Search

Controlling the total amount of river pollutant discharge is an important means of water resource protection and management, and it is also a necessary condition for ensuring the normal functioning of water areas. The total amount of pollutant discharge is closely related to the water environmental capacity (WEC). Shifting from the traditional method of calculating WEC to dynamic analyses and calculations, concerning practical applications, in this paper, a dynamic adaptive calculation method is proposed for the river WEC that considers the changes in adaptive demand and hydrological conditions. In this method, the dynamic WEC is represented by intervals based on dynamic changes in different spatial and temporal scales, various calculation methods, hydrological conditions, and parameters. According to the calculation results for the WEC, a variable interval was formed. Taking the Shaanxi section of the main stream of the Wei River as the research object, with the support of an integrated platform, the dynamic adaptive calculation of the WEC in the Shaanxi section of the Wei River was realized, and a corresponding simulation system was constructed. The verification results show that (1) the dynamic calculation of WEC can be realized by freely combining different model methods and calculation conditions; (2) the WEC is described using a variable interval, which has strong applicability and operability; and (3) the simulation system can quickly adapt to the changing needs of practical applications and provide managers with visual and credible decision support. The research results provide a theoretical basis for river water environment pollution prevention and environmental management decision-making and help in the high-quality development of the river basin. [ABSTRACT FROM AUTHOR]

The digital twin (DT) technology facilitates the complete lifecycle management of equipment by integrating physical and virtual spaces through data mapping. Many narrative DT frameworks and modeling methods have been proposed. However, the heterogeneous processes and methods of applying these DT frameworks in different objects and different scenarios of manufacturing restricts the function and promotion of DT. Given that there are some existing discussions on narrative DT frameworks, this paper proposes an application-oriented DT framework that integrates information models, principle models, and field models. Then, the unified DT application process is discussed. The mechanism of how to fuse the multi models for typical applications in evaluation, prediction, and optimization are elaborated in detail respectively. Finally, the proposed framework and application process are validated through two DT models: vehicle wheel polygonal diagnosis digital twin and bogie frame manufacturing optimization digital twin. The correctness and feasibility of the proposed approach is demonstrated through these case studies. [ABSTRACT FROM AUTHOR]

With the operation of the first route in Xi'an City, the matching relationship between the metro networks and the urban population is a root factor affecting the utilization of rail transit facilities. The mismatch between the metro networks and the urban population has led to an imbalance between the supply and demand for rail transport, resulting in wasted urban infrastructure. Based on this issue, the research objective is to focus on the spatiotemporal variations of the matching relationship. Firstly, the topological network model abstractly extracted metro spatial distribution features, and the spatial autocorrelation model was adopted to identify the evolution characteristics of the metro networks and urban population. Secondly, this paper adopted a time-lagged regression model to demonstrate the action relationship from 2011 to 2021. Then, the compositive coordination index was utilized to assess the variation of the global matching relationship. Finally, the paper explored spatial heterogeneity through the coupling coherence degree attached to grid cells. The research results indicate that the Moran's I value of metro elements decreased from 0.782 to 0.510 with the further complexity of topological networks, while the population was consistently high in spatial dependence with a Moran's I value of around 0.75 during the decade. Based on the regression coefficients and significance, this paper verified the hypothesis that the metro networks and urban population had a positive time-lagged feedback effect in urban development. From 2011 to 2021, the compositive coordination index symbolizing the global matching relationship increased from 0.29 to 0.90, but the coupling coherence degree shows significant spatial heterogeneity in different grid units. Differentiated spatial planning strategies were proposed for varied areas to efficiently utilize rail transit, which may provide a reference for other cities with the same reality problem. [ABSTRACT FROM AUTHOR]

The factors of water quality in the intensive marine stichopus japonicus aquaculture process are changing with seasons, so water temperature, salinity, pH value and nitrite were selected as auxiliary variables to measure the concentration of ammonia nitrogen. FCM (Fuzzy C-means) algorithm was adopted to classify them. Based on the EM (Expectation Maximization) algorithm, fuzzy sub-models of ammonia nitrogen concentration were constructed around each operating point, and finally the fuzzy sub-models were combined according to the posterior distribution of the characteristics of the sampling data. Based on the data collected at Xinyulong Marine Biological Seed Technology Co., Ltd, in Dalian China, the ammonia nitrogen concentration prediction model was tested and verified. [ABSTRACT FROM AUTHOR]

With emergence of data driven decision making, data analytics and data science, regular as well as ad-hoc decision making has become important. We argue that this requires to model the decisional behaviour of an enterprise as different from its functional behaviour. We propose Decision Enterprise Modelling as a multi-model activity consisting of three models, the Decision Structure Model for modelling business decisions, a Decision logic Model for representing decision logic and a Decision Information Model for the data needed for decision making. We present an example of Decisional Enterprise Modelling for a micro-organization. [ABSTRACT FROM AUTHOR]

