Search

In order to predict sports competition data, the author needs to implement the structure and related processes of the relevant competition victory and defeat prediction system, and specifically introduce and plan the implementation of each functional module. The data collection and storage module adopts Alibaba Cloud servers and combines Python to remotely and automatically collect data on a scheduled basis, according to the actual situation of game wins and losses, data cleaning and filtering are carried out, and multiple encoding forms are used to vectorize the data in order to find the best model. The data is divided according to the standard training and testing sets, and multiple classifiers are used for model training and saved locally for direct use next time; Test the above model using the training set; Compare the advantages and disadvantages of each vectorized encoding and classifier based on the final performance evaluation module. Based on the relevant experimental results, a detailed analysis was conducted to compare the advantages and disadvantages of each model, proving that introducing word vectors (word embeddings) into the competition data analysis system is worthwhile. We have obtained an excellent performance prediction model with a highest accuracy P of 0.825, a recall R of 0.729, and a corresponding F1 value of 0.774. For a prediction model that only knows the initial lineup allocation as a prerequisite, this already has sufficient practical guidance significance. [ABSTRACT FROM AUTHOR]

This study aims to improve the predictive ability of financial brand data. help investors and decision-makers better identify different financial brands' performance, and reduce unnecessary financial risks. The stock prices of various financial brands are undertaken as the experimental objects. The characteristics of financial data and the original model network structure are analyzed based on the Internet of Things (IoT). The long short-term memory (LSIM) neural and the particle swarm optimization algorithm (PSO algorithm) are adopted to optimize the model's parameters, The autoregressive integrated moving average model (ARIMA) algorithm is used to analyze the spatio-temporal data, and a data prediction model for the financial brand based on the ARIMA-PSO-LSTM algorithm is proposed. In addition, the validity and effectiveness of the proposed model are proved through the analysis and testing of specific example data. It is found that the model based on the IoT shows higher processing speed in contrast to the conventional method: the model proposed in this study shows smaller errors and improved accuracy in dam prediction than the PSO-LSTM model and the LSTM model; the model presents better fitting effects and better performance compared with the latest research model. The experimental results reveal that combining the three algorithms can integrate the advantages of various algorithms, and the three algorithms can complement each other, thereby improving the ability of financial data analysis. The model established in this study shows high accuracy and good adaptability in identifying financial brands and predicting financial data. [ABSTRACT FROM AUTHOR]

With the development of information technology, the application of machine learning in automatic structure monitoring has been increasing gradually. Data analysis and prediction, as an important component of automatic structure monitoring, play a key role in ensuring structural safety. To address the issues of current structural monitoring data prediction methods, which may not fully leverage data characteristics and can be time-consuming, a monitoring data prediction model based on the gated broad learning system (G-BLS) was proposed. G-BLS can control feature nodes to extract highly relevant information by adding forgetting gates and cyclic feedback gates to feature nodes of BLS. Compared to the deep learning models, the network structure of G-BLS model is much simpler, leading to significantly reduced training times. Test results using measured subsidence data from a subway foundation pit demonstrated that G-BLS effectively achieved both reliability and real-time performance in prediction and monitoring data. This model proves to be an accurate and efficient method for structural monitoring data prediction. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control 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 study aims to enhance the comprehension of the fundamental fluid behavior by comparing Newtonian fluid with second-grade fluid under the influence of periodic magnetic fields, nonlinear radiative nanomaterial, and a porous stretched surface featuring a heat source. The governing equations' dimensionless forms are generated by applying the proper transformations, and the explicit finite difference (EFD) method is used to solve the numerically-derived solution while carefully maintaining stability and convergence standards. The results include velocity, heat, and mass transfer oscillation profiles; streamlines, and isothermal lines. Nusselt and Sherwood numbers are correlated with different factors according to tabular studies, and data prediction and regression are done using graphical representations. This study revealed that, in contrast to Newtonian fluid, second-grade fluid flow elevates velocity profiles with variations in chemical reaction parameters and mass Grashof numbers. Conversely, the thermal non-linear radiation and heat source in second-grade fluid particles effectively enhance the temperature field, although the temperature increase is more pronounced in Newtonian fluid compared to second-grade fluid. Also, second-grade fluid flow exhibits a lower mass transmission rate but higher stress sharing and heat transmission rates compared to Newtonian fluid flow. The implications of this research may impact prostate cancer treatment, as cancer patients have already benefited from the use of magnetic fields to regulate drug release from nanoparticles. Although the greater stress sharing and heat transmission rates may be used for targeted therapy, the lower mass transmission rate raises the possibility of benefits in controlled release scenarios.

Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in time series forecasting. However, two problems weaken the performance of TCNs. One is that in dilated casual convolution, causal convolution leads to the receptive fields of outputs being concentrated in the earlier part of the input sequence, whereas the recent input information will be severely lost. The other is that the distribution shift problem in time series has not been adequately solved. To address the first problem, we propose a subsequence-based dilated convolution method (SDC). By using multiple convolutional filters to convolve elements of neighboring subsequences, the method extracts temporal features from a growing receptive field via a growing subsequence rather than a single element. Ultimately, the receptive field of each output element can cover the whole input sequence. To address the second problem, we propose a difference and compensation method (DCM). The method reduces the discrepancies between and within the input sequences by difference operations and then compensates the outputs for the information lost due to difference operations. Based on SDC and DCM, we further construct a temporal subsequence-based convolutional network with difference (TSCND) for time series forecasting. The experimental results show that TSCND can reduce prediction mean squared error by 7.3% and save runtime, compared with state-of-the-art models and vanilla TCN. [ABSTRACT FROM AUTHOR]

Designing rubber formulations can greatly benefit from using a database that stores the formulations and corresponding property data of rubber composites. Such a database can expedite the decision-making process by swiftly identifying the most suitable formulations for specific applications. However, the management of a rubber formulation database encounters various issues, including missing formulation and property data, as well as data entry errors. These issues can impede the decision-making processes and even result in incorrect decisions being made. In this study, machine learning (ML) algorithms were applied to analyze rubber formulation databases. Our findings highlight the success of the ML algorithm in effectively filling in missing data and identifying erroneous data. Furthermore, it demonstrates the accurate prediction of properties for untested formulations within the pre-determined database space. The results underline the outstanding performance of ML algorithms in expediting the rubber formulation design process and emphasize their immense potential to play a prominent role in the advancement of rubber composites.

The construction and application of underground ponding goaf in coal mine provide important guarantee for underground production and mining and surface industrial water. The mine pays more attention to the safe operation performance of artificial waterproof sealing. For providing reliable monitoring scheme and safety evaluation technical means, taking 3# waterproof sealing wall in 31205 ponding goaf of Shigetai Coal Mine as the research object, the monitoring scheme for surface strain gauge, borehole stress gauge and osmometer is designed, and the surface strain gauge B1, B3 and borehole stress gauge LY are used as the input matrix, and the osmometer LS1 is used as the output matrix. The GRNN model (generalized neural network) is introduced, and the network training and data prediction evaluation are conducted using the ten fold cross validation method and cycle iteration logic. The best smoothing factor is 0.2, and 97% of the absolute error of seepage pressure prediction results under this condition is less than 0.01; at the same time, compared with BP neural network model, GRNN model is superior to BP model. PNN model (probabilistic neural network) is introduced to verify the classification of 100 data in 10 grades of GRNN model classification evaluation results, and the accuracy of evaluation samples is 96.7%. The results show that GRNN model can accurately predict the seepage pressure monitoring data, and the accuracy of GRNN model is higher than that of BP model; the evaluation grade predicted by GRNN model can still be effectively evaluated and verified by using PNN model.

