Pub Date : 2022-12-26DOI: 10.21608/ijicis.2022.147175.1198
Mayar A. Shafaey, Maryam ElBery, M. Salem, Hala Moushier, El-Sayed A. El-Dahshan, M. Tolba
: In recent time, the most applied classification method for hyperspectral images is based on the supervised deep learning approach. The hyperspectral images require special handling while it consists of hundreds of bands / channels. In this article, the experiments are conducted using one of the widespread deep learning models, Convolutional Neural Networks (CNNs), specifically, Csutom Spectral CNN architecture (CSCNN). The introduced network is based on the data reduction and data normalization. It firstly ommits the unnecessary data channels and retains the meaningful ones. Then, it passes the remaining data through the CNN layers (convolutional, rectified linear unit, fully connected, dropout,…etc) until reaches the classification layer. The experiments are applied on four benchmarcks [hyperspectral datasets], namely, Salinas-A, Kenndy Space Center (KSC), Indian Pines (IP), and Pavia University (Pavia-U). The proposed model achieved an overall accuracy more than 99.50 %. In last, a comparison versus the state of the art is also introduced.
近年来，应用最多的高光谱图像分类方法是基于监督深度学习的方法。高光谱图像由数百个波段/通道组成，需要特殊处理。在本文中，实验使用了一种广泛的深度学习模型，卷积神经网络(CNN)，具体来说，是Csutom谱CNN架构(CSCNN)。该网络是基于数据约简和数据归一化的。它首先去掉不必要的数据通道，保留有意义的数据通道。然后，它将剩余的数据通过CNN层(卷积、整流线性单元、完全连接、dropout等)传递，直到到达分类层。实验应用于四个基准[高光谱数据集]，即Salinas-A, kennedy Space Center (KSC)， Indian Pines (IP)和Pavia University (Pavia- u)。该模型的总体准确率达到99.50%以上。最后，还介绍了与当前技术水平的比较。
{"title":"HYPERSPECTRAL IMAGE ANALYSIS USING A CUSTOM SPECTRAL CONVOLUTIONAL NEURAL NETWORK","authors":"Mayar A. Shafaey, Maryam ElBery, M. Salem, Hala Moushier, El-Sayed A. El-Dahshan, M. Tolba","doi":"10.21608/ijicis.2022.147175.1198","DOIUrl":"https://doi.org/10.21608/ijicis.2022.147175.1198","url":null,"abstract":": In recent time, the most applied classification method for hyperspectral images is based on the supervised deep learning approach. The hyperspectral images require special handling while it consists of hundreds of bands / channels. In this article, the experiments are conducted using one of the widespread deep learning models, Convolutional Neural Networks (CNNs), specifically, Csutom Spectral CNN architecture (CSCNN). The introduced network is based on the data reduction and data normalization. It firstly ommits the unnecessary data channels and retains the meaningful ones. Then, it passes the remaining data through the CNN layers (convolutional, rectified linear unit, fully connected, dropout,…etc) until reaches the classification layer. The experiments are applied on four benchmarcks [hyperspectral datasets], namely, Salinas-A, Kenndy Space Center (KSC), Indian Pines (IP), and Pavia University (Pavia-U). The proposed model achieved an overall accuracy more than 99.50 %. In last, a comparison versus the state of the art is also introduced.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130610214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-26DOI: 10.21608/ijicis.2022.140592.1184
Maha Mustafa, Hesham Ibrahim
The Agile development process in software provided many opportunities for development to meet customer expectations and continuous technological changes. Through this research, it was possible to analyze the visions of software users used in production operations in food factories to identify quality specifications for programs and errors as non-value added activities such as errors and time wasters. And iterations in order to study how to reduce it. Data were collected for the research through personal interviews with leaders, officials, software programmers, and distributing 400 survey questionnaire forms to employees. One incomplete survey was excluded to become 399 forms for users of this software in factories. The participants in the research were selected from software users in the factories under study from a random group of workers in food factories in the sample under study, and the rest of the data were also collected through personal interviews with software programmers who develop software for factories The results of the field study, which took place during the food factories in the sample under study, showed that the development of software used in the operation of production in food factories using the Agile development method, ensured the modification of software functions to ensure the prevention or at least the reduction of non-value-added activities. The sample were divided according to the classifications of the food industry and it was found that the increased added value as well as reducing the risks resulting from the use of such software in the operations of production in those factories were established
