Data centers are systems that host devices utilizing recording and communication technologies, which are expected to operate securely and accurately. Consequently, transforming data centers into smart environments for control purposes has become a significant area of focus. In this study, we monitor the cabinet environment within data centers and ensure that the control system reaches the predetermined optimal state values in the event of undesirable situations. Threshold control was implemented for humidity and flame data, while fuzzy logic theory was applied to temperature data. Fuzzy clusters can be adjusted according to the data center's location at the user's request. This approach allows users to input desired optimal and threshold values into the system, which are then evaluated based on the situation. The designed system ensures data center security with minimal personnel involvement. Additionally, all problematic events are recorded in the system, enabling them to be viewed on a webpage and communicated to designated personnel via email. In the conducted study, the fuzzy-controlled temperature value outputs are reported as heating (40%), cooling (53%), and instances where the system does not perform heating or cooling.
{"title":"Data Center Control Application With Fuzzy Logic","authors":"Hasan YILMAZ, Adem Alpaslan ALTUN, Mehmet BİLEN","doi":"10.54569/aair.1203155","DOIUrl":"https://doi.org/10.54569/aair.1203155","url":null,"abstract":"Data centers are systems that host devices utilizing recording and communication technologies, which are expected to operate securely and accurately. Consequently, transforming data centers into smart environments for control purposes has become a significant area of focus. In this study, we monitor the cabinet environment within data centers and ensure that the control system reaches the predetermined optimal state values in the event of undesirable situations. Threshold control was implemented for humidity and flame data, while fuzzy logic theory was applied to temperature data. Fuzzy clusters can be adjusted according to the data center's location at the user's request. This approach allows users to input desired optimal and threshold values into the system, which are then evaluated based on the situation. The designed system ensures data center security with minimal personnel involvement. Additionally, all problematic events are recorded in the system, enabling them to be viewed on a webpage and communicated to designated personnel via email. In the conducted study, the fuzzy-controlled temperature value outputs are reported as heating (40%), cooling (53%), and instances where the system does not perform heating or cooling.","PeriodicalId":286492,"journal":{"name":"Advances in Artificial Intelligence Research","volume":"33 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136133487","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}
Regardless of young or old, people have quickly stepped into the world of internet with today's communication technologies such as phones, tablets, computers and smart devices. As the place of the Internet in people's lives increases, social media platforms are diversifying and users want to take part in these platforms. With the increase in the number of social media users, some negativities are encountered. The most important problem encountered in social media platforms is cyber bullying. Although cyber bullying seems to be a daily dialogue between social media users or between groups, the situation of encountering is increasing day by day with the diversity of shared information, content and agenda social media environments. With the development of technology, it is necessary to develop a platform that detects bullying with artificial intelligence technologies. One of the biggest difficulties in text classification problems that we encounter during the development of these platforms is the need to train the artificial intelligence algorithm to be used with labeled data. In this study, 21 different people, including journalists, athletes, scientists, doctors, politicians, comedians, social media phenomena, and artists who actively use social media, were selected in order to create the necessary dataset for training the models to be developed to detect cyber bullying situations. The public messages (mentions) of these 21 people sent via Twitter were compiled. After filtering the repetitive and meaningless messages sent by bot accounts out of 10500 tweets compiled, the number of messages in the dataset decreased to 7706. The labeling process, which is necessary for the dataset to be used for training and testing purposes in classification processes, was carried out by three independent people who were given preliminary information about cyberbullying (1=Includes Cyber bullying, 0=Does not include Cyber bullying). The majority of the tags, which were read and assigned by 3 different people, were accepted as the final class of the relevant message. Afterwards, the dataset was preprocessed in accordance with the principles of natural language processing and made suitable for classification algorithms. The findings obtained after the classification processes performed with the basic classification algorithms are shared. When the findings are examined, it is understood that the data set created has the competence to be used in the detection and prevention of cyber bullying. In this context, it is predicted that training specially developed and optimized artificial intelligence algorithms with the relevant dataset for the detection of cyberbullying will greatly increase the success rate.
