Search

The Internet of Things (IoT) network is a fast-growing technology, which is efficiently used in various applications. In an IoT network, the massive amount of connecting nodes is the existence of day-to-day communication challenges. The platform of IoT uses a cloud service as a backend for processing information and maintaining remote control. To manage the developing intricacy of cyberattacks, it is critical to have an effectual intrusion detection system (IDS), which can monitor computer sources and create data on suspicious or abnormal actions. The IoT network's security can progressively become a critical concern as IoT technology obtains extensive use. Protecting IoT systems with traditional IDS is challenging due to the vast variety and volume of IoT devices. Currently, Machine Learning (ML) and Deep Learning (DL) techniques are utilized to address the security threats in IoT networks. This manuscript proposes a Cybersecurity through an Attention-based Stacked Autoencoder with a Pelican Optimization Algorithm for the Detection and Mitigation of Attacks (CASAE-POADMA) methodology on an IoT-assisted network. The main purpose of the CASAE-POADMA methodology is to identify and mitigate the presence of cybersecurity attack behavior in the IoT-assisted network. At first, the presented CASAE-POADMA approach utilizes min–max normalization to scale input data into a uniform design. Besides, the greylag goose optimization (GGO) method is employed for the feature selection process. For the detection and mitigation of attack, the presented CASAE-POADMA approach employs the attention-based stacked autoencoder (ASAE) method. Eventually, the hyperparameter tuning of the ASAE method is executed by using pelican optimization algorithm (POA) method. The simulation validation of the CASAE-POADMA approach is verified under a benchmark database. The experimental validation of the CASAE-POADMA approach exhibited a superior accuracy value of 99.50% over existing techniques. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Research in Education Sciences is the property of National Taiwan Normal University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Waterlogging warning has gradually become an important means of urban waterlogging prevention and control. However, the current urban waterlogging warning model still has problems such as low accuracy, real‐time performance, and poor model convergence. To better address these issues, this article combines particle swarm optimization (PSO) and deep neural networks (DNN) to explore the construction of early warning models in depth. First, the influencing factors of urban waterlogging were analyzed in the article, and the PSO algorithm was used to determine the influencing factors of urban waterlogging in this study; then, the selected influencing factors were used as input data to design a backpropagation (BP) neural network (NN) structure; several representative waterlogging points can be selected to construct a BP NN model and perform fitting analysis. Afterward, combined with the PSO algorithm, the constructed model was trained and optimized. In this article, the old town of Hefei City is used as the experimental object, and the building model is used to conduct early warning research on waterlogging. The study's findings indicate that the PSO + BP model's average accuracy in 10 early warning tests is as high as 97.95%, with a response time of only 0.022 ms; the average accuracy and response time of the BP model are 89.06% and 0.255 ms, respectively; the Bayesian network model (BN model) is 82.78% and 0.275 ms. Through the analysis of actual cases in the old urban area of Hefei City, the advantages of this model in practical application were verified, and a new intelligent warning method for urban waterlogging prevention and control was provided, demonstrating its effectiveness and potential in dealing with complex nonlinear problems. [ABSTRACT FROM AUTHOR]

A mathematical model of the aerodynamic and thermal processes in dry granulation of molten blast-furnace slag is developed and evaluated, and a relevant problem is formulated. The model is supposed to be used for numerical optimization of the process parameters when issuing input data for the design of the dry granulation plant. [ABSTRACT FROM AUTHOR]

Machine learning and response surface methods for predicting the compressive strength of high-strength concrete have not been adequately compared. Therefore, this research aimed to predict the compressive strength of high-strength concrete (HSC) using different methods. To achieve this purpose, neuro-fuzzy inference systems (ANFISs), artificial neural networks (ANNs), and response surface methodology (RSM) were used as ensemble methods. Using an ANN and ANFIS, high-strength concrete (HSC) output was modeled and optimized as a function of five independent variables. The RSM was designed with three input variables: cement, and fine and coarse aggregate. To facilitate data entry into Design Expert, the RSM model was divided into six groups, with p-values of responses 1 to 6 of 0.027, 0.010, 0.003, 0.023, 0.002, and 0.026. The following metrics were used to evaluate model compressive strength projection: R, R2, and MSE for ANN and ANFIS modeling; R2, Adj. R2, and Pred. R2 for RSM modeling. Based on the data, it can be concluded that the ANN model (R = 0.999, R2 = 0.998, and MSE = 0.417), RSM model (R = 0.981 and R2 = 0.963), and ANFIS model (R = 0.962, R2 = 0.926, and MSE = 0.655) have a good chance of accurately predicting the compressive strength of high-strength concrete (HSC). Furthermore, there is a strong correlation between the ANN, RSM, and ANFIS models and the experimental data. Nevertheless, the artificial neural network model demonstrates exceptional accuracy. The sensitivity analysis of the ANN model shows that cement and fine aggregate have the most significant effect on predicting compressive strength (45.29% and 35.87%, respectively), while superplasticizer has the least effect (0.227%). RSME values for cement and fine aggregate in the ANFIS model were 0.313 and 0.453 during the test process and 0.733 and 0.563 during the training process. Thus, it was found that both ANN and RSM models presented better results with higher accuracy and can be used for predicting the compressive strength of construction materials. [ABSTRACT FROM AUTHOR]

Mineral prospectivity mapping (MPM) is designed to reduce the exploration search space by combining and analyzing geological prospecting big data. Such geological big data are too large and complex for humans to effectively handle and interpret. Artificial intelligence (AI) algorithms, which are powerful tools for mining nonlinear mineralization patterns in big data obtained from mineral exploration, have demonstrated excellent performance in MPM. However, AI-driven MPM faces several challenges, including difficult interpretability, poor generalizability, and physical inconsistencies. In this study, based on previous studies, we devised a novel workflow that aims to constructing more transparent and explainable artificial intelligence (XAI) models for MPM by embedding domain knowledge throughout the AI-driven MPM, from input data to model design and model output. This newly proposed approach provides strong geological and conceptual leads that guide the entire AI-driven MPM model training process, thereby improving model interpretability and performance. Overall, the development of XAI models for MPM is capable of embedding prior and expert knowledge throughout the modeling process, presenting a valuable and promising area for future research designed to improve MPM. [ABSTRACT FROM AUTHOR]

