Pub Date : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1241-1249
Jayalakshmi Karemallaiah, Prabha Revaiah
Cloud computing is the most exploited research technology in both industry and academia due to wide application and increases in adoption from global organizations. In cloud, computing data storage is one of the primary resources offered through cloud computing, however, an increase in participants raises major security concerns, as the user has no hold over the data. Furthermore, recent research has shown great potential for efficient data sharing with multiple participants. Existing researches suggest complicated and inefficient cloud security architecture. Hence, this research work proposes identifiable data sharing for multiple users (IDSMU) mechanism, which aims to provide security for multiple users in a particular cloud group. A novel signature scheme is used for identifying the participants, further verification of the Novel Signature Scheme is proposed along with a retraction process where the secret keys of the participant and the sender is cross-verified; at last, a module is designed for the elimination of any malicious participants within the group. IDSMU is evaluated on computation count and efficiency is proved by comparing with an existing model considering computation count. IDSMU performs marginal improvisation over the existing model in comparison with the existing model using the novel signature scheme.
{"title":"Verifiable data distribution technique for multiple applicants in a cloud computing ecosystem","authors":"Jayalakshmi Karemallaiah, Prabha Revaiah","doi":"10.11591/ijai.v13.i2.pp1241-1249","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1241-1249","url":null,"abstract":"Cloud computing is the most exploited research technology in both industry and academia due to wide application and increases in adoption from global organizations. In cloud, computing data storage is one of the primary resources offered through cloud computing, however, an increase in participants raises major security concerns, as the user has no hold over the data. Furthermore, recent research has shown great potential for efficient data sharing with multiple participants. Existing researches suggest complicated and inefficient cloud security architecture. Hence, this research work proposes identifiable data sharing for multiple users (IDSMU) mechanism, which aims to provide security for multiple users in a particular cloud group. A novel signature scheme is used for identifying the participants, further verification of the Novel Signature Scheme is proposed along with a retraction process where the secret keys of the participant and the sender is cross-verified; at last, a module is designed for the elimination of any malicious participants within the group. IDSMU is evaluated on computation count and efficiency is proved by comparing with an existing model considering computation count. IDSMU performs marginal improvisation over the existing model in comparison with the existing model using the novel signature scheme. ","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"20 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233251","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1935-1944
J. R. Grande-Ramírez, Ramiro Meza-Palacios, A. Aguilar-Lasserre, Rita Flores-Asis, C. F. Vázquez-Rodríguez
Diabetes is one of the leading causes of death in the world and continues to rise. Type 2 diabetes mellitus is a life-threatening chronic degenerative disease if not appropriately controlled; risk factors and ineffective diagnosis continue to increase its prevalence. This study proposes an intelligent fuzzy system to make a diagnosis and predict the risk of developing type 2 diabetes mellitus. The system consists of two models; the R-T2DM model estimates if a person is at risk of developing type 2 diabetes mellitus. The DT2DM model is based on two systems: the symptomatology system estimates the level of symptoms the patient has, and the diagnosis system diagnoses type 2 diabetes mellitus. The results of this research were compared with those estimated by the team of doctors, and it was observed that the R-T2DM model obtained a success rate of 90.3%. The D-T2DM model got a success rate of 88.3% for the symptomatology system and 95.5% for the diagnosis system. The model developed in this study is focused on being applied in economically marginalized geographic areas of Mexico to improve the patient's quality of life.