{"title":"Agile software development Process Orientation for eliminating errors as non-value-added activities in food and nutrition industries","authors":"Maha Mustafa, Hesham Ibrahim","doi":"10.21608/ijicis.2022.140592.1184","DOIUrl":"https://doi.org/10.21608/ijicis.2022.140592.1184","url":null,"abstract":"The Agile development process in software provided many opportunities for development to meet customer expectations and continuous technological changes. Through this research, it was possible to analyze the visions of software users used in production operations in food factories to identify quality specifications for programs and errors as non-value added activities such as errors and time wasters. And iterations in order to study how to reduce it. Data were collected for the research through personal interviews with leaders, officials, software programmers, and distributing 400 survey questionnaire forms to employees. One incomplete survey was excluded to become 399 forms for users of this software in factories. The participants in the research were selected from software users in the factories under study from a random group of workers in food factories in the sample under study, and the rest of the data were also collected through personal interviews with software programmers who develop software for factories The results of the field study, which took place during the food factories in the sample under study, showed that the development of software used in the operation of production in food factories using the Agile development method, ensured the modification of software functions to ensure the prevention or at least the reduction of non-value-added activities. The sample were divided according to the classifications of the food industry and it was found that the increased added value as well as reducing the risks resulting from the use of such software in the operations of production in those factories were established","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121467455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-26DOI: 10.21608/ijicis.2022.151347.1203
Maha Mustafa
: Achieving HACCP requirements for food control has become a basic requirement in the food industry, and the food control system needs an effective and low-cost tool for food control during work in the supply chain, and this research is based on studying the effectiveness of the RFID-based traceability tool used to identify units Defective supply chain and the traceability system identifies defective units in the supply chain in an easy and cost-effective way in combination with RFID technology. Through research, the effectiveness of the traceability system was studied to achieve the requirements of HACCP for food control, as this system is built and applied in many food factories by discovering defective units in finished products, as well as identifying potential defects during operation and supported by RFID technology dynamically. In order to identify the defective units, the study was carried out by distributing sixty survey forms to workers in ten food factories with a total of 600 forms, but the completed forms were 511 forms to identify the effectiveness of this system and its compatibility with HACCP requirements for food control. It became clear through field study that the system needs to be modified to include all phases in the production chain and to be more dynamic and support it to obtain a final system that helps to track down the defective units during the phases of the supply chain.