Accurate modelling of occupancy patterns is critical for reliable estimation of building stock energy demand, which is a key input for the design of district energy systems. Aiming to investigate the suitability of different occupancy-modelling approaches for the design of district energy systems, the present study examines a set of standard-based schedules (from the UK National Calculation Methodology), a widely used stochastic occupancy model, and a novel energy-data-driven occupancy model. To this end, a dynamic energy model of a higher education office building developed within a stock model of London's Bloomsbury district serves as a testbed to implement the occupancy models, explore their implications for the estimation of annual and peak heating and cooling demand, and extrapolate the findings to the computationally demanding building stock stimulations. Furthermore, the simulations were conducted in two years before and after the COVID-19 pandemic to examine the implications of hybrid working patterns after the pandemic. From the results, the energy-data-driven model demonstrated superior performance in annual heating demand estimations, with errors of ±2.5% compared to 14% and 7% for the standard-based and stochastic models. For peak heating demand, the models performed rather similarly, with the data-driven model showing 28% error compared to 29.5% for both the standard-based and stochastic models in 2019. In cooling demand estimations, the data-driven model yielded noticeably higher annual cooling demand and lower peak cooling demand estimations as compared with the standard-based and stochastic occupancy models. Given the adopted building-modelling approach, these findings can be extended to district-level investigations and inform the decision on the choice of occupancy models for building stock energy simulation. [ABSTRACT FROM AUTHOR]

Tool condition monitoring technology is an indispensable part of intelligent manufacturing. Most current research focuses on complex signal processing techniques or advanced deep learning algorithms to improve prediction performance without fully leveraging the end-to-end advantages of deep learning. The challenge lies in transforming multi-sensor raw data into input data suitable for direct model feeding, all while minimizing data scale and preserving sufficient temporal interpretation of tool wear. However, there is no clear reference standard for this so far. In light of this, this paper innovatively explores the processing methods that transform raw data into input data for deep learning models, a process known as an input paradigm. This paper introduces three new input paradigms: the downsampling paradigm, the periodic paradigm, and the subsequence paradigm. Then an improved hybrid model that combines a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) was employed to validate the model's performance. The subsequence paradigm demonstrated considerable superiority in prediction results based on the PHM2010 dataset, as the newly generated time series maintained the integrity of the raw data. Further investigation revealed that, with 120 subsequences and the temporal indicator being the maximum value, the model's mean absolute error (MAE) and root mean square error (RMSE) were the lowest after threefold cross-validation, outperforming several classical and contemporary methods. The methods explored in this paper provide references for designing input data for deep learning models, helping to enhance the end-to-end potential of deep learning models, and promoting the industrial deployment and practical application of tool condition monitoring systems. [ABSTRACT FROM AUTHOR]

This paper proposes an iteration-based algorithm for the optimum design of a high frequency transformer for solid-state transformer (SST) applications. This algorithm minimizes the total owning cost (TOC) of a distribution type solid-state transformer. The unique features of this algorithm compared with the available algorithms in the literature are as follows: it iterates eight design variables, four constraints are defined for selecting the valid designs, and it works with different core materials and AC test voltages. The algorithm uses various user-defined data inputs to calculate loss capitalization values for TOC calculation. In every iteration, TOC is estimated, and calculated values of design constraints are compared with their threshold limits. A case study is conducted on a high-frequency transformer (HFT) incorporated in 1000-kVA, 11-kV/415-V, Dyn11 three-phase wound core SST. This is to determine the optimum design parameters. In this case study, the algorithm was iterated with 2,100,000 design data inputs, generating 258,272 designs that satisfied all design constraints. The optimum design with minimum TOC is selected from the generated 258,272 designs. The optimum design is validated using finite element analysis in ANSYS software. Comparing the results of both analyses, the deviation is less than 5%. Hence, the algorithm's reliability is proved. [ABSTRACT FROM AUTHOR]

This paper deals with a LabView instrument we made for dimensioning a toroidal transformer that is usually used with low primary voltage and two secondary voltages. This virtual instrument is meant to ease the calculation process of such a transformer by inputting the design data and obtaining the dimensions of the constructive elements and the electrical quantities. Such a tool can be used both in design and in didactic activities, allowing to easily modify the input values for study or to find an optimal option as well. [ABSTRACT FROM AUTHOR]

Given the importance of comfort and safety in various driving circumstances, the suspension system emerges as the most crucial component. Two different suspension systems, passive (PSS) and semi-active (SASS), are compared for effectiveness in this research. MATLAB/Simulink is used for simulation, employing a representative two-degree-of-freedom car model to evaluate and compare the performance results of these systems. The differential equations of motion for the two systems are modeled and simulated using software, which illuminates how they would behave under the same parameters and circumstances. Additionally, a Magnetorheological damper (MR) model with a ¼ vehicle system is used to evaluate its behavior on various types of roads, including those with steps, bumps, and random inputs. This study utilizes the Bingham plastic model to compare the simulation results of SASS and PSS systems. After comparing the numerical and graphical results from the two systems, it is observed that SASSs with controllers perform better than PSSs in terms of suspension adjustment and response time. The SASS is superior to the PSS in suppressing oscillations by 55.12%, 77.47%, and 86.78% for step input, bump, and random inputs, respectively. Additionally, the SASS is faster in eliminating oscillations compared to the PSS by 54% and 51.7% for step input and bump inputs, respectively. [ABSTRACT FROM AUTHOR]

The acquisition of digital images is susceptible to haze, and images captured under such adverse conditions may impact high-level applications designed for clean input data. Image dehazing emerges as a practical solution to this problem, as it can be employed to pre-process images immediately after acquisition. This paper presents a concise review of impactful algorithms, including those based on deep learning models, to identify the existing gap in real-time processing capabilities. Subsequently, a real-time dehazing system on a multiprocessor system-on-a-chip (MPSoC) platform is introduced to bridge this gap. The proposed system balances the trade-off between dehazing performance and computational complexity; hence, the name "Symmetric" is coined. Additionally, the entire system is implemented in programmable logic and wrapped by an interface circuit supporting double-buffering, rendering it highly suitable for seamless integration into existing camera systems. Implementation results on a Zynq UltraScale+ MPSoC ZCU106 Evaluation Kit demonstrate a maximum operating frequency of 356.51 MHz, equivalent to a maximum processing speed of 40.27 frames per second for DCI 4K resolution. [ABSTRACT FROM AUTHOR]

Analyzing the correlation between cephalometric measurements is important for improving our understanding of the anatomy in the oral and maxillofacial region. To minimize bias resulting from the design of the input data and to establish a reference for malocclusion research, the aims of this study were to construct the input set by integrating nine cephalometric analyses and to study the correlation structure of cephalometric variables in Korean adults with normal occlusion. To analyze the complex correlation structure among 65 cephalometric variables, which were based on nine classical cephalometric analyses, network analysis was applied to data obtained from 735 adults (368 males, 367 females) aged 18–25 years with normal occlusion. The structure was better revealed through weighted network analysis and minimum spanning tree. Network analysis revealed cephalometric variable clusters and the inter- and intra-correlation structure. Some metrics were divided based on their geometric interpretation rather than their clinical significance. It was confirmed that various classical cephalometric analyses primarily focus on investigating nine anatomical features. Investigating the correlation between cephalometric variables through network analysis can significantly enhance our understanding of the anatomical characteristics in the oral and maxillofacial region, which is a crucial step in studying malocclusion using artificial intelligence. [ABSTRACT FROM AUTHOR]