{"title":"Intelligent fuzzy system to assess the risk of type 2 diabetes and diagnosis in marginalized regions","authors":"J. R. Grande-Ramírez, Ramiro Meza-Palacios, A. Aguilar-Lasserre, Rita Flores-Asis, C. F. Vázquez-Rodríguez","doi":"10.11591/ijai.v13.i2.pp1935-1944","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1935-1944","url":null,"abstract":"Diabetes is one of the leading causes of death in the world and continues to rise. Type 2 diabetes mellitus is a life-threatening chronic degenerative disease if not appropriately controlled; risk factors and ineffective diagnosis continue to increase its prevalence. This study proposes an intelligent fuzzy system to make a diagnosis and predict the risk of developing type 2 diabetes mellitus. The system consists of two models; the R-T2DM model estimates if a person is at risk of developing type 2 diabetes mellitus. The DT2DM model is based on two systems: the symptomatology system estimates the level of symptoms the patient has, and the diagnosis system diagnoses type 2 diabetes mellitus. The results of this research were compared with those estimated by the team of doctors, and it was observed that the R-T2DM model obtained a success rate of 90.3%. The D-T2DM model got a success rate of 88.3% for the symptomatology system and 95.5% for the diagnosis system. The model developed in this study is focused on being applied in economically marginalized geographic areas of Mexico to improve the patient's quality of life.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"53 25","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232399","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}
Crowd evacuation can be a challenging task, especially in emergency situations involving dynamically moving hazards. Effective obstacle avoidance is crucial for successful crowd evacuation, particularly in scenarios involving dynamic hazards such as natural or man-made disasters. In this paper, we propose a novel application of the emotional reciprocal velocity obstacles (ERVO) method for obstacle avoidance in dynamic hazard scenarios. ERVO is an established method that incorporates agent emotions and obstacle avoidance to produce more efficient and effective crowd navigation. Our approach improves on previous research by using ERVO to model the perceptive danger posed by dynamic hazards in real-time, which is crucial for rapid response in emergency situations. We conducted experiments to evaluate our approach and compared our results with other velocity obstacle methods. Our findings demonstrate that our approach is able to improve agent coordination, reduce congestion, and produce superior avoidance behavior. Our study shows that incorporating emotional reciprocity into obstacle avoidance can enhance crowd behavior in dynamic hazard scenarios.
{"title":"Crowd navigation for dynamic hazard avoidance in evacuation using emotional reciprocal velocity obstacles","authors":"Moch Fachri, Didit Prasetyo, Fardani Annisa Damastuti, Nugrahardi Ramadhani, Supeno Mardi Susiki Nugroho, Mochamad Hariadi","doi":"10.11591/ijai.v13.i2.pp1371-1379","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1371-1379","url":null,"abstract":"Crowd evacuation can be a challenging task, especially in emergency situations involving dynamically moving hazards. Effective obstacle avoidance is crucial for successful crowd evacuation, particularly in scenarios involving dynamic hazards such as natural or man-made disasters. In this paper, we propose a novel application of the emotional reciprocal velocity obstacles (ERVO) method for obstacle avoidance in dynamic hazard scenarios. ERVO is an established method that incorporates agent emotions and obstacle avoidance to produce more efficient and effective crowd navigation. Our approach improves on previous research by using ERVO to model the perceptive danger posed by dynamic hazards in real-time, which is crucial for rapid response in emergency situations. We conducted experiments to evaluate our approach and compared our results with other velocity obstacle methods. Our findings demonstrate that our approach is able to improve agent coordination, reduce congestion, and produce superior avoidance behavior. Our study shows that incorporating emotional reciprocity into obstacle avoidance can enhance crowd behavior in dynamic hazard scenarios.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"2 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141229244","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1459-1468
Nissabouri Salah, Elhadji Barra Ndiaye
This paper presents a damage detection method based on the inverse pattern recognition technique by artificial neural network (ANN) using ultrasonic waves. Lamb waves are guided elastic waves, are widely employed in nondestructive testing thanks to their attractive properties such as their sensitivity to the small defects. In this work, finite element method was conducted by Abaqus to study Lamb modes propagation. A data collection is performed by the signals recorded from the sensor of 300 models: healthy and damaged plates excited by a tone burst signal with the frequencies: 100 kHz, 125 kHz, 150 kHz, 175 kHz, 200 kHz, and 225 kHz. The captured signals in undamaged plat are the baseline, whereas the signals measured in damaged plates are recorded for various positions of external rectangular defects. To reduce the amount of training data, only two peaks of measured signals are required to be the input of the model. Continuous wavelet transform (CWT) was adopted to calculate the key features of the signal in the time domain. The feed forward neural network is implemented using MATLAB program. The data are divided as follows: 70% for training the model, 25% for the validation, and 5% for the test. The proposed model is accurate estimating the position of the defect with an accuracy of 99.98%.