In the face of the problem of low accuracy of university sports load data prediction method, a deep learning university sports load data prediction method is designed. Identify the style and rules of human movement, extract the characteristics of time domain to calculate in frequency domain, construct the target tracking model by deep learning, calculate the error of the output layer, extract the characteristics of college sports load, judge the rationality of the movement contact configuration between bones, and design the data prediction method. Experimental results: The average prediction accuracy of the college sports load data prediction method in this paper and the other two methods are 0.417, 0.342 and 0.333 respectively, indicating that the precision of the college sports load data prediction method designed after the full integration of deep learning technology has been improved. [ABSTRACT FROM AUTHOR]

Nowadays, to improve animal well being in livestock farming application, a wireless video sensor network (WVSN) can be deployed to early detect injury and monitor animals. They are composed of small embedded video and camera motes that capture video frames periodically and send them to a specific node called a sink. Sending all the captured images to the sink consumes a lot of energy on every sensor and may cause a bottleneck at the sink level. Energy consumption and bandwidth limitation are two important challenges in WVSNs because of the limited energy resources of the nodes and the medium scarcity. In this work, we introduce two mechanisms to reduce the overall number of frames sensed and sent to the sink. The first approach is applied on each sensor node, where the FRABID algorithm, a joint data reduction, and frame rate adaptation on sensing and transmission phases mechanism is introduced. This approach reduces the number of sensed frames based on a similarity method. The aim is to adapt the number of sensed frames based on the degree of difference between two consecutive sensed frames in each period. This adaptation technique maintains the accuracy of the video while capturing frames holding new information. This approach is validated through simulations using real data-sets from video sensors (Wang et al. in: 2014 IEEE conference on computer vision and pattern recognition workshops, pp 393–400, 2014). The results show that the amount of sensed data is reduced by more than 70% compared to a recent algorithm in Christian et al. (Multimed Tools Appl 79(3):1801–1819, 2020) while guaranteeing the detection of all the critical events at the sensor node level. The second approach exploits the Spatio-temporal correlation between neighboring nodes to reduce the number of captured frames. For that purpose, Synchronization with Frame Rate Adaptation SFRA algorithm is introduced where overlapping nodes capture frames in a synchronized fashion every N - 1 periods, where N is the number of overlapping sensor nodes. The results show more than 90% data reduction, surpassing other techniques in the literature at the level of the number of sensed frames by 20% at least. [ABSTRACT FROM AUTHOR]

Copyright of China Synthetic Fiber Industry is the property of Sinopec Baling Petrochemical Company 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.)

Deterioration of moral and psychological state on the background of a full–scale war is observed in many social groups. Timely detection of various types of pre–depressive states and appropriate therapy is a critically important task nowadays. In addition, an equally important task is to identify relationships between physical and psychological indicators of health. Establishing such regularities will allow detecting anxious states, avoiding direct profile testing of a patient. The article is devoted to construction of a mathematical apparatus for predicting psychological conclusions based on cardiological data. For this, a linear regression model and the ellipsoid method are used to determine its parameters with a criterion based on least moduli method (LMM), a feature selection procedure and a metric for assessing consistency of a data set. Material of the article is presented in 5 sections. Section 1 describes the ellipsoid method for finding parameters of linear regression with the least moduli method as a criterion in the power of p. Problem dimensions that can be successfully solved using the ellipsoid method on modern computers are indicated. The 2nd Section is devoted to Octave program emlmp, which implements the ellipsoid method, and the results of two computational experiments with its use. The obtained results demonstrate robustness of the obtained solutions when parameter p values are close to one. The 3rd Section describes mechanism of variable selection for the best prediction of psychological state of patients based on cardiological data. Variable selection was carried out using the Python Sequential Feature Selector procedure for predicting two psychological indicators – Beck's anxiety scale and psychologist's formalized conclusion. The 4th Section contains the results of a computational experiment using the emlmp program with LMM and least square method (LSM) criteria for predicting a psychologist’s formalized conclusion based on 84 selected patients and 22 parameters. Obtained solutions and forecasts for comparing criteria based on LMM and LSM are given. In the 5th Section, a metric for evaluation consistency of a data set is proposed, which allows to evaluate consistency for each parameter separately. A linear connection was found between 4 psychological parameters and the maximum accuracy of regression models with optimal number of parameters in specified models.