The software testing phase requires considerable time, effort, and cost, particularly when there are many faults. Thus, developers focus on the evolution of Software Fault Prediction (SFP) to predict faulty units in advance, therefore, improving software quality significantly. Forecasting the number of faults in software units can efficiently direct software testing efforts. Previous studies have employed several machine learning models to determine whether a software unit is faulty. In this study, a new, simple deep neural network approach that can adapt to the type of input data was designed, utilizing Convolutional Neural Networks (CNNs) and Multi-Layer Perceptron (MLP), to predict the number of software faults. Twelve open-source software project datasets from the PROMISE repository were used for testing and validation. As data imbalance can negatively impact prediction accuracy, the new version of synthetic minority oversampling technique (SMOTEND) was used to resolve data imbalance. In experimental results, a lower error rate was obtained for MLP, compared to CNN, reaching 0.195, indicating the accuracy of this prediction model. The proposed approach proved to be effective when compared with two of the best machine learning models in the field of prediction. The code will be available on GitHub. [ABSTRACT FROM AUTHOR]

With a large proportion of wind farms connected to the power grid, it brings more pressure on the stable operation of power systems in shorter time scales. Efficient and accurate scheduling, operation control and decision making require high time resolution power forecasting algorithms with higher accuracy and real-time performance. In this paper, we innovatively propose a high temporal resolution wind power forecasting method based on a light convolutional architecture—DC_LCNN. The method starts from the source data and novelly designs the dual-channel data input mode to provide different combinations of feature data for the model, thus improving the upper limit of the learning ability of the whole model. The dual-channel convolutional neural network (CNN) structure extracts different spatial and temporal constraints of the input features. The light global maximum pooling method replaces the flat operation combined with the fully connected (FC) forecasting method in the traditional CNN, extracts the most significant features of the global method, and directly performs data downscaling at the same time, which significantly improves the forecasting accuracy and efficiency of the model. In this paper, the experiments are carried out on the 1 s resolution data of the actual wind field, and the single-step forecasting task with 1 s ahead of time and the multi-step forecasting task with 1~10 s ahead of time are executed, respectively. Comparing the experimental results with the classical deep learning models in the current field, the proposed model shows absolute accuracy advantages on both forecasting tasks. This also shows that the light architecture design based on simple deep learning models is also a good solution in performing high time resolution wind power forecasting tasks. [ABSTRACT FROM AUTHOR]

Background: Neonatal sepsis made the neonatal period the most perilous time for child survival, and it continued to cause preventable mortalities worldwide. These mortalities stem from the interaction of several factors that have not been sufficiently studied and, in some cases, remain overlooked. Thus, the study aims to investigate the predictors of mortality that arise from the interaction of these factors and quantitatively determine their etiologic fraction. Methods: A case–control study with hierarchical data input was conducted at Jimma Medical Center (JMC) in Oromia, Ethiopia, spanning from May 2022 to July 2023. It employed logistic regression to calculate adjusted odds ratios (AORs) and their corresponding 95% confidence intervals (CI) at a significance level of p ≤ 0.05. The model adjusted odds ratios (ORs) for variables within each level and farther levels and presented an etiologic fraction (EF), indicating the proportion of neonatal mortality attributable to specific factors. Results: The analysis of 67 cases and 268 controls unveiled significant predictors of mortality in sepsis that emerged from distal, intermediate, and proximal levels. In the final model, thus, rural residence [AOR 3.1; 95% CI (1.5, 6.3), p ≤ 0.01], prolonged labor [AOR 4.5; 95% CI (2.2, 9.3), p ≤ 0.01], prematurity [AOR 3.9; 95% CI (1.9, 7.9), P ≤ 0.0], gram-negative bacteremia [AOR 3.8; 95% CI (1.9, 7.6); P ≤ 0.01], convulsion [AOR 3.2; 95% CI (1.6, 6.4); P ≤ 0.03], low birth weight [AOR 2.7; 95% CI (1.3, 5.4); P≤ 0.01], and delayed breastfeeding [AOR 2.5; 95% CI (1.2, 4.9); P ≤ 0.01] attributed a variable percentage of mortality. Conclusion: Factors emerging and interacting at distal (residence), intermediate (prolonged labor), and proximal (prematurity, birth weight, convulsion, bacterial etiology, and feeding) levels influence neonatal mortality in sepsis at JMC. Therefore, concurrently improving rural family characteristics, managing labor duration, strengthening diagnostic stewardship, and promoting essential newborn care can actively prevent and reduce these mortalities. Plain Language Summary: The existing body of literature indicates that neonatal mortality in sepsis is influenced by a complex interplay of factors at different hierarchical levels. These factors encompass maternal characteristics, neonatal health status, healthcare system capacity, and socio-economic conditions. To accurately predict outcomes related to neonatal sepsis mortality, it is vital to have a comprehensive understanding of the intricate relationship among these factors. However, previous studies have not thoroughly explored the extent and role of these factors in relation to neonatal sepsis mortality. In a recent study, researchers conducted a comprehensive investigation into the implications of factors at three levels: distal, intermediate, and proximate. Employing a case–control design and hierarchical data input, the study aimed to explore the etiological fraction associated with each level. The findings of this study shed light on the presence, interaction, and contribution of predictors at each level, emphasizing the vital importance of addressing factors at all levels to effectively prevent and control neonatal mortality in sepsis. [ABSTRACT FROM AUTHOR]

An express model for quantitative and qualitative evaluation of the dynamic of heat and mass exchange in flash evaporators that recover low-temperature heat of metallurgical and chemical industries is developed. This model is supposed to be used for computer optimization of the process parameters for providing input data for designing an evaporator. [ABSTRACT FROM AUTHOR]

Sequence design is a crucial step in the process of designing or engineering proteins. Traditionally, physics-based methods have been used to solve for optimal sequences, with the main disadvantages being that they are computationally intensive for the end user. Deep learning-based methods offer an attractive alternative, outperforming physics-based methods at a significantly lower computational cost. In this paper, we explore the application of Convolutional Neural Networks (CNNs) for sequence design. We describe the development and benchmarking of a range of networks, as well as reimplementations of previously described CNNs. We demonstrate the flexibility of representing proteins in a three-dimensional voxel grid by encoding additional design constraints into the input data. Finally, we describe TIMED-Design, a web application and command line tool for exploring and applying the models described in this paper. The user interface will be available at the URL: https://pragmaticproteindesign.bio.ed.ac.uk/timed. The source code for TIMED-Design is available at https://github.com/wells-wood-research/timed-design. [ABSTRACT FROM AUTHOR]