Key digested message This article explores an innovative ensemble approach integrating multiple AI models to achieve consensus in psychological assessments in the educational psychology domain. Addressing the rapid advancements in Artificial General Intelligence (AGI), it emphasises the importance of principles over specific models in this fast-evolving field. The study compares responses from various AI models using a set of literacy and socioeconomic questions. The findings highlight the diversity of responses from individual models and the holistic ensemble perspective offered by DAIM. The article underscores the potential shift towards Artificial Specific Intelligence (ASI) in psychology, advocating for a focus on multi-model approaches and, potentially, a re-evaluation of humanconsensus in psychological research. [ABSTRACT FROM AUTHOR]

With the development of computer technology, forest fire spread simulation using computers has gradually developed. According to the existing research on forest fire spread, the models established in various countries have typical regional characteristics. A fire spread model established in a specific region is only suitable for the local area, and there is still a great deal of uncertainty as to whether or not the established model is suitable for fire spread simulation for the same fuel in other regions. Although many fire spread models have been established, the fuel characteristics applicable to each model, such as the fuel loading, fuel moisture content, combustibility, etc., are not similar. It is necessary to evaluate the applicability of different fuel characteristics to different fire spread models. We combined ground investigation, historical data collection, model improvements, and statistical analysis to establish a multi-model forest fire spread simulation method (FIRER) that shows the burning time, perimeter, burning area, overlap area, and spread rate of fire sites. This method is a large-scale, high-resolution fire growth model based on fire spread in eight directions on a regular 30 m grid. This method could use any one of four different physical models (McArthur, Rothermel, FBP, and Wang Zhengfei (China)) for fire behavior. This method has an option to represent fire breaks from roads, rivers, and fire suppression. We can evaluate which model is more suitable in a specific area. This method was tested on a single historical lightning fire in the Daxing'an Mountains. Different scenarios were tested and compared: using each of the four fire behavior models, with fire breaks on or off, and with a single or suspected double fire ignition location of the historical fire. The results show that the Rothermel model is the best model in the simulation of the Hanma lightning fire; the overlap area is 5694.4 hm2. Meanwhile, the real fire area in FIRER is 5800.9 hm2; both the Kappa and Sørensen values exceed 0.8, providing high accuracy in fire spread simulations. FIRER performs well in the automatic identification of fire break zones and multiple ignited points. Compared with FARSITE, FIRER performs well in predicting accuracy. Compared with BehavePlus, FIRER also has advantages in simulating large-scale fire spread. However, the complex data preparation stage of FIRER means that FIRER still has great room for improvement. This research provides a practical basis for the comparison of the practicability and applicability of various fire spread models and provides more effective practical tools and a scientific basis for decision-making and the management of fighting forest fires. [ABSTRACT FROM AUTHOR]

The fidelity of the decadal experiment in Coupled Model Intercomparison Project Phase-5 (CMIP5) has been examined, over different climate variables for multiple temporal and spatial scales, in many previous studies. However, most of the studies were for the temperature and temperature-based climate indices. A quite limited study was conducted on precipitation of decadal experiment, and no attention was paid to the catchment level. This study evaluates the performances of eight GCMs (MIROC4h, EC-EARTH, MRI-CGCM3, MPI-ESM-MR, MPI-ESM-LR, MIROC5, CMCC-CM, and CanCM4) for the monthly hindcast precipitation of decadal experiment over the Brisbane River catchment in Queensland, Australia. First, the GCMs datasets were spatially interpolated onto a spatial resolution of 0.05 × 0.05° (5 × 5 km) matching with the grids of observed data and then were cut for the catchment. Next, model outputs were evaluated for temporal skills, dry and wet periods, and total precipitation (over time and space) based on the observed values. Skill test results revealed that model performances varied over the initialization years and showed comparatively higher scores from the initialization year 1990 and onward. Models with finer spatial resolutions showed comparatively better performances as opposed to the models of coarse spatial resolutions, where MIROC4h outperformed followed by EC-EARTH and MRI-CGCM3. Based on the performances, models were grouped into three categories, where models (MIROC4h, EC-EARTH, and MRI-CGCM3) with high performances fell in the first category, and middle (MPI-ESM-LR and MPI-ESM-MR) and comparatively low-performing models (MIROC5, CanCM4, and CMCC-CM) fell in the second and third categories, respectively. To compare the performances of multi-model ensembles' mean (MMEMs), three MMEMs were formed. The arithmetic mean of the first category formed MMEM1, the second and third categories formed MMEM2, and all eight models formed MMEM3. The performances of MMEMs were also assessed using the same skill tests, and MMEM2 performed best, which suggests that evaluation of models' performances is highly important before the formation of MMEM. [ABSTRACT FROM AUTHOR]