{"title":"Improving traceability systems in the food industry with RFID support to achieve HACCP requirements for food control in the supply chain","authors":"Maha Mustafa","doi":"10.21608/ijicis.2022.151347.1203","DOIUrl":"https://doi.org/10.21608/ijicis.2022.151347.1203","url":null,"abstract":": Achieving HACCP requirements for food control has become a basic requirement in the food industry, and the food control system needs an effective and low-cost tool for food control during work in the supply chain, and this research is based on studying the effectiveness of the RFID-based traceability tool used to identify units Defective supply chain and the traceability system identifies defective units in the supply chain in an easy and cost-effective way in combination with RFID technology. Through research, the effectiveness of the traceability system was studied to achieve the requirements of HACCP for food control, as this system is built and applied in many food factories by discovering defective units in finished products, as well as identifying potential defects during operation and supported by RFID technology dynamically. In order to identify the defective units, the study was carried out by distributing sixty survey forms to workers in ten food factories with a total of 600 forms, but the completed forms were 511 forms to identify the effectiveness of this system and its compatibility with HACCP requirements for food control. It became clear through field study that the system needs to be modified to include all phases in the production chain and to be more dynamic and support it to obtain a final system that helps to track down the defective units during the phases of the supply chain.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115928873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-15DOI: 10.21608/ijicis.2022.139226.1182
salma mostafa ahmed helmy, Ayman Mahmoud Amar, El-Sayed M. El-Horabty
: The health support of everybody should be considered as a highly significant, due to the huge increases in various health concerns. Meanwhile, heart attacks and cardiovascular disorders caused a public issue with high mortality ratios and cardiac patients, thereby increasing the open-heart surgery cases, limiting the available number of doctors, and most importantly generating an inefficient environment for caring patients, particularly with severe and fragile health problems. Hence, healthcare systems have begun to connect with IoT to keep each patient's digital identification. We, therefore, aimed at designing a smart device for cardiac patient’s monitoring to save time and effort for both caregivers and patients. Our design also could prevent crowding in health care places, provide a link between a person's hectic lifestyle and regular, and continuous the health checkups via remote access. The results from our prototype device can be employed for cardiac patient monitoring using IoT-technique which will monitor several health signs, i.e., blood oxygen ratios, heart rate, and body temperature. These signs can be remotely retrieved and/or imagined via medical experts on a handheld device through blynk APP from any location at any time. They also can gather the data and provide the real-time information about the patient through the Bluetooth module. Several individuals were put through a series of tests based on a variety of parameters. In conclusion, IoT could be recommended as a smart tool in the health care for monitoring the cardiac patients quickly and efficiently.
{"title":"Internet of Things (IoT) based smart device for cardiac patients monitoring using Blynk App","authors":"salma mostafa ahmed helmy, Ayman Mahmoud Amar, El-Sayed M. El-Horabty","doi":"10.21608/ijicis.2022.139226.1182","DOIUrl":"https://doi.org/10.21608/ijicis.2022.139226.1182","url":null,"abstract":": The health support of everybody should be considered as a highly significant, due to the huge increases in various health concerns. Meanwhile, heart attacks and cardiovascular disorders caused a public issue with high mortality ratios and cardiac patients, thereby increasing the open-heart surgery cases, limiting the available number of doctors, and most importantly generating an inefficient environment for caring patients, particularly with severe and fragile health problems. Hence, healthcare systems have begun to connect with IoT to keep each patient's digital identification. We, therefore, aimed at designing a smart device for cardiac patient’s monitoring to save time and effort for both caregivers and patients. Our design also could prevent crowding in health care places, provide a link between a person's hectic lifestyle and regular, and continuous the health checkups via remote access. The results from our prototype device can be employed for cardiac patient monitoring using IoT-technique which will monitor several health signs, i.e., blood oxygen ratios, heart rate, and body temperature. These signs can be remotely retrieved and/or imagined via medical experts on a handheld device through blynk APP from any location at any time. They also can gather the data and provide the real-time information about the patient through the Bluetooth module. Several individuals were put through a series of tests based on a variety of parameters. In conclusion, IoT could be recommended as a smart tool in the health care for monitoring the cardiac patients quickly and efficiently.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115041934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-07DOI: 10.21608/ijicis.2022.161846.1219
{"title":"Automation of Performance Testing: A Review","authors":"","doi":"10.21608/ijicis.2022.161846.1219","DOIUrl":"https://doi.org/10.21608/ijicis.2022.161846.1219","url":null,"abstract":"","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121680041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-07DOI: 10.21608/ijicis.2022.142804.1189
Mohamed Mead
: Managing traffic on roads within cities, especially crowded roads, requires constant and rapid intervention to avoid any traffic congestion on these roads. Forecasting the volume of vehicles on the roads helps to avoid congestion on the roads by directing some of these vehicles to alternative routes. In this paper, it is studied how to deal with road congestion by using deep learning models and Time series dataset with different time intervals to predict the volume of road traffic. Hybrid CNN and LSTM model (HCLM) is developed to predict the volume of road traffic. Determining the suitable hybrid CNN-LSTM model and parameters for this problem is a major objective of this research. The results confirm that the proposed HCLM for time series prediction achieves much better prediction accuracy than autoregressive integrated moving average (ARIMA) model, CNN model, and LSTM model for Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) measures at a time interval of 25 min and, 75 min. The time required to build these models was also compared, and the model HCLM was outperformed as it required 70% of the time to build it from its nearest competitor.