The traditional adaptive weighted fusion algorithm ignores the spatial correlation between the network sensing data and has high fusion bias, significantly reducing network data transmission quality. The network perception data fusion algorithm based on fuzzy time series is proposed, and the network perception data prediction algorithm based on fuzzy time series is used. The network data value is calculated using first and two-order fuzzy relations during the training stage, and the trend value of the network data is obtained. The trend value in the prediction stage dynamically obtains the network sense. Based on the relationship, the fuzzy relation of knowledge data is used to predict the network perception data for the next time series. The network sensing data fusion algorithm based on the confidence matrix is used to fuse the data by predicting the spatial correlation between the data and filtering the noise of the abnormal data to the fusion results. The proposed algorithm’s high fusion accuracy and improved quality of network data transmission are demonstrated by experimental results.

In the context of big data’s growing influence on education, our study presents a novel approach to managing higher vocational student data through a model based on the “three-round education” philosophy. We construct a predictive model to dissect and categorize student performance at X higher vocational college by integrating K-prototypes and LSSVM algorithms. Our findings reveal three primary groups: high achievers (43.65%), average performers (23.38%), and those with challenges (32.97%), each showing apparent differences in academic success indicators. Impressively, the model forecasts student enrollment numbers with less than 1.077% error, providing a reliable tool for educational administrators to make informed decisions and tailor student management strategies effectively.

This paper analyzes the effectiveness of predictive analysis of brain imaging data based on deep learning algorithms, and improves the prediction accuracy and efficiency of brain imaging data through improved methods. The first step is to measure the local consistency of the brain imaging data using Kendall’s concordance coefficient (KCC), and to analyze the differences between the datasets using the two-sample t-test. Secondly, a batch normalized convolutional neural network (BN-CNN)-based prediction method for brain imaging data has been developed. This method extracts spatial and temporal features in two convolutional layers, followed by a fully connected layer for classification. Experimental results show that this method is helpful in predicting missing structural data in brain imaging. Secondly, a batch normalized convolutional neural network (BN-CNN) based brain imaging data prediction method is developed, which extracts spatial and temporal features in two convolutional layers. Then it connects to a fully connected layer for classification. The experimental results show that this method’s structural similarity index (SSIM) and feature similarity index (FSIM) in brain imaging data prediction of missing data reaches 0.9446 and 0.9465, respectively, which is significantly better than that of other GAN benchmarks. In applying the method to epilepsy and Parkinson’s cases, this algorithm is used to epilepsy and Parkinson’s cases, and a two-sample t-test analyzes the differences in the data sets. In the application of epilepsy and Parkinson’s cases, the algorithm in this paper has an average prediction accuracy of 93.37%, effectively reducing the rate of incorrect predictions. Deep learning algorithms are highly efficient and accurate in predicting brain imaging data, which is crucial for future clinical diagnosis and treatment.

The safety factor is a crucial quantitative index for evaluating slope stability. However, the traditional calculation methods suffer from unreasonable assumptions, complex soil composition, and inadequate consideration of the influencing factors, leading to large errors in their calculations. Therefore, a stacking ensemble learning model (stacking-SSAOP) based on multi-layer regression algorithm fusion and optimized by the sparrow search algorithm is proposed for predicting the slope safety factor. In this method, the density, cohesion, friction angle, slope angle, slope height, and pore pressure ratio are selected as characteristic parameters from the 210 sets of established slope sample data. Random Forest, Extra Trees, AdaBoost, Bagging, and Support Vector regression are used as the base model (inner loop) to construct the first-level regression algorithm layer, and XGBoost is used as the meta-model (outer loop) to construct the second-level regression algorithm layer and complete the construction of the stacked learning model for improving the model prediction accuracy. The sparrow search algorithm is used to optimize the hyperparameters of the above six regression models and correct the over- and under-fitting problems of the single regression model to further improve the prediction accuracy. The mean square error (MSE) of the predicted and true values and the fitting of the data are compared and analyzed. The MSE of the stacking-SSAOP model was found to be smaller than that of the single regression model (MSE = 0.03917). Therefore, the former has a higher prediction accuracy and better data fitting. This study innovatively applies the sparrow search algorithm to predict the slope safety factor, showcasing its advantages over traditional methods. Additionally, our proposed stacking-SSAOP model integrates multiple regression algorithms to enhance prediction accuracy. This model not only refines the prediction accuracy of the slope safety factor but also offers a fresh approach to handling the intricate soil composition and other influencing factors, making it a precise and reliable method for slope stability evaluation. This research holds importance for the modernization and digitalization of slope safety assessments. [ABSTRACT FROM AUTHOR]