Current single-model methods for fine-grained image classification suffer from insufficient generalisation ability, while multi-model fusion methods suffer from weight curing. The study suggests and experimentally tests a dynamic weight multi-model fusion strategy for transfer learning-based fine-grained picture classification. The results of the experiment showed that the suggested fusion model enhanced recognition accuracy by 1.33%, 1.19%, and 0.83% compared to the single model on the medical dataset and 3.25%, 1.34%, and 7.28% on the agronomy dataset, respectively. Furthermore, when compared to the comparison method, the models under the proposed method of the study improved recognition accuracy by 0.18%, 0.61%, 0.43%, and 0.43% on the medical dataset, and the experimental time consumed was 3.25 minutes less than that of the sum-of-maximum-probabilities method; however, the fusion models of the proposed method of the study had higher recognition accuracy than that of the comparison met Overall, the proposed dynamic weight multi-model fusion method for fine-grained image classification using migration learning has better performance and generalisation ability, which can improve performance while reducing time cost, and has higher application value for the actual fine-grained image classification task.

Controlling the total amount of river pollutant discharge is an important means of water resource protection and management, and it is also a necessary condition for ensuring the normal functioning of water areas. The total amount of pollutant discharge is closely related to the water environmental capacity (WEC). Shifting from the traditional method of calculating WEC to dynamic analyses and calculations, concerning practical applications, in this paper, a dynamic adaptive calculation method is proposed for the river WEC that considers the changes in adaptive demand and hydrological conditions. In this method, the dynamic WEC is represented by intervals based on dynamic changes in different spatial and temporal scales, various calculation methods, hydrological conditions, and parameters. According to the calculation results for the WEC, a variable interval was formed. Taking the Shaanxi section of the main stream of the Wei River as the research object, with the support of an integrated platform, the dynamic adaptive calculation of the WEC in the Shaanxi section of the Wei River was realized, and a corresponding simulation system was constructed. The verification results show that (1) the dynamic calculation of WEC can be realized by freely combining different model methods and calculation conditions; (2) the WEC is described using a variable interval, which has strong applicability and operability; and (3) the simulation system can quickly adapt to the changing needs of practical applications and provide managers with visual and credible decision support. The research results provide a theoretical basis for river water environment pollution prevention and environmental management decision-making and help in the high-quality development of the river basin.

With the operation of the first route in Xi’an City, the matching relationship between the metro networks and the urban population is a root factor affecting the utilization of rail transit facilities. The mismatch between the metro networks and the urban population has led to an imbalance between the supply and demand for rail transport, resulting in wasted urban infrastructure. Based on this issue, the research objective is to focus on the spatiotemporal variations of the matching relationship. Firstly, the topological network model abstractly extracted metro spatial distribution features, and the spatial autocorrelation model was adopted to identify the evolution characteristics of the metro networks and urban population. Secondly, this paper adopted a time-lagged regression model to demonstrate the action relationship from 2011 to 2021. Then, the compositive coordination index was utilized to assess the variation of the global matching relationship. Finally, the paper explored spatial heterogeneity through the coupling coherence degree attached to grid cells. The research results indicate that the Moran’s I value of metro elements decreased from 0.782 to 0.510 with the further complexity of topological networks, while the population was consistently high in spatial dependence with a Moran’s I value of around 0.75 during the decade. Based on the regression coefficients and significance, this paper verified the hypothesis that the metro networks and urban population had a positive time-lagged feedback effect in urban development. From 2011 to 2021, the compositive coordination index symbolizing the global matching relationship increased from 0.29 to 0.90, but the coupling coherence degree shows significant spatial heterogeneity in different grid units. Differentiated spatial planning strategies were proposed for varied areas to efficiently utilize rail transit, which may provide a reference for other cities with the same reality problem.

This paper describes a new seamless blended multi‐model ensemble configuration of an existing probabilistic medium‐ to extended‐range weather pattern forecasting tool (called Decider) run operationally at the Met Office. In its initial configuration, the tool calculated and presented probabilistic weather pattern forecast information for five individual ensemble forecasting systems, which varied in terms of their number of ensemble members, horizontal resolution, update frequencies and forecast lead time. This resulted in multiple forecasts for the same validity time which varied in terms of forecast skill depending on the lead time in question. This presented challenges for end‐users (e.g., operational meteorologists) in terms of knowing which forecast output is best to use and at which lead time, as well as knowing what to do in situations where forecasts varied between ensembles. To get around these challenges, a new seamless blended multi‐model ensemble configuration has been implemented operationally, comprising of output from five separate ensembles, and provides a single best forecast from day one out to day 45. Objective verification for a set of eight weather pattern groups covering forecasts initialized over a 6‐year period (2017–2022) shows that the seamless blended multi‐model ensemble forecasts are at least as good as, if not better than the best performing individual model. [ABSTRACT FROM AUTHOR]