{"title":"Hybrid CNN and LSTM Model (HCLM) for Short-Term Traffic Volume Prediction","authors":"Mohamed Mead","doi":"10.21608/ijicis.2022.142804.1189","DOIUrl":"https://doi.org/10.21608/ijicis.2022.142804.1189","url":null,"abstract":": Managing traffic on roads within cities, especially crowded roads, requires constant and rapid intervention to avoid any traffic congestion on these roads. Forecasting the volume of vehicles on the roads helps to avoid congestion on the roads by directing some of these vehicles to alternative routes. In this paper, it is studied how to deal with road congestion by using deep learning models and Time series dataset with different time intervals to predict the volume of road traffic. Hybrid CNN and LSTM model (HCLM) is developed to predict the volume of road traffic. Determining the suitable hybrid CNN-LSTM model and parameters for this problem is a major objective of this research. The results confirm that the proposed HCLM for time series prediction achieves much better prediction accuracy than autoregressive integrated moving average (ARIMA) model, CNN model, and LSTM model for Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) measures at a time interval of 25 min and, 75 min. The time required to build these models was also compared, and the model HCLM was outperformed as it required 70% of the time to build it from its nearest competitor.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128911480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-09DOI: 10.21608/ijicis.2022.145103.1192
M. Fouad, Wedad Hussein, S. Rady, Philip S. Yu, Tarek G Gharib
: Based on a variety of information sources, recommender systems can identify specific items for various user interests. Techniques for recommender systems are classified into two types: personalized and non-personalized. Personalized algorithms are based on individual user preferences or collaborative filtering data; as the system learns more about the user, the recommendations will become more satisfying. They do, however, suffer from data sparsity and cold start issues. On the other hand, non-personalized algorithms make recommendations based on the importance of the items in the database; they are very useful when the system has no information about a specific user. Their accuracy, however, is limited by the issue of personalization. In most cases, one of the recommendation categories can be used to make recommendations. Yet, it is a challenge to evaluate the importance of items to the user while simultaneously using personalized and non-personalized preferences functions and ranking a set of candidate items based on these functions. This paper addresses this issue and improves recommendation quality by introducing a new hybrid recommendation technique. The proposed hybrid recommendation technique combines the importance of items to the user obtained by the utility mining method with the similarity weights of items produced by the collaborative filtering technique to make the recommendation process more reasonable and accurate. This technique can provide appropriate recommendations whether or not users have previous purchasing histories. Finally, experimental results show that the proposed hybrid recommendation technique outperforms both implemented collaborative filtering and utility-based recommendation techniques.