Time series data can be used to predict the dynamical behaviors without knowing equation model of a system. In this study, long-short term memory (LSTM) neural network is implemented to construct a complex dynamical system from data series. The network is trained through minimizing the loss function to obtain the optimal weight matrices of LSTM cells. We find that the LSTM network can well "learn" the information of the complex system. The data series generated from periodic orbits of a nonlinear system can be exactly predicted by comparing the output of neural networks with the real complex system. For the chaotic data series, the time evolution of trajectories could exactly match the actual system in the short-term data. Moreover, the long-term ergodic behavior of the complex system remains in our prediction, although such chaotic data series are quite sensitive to the initial conditions and the ensuing increase in uncertainty. [ABSTRACT FROM AUTHOR]

Due to advancements in CPU and storage technologies, the processing speed of tasks has been increasing. However, there has been a relative slowdown in the data transfer speeds between disks and memory. Consequently, the issue of I/O processing speed has become a significant concern in I/O-intensive tasks. This research paper proposes CluMP, which predicts the next block to be requested within a process using a clustered Markov chain. Compared to the simple read-ahead approach commonly used in Linux systems, CluMP can predict prefetching more accurately and requires less memory for the prediction process. CluMP demonstrated a maximum memory hit ratio improvement of 191.41% in the KVM workload compared to read-ahead, as well as a maximum improvement of 130.81% in the Linux kernel build workload. Additionally, CluMP provides the advantage of adaptability to user objectives and utilized workloads by incorporating several parameters, thereby allowing for optimal performance across various workload patterns. [ABSTRACT FROM AUTHOR]

Pollution acquires many forms, such as water, air, noise, heat, and light, whereas air pollution immediately affects human health. Controlling air pollution is a critical task because the sources of air pollution are more and different. Measuring and forecasting the severity level of air pollution helps the public to take safety actions immediately. Hence measuring air pollution precisely and automatically has become the need of the hour. This paper presents a novel Termite Fly Optimization Algorithm (TPO) for predicting the level of air pollution in various places. Based on the pollutants level measured from the air, the TFO algorithm estimates the human health mapping with the termites level in the search space. The high level of pollutants mixed in the air is mapped with the severity level of human health. This paper uses the worst-case comparison between the data and the termites' behavior. The prediction made through this model is converted into an index called the Air quality index (AQI). An open-source dataset is used to train the model, and a real-time dataset of air pollution from Chennai, Manali, is obtained to evaluate its prediction. Air pollution is predicted according to the AQI index. The results are compared with existing models, and the performance is verified.

To ensure the integrity of bridge monitoring data and to better predict the future health status of bridges, a combined model with in-sample and out-of-sample prediction capability was proposed to ensure the integrity of bridge monitoring data, which were commonly missing in the real measurement data of bridge health monitoring systems. The out-of-sample prediction can predict the future bridge health status based on the present data, and the in-sample regression was used to missing data imputation in the sensor data to ensure the integrity of the bridge monitoring data. Due to the strong correlation of the same type of sensors at different locations, ridge regression(RR) was first used to solve the covariance problem, establish the correlation between each sensor data, and predict the missing data. Then, the seasonal autoregressive integrated moving average(SARIMA)method was introduced to predict the future operation data of the bridge by using its out-of-sample prediction capability and combining with the ridge regression method. Finally, the method was applied to a real bridge to verify its effectiveness and provide an effective prediction model for missing sensor data imputation as well as predicting the future state of the bridge. [ABSTRACT FROM AUTHOR]

