Keywords provide a concise and precise description of the document's content. Due to the importance of the keyword and the difficulty of manual markup, automatic keyword extraction makes this process easy and fast. In this paper, Keyword Extraction from Kazakh News Dataset was presented. Model performance results were obtained by using the BERT base - uncased and BERT-base-multilingual-uncased pre-trained language model for the newly compiled Kazakh News Dataset-KND. Compiled Kazakh news data set consists of 7060 data. Data were collected from the web pages anatili.kazgazeta.kz, Bilimdinews.kz, and zhasalash.kz using the BeautifulSoap and Requests libraries. These web pages mostly contain news, history, and literary texts. The dataset includes the publication name or news title, the author of the publication or news subject, and the URL of the Kazakh news site. In the evaluation of the training results, it was observed that the BERT base-multilingual-uncased F-score performance was higher than the BERT model.
{"title":"BERT ile Kazak Haber Veri Kümesinden Anahtar Kelime Çıkarımı","authors":"Aiman Abibullayeva, Aydın Çeti̇n","doi":"10.31202/ecjse.1131826","DOIUrl":"https://doi.org/10.31202/ecjse.1131826","url":null,"abstract":"Keywords provide a concise and precise description of the document's content. Due to the importance of the keyword and the difficulty of manual markup, automatic keyword extraction makes this process easy and fast. In this paper, Keyword Extraction from Kazakh News Dataset was presented. Model performance results were obtained by using the BERT base - uncased and BERT-base-multilingual-uncased pre-trained language model for the newly compiled Kazakh News Dataset-KND. Compiled Kazakh news data set consists of 7060 data. Data were collected from the web pages anatili.kazgazeta.kz, Bilimdinews.kz, and zhasalash.kz using the BeautifulSoap and Requests libraries. These web pages mostly contain news, history, and literary texts. The dataset includes the publication name or news title, the author of the publication or news subject, and the URL of the Kazakh news site. In the evaluation of the training results, it was observed that the BERT base-multilingual-uncased F-score performance was higher than the BERT model.","PeriodicalId":11622,"journal":{"name":"El-Cezeri Fen ve Mühendislik Dergisi","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91329938","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}
Artificial intelligence and its sub-branches, machine learning and deep learning, have proven themselves in many different areas such as medical imaging systems, face recognition, autonomous driving. Especially deep learning models have become very popular today. Because deep learning models are very complex in nature, they are one of the best examples of black-box models. This situation leaves the end user in doubt in terms of interpretability and explainability. Therefore, the need to make such systems understandable methods with explainable artificial intelligence (XAI) has been widely developed in recent years. In this context, a hybrid method has been developed as a result of the study, and classification study has been carried out on the new and original dataset over different deep learning algorithms. Grad-CAM application was performed on VGG16 architecture with classification accuracy of 99.643% and heat maps of pre-processed images were obtained by CLAHE method.
{"title":"A Hybrid Approach for Detection and Classification of Sheep-Goat Pox Disease Using Deep Neural Networks","authors":"Nilgün Sengöz","doi":"10.31202/ecjse.1159621","DOIUrl":"https://doi.org/10.31202/ecjse.1159621","url":null,"abstract":"Artificial intelligence and its sub-branches, machine learning and deep learning, have proven themselves in many different areas such as medical imaging systems, face recognition, autonomous driving. Especially deep learning models have become very popular today. Because deep learning models are very complex in nature, they are one of the best examples of black-box models. This situation leaves the end user in doubt in terms of interpretability and explainability. Therefore, the need to make such systems understandable methods with explainable artificial intelligence (XAI) has been widely developed in recent years. In this context, a hybrid method has been developed as a result of the study, and classification study has been carried out on the new and original dataset over different deep learning algorithms. Grad-CAM application was performed on VGG16 architecture with classification accuracy of 99.643% and heat maps of pre-processed images were obtained by CLAHE method.","PeriodicalId":11622,"journal":{"name":"El-Cezeri Fen ve Mühendislik Dergisi","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90597301","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}
Metaheuristic algorithms are algorithms inspired by natural phenomena and that are used to decide which possible solution is more efficient to solve a problem. Although these algorithms, whose numbers are increasing day by day, do not guarantee the exact solution, they promise to reach a solution around the exact solution quickly. Artificial Jellyfish Search Algorithm (YDA) is also a new metaheuristic algorithm proposed in 2021. In this study, a modification has been made to the global search part of the standard algorithm in order to improve the global search capability of YDA. Accordingly, the "current-to-best" approach, which is one of the successful mutation strategies in the Differential Evolution Algorithm, has been integrated into the global search method of YDA. The advanced algorithm (MYDA) obtained as a result of this modification has been tested for 10,30,50,100,500 and 1000 dimensions on a total of twelve benchmark functions, seven of which are uni-modal and five are multi-modal. In addition, MYDA has also been compared with algorithms selected from the literature. The results have been interpreted with the help of statistical tests. When the results obtained are examined, it has been determined that the proposed algorithm outperforms the standard algorithm for all dimensions in all functions. In the comparison with the literature, it has been determined that the algorithm produces successful and competitive results.