The preparation of laser scanning missions is important for efficiency and data quality. Furthermore, it is a prerequisite for automated data acquisition, which has numerous applications in the built environment, including autonomous inspections and monitoring of construction progress and quality criteria. The scene and potential scanning locations can be discretized to facilitate the analysis of visibility and quality aspects. The remaining mathematical problem to generate an economic scan strategy is the Viewpoint Planning Problem (VPP), which asks for a minimum number of scanning locations within the given scene to cover the scene under pre-defined requirements. Solutions for this problem are most commonly found using heuristics. While these efficient methods scale well, they cannot generally return globally optimal solutions. This paper investigates the VPP based on a problem description that considers quality-constrained visibility in 3D scenes and suitable overlaps between individual viewpoints for targetless registration of acquired point clouds. The methodology includes the introduction of a preprocessing method designed to simplify the input data without losing information about the problem. The paper details various solution methods for the VPP, encompassing conventional heuristics and a mixed-integer linear programming formulation, which is solved using Benders decomposition. Experiments are carried out on two case study datasets, varying in specifications and sizes, to evaluate these methods. The results show the actual quality of the obtained solutions and their deviation from optimality (in terms of the estimated optimality gap) for instances where exact solutions can not be achieved. [ABSTRACT FROM AUTHOR]

In this paper, a data-driven modeling method for precast concrete (PC) balcony components was proposed to solve the problems of low informatization and the difficult modeling of components at the design stage. Through the analysis of the characteristics of PC balcony components and the combination of modular design methods, the paper designed a data structure for the components and developed a data-driven modeling tool for PC balcony components that can realize the input of structural design data, automatically generating component models. First, this paper introduced the data-driven modeling concept and the modeling process. Second, the PC balcony components in common prefabricated residential projects were analyzed to identify their characteristics. By using a modular design approach, these components were divided and a module dataset was created based on the split modules. Consequently, a data structure for the prefabricated balcony component model was established, wherein both conventional parameters and adaptive parameters between modules were interrelated. Finally, the function of data-driven modeling was achieved by developing a modular design tool on the Revit platform using the C# programming language. The application conducted on a prefabricated building project demonstrated that the software tool and modeling method in this paper effectively improve the level of informatization and modeling efficiency of PC balcony components. The modular design approach was satisfied with the standardization and diversification requirements of balcony components, thereby offering insights for modeling other complex components. [ABSTRACT FROM AUTHOR]

The different perceptions of food and agriculture stakeholders about the future is a key input to design future-oriented public policies and to build a shared vision of the future. By applying the futures triangle to the results of a qualitative study concerning the future of food and agriculture innovation system in Argentine, five archetypes of images of the future were inferred. The archetypes reflect a distinct combination between the weight of history, the pushes of the present and the pulls of the future, corresponding to the perception of the future of nine distinct stakeholders of the food and agriculture system in Argentine. The archetypes are named: stuck in the present, the future is not ours, the future never comes, the future is being built and the future is ours. The analysis show that the stakeholders can envision the future of the world's agriculture with a certain degree of creativity. However, they find it difficult to imagine the future of the Argentine agricultural industry in new ways: they repeat the old ideas or notions they have about it. All those visions lead to a demand for changes that are more connected to the present than to the future. This foresight study offers a first approach to explore the different views regarding the future of food and agriculture and it reveals how such views influence the type and characteristics of the new stakeholders demands to the public agriculture sector in Argentina to the year 2030. [ABSTRACT FROM AUTHOR]

Objective: Using a model-based analysis, we calculated the total costs associated with the exclusive breast-feeding (EBF) and breast milk substitute (BMS) usage for one infant for six months within select humanitarian contexts to (a) determine if there is a notable difference in costs and (b) use these results to inform future creation of data-informed humanitarian response standard operating procedures. Design: The inputs and costing data were drawn from a mixture of local e-commerce vendors, peer-reviewed literature and personal communications with field-based humanitarian responders. To account for cost fluctuations, each input's costs along with low and high parameters are presented. All costs are presented in 2021 United States Dollars. Setting: Humanitarian responses within Indonesia and Jordan. Participants: Not applicable. Results: There was a notable difference in the total cost of care in both selected locations across the study arms (Indonesia: $542; Jordan: $892). Conclusions: Given the reality of limited funding for comprehensive humanitarian response around the world and the necessity of prioritising certain interventions, humanitarian response organisations should consider the notable cost difference between EBF and BMS usage (along with the proven health benefits of EBF). This difference should play a role in informing the future creation of standard operating procedures while also ensuring that all infants within a humanitarian crisis receive appropriate feeding. [ABSTRACT FROM AUTHOR]

For FAIR data storage and retrieval, GroMoPo is linked to the CUAHSI HydroShare repository (https://www.hydroshare.org/) via a resource submission with a "GroMoPo" tag. Approximately weekly, a HydroShare Python API script compiles all tagged GroMoPo resources as a single HydroShare resource (http://www.hydroshare.org/resource/114b76f89d1c41c38e0e235443c7544c) and uses this to populate the GroMoPo map. Groundwater systems are threatened worldwide by stressors including climate change, land-use/land cover change, contamination, and water use (Gleeson et al. [3]). [Extracted from the article]

The paper presents specifications for the Long-Endurance Mars Exploration Flying Vehicle (LEMFEV), which will be used as future design input data. The specifications are based on the analysis of previous Mars missions and scientific data collected by the operating Martian probes. The design specifications include the requirements related to the airplane's delivery to the Martian surface; the requirements related to the Martian conditions (atmosphere and climate); and the requirements related to the scientific payload parameters and the mission flight profile. [ABSTRACT FROM AUTHOR]

Featured Application: This study presents an overview of the several mitigation measures, including several check dams and flexible net barriers constructed in a typical Alpine torrential catchment in northern Slovenia (Europe) in order to protect infrastructure (i.e., ski resort cabin lift station, access road to the station, downstream settlements) against sediment-related disasters due to torrential hazards, such as flash floods and debris floods, debris flows, and shallow landslides. This newly introduced combination of technical countermeasures in Slovenia withstood the extreme floods in August 2023. Different sediment-related disasters due to torrential hazards, such as flash floods, debris flows, and landslides, can occur in an Alpine torrential catchment. When protecting infrastructure and human lives, different structural and non-structural protection measures can be used to mitigate permanent and future risks. An overview of the mitigation measures constructed near the Krvavec ski resort in northwest Slovenia (Central Europe) is presented. In May 2018, an extreme debris flood occurred in this area, causing significant economic damage. After the May 2018 event, different field investigations (i.e., geological and topographic surveys) and modeling applications (e.g., hydrological modeling, debris flow) have been conducted with the purpose of preparing the required input data for the design of protection measures against such disasters in future—due to climate change, more disasters are expected to happen in this torrential watershed. The mitigation includes the restoration of local streams, the construction of a large slit check dam for sediment retention, the construction of several smaller check dams and the construction of 16 flexible net barriers with an estimated ~8000 m3 retention volume for controlling in-channel erosion in steep torrential streams. Additionally, in order to observe and monitor potential future extreme events, an extensive monitoring system has been established in the investigated area. This monitoring system will cover measurements of flexible net corrosion, the estimation of concrete abrasion at check dams, periodical geodetic surveys using small drones (UAV), hydro-meteorological measurements using rainfall gauges and water level sensors. The recent extreme floods of August 2023 also hit this part of Slovenia, and this combination of technical countermeasures withstood the event and prevented large amounts of coarse debris from being transported to the downstream section and devastating infrastructure, as was the case in May 2018 during a less extreme event. Therefore, such mitigation measures can also be used in other torrential catchments in the Alpine environment. [ABSTRACT FROM AUTHOR]