{"title":"Towards an optimization of automatic defect detection by artificial neural network using Lamb waves","authors":"Nissabouri Salah, Elhadji Barra Ndiaye","doi":"10.11591/ijai.v13.i2.pp1459-1468","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1459-1468","url":null,"abstract":"This paper presents a damage detection method based on the inverse pattern recognition technique by artificial neural network (ANN) using ultrasonic waves. Lamb waves are guided elastic waves, are widely employed in nondestructive testing thanks to their attractive properties such as their sensitivity to the small defects. In this work, finite element method was conducted by Abaqus to study Lamb modes propagation. A data collection is performed by the signals recorded from the sensor of 300 models: healthy and damaged plates excited by a tone burst signal with the frequencies: 100 kHz, 125 kHz, 150 kHz, 175 kHz, 200 kHz, and 225 kHz. The captured signals in undamaged plat are the baseline, whereas the signals measured in damaged plates are recorded for various positions of external rectangular defects. To reduce the amount of training data, only two peaks of measured signals are required to be the input of the model. Continuous wavelet transform (CWT) was adopted to calculate the key features of the signal in the time domain. The feed forward neural network is implemented using MATLAB program. The data are divided as follows: 70% for training the model, 25% for the validation, and 5% for the test. The proposed model is accurate estimating the position of the defect with an accuracy of 99.98%.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"15 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141231889","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1632-1639
M. Elveny, Rahmad B. Y. Syah, Mahyuddin K. M. Nasution
When a business concentrates too much on acquiring new clients rather than retaining old ones, mistakes are sometimes made. Each customer has a different value. Customer lifetime value (CLV) is a metric used to assess longterm customer value. Customer value is a key concern in any commercial endeavor. When there are variations in customer behavior, CLV forecasts the value of total customer income when the data distribution is not normal, and outliers are present. Robust M-estimation, a maximum likelihood type estimator, is used in this study to enhance CLV data. Through the minimization of the regression parameter from the residual value, robust Mestimation eliminates data outliers in customer metric data. With an accuracy of 94.15%, R-square is used to gauge model performance. This research shows that CLV optimization can be used as a marketing and sales strategy by companies.
{"title":"An boosting business intelligent to customer lifetime value with robust M-estimation","authors":"M. Elveny, Rahmad B. Y. Syah, Mahyuddin K. M. Nasution","doi":"10.11591/ijai.v13.i2.pp1632-1639","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1632-1639","url":null,"abstract":"When a business concentrates too much on acquiring new clients rather than retaining old ones, mistakes are sometimes made. Each customer has a different value. Customer lifetime value (CLV) is a metric used to assess longterm customer value. Customer value is a key concern in any commercial endeavor. When there are variations in customer behavior, CLV forecasts the value of total customer income when the data distribution is not normal, and outliers are present. Robust M-estimation, a maximum likelihood type estimator, is used in this study to enhance CLV data. Through the minimization of the regression parameter from the residual value, robust Mestimation eliminates data outliers in customer metric data. With an accuracy of 94.15%, R-square is used to gauge model performance. This research shows that CLV optimization can be used as a marketing and sales strategy by companies.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"118 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141234628","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1294-1303
Akara Thammastitkul, Jitsanga Petsuwan
This research paper presents a comprehensive evaluation of the effectiveness of Imagga and Google cloud vision application programming interface (API) as image recognition tools for generating metadata in digital archive images. The assessment encompasses a diverse range of archive images, including those without text, images with text, and both color and black-and-white images. Through the use of evaluation metrics such as cosine similarity, word overlap similarity, recall, precision, and F1 score, the performance of these tools is quantitatively measured. The findings highlight the strong individual performance of both Imagga and Google cloud vision API, with the combined metadata outputs achieving significantly higher scores across all metrics. This emphasizes the potential benefits of employing a combined approach, leveraging the strengths of multiple tools to enhance the reliability and robustness of the metadata extraction process. The findings contribute to the advancement of metadata management in digital archives and underscore the importance of utilizing multiple tools for improved performance in image metadata generation.