{"title":"A Novel Artificial Jellyfish Search Algorithm Improved with a Differential Evolution Algorithm-Based Global Search Strategy","authors":"Gulnur Yildizdan","doi":"10.31202/ecjse.1131734","DOIUrl":"https://doi.org/10.31202/ecjse.1131734","url":null,"abstract":"Metaheuristic algorithms are algorithms inspired by natural phenomena and that are used to decide which possible solution is more efficient to solve a problem. Although these algorithms, whose numbers are increasing day by day, do not guarantee the exact solution, they promise to reach a solution around the exact solution quickly. Artificial Jellyfish Search Algorithm (YDA) is also a new metaheuristic algorithm proposed in 2021. In this study, a modification has been made to the global search part of the standard algorithm in order to improve the global search capability of YDA. Accordingly, the \"current-to-best\" approach, which is one of the successful mutation strategies in the Differential Evolution Algorithm, has been integrated into the global search method of YDA. The advanced algorithm (MYDA) obtained as a result of this modification has been tested for 10,30,50,100,500 and 1000 dimensions on a total of twelve benchmark functions, seven of which are uni-modal and five are multi-modal. In addition, MYDA has also been compared with algorithms selected from the literature. The results have been interpreted with the help of statistical tests. When the results obtained are examined, it has been determined that the proposed algorithm outperforms the standard algorithm for all dimensions in all functions. In the comparison with the literature, it has been determined that the algorithm produces successful and competitive results.","PeriodicalId":11622,"journal":{"name":"El-Cezeri Fen ve Mühendislik Dergisi","volume":"107 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75310124","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}
Cihan Kantar, Zeliha Er, Nimet Baltaş, Selami Şaşmaz
Although various azo compounds containing some natural origin catechins had been synthesized and determined their dyeing properties for various textile products, azo compounds containing black tea waste catechins and their antioxidant capacity and urease enzyme inhibition were not investigated until this study. The urease enzyme is the most important enzyme that allows the bacteria Helicobacter pylori, which is considered the main factor of stomach cancer, to live in the stomach. Inhibition of this enzyme is very important for the treatment of Helicobacter pylori infection. It has been known that catechin extracts of natural origin inhibit the urease enzyme of Helicobacter pylori from literature. Black tea processing waste is a residue that is separated from the sieves during tea processing and has no economic value. The transformation of this residue into products that produce added value is very important because it contains many chemicals contained in the tea plant. In this study, some azo compounds containing black tea processing waste catechins were synthesized and investigated their antioxidant capacity, urease enzyme inhibition properties.