DEMATEL serves as a tool for addressing multi-criteria decision-making problems, primarily by identifying critical factors that exert the most significant influence on a specific system. To enhance its capabilities in handling contextual decision problems, DEMATEL has been further developed through integration with various other MCDM methods. The inherent reliance on direct input from experts for initial decision information in DEMATEL raises concerns about the potential limitations imposed by experts' domain knowledge and bounded rationalities. The effectiveness of decision-making can be compromised if the initial information provided by experts is deemed unreliable, leading to debatable outcomes. To address these challenges, this study proposes the incorporation of a Bonferroni mean aggregation operator within a Pythagorean neutrosophic environment, illustrated through a numerical example applied to DEMATEL. This integration is intended to fortify decision accuracy by introducing a more enhanced decision framework by developing a new normalized weighted Bonferroni mean operator for Pythagorean neutrosophic set aggregation (PN-NWBM). By integrating this operator, this study aims to alleviate the impact of unreliable initial information and enhance the overall reliability of decision outcomes thereby contributing to its improvement in decision making. Through the implementation of the Bonferroni mean aggregation operator, the study anticipates achieving a more comprehensive and accurate representation of decision factors as illustrated in the numerical example. This research includes a comparative and sensitivity analysis to thoroughly examine the implications and effectiveness of the proposed integration. [ABSTRACT FROM AUTHOR]

The idea of the person re-identification (Re-ID) task is to find the person depicted in the query image among other images obtained from different cameras. Algorithms solving this task have important practical applications, such as illegal action prevention and searching for missing persons through a smart city's video surveillance. In most of the papers devoted to the problem under consideration, the authors propose complex algorithms to achieve a better quality of person Re-ID. Some of these methods cannot be used in practice due to technical limitations. In this paper, we propose several approaches that can be used in almost all popular modern re-identification algorithms to improve the quality of the problem being solved and do not practically increase the computational complexity of algorithms. In real-world data, bad images can be fed into the input of the Re-ID algorithm; therefore, the new Filter Module is proposed in this paper, designed to pre-filter input data before feeding the data to the main re-identification algorithm. The Filter Module improves the quality of the baseline by 2.6 % according to the R a n k 1 metric and 3.4 % according to the m A P metric on the Market-1501 dataset. Furthermore, in this paper, a fully automated data collection strategy from surveillance cameras for self-supervised pre-training is proposed in order to increase the generality of neural networks on real-world data. The use of self-supervised pre-training on the data collected using the proposed strategy improves the quality of cross-domain upper-body Re-ID on the DukeMTMC-reID dataset by 1.0 % according to the R a n k 1 and m A P metrics. [ABSTRACT FROM AUTHOR]

Rapid urbanization has negative effects on ecology, economics, and public health, primarily due to unchecked population growth. Sustainable building materials and methods are needed to mitigate these issues and reduce energy use, waste production, and environmental damage. This study highlights the potential of agricultural waste as a sustainable source of construction materials and provides valuable insights into the performance and benefits of using fired clay bricks made from pomegranate peel waste. In this study, fired clay bricks were produced using pomegranate peel waste as a sustainable building material. To optimize the firing temperature and percentage of pomegranate peel waste, a series of experiments was conducted to determine fundamental properties such as mechanical, physical, and thermal properties. Subsequently, the obtained thermal properties were utilized as input data in Design Builder software version (V.5.0.0.105) to assess the thermal and energy performance of the produced bricks. The results showed that the optimum firing temperature for the bricks was 900 °C with 10% pomegranate peel waste. The fabricated bricks reduced energy consumption by 6.97%, 8.54%, and 13.89% at firing temperatures of 700 °C, 800 °C, and 900 °C, respectively, due to their decreased thermal conductivity. CO2 emissions also decreased by 4.85%, 6.07%, and 12% at the same firing temperatures. The payback time for the bricks was found to be 0.65 years at a firing temperature of 900 °C. These findings demonstrate the potential of fired clay bricks made from pomegranate peel waste as a promising construction material that limits heat gain, preserves energy, reduces CO2 emissions, and provides a fast return on investment. [ABSTRACT FROM AUTHOR]

The process of building microgrids on top of existing passive distribution networks warrants a multi-criteria analysis. Besides the calculation of the investment outlays needed for the modernization of distribution networks, such an analysis covers an assessment of the technological and economic effects of building microgrids. The resulting effects depend on the topology and configuration of distribution networks, specific microgrid features, the choice of the current type for the entire microgrid or its individual parts, the methods of connecting distributed energy resources (DERs), the availability and maturity of information and communications technology (ICT) infrastructure, and other factors. Comprehensive input data allow for designing an optimal microgrid configuration, but the main technological and economic effects are determined by the algorithms of operation and the parameter settings of the automatic control system (ACS) and the protection system. The known approaches to designing microgrids focus on addressing basic tasks while minimizing the investment required for their implementation. The above is fully justified when constructing new microgrids, but building microgrids on top of existing distribution networks, given the uniqueness of their topology and configuration, does not allow the use of standardized solutions. The development of approaches to the design of microgrids under such constraints, with minimized investment in the modernization of existing distribution networks, is an urgent task. The use of different types of current for individual microgrid segments determines the choice of the particular ACS and protection system, which depends on the availability of information and communications technology infrastructure. This article contributes a review of approaches to designing AC and AC–DC microgrids so as to maximize their technological and economic effects. We review techniques for analyzing the existing distribution networks aimed at choosing the type of current for the entire microgrid or its individual parts, the optimal points for the connection of microgrids to distribution networks, and the mix and capacity of DERs, with such choices informed by the conditions of the switching devices and information and communications technology infrastructure. This article presents the results of the analysis of approaches to choosing the optimal configuration of microgrids, microgrid ACS, and protection system, with an evaluation of the technological and economic effects subject to the minimization of investment in the modernization of the existing distribution networks. [ABSTRACT FROM AUTHOR]

During strategic network design, not only strategic but also operational decisions must be made long before a production network is put into operation. These include determining the location and size of inventories within the production network and setting operational parameters for production lines, such as the shift model. However, the large solution space comprising a high number of highly uncertain design parameters makes these decisions challenging without decision support. Therefore, data farming offers a potential solution, as synthetic data can be generated via the execution of multiple simulation experiments spanning the solution space and then analyzed using data mining techniques to provide data-based decision support. However, data farming has not yet been applied to strategic network design due to the lack of adequate solution space management. To address this shortcoming, this paper presents a structured solution space management approach that integrates production network-specific requirements and Design of Experiment (DoE) methods. The approach enables converting the solution space in strategic network design into individual input data sets for simulation experiments, generating a comprehensive database that can be mined for data-based decision support. The applicability and validity of the comprehensive approach are ensured via a case study in the automotive industry. [ABSTRACT FROM AUTHOR]

