{"title":"在预测中应用人工神经网络模型","authors":"Rugia Elbashir, Khalid Genawi","doi":"10.59992/ijsr.2024.v3n7p2","DOIUrl":null,"url":null,"abstract":"In this study we viewed concept of the Artificial Neural Networks (ANN) technology, and displayed its advantages, and its applications, and applied this technology in the prediction in time series, we were use the monthly closing price from Khartoum Stock Exchange index for the period from January 2012 to December 2021, to predict future values, by using software MATLAP R 2013a. The model building steps were done easily by MATLAB program, which selected the learning algorithm and functions to training the network automatically, we determined the number of layers and decay, the data series were divided to three sets: training, validation, and testing set. Depend on values of Mean Square Error (MSE) and Correlation Coefficient between target values and output values (R), the best forecasting model was selected, that has least (MSE) and high value of (R). The figure7 represent the predicted values were consistent with the real values of the series showing the efficiency of the model.","PeriodicalId":513336,"journal":{"name":"International Journal for Scientific Research","volume":"85 17","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Appling Artificial Neural Networks Models in Prediction\",\"authors\":\"Rugia Elbashir, Khalid Genawi\",\"doi\":\"10.59992/ijsr.2024.v3n7p2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this study we viewed concept of the Artificial Neural Networks (ANN) technology, and displayed its advantages, and its applications, and applied this technology in the prediction in time series, we were use the monthly closing price from Khartoum Stock Exchange index for the period from January 2012 to December 2021, to predict future values, by using software MATLAP R 2013a. The model building steps were done easily by MATLAB program, which selected the learning algorithm and functions to training the network automatically, we determined the number of layers and decay, the data series were divided to three sets: training, validation, and testing set. Depend on values of Mean Square Error (MSE) and Correlation Coefficient between target values and output values (R), the best forecasting model was selected, that has least (MSE) and high value of (R). The figure7 represent the predicted values were consistent with the real values of the series showing the efficiency of the model.\",\"PeriodicalId\":513336,\"journal\":{\"name\":\"International Journal for Scientific Research\",\"volume\":\"85 17\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal for Scientific Research\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.59992/ijsr.2024.v3n7p2\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal for Scientific Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.59992/ijsr.2024.v3n7p2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Appling Artificial Neural Networks Models in Prediction
In this study we viewed concept of the Artificial Neural Networks (ANN) technology, and displayed its advantages, and its applications, and applied this technology in the prediction in time series, we were use the monthly closing price from Khartoum Stock Exchange index for the period from January 2012 to December 2021, to predict future values, by using software MATLAP R 2013a. The model building steps were done easily by MATLAB program, which selected the learning algorithm and functions to training the network automatically, we determined the number of layers and decay, the data series were divided to three sets: training, validation, and testing set. Depend on values of Mean Square Error (MSE) and Correlation Coefficient between target values and output values (R), the best forecasting model was selected, that has least (MSE) and high value of (R). The figure7 represent the predicted values were consistent with the real values of the series showing the efficiency of the model.