{"title":"Antioksidan ve Üreaz Enzim İnhibitörü Olarak Siyah Çay İşleme Atığındaki Kateşinleri İçeren Bazı Azo Bileşikleri","authors":"Cihan Kantar, Zeliha Er, Nimet Baltaş, Selami Şaşmaz","doi":"10.31202/ecjse.1131913","DOIUrl":"https://doi.org/10.31202/ecjse.1131913","url":null,"abstract":"Although various azo compounds containing some natural origin catechins had been synthesized and determined their dyeing properties for various textile products, azo compounds containing black tea waste catechins and their antioxidant capacity and urease enzyme inhibition were not investigated until this study. The urease enzyme is the most important enzyme that allows the bacteria Helicobacter pylori, which is considered the main factor of stomach cancer, to live in the stomach. Inhibition of this enzyme is very important for the treatment of Helicobacter pylori infection. It has been known that catechin extracts of natural origin inhibit the urease enzyme of Helicobacter pylori from literature. Black tea processing waste is a residue that is separated from the sieves during tea processing and has no economic value. The transformation of this residue into products that produce added value is very important because it contains many chemicals contained in the tea plant. \u0000In this study, some azo compounds containing black tea processing waste catechins were synthesized and investigated their antioxidant capacity, urease enzyme inhibition properties.","PeriodicalId":11622,"journal":{"name":"El-Cezeri Fen ve Mühendislik Dergisi","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75549556","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}
M. M. Özmen, Fatmanur Ateş, Muzaffer Eylence, R. Şenol, B. Aksoy
Today, bombing activities are frequently on the agenda. Bomb devices placed under vehicles are the most common example of bombing activities. Shopping malls, military camps, etc. In places, vehicles are allowed to pass by checking under the vehicle with a mirror. This situation may leave the door open to mistakes that can be made by the personnel checking under the vehicle. In this study, an automatic controlled system was designed for vehicle passage. It is aimed to take under-vehicle images of the vehicles to be taken to a military campus, depending on the license plate recognition system, and to allow these images to pass into the military campus in a controlled manner after determining whether there is a foreign object under the vehicle by using artificial intelligence methods. An interface screen has been created for the designed system. If the incoming license plate is registered in the system and there is no foreign object under the vehicle, the barrier is opened and the vehicle passes.
{"title":"Detection Of Foreign Material Under Vehicle By Artificial Intelligence Methods And Automatic Passing System","authors":"M. M. Özmen, Fatmanur Ateş, Muzaffer Eylence, R. Şenol, B. Aksoy","doi":"10.31202/ecjse.1137522","DOIUrl":"https://doi.org/10.31202/ecjse.1137522","url":null,"abstract":"Today, bombing activities are frequently on the agenda. Bomb devices placed under vehicles are the most common example of bombing activities. Shopping malls, military camps, etc. In places, vehicles are allowed to pass by checking under the vehicle with a mirror. This situation may leave the door open to mistakes that can be made by the personnel checking under the vehicle. In this study, an automatic controlled system was designed for vehicle passage. It is aimed to take under-vehicle images of the vehicles to be taken to a military campus, depending on the license plate recognition system, and to allow these images to pass into the military campus in a controlled manner after determining whether there is a foreign object under the vehicle by using artificial intelligence methods. An interface screen has been created for the designed system. If the incoming license plate is registered in the system and there is no foreign object under the vehicle, the barrier is opened and the vehicle passes.","PeriodicalId":11622,"journal":{"name":"El-Cezeri Fen ve Mühendislik Dergisi","volume":"446 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79670714","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}
Plants have an important place in human life in many sectors for many years. Rosa damascena Mill plant, which is called Pink Oil Rose, is a species that has economic value for sectors such as cosmetics, perfume, medicine and food industry with its distinctive sharp and intense scent among rose varieties. Oil rose is harvested in May in Turkey when its buds bloom. Roses in bud form are left unharvested until they bloom. In this study, binary classification of each oil rose according to "harvestable/non-harvestable" status was carried out using machine learning and deep learning methods. The data set created with the images obtained from the rose gardens was used in the training and testing of artificial intelligence models. DVM classifier was used as machine learning model, and VGG16, VGG19 and InceptionV3 were used as deep learning models. Classification performance is 71.06% in the DVM model, 96.44% in the VGG16 model, 97.96% in the VGG19 model and 72.08% in the InceptionV3 model.