本研究论文全面评估了 Imagga 和谷歌云视觉应用编程接口（API）作为图像识别工具在数字档案图像中生成元数据的有效性。评估涵盖各种档案图像，包括无文本图像、有文本图像以及彩色和黑白图像。通过使用余弦相似度、单词重叠相似度、召回率、精确度和 F1 分数等评估指标，对这些工具的性能进行了量化测量。研究结果表明，Imagga 和谷歌云视觉应用程序接口（Google cloud vision API）的单独性能都很强，而组合元数据输出在所有指标上都获得了明显更高的分数。这强调了采用组合方法的潜在优势，即利用多种工具的优势来提高元数据提取过程的可靠性和稳健性。这些发现有助于推动数字档案中的元数据管理，并强调了利用多种工具提高图像元数据生成性能的重要性。
{"title":"Enhancing accessibility and discoverability of digital archive images through automated image recognition tool","authors":"Akara Thammastitkul, Jitsanga Petsuwan","doi":"10.11591/ijai.v13.i2.pp1294-1303","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1294-1303","url":null,"abstract":"This research paper presents a comprehensive evaluation of the effectiveness of Imagga and Google cloud vision application programming interface (API) as image recognition tools for generating metadata in digital archive images. The assessment encompasses a diverse range of archive images, including those without text, images with text, and both color and black-and-white images. Through the use of evaluation metrics such as cosine similarity, word overlap similarity, recall, precision, and F1 score, the performance of these tools is quantitatively measured. The findings highlight the strong individual performance of both Imagga and Google cloud vision API, with the combined metadata outputs achieving significantly higher scores across all metrics. This emphasizes the potential benefits of employing a combined approach, leveraging the strengths of multiple tools to enhance the reliability and robustness of the metadata extraction process. The findings contribute to the advancement of metadata management in digital archives and underscore the importance of utilizing multiple tools for improved performance in image metadata generation.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"14 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141235300","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}
Soil image classification is a critical task within the realms of agriculture and environmental applications. In recent years, the integration of deep learning has sparked significant interest in image-based soil classification. Transfer learning, a well-established technique in image classification, involves finetuning a pre-trained model on a specific dataset. However, conventional transfer learning methods typically focus solely on fine-tuning the final layer of the pre-trained model, which may not suffice to attain high performance on a new task. HybridTransferNet, a unique hybrid transfer learning approach designed for soil classification based on images is proposed in this paper. HybridTransferNet goes beyond the conventional approach by finetuning not only the final layer but also a select number of earlier layers in a pre-trained ResNet50 model. This extension results in substantially enhanced ability to classify when compared to standard transfer learning methods. Our evaluation of HybridTransferNet, conducted on a soil classification dataset, encompasses the reporting of various performance indicators, such as the F1 score, recall, accuracy, and precision. Our findings from experiments highlight HybridTransferNet's advantages over conventional transfer learning strategies, establishing it as a state-of-the-art solution in the domain of soil classification.