This paper introduces a structural classification scheme for folk music using a multimodal fusion of musical features and textual information. A data corpus of Thiruvathirakali music (a popular folk dance in India) is compiled for this purpose. The musical features are learned using a gated recurrent unit (GRU) with an attention mechanism from musical texture features. A term frequency-inverse document frequency (TF-IDF) model is employed to derive text-based features from transcription data. Early integration of the GRU-derived features and TF-IDF features is employed for multimodal fusion. The performance is evaluated using Thiruvathirakali music corpus. The performance of the proposed system is also compared with that of a support vector machine-based classifier. The proposed system reports an overall precision, recall and F1 measure of 0.81 each for the GRU-attention-based model for multi-modal fusion. The scope of the proposed work for structural segmentation is also demonstrated with the help of an example. [ABSTRACT FROM AUTHOR]

The accurate prediction of mining area surface deformation is essential to preventing large-scale coal mining-related surface collapse and ensure safety and daily life continuity. Monitoring subsidence in mining areas is challenged by environmental interference, causing data noise. This paper employs the Sparrow Search Algorithm, which integrates Sine Cosine and Cauchy mutation (SCSSA), to optimize variational mode decomposition (VMD) and combine multi-models for prediction. Firstly, SCSSA is employed to adaptively determine the parameters of VMD using envelope entropy as the fitness value. Subsequently, the VMD method optimized using SCSSA adaptively decomposes the original mining area subsidence data sequence into various sub-sequences. Then, SCSSA-VMD is applied to adaptively decompose the original mining subsidence data sequence into multiple sub-sequences. Meanwhile, using sample entropy, the sub-sequences are categorized into trend sequences and fluctuation sequences, and different models are employed to predict sub-sequences at different frequencies. Finally, the prediction results from different sub-sequences are integrated to obtain the final prediction of mining area subsidence. To validate the predictive performance of the established model, experiments are conducted using GNSS monitoring data from the 110801 working face of Banji Coal Mine in Bozhou. The results demonstrate the following: (1) The hybrid model enhanced the prediction accuracy and trends by decomposing the data and optimizing the parameters with VMD. It outperformed single models, reducing errors and improving predictive trends. (2) The hybrid model significantly improved the prediction accuracy for subsidence data at work surface monitoring stations. It is particularly effective at critical subsidence points, making it a valuable reference for safety in mining operations. [ABSTRACT FROM AUTHOR]

Featured Application: The proposed multi-sensor data fusion method utilizes the self-attention mechanism in CNN-SA networks to enhance data integrity and accuracy, and it has potential applications in various fields where accurate and reliable multi-sensor data fusion is required. In 3D reconstruction tasks, single-sensor data fusion based on deep learning is limited by the integrity and accuracy of the data, which reduces the accuracy and reliability of the fusion results. To address this issue, this study proposes a multi-sensor data fusion method based on a self-attention mechanism. A multi-sensor data fusion model for acquiring multi-source and multi-modal data is constructed, with the core component being a convolutional neural network with self-attention (CNN-SA), which employs CNNs to process multi-source and multi-modal data by extracting their features. Additionally, it introduces an SA mechanism to weigh and sum the features of different modalities, adaptively focusing on the importance of different modal data. This enables mutual support, complementarity, and correction among the multi-modal data. Experimental results demonstrate that the accuracy of the CNN-SA network is improved by 72.6%, surpassing the improvements of 29.9% for CNN-CBAM, 23.6% for CNN, and 11.4% for CNN-LSTM, exhibiting enhanced generalization capability, accuracy, and robustness. The proposed approach will contribute to the effectiveness of multi-sensor data fusion processing. [ABSTRACT FROM AUTHOR]

Evaluating the impact of multi-source uncertainties in complex forecasting systems is essential to understanding and improving the systems. Previous studies have paid little attention to the influence of multi-source uncertainties in complex meteorological and hydrological forecasting systems. In this study, we developed a general ensemble framework based on Bayesian model averaging (BMA) for evaluating the impact of multi-source uncertainties in complex forecast systems. Based on this framework, we used eight numerical weather prediction products from the International Grand Global Ensemble (TIGGE) dataset, four hydrological models with different structures, and 1000 sets of parameters to comprehensively account for the input, structure, and parameter uncertainties. The framework’s application to the Chitan Basin in China revealed that the numerical weather prediction input uncertainty in the forecasting system was more significant than the hydrological model uncertainty. The hydrological model structure uncertainty was more prominent than the parameter uncertainty. The accuracy of the numerical weather prediction dominates the accuracy of the forecast of high flows. In addition, the structures and parameters of the hydrological model and their interactions contributed to the main uncertainty of the low flow forecasts. The streamflow was more realistically represented when the three uncertainty sources were considered jointly. By accounting for the significant uncertainty sources in complex forecast systems, the BMA ensemble forecasting produces more realistic and reliable predictions and reduces the influences of other incomplete considerations. The developed multi-source uncertainty assessment framework improves our understanding of the complex meteorological and hydrological forecasting system. Therefore, the framework is promising for improving the accuracy and reliability of complex forecasting systems.