The prediction of power consumption of smart meters plays a vital role in power distribution and management in the smart grid, which depends on real-time and historical data. However, existing schemes do not meet the standard requirements of the prediction, are difficult to deploy, and do not achieve the desired accuracy. In this paper, an Ensemble learning based power consumption prediction model (EPC-PM) is proposed for the smart meter. Ensemble learning calculates the weights of base predictors and the voting engine selects the suitable predictor that has high accuracy and generates the final predicted output. The performance of base predictors is considered for the next iterations of prediction. Further, the predicted output can be used for power distribution and management by the smart grid. Experimental and statistical analysis shows that EPC-PM is more efficient than existing state-of-the-art works in terms of performance. The proposed EPC-PM improves the root mean square error, normalized root mean square error, and mean absolute error up to 0.2467, 13.45, and 0.1761, respectively, over the UMass Smart* dataset. [ABSTRACT FROM AUTHOR]

The objective of this paper is to present development results a technological solution supported by artificial intelligence (AI), for the company Servicios Amma S.A.S. This technological solution has the function to allow the correlation of the socio-behavioral characteristics of the customer, with the profile of the operational staff. This will provide the detection of patterns and prediction of consumption behaviors for the service that leads to the identification of opportunities, reduction of dissatisfaction risks, and improvement of the user's service experience. The methodology used in this study is quantitative, therefore, the demographic, social, psychographic, behavioral and lifestyle characteristics of customers and operating personnel of the company, as well as the beneficiary companies, are the variables defined for the development of this research. Additionally, the development of mathematical algorithms will be used to gather information for data correlation and prediction. The results obtained from this research allowed us to develop and program a mobile application and Land Page that allows data entry for the creation of user profiles for customers, employees, and platform administrators. In this way, Servicios Amma S.A.S. will be able to enhance the services it offers with the help of Artificial Intelligence. [ABSTRACT FROM AUTHOR]

Recently with the high implementation of numerous Internet of Things (IoT) based systems, it becomes a crucial need to have an effective data prediction approach for IoT data analysis that copes with sustainable smart city services. Nevertheless, IoT data add many data perspectives to consider, which complicate the data prediction process. This poses the urge for advanced data fusion methods that would preserve IoT data while ensuring data prediction accuracy, reliability, and robustness. Although different data prediction approaches have been presented for IoT applications, but maintaining IoT data characteristics is still a challenge. This paper presents our proposed approach the domain-independent Data Fusion for Data Prediction (DFDP) that consists of: (1) data fusion, which maintains IoT data massive size, faults, spatiotemporality, and freshness by employing a data input-data output fusion approach, and (2) data prediction, which utilizes the K-Nearest Neighbor data prediction technique on the fused data. DFDP is validated using IoT data from different smart cities datasets. The experiments examine the effective performance of DFDP that reaches 91.8% accuracy level. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) are periodically collecting data through randomly dispersed sensors (motes), which typically consume high energy in radio communication that mainly leans on data transmission within the network. Furthermore, dissemination mode in WSN usually produces noisy values, incorrect measurements or missing information that affect the behaviour of WSN. In this article, a Distributed Data Predictive Model (DDPM) was proposed to extend the network lifetime by decreasing the consumption in the energy of sensor nodes. It was built upon a distributive clustering model for predicting dissemination-faults in WSN. The proposed model was developed using Recursive least squares (RLS) adaptive filter integrated with a Finite Impulse Response (FIR) filter, for removing unwanted reflections and noise accompanying of the transferred signals among the sensors, aiming to minimize the size of transferred data for providing energy efficient. The experimental results demonstrated that DDPM reduced the rate of data transmission to ∼20%. Also, it decreased the energy consumption to 95% throughout the dataset sample and upgraded the performance of the sensory network by about 19.5%. Thus, it prolonged the lifetime of the network.