{"title":"Creating a New Dataset for the Classification of Cyber Bullying","authors":"Çilem KOÇAK, Tuncay YİĞİT, Mehmet BİLEN","doi":"10.54569/aair.1206144","DOIUrl":"https://doi.org/10.54569/aair.1206144","url":null,"abstract":"Regardless of young or old, people have quickly stepped into the world of internet with today's communication technologies such as phones, tablets, computers and smart devices. As the place of the Internet in people's lives increases, social media platforms are diversifying and users want to take part in these platforms. With the increase in the number of social media users, some negativities are encountered. The most important problem encountered in social media platforms is cyber bullying. Although cyber bullying seems to be a daily dialogue between social media users or between groups, the situation of encountering is increasing day by day with the diversity of shared information, content and agenda social media environments. With the development of technology, it is necessary to develop a platform that detects bullying with artificial intelligence technologies. One of the biggest difficulties in text classification problems that we encounter during the development of these platforms is the need to train the artificial intelligence algorithm to be used with labeled data. In this study, 21 different people, including journalists, athletes, scientists, doctors, politicians, comedians, social media phenomena, and artists who actively use social media, were selected in order to create the necessary dataset for training the models to be developed to detect cyber bullying situations. The public messages (mentions) of these 21 people sent via Twitter were compiled. After filtering the repetitive and meaningless messages sent by bot accounts out of 10500 tweets compiled, the number of messages in the dataset decreased to 7706. The labeling process, which is necessary for the dataset to be used for training and testing purposes in classification processes, was carried out by three independent people who were given preliminary information about cyberbullying (1=Includes Cyber bullying, 0=Does not include Cyber bullying). The majority of the tags, which were read and assigned by 3 different people, were accepted as the final class of the relevant message. Afterwards, the dataset was preprocessed in accordance with the principles of natural language processing and made suitable for classification algorithms. The findings obtained after the classification processes performed with the basic classification algorithms are shared. When the findings are examined, it is understood that the data set created has the competence to be used in the detection and prevention of cyber bullying. In this context, it is predicted that training specially developed and optimized artificial intelligence algorithms with the relevant dataset for the detection of cyberbullying will greatly increase the success rate.","PeriodicalId":286492,"journal":{"name":"Advances in Artificial Intelligence Research","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136133488","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}
The age distribution of a population is extremely valuable to any business or country. In order to make decisions with regard to facility allocations and other social economic developmental issues, determination of age group distribution information is essential. The attempt to deceive others about one's age is a significant problem in the sporting world, as well as in other organizations and electoral processes. Therefore, there is a requirement for an age detection system, which is required to authenticate individual claims. Fingerprint-based age estimate research is scarce due to paucity of dataset. However, there are indications that fingerprints can reveal age demographic. This study's objective is to live-scan fingerprint images in order to identify age groups. This study proposed novel Dynamic Horizontal Voting Ensemble (DHVE) with Hybrid of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) as the base learner. The method constructs a horizontal voting ensemble for prediction by dynamically determining proficient models based on the validation accuracy metric during base learner training on the training set. Accuracy, recall, precision, and the F1 score were employed as standard performance metrics to measures the model's performance analysis. According to this study, predicting individual age group was accurate to a degree of above 91%. The DHVE network performed well due to the design of the layers. Integration of dynamic selection approach to horizontal voting ensemble improved the average performance of the model output.
{"title":"Deep Learning Ensemble Approach to Age Group Classification Based On Fingerprint Pattern","authors":"Olufunso OLORUNSOLA, Oluwaseyi OLORUNSHOLA","doi":"10.54569/aair.1303116","DOIUrl":"https://doi.org/10.54569/aair.1303116","url":null,"abstract":"The age distribution of a population is extremely valuable to any business or country. In order to make decisions with regard to facility allocations and other social economic developmental issues, determination of age group distribution information is essential. The attempt to deceive others about one's age is a significant problem in the sporting world, as well as in other organizations and electoral processes. Therefore, there is a requirement for an age detection system, which is required to authenticate individual claims. Fingerprint-based age estimate research is scarce due to paucity of dataset. However, there are indications that fingerprints can reveal age demographic. This study's objective is to live-scan fingerprint images in order to identify age groups. This study proposed novel Dynamic Horizontal Voting Ensemble (DHVE) with Hybrid of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) as the base learner. The method constructs a horizontal voting ensemble for prediction by dynamically determining proficient models based on the validation accuracy metric during base learner training on the training set. Accuracy, recall, precision, and the F1 score were employed as standard performance metrics to measures the model's performance analysis. According to this study, predicting individual age group was accurate to a degree of above 91%. The DHVE network performed well due to the design of the layers. Integration of dynamic selection approach to horizontal voting ensemble improved the average performance of the model output.","PeriodicalId":286492,"journal":{"name":"Advances in Artificial Intelligence Research","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136133493","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}
Deep Learning has brought forth captivating applications, and among them, Natural Language Processing (NLP) stands out. This study delves into the role of the data augmentation training strategy in advancing NLP. Data augmentation involves the creation of synthetic training data through transformations, and it is a well-explored research area across various machine learning domains. Apart from enhancing a model's generalization capabilities, data augmentation addresses a wide range of challenges, such as limited training data, regularization of the learning objective, and privacy protection by limiting data usage. The objective of this study is to investigate how data augmentation improves model accuracy and precise predictions, specifically using deep learning-based models. Furthermore, the study conducts a comparative analysis between deep learning models without data augmentation and those with data augmentation.