Abstract This paper describes a new seamless blended multi‐model ensemble configuration of an existing probabilistic medium‐ to extended‐range weather pattern forecasting tool (called Decider) run operationally at the Met Office. In its initial configuration, the tool calculated and presented probabilistic weather pattern forecast information for five individual ensemble forecasting systems, which varied in terms of their number of ensemble members, horizontal resolution, update frequencies and forecast lead time. This resulted in multiple forecasts for the same validity time which varied in terms of forecast skill depending on the lead time in question. This presented challenges for end‐users (e.g., operational meteorologists) in terms of knowing which forecast output is best to use and at which lead time, as well as knowing what to do in situations where forecasts varied between ensembles. To get around these challenges, a new seamless blended multi‐model ensemble configuration has been implemented operationally, comprising of output from five separate ensembles, and provides a single best forecast from day one out to day 45. Objective verification for a set of eight weather pattern groups covering forecasts initialized over a 6‐year period (2017–2022) shows that the seamless blended multi‐model ensemble forecasts are at least as good as, if not better than the best performing individual model.

Compared to traditional unimodal methods, multimodal audio-visual correspondence learning has many advantages in the field of video understanding, but it also faces significant challenges. In order to fully utilize the feature information from both modalities, we needs to ensure accurate alignment of the semantic information from each modality, rather than simply concatenating them together. This requires consideration of how to design fusion networks that can better perform this task. Current algorithms heavily rely on the network's output results for sound-object localization while neglecting the potential issue of suppressed feature information due to the internal structure of the network. Thus, we propose a sound promotion method (SPM), a self-supervised framework that aims to increase the contribution of voices to produce better performance of the audiovisual learning. We first cluster the audio separately to generate pseudo-labels and then use the clusters to train the backbone of audio. Finally, we explore the impact of our method to several existing approaches on MUSIC datasets and the results prove that our proposed method is able to produce better performance. [ABSTRACT FROM AUTHOR]

With the development of computer technology, forest fire spread simulation using computers has gradually developed. According to the existing research on forest fire spread, the models established in various countries have typical regional characteristics. A fire spread model established in a specific region is only suitable for the local area, and there is still a great deal of uncertainty as to whether or not the established model is suitable for fire spread simulation for the same fuel in other regions. Although many fire spread models have been established, the fuel characteristics applicable to each model, such as the fuel loading, fuel moisture content, combustibility, etc., are not similar. It is necessary to evaluate the applicability of different fuel characteristics to different fire spread models. We combined ground investigation, historical data collection, model improvements, and statistical analysis to establish a multi-model forest fire spread simulation method (FIRER) that shows the burning time, perimeter, burning area, overlap area, and spread rate of fire sites. This method is a large-scale, high-resolution fire growth model based on fire spread in eight directions on a regular 30 m grid. This method could use any one of four different physical models (McArthur, Rothermel, FBP, and Wang Zhengfei (China)) for fire behavior. This method has an option to represent fire breaks from roads, rivers, and fire suppression. We can evaluate which model is more suitable in a specific area. This method was tested on a single historical lightning fire in the Daxing’an Mountains. Different scenarios were tested and compared: using each of the four fire behavior models, with fire breaks on or off, and with a single or suspected double fire ignition location of the historical fire. The results show that the Rothermel model is the best model in the simulation of the Hanma lightning fire; the overlap area is 5694.4 hm2. Meanwhile, the real fire area in FIRER is 5800.9 hm2; both the Kappa and Sørensen values exceed 0.8, providing high accuracy in fire spread simulations. FIRER performs well in the automatic identification of fire break zones and multiple ignited points. Compared with FARSITE, FIRER performs well in predicting accuracy. Compared with BehavePlus, FIRER also has advantages in simulating large-scale fire spread. However, the complex data preparation stage of FIRER means that FIRER still has great room for improvement. This research provides a practical basis for the comparison of the practicability and applicability of various fire spread models and provides more effective practical tools and a scientific basis for decision-making and the management of fighting forest fires.