{"title":"A Hybrid Recommender System Combining Collaborative Filtering with Utility Mining","authors":"M. Fouad, Wedad Hussein, S. Rady, Philip S. Yu, Tarek G Gharib","doi":"10.21608/ijicis.2022.145103.1192","DOIUrl":"https://doi.org/10.21608/ijicis.2022.145103.1192","url":null,"abstract":": Based on a variety of information sources, recommender systems can identify specific items for various user interests. Techniques for recommender systems are classified into two types: personalized and non-personalized. Personalized algorithms are based on individual user preferences or collaborative filtering data; as the system learns more about the user, the recommendations will become more satisfying. They do, however, suffer from data sparsity and cold start issues. On the other hand, non-personalized algorithms make recommendations based on the importance of the items in the database; they are very useful when the system has no information about a specific user. Their accuracy, however, is limited by the issue of personalization. In most cases, one of the recommendation categories can be used to make recommendations. Yet, it is a challenge to evaluate the importance of items to the user while simultaneously using personalized and non-personalized preferences functions and ranking a set of candidate items based on these functions. This paper addresses this issue and improves recommendation quality by introducing a new hybrid recommendation technique. The proposed hybrid recommendation technique combines the importance of items to the user obtained by the utility mining method with the similarity weights of items produced by the collaborative filtering technique to make the recommendation process more reasonable and accurate. This technique can provide appropriate recommendations whether or not users have previous purchasing histories. Finally, experimental results show that the proposed hybrid recommendation technique outperforms both implemented collaborative filtering and utility-based recommendation techniques.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"484 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116532756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-09DOI: 10.21608/ijicis.2022.152368.1207
M. Abdelazim, Wedad Hussein, N. Badr
: Dialect identification is considered a subtask of the language identification problem and it is thought to be a more complex case due to the linguistic similarity between different dialects of the same language. In this paper, a novel approach is introduced for identifying three of the most used Arabic dialects: Egyptian, Levantine, and Gulf dialects. In this study, four experiments were conducted using different classification approaches that vary from simple classifiers such as Gaussian Naïve Bayes and Support Vector Machines to more complex classifiers using Deep Neural Networks (DNN). A features vector of 13 Mel cepstral coefficients (MFCCs) of the audio signals was used to train the classifiers using a multi-dialect parallel corpus. The experimental results showed that the proposed convolutional neural networks-based classifier has outperformed other classifiers in all three dialects. It has achieved an average improvement of 0.16, 0.19, and 0.19 in the Egyptian dialect, and of 0.07, 0.13, and 0.1 in the Gulf dialect, and of 0.52, 0.35, and 0.49 in the Levantine dialect for the Precision, recall and f1-score metrics respectively.
{"title":"Automatic Dialect identification of Spoken Arabic Speech using Deep Neural Networks","authors":"M. Abdelazim, Wedad Hussein, N. Badr","doi":"10.21608/ijicis.2022.152368.1207","DOIUrl":"https://doi.org/10.21608/ijicis.2022.152368.1207","url":null,"abstract":": Dialect identification is considered a subtask of the language identification problem and it is thought to be a more complex case due to the linguistic similarity between different dialects of the same language. In this paper, a novel approach is introduced for identifying three of the most used Arabic dialects: Egyptian, Levantine, and Gulf dialects. In this study, four experiments were conducted using different classification approaches that vary from simple classifiers such as Gaussian Naïve Bayes and Support Vector Machines to more complex classifiers using Deep Neural Networks (DNN). A features vector of 13 Mel cepstral coefficients (MFCCs) of the audio signals was used to train the classifiers using a multi-dialect parallel corpus. The experimental results showed that the proposed convolutional neural networks-based classifier has outperformed other classifiers in all three dialects. It has achieved an average improvement of 0.16, 0.19, and 0.19 in the Egyptian dialect, and of 0.07, 0.13, and 0.1 in the Gulf dialect, and of 0.52, 0.35, and 0.49 in the Levantine dialect for the Precision, recall and f1-score metrics respectively.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126743526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-09DOI: 10.21608/ijicis.2022.117905.1160
Anas Alokla, Walaa K. Gad, M. Aref, Abdel-Badeeh M. Salem
: Generating source code is necessary especially as software evolves in complexity and demand. Finding a mechanism to generate the source code according to the requirements will save time for developers at the stage of development of the software. In this paper, a mechanism is proposed to generate the source code based on the database schema and user requirements (user story). This model contains three layers: The first layer is to analyze each of the database schema, extract the relationships between the tables, determine the meanings of the fields and analyze the user’s story to find the functions performed by each role of the software users. The second layer is deducing new functions based on what was mentioned in the first layer and extracting the knowledge that contains the solutions to the problems that are inferred. The knowledge bases used are WordNet and Backend Ontology built from scratch. In the third Layer, the solutions are converted to source code based on templates extracted from the knowledge and configured, that is applied to the templates. The model showed success in generating the source code, generating PHP source code for a site that is tested and generated seventy percent of what was required to be written by programmers.