{"title":"HybridTransferNet: soil image classification through comprehensive evaluation for crop suggestion","authors":"Chetan Raju, Ashoka Davanageri Virupakshappa, Ajay Prakash Basappa Vijaya","doi":"10.11591/ijai.v13.i2.pp1702-1710","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1702-1710","url":null,"abstract":"Soil image classification is a critical task within the realms of agriculture and environmental applications. In recent years, the integration of deep learning has sparked significant interest in image-based soil classification. Transfer learning, a well-established technique in image classification, involves finetuning a pre-trained model on a specific dataset. However, conventional transfer learning methods typically focus solely on fine-tuning the final layer of the pre-trained model, which may not suffice to attain high performance on a new task. HybridTransferNet, a unique hybrid transfer learning approach designed for soil classification based on images is proposed in this paper. HybridTransferNet goes beyond the conventional approach by finetuning not only the final layer but also a select number of earlier layers in a pre-trained ResNet50 model. This extension results in substantially enhanced ability to classify when compared to standard transfer learning methods. Our evaluation of HybridTransferNet, conducted on a soil classification dataset, encompasses the reporting of various performance indicators, such as the F1 score, recall, accuracy, and precision. Our findings from experiments highlight HybridTransferNet's advantages over conventional transfer learning strategies, establishing it as a state-of-the-art solution in the domain of soil classification.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"42 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141232725","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1658-1667
James Julian, Annastya Bagas Dewantara, F. Wahyuni
The fire safety system is an important component that controls material and immaterial losses. Fire disasters are generally indicated by the appearance of excess smoke and changes in temperature, pressure, and changes in other parameters in the environment. Conventional smoke sensors are limited in reading parameter changes around their environment, making them less effective in early fire detection. This study aims to design a smoke detection system as an early fire detection system, using sensor fusion based on deep learning using the recursive feature elimination method with cross-validation (RFECV) using a random forest classifier used to select optimal parameters from public datasets as the basis for determining the sensor to be used. Based on the RFECV optimal feature, a deep learning algorithm was performed and obtained an accuracy of 0.99, a precision of 0.99, a recall of 1.00, and an F1 score of 0.99, with a latency time of 34.02 μs, which is 71.76% times faster than the original model.
{"title":"Design of smoke detection system using deep learning and sensor fusion with recursive feature elimination cross-validation","authors":"James Julian, Annastya Bagas Dewantara, F. Wahyuni","doi":"10.11591/ijai.v13.i2.pp1658-1667","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1658-1667","url":null,"abstract":"The fire safety system is an important component that controls material and immaterial losses. Fire disasters are generally indicated by the appearance of excess smoke and changes in temperature, pressure, and changes in other parameters in the environment. Conventional smoke sensors are limited in reading parameter changes around their environment, making them less effective in early fire detection. This study aims to design a smoke detection system as an early fire detection system, using sensor fusion based on deep learning using the recursive feature elimination method with cross-validation (RFECV) using a random forest classifier used to select optimal parameters from public datasets as the basis for determining the sensor to be used. Based on the RFECV optimal feature, a deep learning algorithm was performed and obtained an accuracy of 0.99, a precision of 0.99, a recall of 1.00, and an F1 score of 0.99, with a latency time of 34.02 μs, which is 71.76% times faster than the original model.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"34 33","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141233007","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp1499-1510
Duaa Faris Abdlkader, Mayada Faris Ghanim
This research presents a face recognition system based on different classifiers that deal with various face positions. The proposed system involves the extraction of features through the VGG-Face-16 deep neural network, which only extracts essential features of input images, leading to an improved recognition step and enhanced algorithm efficiency, while the recognition involves the radial basis function in support vector machine (SVM) classifier and evaluate the performance of the system. Also, the system is designed and implemented later by using other classifiers; they are K-neareste2 neighbour (KNN) classifiers, logistic regression (LR), gradient boosting (XGBoost), decision tree classifier (DT) and Naive Bayes classifier (NB). The proposed algorithm was tested with the four face databases: AT&T, PINs Face, linear friction welding (LFW) and real database. The database was divided into two groups: One contains a percentage of images that are used for training and the second contains a percentage of images (remainder) which was used for testing. The results show that the classification by RBF in SVM has the highest recognition rate in the case of using small, medium and large databases; it was 100% in AT&T and Real database, while its efficiency appears to be lower when using large-size databases whereas it is 96% in PINs database and 60.1% in LFW database.