The fidelity of the decadal experiment in Coupled Model Intercomparison Project Phase-5 (CMIP5) has been examined, over different climate variables for multiple temporal and spatial scales, in many previous studies. However, most of the studies were for the temperature and temperature-based climate indices. A quite limited study was conducted on precipitation of decadal experiment, and no attention was paid to the catchment level. This study evaluates the performances of eight GCMs (MIROC4h, EC-EARTH, MRI-CGCM3, MPI-ESM-MR, MPI-ESM-LR, MIROC5, CMCC-CM, and CanCM4) for the monthly hindcast precipitation of decadal experiment over the Brisbane River catchment in Queensland, Australia. First, the GCMs datasets were spatially interpolated onto a spatial resolution of 0.05 × 0.05° (5 × 5 km) matching with the grids of observed data and then were cut for the catchment. Next, model outputs were evaluated for temporal skills, dry and wet periods, and total precipitation (over time and space) based on the observed values. Skill test results revealed that model performances varied over the initialization years and showed comparatively higher scores from the initialization year 1990 and onward. Models with finer spatial resolutions showed comparatively better performances as opposed to the models of coarse spatial resolutions, where MIROC4h outperformed followed by EC-EARTH and MRI-CGCM3. Based on the performances, models were grouped into three categories, where models (MIROC4h, EC-EARTH, and MRI-CGCM3) with high performances fell in the first category, and middle (MPI-ESM-LR and MPI-ESM-MR) and comparatively low-performing models (MIROC5, CanCM4, and CMCC-CM) fell in the second and third categories, respectively. To compare the performances of multi-model ensembles’ mean (MMEMs), three MMEMs were formed. The arithmetic mean of the first category formed MMEM1, the second and third categories formed MMEM2, and all eight models formed MMEM3. The performances of MMEMs were also assessed using the same skill tests, and MMEM2 performed best, which suggests that evaluation of models’ performances is highly important before the formation of MMEM.

The Grey Wolf Optimization Algorithm (GWO) replicates the leadership and foraging mechanisms of the natural grey wolf and excels in solving problems in a variety of domains. However, the algorithm tends to converge to a local optimal and has a slow convergence rate. This paper proposes an enhanced Grey Wolf optimization algorithm (HTGWO) based on hyperbolic tangent inertia weights to solve this problem. HTGWO employs inertia weights based on hyperbolic tangent functions to balance GWO’s global and local search capabilities of the GWO. HTGWO has a faster convergence rate and more accurate solutions than GWO. Five classical test functions were used to construct comparative experiments between the HWGWO and five classical intelligent optimization algorithms. The comparison results indicate that HWGWO has superior convergence speed, solution precision, and stability compared with the other five classical intelligent optimization algorithms. Moreover, experimental evidence suggests that the HWGWO is more effective at solving multimodal functions than unimodal functions. In addition, HTGWO can balance exploration and exploitation by adjusting the parameters according to the characteristics of different problems.

Efficient video compression is fundamental for enabling today’s highly interactive multimedia landscape. With the trend towards virtual reality, efficient storage and transmission of 360-degree video content becomes increasingly important. Recent works in this area addressed the design and investigation of 360-degree-specific motion models for improved compression efficiency. We investigate the strengths and limitations of these motion models and show that a single model cannot sufficiently cover all motion scenarios. A video codec that combines the strengths of multiple models in the motion compensation procedure is expected to achieve notable gains in compression efficiency. However, the additional motion model signaling and switching costs quickly outweigh the gains achieved by improved motion compensation. In this paper, we address this challenge by proposing advanced motion prediction and coding schemes that significantly reduce the resulting side information overhead. A novel multi-model motion vector prediction technique ensures seamless cooperation between different motion models by generalizing the motion modeling concept through forward and backward passes, and yields significant improvements in the overall compression efficiency. Our proposed hierarchical coding scheme is broadly applicable and is shown to be the most effective among comparable coding schemes. Experimental results demonstrate the performance of the proposed multi-model coding framework with average Bjøntegaard Delta rate savings of 3.20% with a peak of 4.49% based on PSNR and 2.76% with a peak of 4.04% based on WS-PSNR compared to the state-of-the-art H.266/VVC video coding standard.

Accounting for the variability of hydrological processes and climate conditions between catchments and within catchments remains a challenge in rainfall-runoff modelling. Among the many approaches developed over the past decades, multi-model approaches provide a way to take into account the uncertainty linked to the choice of model structure and its parameter estimates. Semi-distributed approaches make it possible to account explicitly for spatial variability while maintaining a limited level of complexity. However, these two approaches have rarely been used together. Such a combination would allow us to take advantage of both methods. The aim of this work is to answer the following question: What is the possible contribution of a multi-model approach within a variable spatial framework compared to lumped single models for streamflow simulation? To this end, a set of 121 catchments with limited influence in France was assembled, with precipitation, potential evapotranspiration and streamflow data at the hourly time step over the period 1998-2018. The semi-distribution set-up was kept simple by considering a single downstream catchment defined by an outlet, and one or more upstream sub-catchments. The multi-model approach was implemented with 13 rainfall-runoff model structures, three calibration options and two spatial frameworks, for a total of 78 distinct modelling options. A simple average method was used to combine the various simulated streamflow at the outlet of the catchments and sub-catchments. The most efficient lumped model on a given catchment was taken as the benchmark for model evaluation. Overall, the semi-distributed multi-model approach yields better performance than the different lumped models considered individually. The gain is mainly brought about by the multi-model set-up, with the spatial framework providing a benefit on more occasional basis. These results, based on a large catchment set, evince the benefits of using a multi-model in a variable spatial framework to simulate streamflow. [ABSTRACT FROM AUTHOR]

