for the purpose of detecting MCI. Firstly, each EEG signal from each channel is decomposed into subbands using either variational mode decomposition (VMD) or discrete wavelet transform (DWT). A feature is then extracted from each subband using one of the following measures: standard deviation, interquartile range, band power, Teager energy, Katz's and Higuchi's fractal dimensions, Shannon entropy, sure entropy, or threshold entropy. Different machine learning techniques are used to classify the features of MCI cases from those of healthy controls. The classifier's performance is validated using leave-one-subject-out (LOSO) cross-validation (CV). The non-dominated sorting genetic algorithm (NSGA)-II is designed with the aim of minimizing the number of EEG channels (or features) and maximizing classification accuracy. The performance is evaluated using a publicly available online dataset containing EEGs from 19 channels recorded from 24 participants. The results demonstrate a significant improvement in performance when utilizing the NSGA-II algorithm. By selecting only a few appropriate EEG channels, the LOSO CV-based results show a significant improvement compared to using all 19 channels. Additionally, the outcomes indicate that accuracy can be further improved by selecting suitable features from different channels. For instance, by combining VMD and Teager energy, the SVM accuracy obtained using all channels is 74.24%. Interestingly, when only five channels are selected using NSGA-II, the accuracy increases to 91.56%. The accuracy is further improved to 95.28% when using only 8 features selected from 7 channels. This demonstrates that by choosing informative features or channels while excluding noisy or irrelevant information, the impact of noise is reduced, resulting in improved accuracy. These promising findings indicate that, with a limited number of channels and features, accurate diagnosis of MCI is achievable, which opens the door for its application in clinical practice. [ABSTRACT FROM AUTHOR]

One of the major problems of using nanofluids in heat exchange applications is the forming and deposition of nanoparticles on the inner surface of the heat exchanger. In this paper, Water-Cmc fluid is used as a surfactant for nanoparticles to prevent deposition and congregation. The pressure drops and heat transfer in U-bend double pipe heat exchanger based on water-MgO-Cmc fluid, are examined. Nanoparticles of Magnesium Oxide (MgO) and Carboxymethyl Cellulose (Cmc) are used with pure water as a base fluid. The experimental rig and procedures are designed to facilitate various operational conditions such as flow rate, volume concentration of MgO particles and weight concentration of Cmc particles. Furthermore, convective heat transfer coefficient, heat exchanger effectiveness, pressure drop, friction factor, under different conditions, are measured. The results demonstrate convective heat transfer coefficient of U-bend double pipe heat exchangers is enhanced by 35% for 1 MgO vol.% and 0.2 Cmc wt.% compared to base fluid (Water-Cmc). It is concluded that pressure drops are directly proportion to the increase of MgO nanoparticles at same Cmc concentration by 23% at 0.2 wt.%. Whilst, friction factor of the system is inversely proportion to the increase of volumetric flow rate of water-MgO-Cmc fluid. An increase in MgO nanoparticle concentration increases the friction factor, hence maximum friction factor enhancement by 38% for MgO concentration of 1 vol.%. The effectiveness of heat exchanger is slightly increased by 8% with increase of MgO concentration and flow rate. Finally, thermo-physical characteristics of water-MgO-Cmc fluid at various temperatures, are measured [ABSTRACT FROM AUTHOR]

The min–max multi-vehicle Chinese postman problem is an NP-hard problem, which is widely used in path planning problems based on road network graphs, such as urban road structure probing planning, urban road underground cavity detection planning, high-voltage line inspection planning, and so on. With the rapid increase in the number of nodes and connections of road network graph, the solution time and path equilibrium constraints pose new challenges to the problem solving. In this paper, we propose a critical-edge tabu search algorithm, CTA-kroutes, for solving the min–max multi-vehicle postman problem for large-scale road networks. First, the initial solution with balanced path lengths is obtained by segmenting the Eulerian paths; second, the critical edges are moved in the initial solution to construct the neighborhood solution, and the tabu search algorithm is used to find the optimal solution iteratively; and lastly, the solution optimization algorithm is used at the end of each iteration to de-duplicate and optimally reconstruct the current search result. Experiments show that the CTA-kroutes algorithm can effectively improve the equalization of multi-vehicle paths and its applicability to large-scale road networks. [ABSTRACT FROM AUTHOR]

The advent of Industry 4.0 has significantly promoted the field of intelligent manufacturing, which is facilitated by the development of new technologies are emerging. Robot technology and robot intelligence methods have rapidly developed and been widely applied. Manipulators are widely used in industry, and their control is a crucial research topic. The inverse kinematics solution of manipulators is an important part of manipulator control, which calculates the joint angles required for the end effector to reach a desired position and posture. Traditional inverse kinematics solution algorithms often face the problem of insufficient generalization, and iterative methods have challenges such as large computation and long solution time. This paper proposes a reinforcement learning-based inverse kinematics solution algorithm, called the MAPPO-IK algorithm. The algorithm trains the manipulator agent using the MAPPO algorithm and calculates the difference between the end effector state of the manipulator and the target posture in real-time by designing a reward mechanism, while considering Gaussian distance and cosine distance. Through experimental comparative analysis, the feasibility, computational efficiency, and superiority of this reinforcement learning algorithm are verified. Compared with traditional inverse kinematics solution algorithms, this method has good generalization and supports real-time computation, and the obtained result is a unique solution. Reinforcement learning algorithms have better adaptability to complex environments and can handle different sudden situations in different environments. This algorithm also has the advantages of path planning, intelligent obstacle avoidance, and other advantages in dynamically processing complex environmental scenes. [ABSTRACT FROM AUTHOR]

Farmland transfer is a critical component in facilitating agricultural scale management and improving agricultural production efficiency. This study examines the spatial distribution of farmland transfer in China and identifies the factors influencing it, offering valuable guidance for advancing China's farmland transfer practices. Through the application of mathematical statistics and GIS spatial analysis, the study investigates changes in spatial patterns related to the scale, rate, mode, and recipients of farmland transfer across China's 30 provinces from 2015 to 2020. Geographical detectors are also employed to identify the key factors influencing the extent and pace of farmland transfer. The study reveals that between 2015 and 2020, China's farmland transfer area increased from 29,789 to 37,638 million hectares. Provinces with abundant farmland resources generally experienced larger farmland transfers, while economically developed regions and major grain-producing areas saw higher rates of farmland transfers. The predominant mode of farmland transfer in China was leasing (subcontracting), accounting for over 80% of the total transferred area. Large-scale grain growers and family farms were significant participants in farmland transfers, acquiring approximately 60.1% of the transferred lands, followed by professional cooperatives (21.5%), enterprises (10.4%), and other entities (7.9%). Key factors influencing the farmland transfer area include the "regional farmland area", the "proportion of family farms supported by loans", and the "proportion of non-agricultural population", with explanatory powers of 0.663, 0.319, and 0.225, respectively. Notably, there is a substantial interaction between the "regional farmland area" and factors such as the "proportion of family farms supported by loans" and the "grain yield per unit area", with explanatory powers reaching 0.957 and 0.901, respectively. These findings offer valuable insights for promoting farmland transfer in agriculturally rich regions. Factors affecting the farmland transfer rate include "grain yield per unit area", "GDP per capita", and the "proportion of non-agricultural population", each with an explanatory power above 0.500. Moreover, their interactive explanatory powers with other indicators exceed 0.600, indicating that provinces with high agricultural productivity or economic development levels are more likely to undergo farmland transfer. The paper concludes by proposing strategies and recommendations to promote farmland transfer in both "large agricultural areas" and "metropolitan suburbs." [ABSTRACT FROM AUTHOR]