Background: Between March, 2020 and December, 2021 due to cholera and coronavirus disease 2019 (COVID-19) pandemics, there were 1,534 cholera cases with 14 deaths and 136,065 COVID-19 cases with 3,285 deaths reported respectively in Uganda. This study investigated mass vaccination campaigns for the prevention of the two pandemics namely: oral cholera vaccine (OCV) and COVID-19 vaccine coverage; adverse events following immunization (AEFI); barriers and enablers for the vaccine uptake and assessed water, sanitation and hygiene (WASH) conditions in the six cholera and COVID-19 hotspot districts of Uganda. Methods: A household survey was conducted between January and February, 2022 in the six cholera hotspot districts of Uganda which had recently conducted OCV mass vaccination campaigns and had ongoing COVID-19 mass vaccination campaigns. The survey randomly enrolled 900 households with 4,315 persons of whom 2,085 were above 18 years. Data were collected using a data entry application designed in KoBoToolbox and analysed using STATA version 14. Frequencies, percentages, odds ratios, means, confidence intervals and maps were generated and interpreted. Results: The OCV coverage for dose one and two were 85% (95% CI: 84.2—86.4) and 67% (95% CI: 65.6—68.4) respectively. Among the 4,315 OCV recipients, 2% reported mild AEFI, 0.16% reported moderate AEFI and none reported severe AEFI. The COVID-19 vaccination coverage for dose one and two were 69.8% (95% CI: 67.8–71.8) and 18.8% (95% CI: 17.1–20.5) respectively. Approximately, 23% (478/2,085) of COVID-19 vaccine recipient reported AEFI; most 94% were mild, 0.6% were moderate and 2 cases were severe. The commonest reason for missing COVID-19 vaccine was fear of the side effects. For most districts (5/6), sanitation (latrine/toilet) coverage were low at 7.4%—37.4%. Conclusion: There is high OCV coverage but low COVID-19 vaccine and sanitation coverage with high number of moderate cases of AEFI recorded due to COVID-19 vaccines. The low COVID-19 vaccine coverage could indicate vaccine hesitancy for COVID-19 vaccines. Furthermore, incorporation of WASH conditions assessment in the OCV coverage surveys is recommended for similar settings to generate data for better planning. However, more studies are required on COVID-19 vaccine hesitancy. [ABSTRACT FROM AUTHOR]

Data-driven models have been successfully applied to flood prediction. However, the nonlinearity and uncertainty of the prediction process and the possible noise or outliers in the data set will lead to incorrect results. In addition, data-driven models are only trained from available datasets and do not involve scientific principles or laws during the model training process, which may lead to predictions that do not conform to physical laws. To this end, we propose a flood prediction method based on data-driven and knowledge-guided heterogeneous graphs and temporal convolutional networks (DK-HTAN). In the data preprocessing stage, a low-rank approximate decomposition algorithm based on a time tensor was designed to interpolate the input data. Adding an attention mechanism to the heterogeneous graph module is beneficial for introducing prior knowledge. A self-attention mechanism with temporal convolutional network was introduced to dynamically calculate spatiotemporal correlation characteristics of flood data. Finally, we propose physical mechanism constraints for flood processes, adjusted and optimized data-driven models, corrected predictions that did not conform to physical mechanisms, and quantified the uncertainty of predictions. The experimental results on the Qijiang River Basin dataset show that the model has good predictive performance in terms of interval prediction index (PI), RMSE, and MAPE. [ABSTRACT FROM AUTHOR]

Precipitation and temperature are the most important meteorological parameters and their quantitative measurement at various return periods is one of the key inputs in the design of various hydraulic structures in diverse contexts. The present research focuses on statistical modelling of monthly maximum precipitation and temperature in the western Indian Himalayan state, Uttarakhand, over the last century (1901–2002), applying extreme value theory (EVT). EVT is an excellent statistical tool to interpret the records to estimate the future probability of the occurrence of extremities. In addition, return levels are used to forecast the likelihood of extremes of the stated meteorological parameters occurring once every 50, 100, 200, 300, and 500 years. The primary goal of this research is to provide statistical information on the behaviour of extreme temperatures and precipitation that will be useful to disaster management organisations and government policymakers in determining appropriate risk mitigation measures for the natural disaster-prone Indian Himalayan state of Uttarakhand. [ABSTRACT FROM AUTHOR]

Motivation From a systematic perspective, it is crucial to infer and analyze gene regulatory network (GRN) from high-throughput single-cell RNA sequencing data. However, most existing GRN inference methods mainly focus on the network topology, only few of them consider how to explicitly describe the updated logic rules of regulation in GRNs to obtain their dynamics. Moreover, some inference methods also fail to deal with the over-fitting problem caused by the noise in time series data. Results In this article, we propose a novel embedded Boolean threshold network method called LogBTF, which effectively infers GRN by integrating regularized logistic regression and Boolean threshold function. First, the continuous gene expression values are converted into Boolean values and the elastic net regression model is adopted to fit the binarized time series data. Then, the estimated regression coefficients are applied to represent the unknown Boolean threshold function of the candidate Boolean threshold network as the dynamical equations. To overcome the multi-collinearity and over-fitting problems, a new and effective approach is designed to optimize the network topology by adding a perturbation design matrix to the input data and thereafter setting sufficiently small elements of the output coefficient vector to zeros. In addition, the cross-validation procedure is implemented into the Boolean threshold network model framework to strengthen the inference capability. Finally, extensive experiments on one simulated Boolean value dataset, dozens of simulation datasets, and three real single-cell RNA sequencing datasets demonstrate that the LogBTF method can infer GRNs from time series data more accurately than some other alternative methods for GRN inference. Availability and implementation The source data and code are available at https://github.com/zpliulab/LogBTF. [ABSTRACT FROM AUTHOR]

This paper refers to experiments developed on the deep tunnels design of the Snowy 2.0 pumped-storage hydroelectric project in NSW, Australia. The 27 km long waterway and the power station complex are about 800 m below ground, and are in a complex tectonic and lithological setting. Long-term temperature monitoring in boreholes has been used to infer an empirical thermal model along the deep tunnels, which is presented as an example of input data for the ventilation design during construction, and for durability design during operation. An innovative aspect of this paper is related to the graphical interpretative method of borehole temperature logs that is proposed to infer downward or upward groundwater flows and predict the hydrogeological behaviour of fractured and faulted zones that cross the tunnel alignment. A large campaign of thermal acquisition in boreholes, using an acoustic televiewer probe, identified local anomalies of the geothermal gradient, which were correlated to permeability and pressure data measured in the boreholes, to identify zones of greater permeability that intersect the tunnels. Furthermore, the application of thermal measurements during tunnel excavation is proposed as an additional tool for the prediction of water inflow or identification of zones to be pre-grouted and/or drained. Thematic collection: This article is part of the Leading to Innovative Engineering Geology Practices collection available at: https://www.lyellcollection.org/topic/collections/leading-to-innovative-engineering-geology-practices [ABSTRACT FROM AUTHOR]