{"title":"Detection of Harvest Status of Oil Rose (Rosa damascena Mill.) with Machine Learning and Deep Learning Methods","authors":"Burhan Duman, K. Kayaalp","doi":"10.31202/ecjse.1134822","DOIUrl":"https://doi.org/10.31202/ecjse.1134822","url":null,"abstract":"Plants have an important place in human life in many sectors for many years. Rosa damascena Mill plant, which is called Pink Oil Rose, is a species that has economic value for sectors such as cosmetics, perfume, medicine and food industry with its distinctive sharp and intense scent among rose varieties. Oil rose is harvested in May in Turkey when its buds bloom. Roses in bud form are left unharvested until they bloom. In this study, binary classification of each oil rose according to \"harvestable/non-harvestable\" status was carried out using machine learning and deep learning methods. The data set created with the images obtained from the rose gardens was used in the training and testing of artificial intelligence models. DVM classifier was used as machine learning model, and VGG16, VGG19 and InceptionV3 were used as deep learning models. Classification performance is 71.06% in the DVM model, 96.44% in the VGG16 model, 97.96% in the VGG19 model and 72.08% in the InceptionV3 model.","PeriodicalId":11622,"journal":{"name":"El-Cezeri Fen ve Mühendislik Dergisi","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81848837","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}
Aslı Yıldız, Coskun Özkan, Selçuk Alp, E. Ayyıldız
Successfully managing the supply chain, which has become complex with many factors such as changes in customer demands, social perception, ease of access to information, advances in technology, increasing needs, and changing environmental conditions, provides great convenience to businesses. Effective supply chain and all operations management in this chain has great importance for retailers, which play a key role in the distribution of products and services to the end consumer. Vending machines, which are called the customers of retailers in a vendor-managed system, are among the distribution channels that are widely used in delivering products or services to the end consumer. The study, it is aimed to make a risk assessment for product distribution to vending machines. For this purpose, the Best Worst method, which is one of the Multi-Criteria Decision Making methods, is used to determine and evaluate supply risks. As a result of the evaluation of the nine risk criteria determined for the study according to the method, the risks that should be considered primarily are determined as "Errors in demand tracking", "Qualitative and quantitative inadequacies compared to competitors", "Insufficient vehicle compartment and capacity".
{"title":"Risk Assessment in Vending Machine Product Distribution","authors":"Aslı Yıldız, Coskun Özkan, Selçuk Alp, E. Ayyıldız","doi":"10.31202/ecjse.1132087","DOIUrl":"https://doi.org/10.31202/ecjse.1132087","url":null,"abstract":"Successfully managing the supply chain, which has become complex with many factors such as changes in customer demands, social perception, ease of access to information, advances in technology, increasing needs, and changing environmental conditions, provides great convenience to businesses. Effective supply chain and all operations management in this chain has great importance for retailers, which play a key role in the distribution of products and services to the end consumer. Vending machines, which are called the customers of retailers in a vendor-managed system, are among the distribution channels that are widely used in delivering products or services to the end consumer. The study, it is aimed to make a risk assessment for product distribution to vending machines. For this purpose, the Best Worst method, which is one of the Multi-Criteria Decision Making methods, is used to determine and evaluate supply risks. As a result of the evaluation of the nine risk criteria determined for the study according to the method, the risks that should be considered primarily are determined as \"Errors in demand tracking\", \"Qualitative and quantitative inadequacies compared to competitors\", \"Insufficient vehicle compartment and capacity\".","PeriodicalId":11622,"journal":{"name":"El-Cezeri Fen ve Mühendislik Dergisi","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81989369","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}
Asteroids have attracted people's attention from the past to the present. It has a wide place in the beliefs and cultures of ancient civilizations. The sense of discovery and curiosity of human beings causes an increase in their interest in these objects. With the technology coming to a certain level, the detection, diagnosis and materials of asteroids can be found clearly. The route and collision effects of these objects require constant observation. In our study, asteroids that are likely to hit the Earth have been classified using an asteroid data set in Kaggle and the source of which is NASA-JPL. The dataset contains 4687 asteroid data. Pre-processing steps such as filling in missing data, anomaly detection and normalization were applied on the data. Then, with the help of correlation, 19 features were determined from the dataset for dangerous situations. Asteroid classification was made by using Decision Tree with features, Naive Bayes, Logistic Regression, Random Forest, Support Vector Machines, K-Nearest Neighbor, Xgboost and Adaboost machine learning algorithms. With the artificial neural network with different number of neurons and layers, the data were trained and compared with classification algorithms. As a result of the comparison, the highest performance was achieved with the AdaBoost algorithm with 99.80%. Hyperparameter optimization was performed using the grid-search method in all the classification algorithms that were run. Thus, a method that requires continuous observation and enables the processing of large amounts of data in a more efficient way has been proposed.