To accelerate the computation of hydrogen storage capacity in uniform slit-shaped porous carbon determined by molecular simulation, the traditional Gradient Boosting and XGBoost algorithms are introduced to create the predictive models, and evaluate their prediction effectiveness and accuracy. The resultant models are tuned their hyperparameters by the random grid search method. From the comparison among the obtained models, it is found that the XGBoost model with optimized hyperparameters shows superior performance in predicting the hydrogen storage capacity in simulated carbon pores. According to the comparison of the results, the XGBoost model with optimized hyperparameters outperforms the other models in forecasting hydrogen storage capacity in simulated carbon pores as a function of pressure and pore sizes. Furthermore, the predicted results are in the best agreement with the pristine target dataset as measured by various evaluation metrics. Note that other models yield reasonable performance metrics, but they are unable to forecast high-pressure storage capacity in the ultramicropore region (less than 1 nm). The developed model could be applied for precisely and rapidly searching and comprehending the temperature-dependent optimal pore size for high-capacity hydrogen-storage systems in vehicular applications.

In this investigation, an artificial-neural-network-based mathematical model was developed for the prediction of nickel adsorption data. As input variables, the initial concentration, adsorbent dosage, and pH of the nickel solution were chosen, while the removal efficiency was chosen as an output variable. The hyperparameters were optimized to determine the perfect topology for the model. The study demonstrated that the 3-2-1 ANN architecture was the most suitable topology. The determination coefficient of 0.98 and the mean squared error of 0.02 indicated the high performance of the developed model, which was successfully applied for isotherm data prediction. [ABSTRACT FROM AUTHOR]

Time series forecasting and analysis are widely used in many fields and application scenarios. Time series historical data reflects the change pattern and trend, which can serve the application and decision in each application scenario to a certain extent. In this paper, we select the time series prediction problem in the atmospheric environment scenario to start the application research. In terms of data support, we obtain the data of nearly 3500 vehicles in some cities in China fromRunwoda Research Institute, focusing on the major pollutant emission data of non-road mobile machinery and high emission vehicles in Beijing and Bozhou, Anhui Province to build the dataset and conduct the time series prediction analysis experiments on them. This paper proposes a P-gLSTNet model, and uses Autoregressive Integrated Moving Average model (ARIMA), long and short-term memory (LSTM), and Prophet to predict and compare the emissions in the future period. The experiments are validated on four public data sets and one self-collected data set, and the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) are selected as the evaluationmetrics. The experimental results show that the proposed P-gLSTNet fusion model predicts less error, outperforms the backbone method, and is more suitable for the prediction of time-series data in this scenario. [ABSTRACT FROM AUTHOR]

Optimization of alkali transesterification of pawpaw seed extract to biodiesel using NaOH catalyst was carried out to analyze kinetics, thermodynamic parameters, and optimum conditions. Response Surface Methodology (RSM) and Multiple Linear Regression (MLR) algorithms were used to confirm the optimum yield results. GC chromatography and X-ray diffraction (XRD) were used to determine the fatty acid profile and characteristics of the pawpaw seed oil (PSO). The maximum biodiesel yield of 80% was obtained at optimum temperature, catalyst weight, and methanol to oil ratio of 60 °C, 1.0 wt%, and 3:1 via the RSM. Kinetics shows that the effect of NaOH on the overall reaction rate was feasible at 30 min while MLR predictions exercised outside the design matrix confirmed that increasing catalyst weights and temperature increases biodiesel yield within the optimum conditions. The finding obtained from the MLR was consistent with the experimentally determined percentage yield practicable based on the experimentally determined value conducted to verify the predicted output. The predicted output indicated a ± 0.025 standard deviation from the result practicable. Some key fuel properties derived from PSO satisfied ASTM (D6751) specifications and complied with EN141215 standards. The XRD patterns and GC/MC characterization confirm PSO is a good source for biodiesel production.