A methodological approach to estimate the sustainability performance of biorefineries is proposed as a way to elucidate the best alternative to upgrade biomass under a specific context. This methodology is based on the estimation of technical, economic, environmental, and social metrics. The methodology provides flexibility to design biorefineries using knowledge-based or optimization approaches. The advantage of the optimization approach is the possibility to ensure the economic feasibility of a process configuration without repeating the dimensions analysis for different scenarios. Then, the sustainability index is proposed as an indicator to compare different biorefinery configurations wherever. An avocado case study was analyzed considering a superstructure based on the possible upgrading pathways at a small-scale level. The sustainability index for a biorefinery addressed to producing avocado oil, animal feed, biogas, and electricity was about 54%. This performance suggests the need of improving processing lines and proposing new products. Finally, the sustainability index is proposed as an indicator easy to calculate, analyze, and understand for stakeholders and shareholders (i.e., decision-making groups). • A methodology to estimate the sustainability index of a biorefinery is proposed. • Avocado-based processes are analyzed considering the rural areas context. • Pilot-scale gasification of avocado seeds is presented. • Context variables and logistic variables are presented as key inputs for biorefineries design. [ABSTRACT FROM AUTHOR]

Copyright of Railway Standard Design is the property of Railway Standard Design Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This article aims to investigate the influence of different contact conditions on the friction properties of an Nb-stabilized AISI 430 ferritic stainless-steel sheet with deep drawing quality. Three tribological tests were performed: pin-on-disk, bending under tension, and strip-tension test. Moreover, counter samples of a hard metal (WC-12%Co) with surface finishes of 0.27 and 0.54 μm were used in the friction tests under dry and lubricated conditions. The influence of the texture and relative elongation of the strip on formability also were investigated. A comparative analysis of the results revealed that the coefficients of friction, wear, lubricant efficiency, and hardness measured below the wear surface indicated a strong dependence on surface roughness and the friction test type. The coefficients of friction obtained from the pin-on-disk test were higher than those obtained from the formability tests. In addition, the coefficient of friction increased with increasing relative elongation during the formability tests; it was higher in the bending-under-tension test than in the strip-tension test, mainly owing to the increasing strip surface roughness. The contact pressure during the formability tests was non-uniform during strip sliding under the tool. According to our results, for each friction condition in a specific area of the forming die, there is a value of the coefficient of friction, depending on the kinematic conditions. Therefore, the results can be used as input data to define design guidelines, improve productivity, and improve product quality from this steel sheet. [ABSTRACT FROM AUTHOR]

Over the last decades, computational methods have provided significant potential for integrated façade systems with energy efficiency, the generation of numerous alternatives, the optimisation of complex requirements, and the inspiration of creativity in architecture. In this sense, the study addresses two primary issues. First, conventional methods are inadequate in a holistic perspective of the multiple objectives of façade systems. Second, poorly designed or transformed media façades are a common problem in many developing countries. This study developed a design strategy for an Integrated Façade System (IFS) that consists of (i) simulation, (ii) analysis, and (iii) optimisation stages in a feedback loop. This design strategy was implemented to integrate the façade in terms of multiple data based on functions. The methodology is organised into two main sections based on the urban scale fieldwork and test of the suggested strategy through the case study. The fieldwork has been done to determine the case study building in Istanbul. Two additional façade functions, media display, and solar shading are chosen here to investigate the constraints, correlations, and consistency of multifunctional integration in a façade system. The finding showed that the developed IFS can contribute to the use of factual data as a design input. Another result showed that this IFS decreased solar radiation by 51% during the summer period. This algorithmic system has flexibility and affordance that refers to enhancing building performance within different contexts. [ABSTRACT FROM AUTHOR]

Vanadium redox flow batteries (VRFB) are a fertile energy storage technology especially for customized storage applications with special energy and power requirements. The dimensioning and control of these storages is mostly calculated beforehand using battery models in embedded simulation structures. To cover various stack designs, chemistries, application strategies and system architectures, battery simulation models should be validated with different experimental input data and thus show universal functionality. In this study the functionality of a grey box VRFB model using current, voltage and state of charge (SOC) of a 10 kW/100 kWh VRFB as input data are validated for an adapted input data set using of a 5 kW/10 kWh VRFB. This model is designed for stationary applications of VRFB only. The contribution of this study is (i) to apply a suitable SOC conversion method to the raw data from the used 5 kW VRFB system, (ii) to adapt the modeling code for broader use and integration of the SOC conversion, (iii) to validate the functionality and (iv) to investigate the influence of constant current and constant voltage phases in the raw data on the accuracy of the model. A comparison of experimental data between different redox flow batteries shows that most VRFB measure the open circuit voltage (OCV) to calculate the SOC of the battery. Using the calculated SOC as an input data the proposed simulation model need to be adapted and a method is applied to use OCV input data for model validation. Although simulation models in general often assume linearity between SOC and OCV, the study showed sufficient accuracy using polynomic fitting of second order. Applying a parametrization process the results of the simulation model are compared to the raw data and the scope of application of the grey box VRFB model is defined. While using the dominant constant current phase for the charging and discharging cycle, the grey box simulation model has been sufficiently parametrized and validated for adapted input data. [ABSTRACT FROM AUTHOR]

• The study proposes a novel cross-subject gesture recognition approach. • An extended VAE is designed to disentangle input data into three representations. • A competitive voting strategy is to further bolster accuracy and stability in recognition. • The performance of the proposed method is evaluated on the Myo dataset. • The source code and the Myo dataset will be publicly available. Surface electromyographic hand gesture recognition has gained significant attention in recent years, especially within the field of human–computer interfaces. However, cross-subject tasks remain challenging due to inherent individual differences. To address this, a novel approach for hand gesture recognition is proposed that leverages a subject-generalized variational autoencoder. This approach involves an extended variational autoencoder designed to disentangle input data into three distinct feature-specific representations. The primary classifier within the variational autoencoder focuses on gesture recognition, while two auxiliary classifiers work together to extract subject-specific and gesture-specific features. The gesture-specific features capture generalized characteristics applicable across all subjects, enabling direct application to new subjects. To enhance accuracy and stability, a competitive voting strategy is implemented. The effectiveness of the proposed method was evaluated using a dataset comprising six representative gestures performed by eight subjects. Comparative analysis with baseline models shows that our approach outperforms others, demonstrating superior generalization with an average accuracy of 90.52% in cross-subject validation. [ABSTRACT FROM AUTHOR]