{"title":"Source Code Generation-based on NLP and Ontology","authors":"Anas Alokla, Walaa K. Gad, M. Aref, Abdel-Badeeh M. Salem","doi":"10.21608/ijicis.2022.117905.1160","DOIUrl":"https://doi.org/10.21608/ijicis.2022.117905.1160","url":null,"abstract":": Generating source code is necessary especially as software evolves in complexity and demand. Finding a mechanism to generate the source code according to the requirements will save time for developers at the stage of development of the software. In this paper, a mechanism is proposed to generate the source code based on the database schema and user requirements (user story). This model contains three layers: The first layer is to analyze each of the database schema, extract the relationships between the tables, determine the meanings of the fields and analyze the user’s story to find the functions performed by each role of the software users. The second layer is deducing new functions based on what was mentioned in the first layer and extracting the knowledge that contains the solutions to the problems that are inferred. The knowledge bases used are WordNet and Backend Ontology built from scratch. In the third Layer, the solutions are converted to source code based on templates extracted from the knowledge and configured, that is applied to the templates. The model showed success in generating the source code, generating PHP source code for a site that is tested and generated seventy percent of what was required to be written by programmers.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123605530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-14DOI: 10.21608/ijicis.2022.105654.1138
Samar Aly, Marco Alfonse, Abdel-Badeeh M. Salem
: Bankruptcy prediction is one of the most significant financial decision-making problems, which prevents financial institutions from sever risks. Most of bankruptcy datasets suffer from imbalanced distribution between output classes, which could lead to misclassification in the prediction results. This research paper presents an efficient bankruptcy prediction model that can handle imbalanced dataset problem by applying Synthetic Minority Oversampling Technique (SMOTE) as a pre-processing step. It applies ensemble-based machine learning classifier, namely, Categorical Boosting (CatBoost) to classify between active and inactive classes. Moreover, the proposed model reduces the dimensionality of the used dataset to increase predictive performance by using three different feature selection techniques. The proposed model is evaluated across the most popular imbalanced bankrupt dataset, which is the Polish dataset. The obtained results proved the efficiency of the applied model, especially in terms of the accuracy. The accuracies ofthe proposed model in predicting bankruptcy on the Polish five years datasets are 98%, 98%, 97%, 97% and 95%, respectively.
{"title":"Intelligent Model for Enhancing the Bankruptcy Prediction with Imbalanced Data Using Oversampling and CatBoost","authors":"Samar Aly, Marco Alfonse, Abdel-Badeeh M. Salem","doi":"10.21608/ijicis.2022.105654.1138","DOIUrl":"https://doi.org/10.21608/ijicis.2022.105654.1138","url":null,"abstract":": Bankruptcy prediction is one of the most significant financial decision-making problems, which prevents financial institutions from sever risks. Most of bankruptcy datasets suffer from imbalanced distribution between output classes, which could lead to misclassification in the prediction results. This research paper presents an efficient bankruptcy prediction model that can handle imbalanced dataset problem by applying Synthetic Minority Oversampling Technique (SMOTE) as a pre-processing step. It applies ensemble-based machine learning classifier, namely, Categorical Boosting (CatBoost) to classify between active and inactive classes. Moreover, the proposed model reduces the dimensionality of the used dataset to increase predictive performance by using three different feature selection techniques. The proposed model is evaluated across the most popular imbalanced bankrupt dataset, which is the Polish dataset. The obtained results proved the efficiency of the applied model, especially in terms of the accuracy. The accuracies ofthe proposed model in predicting bankruptcy on the Polish five years datasets are 98%, 98%, 97%, 97% and 95%, respectively.","PeriodicalId":244591,"journal":{"name":"International Journal of Intelligent Computing and Information Sciences","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114201138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：