Wireless sensor networks (WSNs) are periodically collecting data through randomly dispersed sensors (motes), which typically consume high energy in radio communication that mainly leans on data transmission within the network. Furthermore, dissemination mode in WSN usually produces noisy values, incorrect measurements or missing information that affect the behaviour of WSN. In this article, a Distributed Data Predictive Model (DDPM) was proposed to extend the network lifetime by decreasing the consumption in the energy of sensor nodes. It was built upon a distributive clustering model for predicting dissemination-faults in WSN. The proposed model was developed using Recursive least squares (RLS) adaptive filter integrated with a Finite Impulse Response (FIR) filter, for removing unwanted reflections and noise accompanying of the transferred signals among the sensors, aiming to minimize the size of transferred data for providing energy efficient. The experimental results demonstrated that DDPM reduced the rate of data transmission to ∼20%. Also, it decreased the energy consumption to 95% throughout the dataset sample and upgraded the performance of the sensory network by about 19.5%. Thus, it prolonged the lifetime of the network. [ABSTRACT FROM AUTHOR]

The energy consumption of production processes is increasingly becoming a concern for the industry, driven by the high cost of electricity, the growing concern for the environment and the greenhouse emissions. It is necessary to develop and improve energy efficiency systems, to reduce the ecological footprint and production costs. Thus, in this work, a system is developed capable of extracting and evaluating useful data regarding production metrics and outputs. With the extracted data, machine learning-based models were created to predict the expected energy consumption of an automotive spot welding, proving a clear insight into how the input values can contribute to the energy consumption of each product or machine, but also correlate the real values to the ideal ones and use this information to determine if some process is not working as intended. The method is demonstrated in real-world scenarios with robotic cells that meet Volkswagen and Ford standards. The results are promising, as models can accurately predict the expected consumption from the cells and allow managers to infer problems or optimize schedule decisions based on the energy consumption. Additionally, by the nature of the conceived architecture, there is room to expand and build additional systems upon the currently existing software. [ABSTRACT FROM AUTHOR]

Root studies like propagation and morphological traits unlock a higher-level understanding of plants to better the growth of agricultural crops and maximize farm yields. As they are located underground, there is an additional challenge in elucidating their structure and behavior. Root imaging allows for real-time observations and there are several known methods. One imaging dataset simulated entire 3D root systems to create 2D images for data analysis and measurements. In this study, the dataset's extracted measurements will be used to reconstruct the true parameters of the simulated 3D root system through the use of multigene symbolic regression genetic programming (MSRGP). Eleven (11) parameters were selected as the output variables, each for monocot and dicot data for a total of 22 MSRGP models. Among these, thirteen of them showed high R² values greater than 80%, proving the high accuracy of the MSRGP method. Input variables that were frequently used across multiple models were also noted, such as tip count, exploration ratio, and area. In addition to the accuracy that MSRGP provides in predicting variables, the computation time of these models is found to be as low as a few milliseconds. Once trained, this speed allows the models to be integrated into relevant applications without significant increases in computation cost. [ABSTRACT FROM AUTHOR]

In this era, we need to make everything about us more smartly and communicating. Hence, the popularity of Internet of Thing (IoT) is increasing quickly across industries. In such networks, the sensors represent the eyes of the IoT that collect data about different environments and states, while the sink node forms the brain of the network that must analyze the collected data and take decisions. However, the big amount of data collected by the sensors leads, from one hand, to consume the limited energy of the sensor and, from another hand, to complicate the exploitation of the data at the sink for decision making. In this paper, we propose a multi-tier prediction mechanism in order to handle big data collected by sensor networks based on the clustering scheme. The prediction model uses the least squares approximation method which is applied at both tiers of each cluster: sensors and cluster-heads (CHs). At the first tier, each sensor applies the prediction model in order to send a reduced set of data to its appropriate CH; At the second tier, the CH combines data coming from sensors and provides a predictive model to the sink, representing data for all sensors of the cluster. Extensive simulations on real sensor data collected from several applications demonstrated that our mechanism can efficiently reduce the data transmission and save the network energy, while maintaining an acceptable data accuracy level. [ABSTRACT FROM AUTHOR]