In 3D reconstruction tasks, single-sensor data fusion based on deep learning is limited by the integrity and accuracy of the data, which reduces the accuracy and reliability of the fusion results. To address this issue, this study proposes a multi-sensor data fusion method based on a self-attention mechanism. A multi-sensor data fusion model for acquiring multi-source and multi-modal data is constructed, with the core component being a convolutional neural network with self-attention (CNN-SA), which employs CNNs to process multi-source and multi-modal data by extracting their features. Additionally, it introduces an SA mechanism to weigh and sum the features of different modalities, adaptively focusing on the importance of different modal data. This enables mutual support, complementarity, and correction among the multi-modal data. Experimental results demonstrate that the accuracy of the CNN-SA network is improved by 72.6%, surpassing the improvements of 29.9% for CNN-CBAM, 23.6% for CNN, and 11.4% for CNN-LSTM, exhibiting enhanced generalization capability, accuracy, and robustness. The proposed approach will contribute to the effectiveness of multi-sensor data fusion processing.

Modifier Adaptation (MA) is a method of real-time optimization (RTO) which modifies a single model to match the first order properties of the plant. Known uncertainties in the parameters of this model are discarded in favor of real-time measurements, but they can be used to quantify the mismatch between the plant and model. Using multi-model methods increases the computation time, but can improve rate of convergence of the RTO scheme. This article proposes a framework, known as multiple solution modifier adaptation (MSMA), which produces several models which are all modified in the same way as standard MA, each producing a potential solution to be applied to the plant. From this framework, three recommended schemes are proposed on how to select the operating point to be applied to the plant: (1) Selecting the solution based off the modifiers; (2) Selecting the mean solution from convex models; (3) Selecting the closest solution to the current operating point. Each of these methods have different advantages, including limiting the increase in computational complexity and improving the model adequacy conditions of the scheme. These recommended schemes are shown on three different case studies of varying complexity with all three schemes showing improvements over standard MA. [ABSTRACT FROM AUTHOR]

Tool wear monitoring is essential in precision machining and helps to ensure processing quality. Although numerous data-driven methods have been proposed for tool wear monitoring, most of them build global models that ignore local wear characteristics and the changeable working conditions. This study proposes a dual-compensation (DC) strategy based on multi-model support vector regression (MSVR) to improve estimation accuracy and model maintenance. By dividing the original samples into two clusters with the K-means algorithm, the DC strategy develops a separate SVR model for each cluster. Test samples are classified using the decision function and input into the corresponding model. Finally, the predicted value obtained by MSVR is corrected by system error compensation and nearest bias updating, which is improved to adapt to milling environments. In addition, the database is updated after each process. Two groups of milling experiments were conducted to validate the improved strategy in comparison with other methods. The results show that multi-model SVR improves performance by more than 28.7% and has better generalization ability. The root mean square error value decreases from 0.1109 to 0.0392, a 64.7% reduction, with our complete strategy. The DC strategy based on multi-model support vector regression (DCMSVR) can achieve high prediction accuracy in variable working conditions due to its high estimation accuracy and adaptability. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Agricultural Big Data is the property of Journal of Agricultural Big Data 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.)

Recent advances in both lightweight deep learning algorithms and edge computing increasingly enable multiple model inference tasks to be conducted concurrently on resource-constrained edge devices, allowing us to achieve one goal collaboratively rather than getting high quality in each standalone task. However, the high overall running latency for performing multi-model inferences always negatively affects the real-time applications. To combat latency, the algorithms should be optimized to minimize the latency for multi-model deployment without compromising the safety-critical situation. This work focuses on the real-time task scheduling strategy for multi-model deployment and investigating the model inference using an open neural network exchange (ONNX) runtime engine. Then, an application deployment strategy is proposed based on the container technology and inference tasks are scheduled to different containers based on the scheduling strategies. Experimental results show that the proposed solution is able to significantly reduce the overall running latency in real-time applications. [ABSTRACT FROM AUTHOR]