{"title":"Analyzing the Impact of Augmentation Techniques on Deep Learning Models for Deceptive Review Detection: A Comparative Study","authors":"Anusuya KRİSHNAN, Kennedyraj MARİAFRANCİS","doi":"10.54569/aair.1329048","DOIUrl":"https://doi.org/10.54569/aair.1329048","url":null,"abstract":"Deep Learning has brought forth captivating applications, and among them, Natural Language Processing (NLP) stands out. This study delves into the role of the data augmentation training strategy in advancing NLP. Data augmentation involves the creation of synthetic training data through transformations, and it is a well-explored research area across various machine learning domains. Apart from enhancing a model's generalization capabilities, data augmentation addresses a wide range of challenges, such as limited training data, regularization of the learning objective, and privacy protection by limiting data usage. The objective of this study is to investigate how data augmentation improves model accuracy and precise predictions, specifically using deep learning-based models. Furthermore, the study conducts a comparative analysis between deep learning models without data augmentation and those with data augmentation.","PeriodicalId":286492,"journal":{"name":"Advances in Artificial Intelligence Research","volume":"59 13","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136133639","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}
Exterior structures are susceptible to deformation, which can manifest as cracks on the surface. Deformations that occur on surfaces subjected to daily human use can exacerbate rapidly, potentially leading to irreversible structural damage. They have a potential to result in fatalities. Thus, continuous inspection of these deformations is of invaluable importance. In addition, the identification of the materials comprising the structures is essential to facilitate the implementation of appropriate precautionary measures. However, the inspections are hard to maintain with a solely human workforce. More advanced actions can be taken thanks to the developments in technology. Machine Learning methods could be used in this area where human workforce is ineffective. In this regard, an end-to-end Machine Learning approach was proposed in this study. The power of classical feature extraction methods and Artificial Neural Networks were combined to detect cracks and material of the surface simultaneously. The 2D Discrete Wavelet Transform and statistical properties gained from Gray Level Co-Occurrence Matrix were utilized in the feature extraction mechanism, and an ANN structure was designed. The findings of the study indicate that the proposed mechanism achieved an acceptable level of accuracy for recognizing the structural deformations, despite the challenges posed by the complexity of the problem.
{"title":"A Machine Learning Approach for Simultaneous Classification of Material Types and Cracks","authors":"Ömer MİNTEMUR","doi":"10.54569/aair.1254810","DOIUrl":"https://doi.org/10.54569/aair.1254810","url":null,"abstract":"Exterior structures are susceptible to deformation, which can manifest as cracks on the surface. Deformations that occur on surfaces subjected to daily human use can exacerbate rapidly, potentially leading to irreversible structural damage. They have a potential to result in fatalities. Thus, continuous inspection of these deformations is of invaluable importance. In addition, the identification of the materials comprising the structures is essential to facilitate the implementation of appropriate precautionary measures. However, the inspections are hard to maintain with a solely human workforce. More advanced actions can be taken thanks to the developments in technology. Machine Learning methods could be used in this area where human workforce is ineffective. In this regard, an end-to-end Machine Learning approach was proposed in this study. The power of classical feature extraction methods and Artificial Neural Networks were combined to detect cracks and material of the surface simultaneously. The 2D Discrete Wavelet Transform and statistical properties gained from Gray Level Co-Occurrence Matrix were utilized in the feature extraction mechanism, and an ANN structure was designed. The findings of the study indicate that the proposed mechanism achieved an acceptable level of accuracy for recognizing the structural deformations, despite the challenges posed by the complexity of the problem.","PeriodicalId":286492,"journal":{"name":"Advances in Artificial Intelligence Research","volume":"48 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136134326","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}
Recent developments in artificial intelligence technologies have accelerated the transition to smart systems in the automotive industry. By anticipating driving conditions, these technologies enable the prevention of driver-related errors and accidents as well as the provision of crucial information to the driver. In this study, an artificial intelligence-based system is designed to provide information to drivers about speed signs on the road in order to support traffic safety. In this system, Yolov4 model is used to achieve high speed and accuracy levels. After the model training, the model was validated and the test results were found to be 98%.