小行星从过去到现在都吸引着人们的注意。它在古代文明的信仰和文化中占有广泛的地位。人类的发现意识和好奇心使他们对这些物品的兴趣增加。随着技术发展到一定水平，小行星的探测、诊断和材料都可以清晰地找到。这些物体的路径和碰撞效果需要持续观察。在我们的研究中，可能撞击地球的小行星已经使用Kaggle的小行星数据集进行了分类，这些数据的来源是NASA-JPL。该数据集包含4687颗小行星的数据。对数据进行了缺失数据填充、异常检测和归一化等预处理。然后，在相关性的帮助下，从数据集中确定了危险情况的19个特征。采用Decision Tree with feature、Naive Bayes、Logistic Regression、Random Forest、Support Vector Machines、K-Nearest Neighbor、Xgboost和Adaboost机器学习算法对小行星进行分类。使用不同神经元数和层数的人工神经网络对数据进行训练，并与分类算法进行比较。经过比较，AdaBoost算法达到了99.80%的最高性能。在运行的所有分类算法中，使用网格搜索方法进行超参数优化。因此，提出了一种需要连续观测并能够以更有效的方式处理大量数据的方法。
{"title":"Machine Learning Detection of Collision-Risk Asteroids","authors":"Ö. Eskicioğlu, A. Işık, Onur Sevli","doi":"10.31202/ecjse.1135651","DOIUrl":"https://doi.org/10.31202/ecjse.1135651","url":null,"abstract":"Asteroids have attracted people's attention from the past to the present. It has a wide place in the beliefs and cultures of ancient civilizations. The sense of discovery and curiosity of human beings causes an increase in their interest in these objects. With the technology coming to a certain level, the detection, diagnosis and materials of asteroids can be found clearly. The route and collision effects of these objects require constant observation. In our study, asteroids that are likely to hit the Earth have been classified using an asteroid data set in Kaggle and the source of which is NASA-JPL. The dataset contains 4687 asteroid data. Pre-processing steps such as filling in missing data, anomaly detection and normalization were applied on the data. Then, with the help of correlation, 19 features were determined from the dataset for dangerous situations. Asteroid classification was made by using Decision Tree with features, Naive Bayes, Logistic Regression, Random Forest, Support Vector Machines, K-Nearest Neighbor, Xgboost and Adaboost machine learning algorithms. With the artificial neural network with different number of neurons and layers, the data were trained and compared with classification algorithms. As a result of the comparison, the highest performance was achieved with the AdaBoost algorithm with 99.80%. Hyperparameter optimization was performed using the grid-search method in all the classification algorithms that were run. Thus, a method that requires continuous observation and enables the processing of large amounts of data in a more efficient way has been proposed.","PeriodicalId":11622,"journal":{"name":"El-Cezeri Fen ve Mühendislik Dergisi","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85522085","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 latest advances in technology and the improvement of decision processes with learning methods based on artificial intelligence have put the word "smart" ahead of all systems that make human life easier. Based on intelligent transportation systems, it is aimed to reduce the damage to the country's economy and the environment while providing technology-based and faster, safer, more accessible, more sustainable and more efficient transportation. The main goal of creating the intelligent transportation systems architecture is to design and implement human-focused, sustainable transportation systems together with cutting-edge technologies such as industry 4.0 technologies, mobile applications, augmented reality, and the internet of things. The transition to the Cooperative Intelligent Transportation Systems (C-ITS) structure by strengthening the infrastructure of intelligent transportation systems is included in the "National Intelligent Transportation Systems Strategy Document and 2020-2023 Action Plan". Intelligent transportation systems architecture needs to be updated according to C-ITS systems that provide interoperability and data integrity. With C-ITS, the aggregate collection of intelligent systems under one roof and the integrity of data will enable sustainable mobility such as monomedical payment in multi-mode transport. Therefore, the main factor in creating the architecture of intelligent transport systems is to create system architecture by making complex systems with data integrity and numerous insignificant idle data into systems that communicate with each other and reach the level of interoperability. In this study, intelligent transportation systems policies in the world have been analyzed and systems that have reached the level of interoperability that will provide the basis of C-ITS and intelligent transportation systems architecture have been proposed.