Defects on rail surfaces, which have become critical problems, need to be detected and removed as quickly as possible to ensure the fast, safe, and stable operation of trains. At present, although many solutions have been proposed to address these problems, the comprehensiveness, rapidity, and accuracy of defect detection remain unsatisfactory. This study aims to resolve these existing problems and accordingly proposes a multi-model rail surface defect detection system based on convolutional neural networks (MRSDI-CNN) from the standpoint of studying the squat on the rail surface. The convolutional neural networks utilized include the improved Single Shot MultiBox Detector (SSD) and You Only Look Once version 3(YOLOv3)—two types of one-stage networks. We expounded and analyzed the performance of the convolutional neural networks as well as their applicability to rail surface defect detection. We used a diverse range of rail defect sizes to improve the detection performance of the two deep learning networks, following which they could identify three types of squats in parallel with improved accuracy and without reduction of the detection speed. The experimental results confirm the effectiveness and superiority of the proposed method over those of previous studies. [ABSTRACT FROM AUTHOR]

To obtain quality variables that cannot be measured in real time during the production process but reflect information on the quality of the final product, the batch production process has the characteristics of a strong time-varying nature, non-Gaussian data distribution and high nonlinearity. A locally weighted partial least squares regression quality prediction model (KICA-JITL-LWPLS), based on wavelet kernel function independent meta-analysis with immediate learning, is proposed. The model first measures the similarity between the normalized input data and the historical data and assigns the input data to the group of historical data with high similarity to it, based on the posterior probability of the Bayesian classifier; subsequently, wavelet kernel functions are selected and kernel learning methods are introduced into the independent meta-analysis algorithm. An independent meta-analysis, based on the wavelet kernel function, is performed on the classified input data to obtain probabilistically significant independent sets of variables. Finally, a real-time learning-based LWPLS regression analysis is performed on this variable set to construct a local prediction model for the current sample by calculating the similarity between the local input data. The local predictions from the PLS output are fused with the posterior probability output from the Bayesian classifier to produce the final prediction. The method was used to predict the product concentration and bacteriophage concentration during penicillin fermentation through a simulation platform. The prediction results were basically consistent with the real values, proving that the proposed KICA-JITL-LWPLS quality prediction model, based on wavelet kernel functions, has reliable prediction results. [ABSTRACT FROM AUTHOR]

As a kind of relatively clean fossil energy, natural gas will face severe uncertainties in the background of carbon neutrality. Reviewing the medium- and long-term development trend of natural gas consumption is the prerequisite to better understanding the status of natural gas and ensure the sustainable development of natural gas industry. In this paper, a multi-model comparison framework is established on the basis of 8 representative integrated assessment models (CE3METL, DNE21+, IPAC, AIM/CGE, IMAGE, REMIND, WITCH and POLES). Then, the medium- and long-term evolution trend of China's total primary energy consumption and natural gas consumption in different scenarios of climate policy is discussed. In addition, comparative analysis is conducted on key time nodes such as 2030, 2045 and 2060. And the following research results are obtained. Firstly, the prediction results of most models indicate that China's total primary energy consumption in 2060 will be lower than the level in 2019 except for the scenario of national determined contribution (NDC). Secondly, by 2060, the carbon neutrality goal year, the cross-model average level of natural gas consumption under the NDC, 2.0 °C, and 1.5 °C scenarios will be 6943 × 108 m3, 4342 × 108 m3 and 2502 × 108 m3, respectively. Thirdly, under the 1.5 °C scenario, the decrease of total primary energy consumption shall begin in 2020, which means that faster technological progress and more effective combination of “nudge” policies are needed. Fourthly, under the temperature control goal of 2.0 °C, natural gas consumption will account for about 13.6% of China's primary energy consumption in 2060, and this proportion will drop to 9% under the stricter 1.5 °C scenario. In conclusion, the multi-model comparison results can present different development paths of China's total primary energy consumption and natural gas consumption and its proportion during 2020–2060 more comprehensively, so as to provide support for formulating the medium- and long-term policies and strategies of natural gas industry under the challenge of climate change.

Flow distortions caused by ambient wind can have complex negative effects on the performance of direct air-cooling condensers, which use air as their cooling medium. A control-oriented model of the direct air-cooling condenser model, considering fan volumetric effectiveness and plume recirculation rate, was developed, and its linearization model was derived. The influences of fan volumetric effectiveness and plume recirculation rate on backpressure were analyzed, and the optimal backpressure was calculated. To improve both the transient performance and steady-state energy saving of the condenser, a multi-model-based predictive control strategy was proposed to divisionally adjust the fan array. Four division schemes of the direct air-cooling fan array constituted the local models, and in each division scheme, axial fans were divided into three groups according to the wind direction: windward fans, leeward fans, and other fans. The simulation results showed that the turbine backpressure can be increased by 15 kPa under the influence of plume recirculation and the reduction of the fan volumetric efficiency. The fan division adjustment strategy can achieve satisfactory control performance with switching rules. [ABSTRACT FROM AUTHOR]