{"title":"Design and analysis of face recognition system based on VGGFace-16 with various classifiers","authors":"Duaa Faris Abdlkader, Mayada Faris Ghanim","doi":"10.11591/ijai.v13.i2.pp1499-1510","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp1499-1510","url":null,"abstract":"This research presents a face recognition system based on different classifiers that deal with various face positions. The proposed system involves the extraction of features through the VGG-Face-16 deep neural network, which only extracts essential features of input images, leading to an improved recognition step and enhanced algorithm efficiency, while the recognition involves the radial basis function in support vector machine (SVM) classifier and evaluate the performance of the system. Also, the system is designed and implemented later by using other classifiers; they are K-neareste2 neighbour (KNN) classifiers, logistic regression (LR), gradient boosting (XGBoost), decision tree classifier (DT) and Naive Bayes classifier (NB). The proposed algorithm was tested with the four face databases: AT&T, PINs Face, linear friction welding (LFW) and real database. The database was divided into two groups: One contains a percentage of images that are used for training and the second contains a percentage of images (remainder) which was used for testing. The results show that the classification by RBF in SVM has the highest recognition rate in the case of using small, medium and large databases; it was 100% in AT&T and Real database, while its efficiency appears to be lower when using large-size databases whereas it is 96% in PINs database and 60.1% in LFW database.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"78 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141231279","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 : 2024-06-01DOI: 10.11591/ijai.v13.i2.pp2111-2121
Miloud Bahiddine, Ali Belhamra
This paper describes direct torque control (DTC) of a permanent magnet synchronous machine (PMSM) powered by a two-level voltage inverter whose switching of switches is based on the Space Vector Modulation. To overcome the robustness of the control to the presence of a fault, we included an improvement of the direct torque control with Space vector modulation (DTC-SVM) by the use of the filters for the flux and the torque and compared to the direct torque control of the DTC-SVM, the PI controllers are replaced with sliding mode blocks, This control method allows giving a new structure DTC -SVM with sliding mode control. The analysis of the results shows good performances for the speed and a considerable reduction of the fluctuations at the level of the torque and the flux.
本文介绍了由两电平电压逆变器供电的永磁同步机（PMSM）的直接转矩控制（DTC），该逆变器的开关切换基于空间矢量调制。为了克服控制对故障存在的鲁棒性，我们对空间矢量调制直接转矩控制（DTC-SVM）进行了改进，使用了通量和转矩滤波器，与 DTC-SVM 直接转矩控制相比，用滑动模式块取代了 PI 控制器。对结果的分析表明，DTC-SVM 具有良好的速度性能，并大大降低了转矩和磁通的波动。
{"title":"Fault tolerant control of permanent magnet synchronous motor based on hybrid control strategies DTC-SVM with second order sliding mode control using multi-variable filter","authors":"Miloud Bahiddine, Ali Belhamra","doi":"10.11591/ijai.v13.i2.pp2111-2121","DOIUrl":"https://doi.org/10.11591/ijai.v13.i2.pp2111-2121","url":null,"abstract":"This paper describes direct torque control (DTC) of a permanent magnet synchronous machine (PMSM) powered by a two-level voltage inverter whose switching of switches is based on the Space Vector Modulation. To overcome the robustness of the control to the presence of a fault, we included an improvement of the direct torque control with Space vector modulation (DTC-SVM) by the use of the filters for the flux and the torque and compared to the direct torque control of the DTC-SVM, the PI controllers are replaced with sliding mode blocks, This control method allows giving a new structure DTC -SVM with sliding mode control. The analysis of the results shows good performances for the speed and a considerable reduction of the fluctuations at the level of the torque and the flux.","PeriodicalId":507934,"journal":{"name":"IAES International Journal of Artificial Intelligence (IJ-AI)","volume":"23 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141235573","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：