{"title":"Development of a Traffic Speed Limit Sign Detection System Based on Yolov4 Network","authors":"Semih SELÇUK, Sefa BEKER, Ömer Faruk BOYRAZ","doi":"10.54569/aair.1184569","DOIUrl":"https://doi.org/10.54569/aair.1184569","url":null,"abstract":"Recent developments in artificial intelligence technologies have accelerated the transition to smart systems in the automotive industry. By anticipating driving conditions, these technologies enable the prevention of driver-related errors and accidents as well as the provision of crucial information to the driver. In this study, an artificial intelligence-based system is designed to provide information to drivers about speed signs on the road in order to support traffic safety. In this system, Yolov4 model is used to achieve high speed and accuracy levels. After the model training, the model was validated and the test results were found to be 98%.","PeriodicalId":286492,"journal":{"name":"Advances in Artificial Intelligence Research","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136133492","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}
The importance of container transportation is constantly increasing. For this reason, lower cost transportation is of great importance for companies in transportation by air, land, rail and sea in domestic and international markets. One way of reducing the costs is to utilize the container volume effectively. In this study, a block-building based GRASP method is proposed for solving the container loading problem. The results are compared with other GRASP methods and other heuristic or meta-heuristic algorithms in the literature. The results show improvements in comparison to the other methods.
{"title":"A Block-Building Based GRASP Method for Solving Container Loading Problem","authors":"M. Özdemir, Tuncay Yiğit","doi":"10.54569/aair.1216400","DOIUrl":"https://doi.org/10.54569/aair.1216400","url":null,"abstract":"The importance of container transportation is constantly increasing. For this reason, lower cost transportation is of great importance for companies in transportation by air, land, rail and sea in domestic and international markets. One way of reducing the costs is to utilize the container volume effectively. In this study, a block-building based GRASP method is proposed for solving the container loading problem. The results are compared with other GRASP methods and other heuristic or meta-heuristic algorithms in the literature. The results show improvements in comparison to the other methods.","PeriodicalId":286492,"journal":{"name":"Advances in Artificial Intelligence Research","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131032828","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}
As monitoring and control of the quality of the water is one of the most important issues in the world since only 74% of the world's population use safely managed water where the water is treated well to reach the minimum limit of safety and quality standards. For observation of the water potability and to take immediate actions to improve the water quality, real-time monitoring and classification process are required. However, monitoring and controlling the quality of the water is not an easy task since it has many requirements such as the collection and analysis of data and measures to be taken. In this paper, we focus on applying machine learning for evaluation of the water quality. We have chosen five ensemble learning algorithms namely, Adaptive Boosting, Random Forest, Extra trees classifier, Gradient Boosting, and Stacking Classifier to evaluate their classification performances in defining the water quality. Results reveal that the Stacking Classifier has the highest performance among the five classifiers that we have studied.