Clutter suppression is a key problem for airborne radar, and space-time adaptive processing (STAP) is a core technology for clutter suppression and moving target detection. However, in practical applications, the non-uniform time-varying environments including clutter range dependence for non-side-looking radar lead to the training samples being unable to satisfy the sample requirements of STAP that they should be independent identical distributed (IID) and that their number should be greater than twice the system's degree of freedom (DOF). The lack of sufficient IID training samples causes difficulty in the convergence of STAP and further results in a serious degeneration of performance. To overcome this problem, this paper proposes a novel autoencoder neural network for clutter suppression with a unique matrix designed to be decoded and encoded. The main challenges are improving the accuracy of the estimation of the clutter-plus-noise covariance matrix (CNCM) for STAP convergence, designing the form of the data input to the network, and making the network successfully explored to the improvement of CNCM. For these challenges, the main proposed solutions include designing a unique matrix with a certain dimension and a series of covariance data selections and matrix transformations. Consequently, the proposed method compresses and retains the characteristics of the covariances, and abandons the deviations caused by the non-uniformity and the deficiency of training samples. Specifically, the proposed method firstly develops a unique matrix whose dimension is less than half of the DOF, meanwhile, it is based on a processing of the selected clutter-plus-noise covariances. Then, an autoencoder neural network with l 2 regularization and the sparsity regularization is proposed for the unique matrix to be decoded and encoded. The training of the proposed autoencoder can be achieved by reducing the total loss function with the gradient descent iterations. Finally, an inverted processing for the autoencoder output is designed for the reconstruct ion of the clutter-plus-noise covariances. Simulation results are used to verify the effectiveness and advantages of the proposed method. It performs obviously superior clutter suppression for both side-looking and non-side-looking radars with strong clutter, and can deal with the insufficient and the non-uniform training samples. For these conditions, the proposed method provides the relatively narrowest and deepest IF notch. Furthermore, on average it improves the improvement factor (IF) by 10 dB more than the ADC, DW, JDL, and original STAP methods. [ABSTRACT FROM AUTHOR]

Time-varying passenger flow is the input data in the optimization design of intercity high-speed railway transportation products, and it plays an important role. Therefore, it is necessary to predict the origin-destination (O-D) passenger flow at different times of the day in combination with the stable time-varying characteristics. In this paper, three neural network-based hybrid forecasting models are designed and compared, named Variational Mode Decomposition-Multilayer Perceptron (VMD-MLP), Variational Mode Decomposition-Gated Recurrent Unit Neural Network (VMD-GRU), and Variational Mode Decomposition-Bidirectional Long Short-Term Memory Neural Network (VMD-Bi-LSTM). First, the time-varying characteristics of passenger travel demand under different time granularities are analyzed and extracted by the VMD method. Second, three neural network prediction models are constructed to predict the passenger flow sequence after VMD decomposition and reconstruction. Experimental analysis is performed on the Guangzhou Zhuhai intercity high-speed railway in China, and the passenger flow at different time periods of the day under different time granularities is predicted. The following results were found: (i) The number of hidden neurons and the number of iterations of the hybrid forecasting model have a great impact on the prediction accuracy. The error of the VMD-MLP model fluctuates less and it performs more smoothly than both the VMD-GRU model and the VMD-Bi-LSTM model. (ii) The VMD-MLP, VMD-GRU, and VMD-Bi-LSTM models can basically reduce the MAPE error to less than 10%. With the increase of time granularity, RMSE and MAE errors tend to gradually increase, while the MAPE error tends to gradually decrease. (iii) For passenger flow under a smaller time granularity, the prediction accuracy of the VMD-MLP model is higher, while for passenger flow under a larger time granularity, the prediction accuracy of the VMD-GRU and VMD-Bi-LSTM models is higher. (iv) The proposed neural network-based hybrid models outperform the existing models and the hybrid models perform better than the single models. [ABSTRACT FROM AUTHOR]

Advances in artificial intelligence have inspired a paradigm shift in human neuroscience, yielding large-scale functional magnetic resonance imaging (fMRI) datasets that provide high-resolution brain responses to thousands of naturalistic visual stimuli. Because such experiments necessarily involve brief stimulus durations and few repetitions of each stimulus, achieving sufficient signal-to-noise ratio can be a major challenge. We address this challenge by introducing GLMsingle, a scalable, user-friendly toolbox available in MATLAB and Python that enables accurate estimation of single-trial fMRI responses (glmsingle.org). Requiring only fMRI time-series data and a design matrix as inputs, GLMsingle integrates three techniques for improving the accuracy of trial-wise general linear model (GLM) beta estimates. First, for each voxel, a custom hemodynamic response function (HRF) is identified from a library of candidate functions. Second, cross-validation is used to derive a set of noise regressors from voxels unrelated to the experiment. Third, to improve the stability of beta estimates for closely spaced trials, betas are regularized on a voxel-wise basis using ridge regression. Applying GLMsingle to the Natural Scenes Dataset and BOLD5000, we find that GLMsingle substantially improves the reliability of beta estimates across visually-responsive cortex in all subjects. Comparable improvements in reliability are also observed in a smaller-scale auditory dataset from the StudyForrest experiment. These improvements translate into tangible benefits for higher-level analyses relevant to systems and cognitive neuroscience. We demonstrate that GLMsingle: (i) helps decorrelate response estimates between trials nearby in time; (ii) enhances representational similarity between subjects within and across datasets; and (iii) boosts one-versus-many decoding of visual stimuli. GLMsingle is a publicly available tool that can significantly improve the quality of past, present, and future neuroimaging datasets sampling brain activity across many experimental conditions. [ABSTRACT FROM AUTHOR]

Purpose: The aim of the study is to analyze and evaluate the massive expansion of organizational spaces resulting from the creation of remote workplaces during the COVID-19 period in employees' homes. Design/methodology/approach: The work uses mixed methods with the use of the spatial trend of Work Design theoretical orientation. A spatial model of work stations was constructed and the correlation between the model and financing, time of use and the results of the tested variant of work organization was statistically verified. Findings: The COVID-19 period is dominated by the transfer of tasks from stationary positions, which mainly have repetitive nature. This is matched by the adaptation of physical space and cyberspace (technology), with various levels of social space features of remote workplaces. Statistical verification shows strong correlations between the features of positions and the determinants of the use of remote work as a variant of work organization. Research limitations/implications: Subjectivity of the analysis due to the use of mixed methods in the part of qualitative research. Future research should focus on (1) work in the context of multifunctionality of the home, (2) creating new work rules, e.g. new time-space patterns of work, and (3) developing criteria for creating remote workplaces at home. Practical implications: The results of the study can be used as input data for the design of remote workplaces in organizations. Originality/value: The work fills the research gap in the design of work forms, showing the need for a modular approach to the development of work systems. [ABSTRACT FROM AUTHOR]