{"title":"Intelligent Transportation Systems Architecture: Recommendation for K-AUS","authors":"Buket Capali","doi":"10.31202/ecjse.1132804","DOIUrl":"https://doi.org/10.31202/ecjse.1132804","url":null,"abstract":"The latest advances in technology and the improvement of decision processes with learning methods based on artificial intelligence have put the word \"smart\" ahead of all systems that make human life easier. Based on intelligent transportation systems, it is aimed to reduce the damage to the country's economy and the environment while providing technology-based and faster, safer, more accessible, more sustainable and more efficient transportation. The main goal of creating the intelligent transportation systems architecture is to design and implement human-focused, sustainable transportation systems together with cutting-edge technologies such as industry 4.0 technologies, mobile applications, augmented reality, and the internet of things. The transition to the Cooperative Intelligent Transportation Systems (C-ITS) structure by strengthening the infrastructure of intelligent transportation systems is included in the \"National Intelligent Transportation Systems Strategy Document and 2020-2023 Action Plan\". Intelligent transportation systems architecture needs to be updated according to C-ITS systems that provide interoperability and data integrity. With C-ITS, the aggregate collection of intelligent systems under one roof and the integrity of data will enable sustainable mobility such as monomedical payment in multi-mode transport. Therefore, the main factor in creating the architecture of intelligent transport systems is to create system architecture by making complex systems with data integrity and numerous insignificant idle data into systems that communicate with each other and reach the level of interoperability. In this study, intelligent transportation systems policies in the world have been analyzed and systems that have reached the level of interoperability that will provide the basis of C-ITS and intelligent transportation systems architecture have been proposed.","PeriodicalId":11622,"journal":{"name":"El-Cezeri Fen ve Mühendislik Dergisi","volume":"72 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72813780","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's computing is one of the basic needs of every human being. Many actions are done with the mouse in the use of the computer. Individuals with physical disabilities, paralysis from the neck down, or ALS patients who have difficulty in making physical contact with the computer are having difficulty using computers. In this study, an artificial intelligence-assisted system has been developed for these individuals, where they can control the mouse with head and eye movements. In this system, facial movements and eyes are detected in real-time through the library of Haar Cascade, Dlib, and Open CV from the images acquired through the camera. When Haar Cascade is used to detect the face region, the Dlib library is used to acquire right and left eye region images from this detected face image. These eye areas are provided as an introduction to the CNN model, which is trained with 2874 eye data (https://github.com/iparaskev/simple-blink-detector), and it is determined that the eye is closed or open. The CNN model 1500 is trained on a public eye image dataset representing open and 1374 closed-eye conditions. The left eye closed and opened state allows the mouse to click left and the right eye to close and open, and the right mouse to click. In addition, the location of the face detected with Haar Cascade is used to model mouse motion. The developed system is a real-time hybrid system with a combination of different methods and has been tested on different users. According to the test results, it was observed that the system correctly identified the eyes and the closed state of these eyes, classifying the blink event with CNN in both eyes correctly. However, it has been determined that there has been a slowness in modeling mouse movement or a poor fit to facial movement. The next study will focus on this issue and improve it by fine-tuning the system with data from many people.
{"title":"Computer Control with Face and Eye Movements Using Deep Learning and Image Processing Methods","authors":"Muhammet Fatih Çapşek, Abdulkadir Karacı","doi":"10.31202/ecjse.1131377","DOIUrl":"https://doi.org/10.31202/ecjse.1131377","url":null,"abstract":"Today's computing is one of the basic needs of every human being. Many actions are done with the mouse in the use of the computer. Individuals with physical disabilities, paralysis from the neck down, or ALS patients who have difficulty in making physical contact with the computer are having difficulty using computers. In this study, an artificial intelligence-assisted system has been developed for these individuals, where they can control the mouse with head and eye movements. In this system, facial movements and eyes are detected in real-time through the library of Haar Cascade, Dlib, and Open CV from the images acquired through the camera. When Haar Cascade is used to detect the face region, the Dlib library is used to acquire right and left eye region images from this detected face image. These eye areas are provided as an introduction to the CNN model, which is trained with 2874 eye data (https://github.com/iparaskev/simple-blink-detector), and it is determined that the eye is closed or open. The CNN model 1500 is trained on a public eye image dataset representing open and 1374 closed-eye conditions. The left eye closed and opened state allows the mouse to click left and the right eye to close and open, and the right mouse to click. In addition, the location of the face detected with Haar Cascade is used to model mouse motion. The developed system is a real-time hybrid system with a combination of different methods and has been tested on different users. According to the test results, it was observed that the system correctly identified the eyes and the closed state of these eyes, classifying the blink event with CNN in both eyes correctly. However, it has been determined that there has been a slowness in modeling mouse movement or a poor fit to facial movement. The next study will focus on this issue and improve it by fine-tuning the system with data from many people.","PeriodicalId":11622,"journal":{"name":"El-Cezeri Fen ve Mühendislik Dergisi","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88761945","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：