{"title":"Prediction of Water Quality with Ensemble Learning Algorithms","authors":"Fatin Aljarah, Aydın Çetin","doi":"10.54569/aair.1200695","DOIUrl":"https://doi.org/10.54569/aair.1200695","url":null,"abstract":"As monitoring and control of the quality of the water is one of the most important issues in the world since only 74% of the world's population use safely managed water where the water is treated well to reach the minimum limit of safety and quality standards. For observation of the water potability and to take immediate actions to improve the water quality, real-time monitoring and classification process are required. However, monitoring and controlling the quality of the water is not an easy task since it has many requirements such as the collection and analysis of data and measures to be taken. In this paper, we focus on applying machine learning for evaluation of the water quality. We have chosen five ensemble learning algorithms namely, Adaptive Boosting, Random Forest, Extra trees classifier, Gradient Boosting, and Stacking Classifier to evaluate their classification performances in defining the water quality. Results reveal that the Stacking Classifier has the highest performance among the five classifiers that we have studied.","PeriodicalId":286492,"journal":{"name":"Advances in Artificial Intelligence Research","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124802233","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}
Cattle’s lumpy skin disease is a viral disease that transmits by blood-feeding insects like mosquitoes. The disease mostly affects animals that have not previously been exposed to the virus. Cattle lumpy skin disease impacts milk, beef, and national and international livestock trade. Traditional lumpy skin disease diagnosis is very difficult due to, the lack of materials, experts, and time-consuming. Due to this, it is crucial to use deep learning algorithms with the ability to classify the disease with high accuracy performance results. Therefore, Deep learning-based segmentation and classification are proposed for disease segmentation and classification by using deep features. For this, 10 layers of Convolutional Neural Networks have been chosen. The developed framework is initially trained on a collected Cattle’s lumpy Skin Disease (CLSD) dataset. The features are extracted from input images; hence the color of the skin is very important to identify the affected area during disease representation we used a color histogram. This segmented area of affected skin color is used for feature extraction by a deep pre-trained CNN. Then the generated result is converted into a binary using a threshold. The Extreme learning machine (ELM) classifier is used for classification. The classification performance of the proposed methodology achieved an accuracy of 0.9012% on CLSD To prove the effectiveness of the proposed methods, we present a comparison with the state-of-the-art techniques.
{"title":"Detecting High-risk Area for Lumpy Skin Disease in Cattle Using Deep Learning Feature","authors":"M. Genemo","doi":"10.54569/aair.1164731","DOIUrl":"https://doi.org/10.54569/aair.1164731","url":null,"abstract":"Cattle’s lumpy skin disease is a viral disease that transmits by blood-feeding insects like mosquitoes. The disease mostly affects animals that have not previously been exposed to the virus. Cattle lumpy skin disease impacts milk, beef, and national and international livestock trade. Traditional lumpy skin disease diagnosis is very difficult due to, the lack of materials, experts, and time-consuming. Due to this, it is crucial to use deep learning algorithms with the ability to classify the disease with high accuracy performance results. Therefore, Deep learning-based segmentation and classification are proposed for disease segmentation and classification by using deep features. For this, 10 layers of Convolutional Neural Networks have been chosen. The developed framework is initially trained on a collected Cattle’s lumpy Skin Disease (CLSD) dataset. The features are extracted from input images; hence the color of the skin is very important to identify the affected area during disease representation we used a color histogram. This segmented area of affected skin color is used for feature extraction by a deep pre-trained CNN. Then the generated result is converted into a binary using a threshold. The Extreme learning machine (ELM) classifier is used for classification. The classification performance of the proposed methodology achieved an accuracy of 0.9012% on CLSD To prove the effectiveness of the proposed methods, we present a comparison with the state-of-the-art techniques.","PeriodicalId":286492,"journal":{"name":"Advances in Artificial Intelligence Research","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125360918","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}
Today, the need for agricultural lands has increased even more due to the increasing population density. For this reason, increasing the yield of crops in agricultural areas becomes a very important need. It is very important to minimize the pests that negatively affect plant productivity in agricultural areas. In the study, it was aimed to detect the mealybug disease, which negatively affects plant productivity in agricultural areas, by using artificial intelligence methods. 539 disease-bearing and disease-free plant images collected from open access websites were used. These images are classified by VGG-16, Resnet-34 and Squeezenet deep learning algorithms. The most successful among the three architectures was determined as the VGG-16 and ResNet-34 model with an accuracy rate of 97%.
{"title":"Detection of Mealy Lice Disease Using Artificial Intelligence Methods","authors":"B. Aksoy, Nergiz Aydin, Sema Çayir, O. Salman","doi":"10.54569/aair.1143632","DOIUrl":"https://doi.org/10.54569/aair.1143632","url":null,"abstract":"Today, the need for agricultural lands has increased even more due to the increasing population density. For this reason, increasing the yield of crops in agricultural areas becomes a very important need. It is very important to minimize the pests that negatively affect plant productivity in agricultural areas. In the study, it was aimed to detect the mealybug disease, which negatively affects plant productivity in agricultural areas, by using artificial intelligence methods. 539 disease-bearing and disease-free plant images collected from open access websites were used. These images are classified by VGG-16, Resnet-34 and Squeezenet deep learning algorithms. The most successful among the three architectures was determined as the VGG-16 and ResNet-34 model with an accuracy rate of 97%.","PeriodicalId":286492,"journal":{"name":"Advances in Artificial Intelligence Research","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129385171","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：