Pub Date : 2023-11-15DOI: 10.35377/saucis...1354791
A. Iorliam
The inter-class classification and source identification of IoT devices has been studied by several researchers recently due to the vast amount of available IoT devices and the huge amount of data these IoT devices generate almost every minute. As such there is every need to identify the source where the IoT data is generated and also separate an IoT device from the other using on the data they generate. This paper proposes a novel additive IoT features with the CNN system for the purpose of IoT source identification and classification. Experimental results shows that indeed the proposed method is very effective achieving an overall classification and source identification accuracy of 99.67 %. This result has a practical application to forensics purposes due to the fact that accurately identifying and classifying the source of an IoT device via the generated data can link organisations/persons to the activities they perform over the network. As such ensuring accountability and responsibility by IoT device users.
{"title":"A NOVEL ADDITIVE INTERNET OF THINGS (IoT) FEATURES AND CONVOLUTIONAL NEURAL NETWORK FOR CLASSIFICATION AND SOURCE IDENTIFICATION OF IoT DEVICES","authors":"A. Iorliam","doi":"10.35377/saucis...1354791","DOIUrl":"https://doi.org/10.35377/saucis...1354791","url":null,"abstract":"The inter-class classification and source identification of IoT devices has been studied by several researchers recently due to the vast amount of available IoT devices and the huge amount of data these IoT devices generate almost every minute. As such there is every need to identify the source where the IoT data is generated and also separate an IoT device from the other using on the data they generate. This paper proposes a novel additive IoT features with the CNN system for the purpose of IoT source identification and classification. Experimental results shows that indeed the proposed method is very effective achieving an overall classification and source identification accuracy of 99.67 %. This result has a practical application to forensics purposes due to the fact that accurately identifying and classifying the source of an IoT device via the generated data can link organisations/persons to the activities they perform over the network. As such ensuring accountability and responsibility by IoT device users.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"109 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139273976","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 : 2023-11-15DOI: 10.35377/saucis...1367326
Erkan Akkur
Cardiovascular Diseases (CVD) or heart diseases cardiovascular diseases lead the list of fatal diseases. However, the treatment of this disease involves a time-consuming process. Therefore, new approaches are being developed for the detection of such diseases. Machine learning methods are one of these new approaches. In particular, these algorithms contribute significantly to solving problems such as predictions in various fields. Given the amount of clinical data currently available in the medical field, it is useful to use these algorithms in areas such as CVD prediction. This study proposes a prediction model based on voting ensemble learning for the prediction of CVD. Furthermore, the SHAP technique is utilized to interpret the suggested prediction model including the risk factors contributing to the detection of this disease. As a result, the suggested model depicted an accuracy of 0.9534 and 0.954 AUC-ROC score for CVD prediction. Compared to similar studies in the literature, the proposed prediction model provides a good classification rate.
{"title":"Prediction of Cardiovascular Disease Based on Voting Ensemble Model and SHAP Analysis","authors":"Erkan Akkur","doi":"10.35377/saucis...1367326","DOIUrl":"https://doi.org/10.35377/saucis...1367326","url":null,"abstract":"Cardiovascular Diseases (CVD) or heart diseases cardiovascular diseases lead the list of fatal diseases. However, the treatment of this disease involves a time-consuming process. Therefore, new approaches are being developed for the detection of such diseases. Machine learning methods are one of these new approaches. In particular, these algorithms contribute significantly to solving problems such as predictions in various fields. Given the amount of clinical data currently available in the medical field, it is useful to use these algorithms in areas such as CVD prediction. This study proposes a prediction model based on voting ensemble learning for the prediction of CVD. Furthermore, the SHAP technique is utilized to interpret the suggested prediction model including the risk factors contributing to the detection of this disease. As a result, the suggested model depicted an accuracy of 0.9534 and 0.954 AUC-ROC score for CVD prediction. Compared to similar studies in the literature, the proposed prediction model provides a good classification rate.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"44 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139272400","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 : 2023-11-07DOI: 10.35377/saucis...1229353
Kenan Baysal, Deniz Taşkin
Encryption algorithms work with very large key values to provide higher security. In order to process high-capacity data in real-time, we need advanced hardware structures. Today, when compared to the previous designing methods, the required hardware solutions can be designed more easily by using Field Programmable Gate Array (FPGA). Over the past decade, FPGA speeds, capacities, and design tools have been improved. Thus, the hardware that can process data with high capacity can be designed and produced with lower costs. The purpose of this study is to create the components of a high-speed arithmetic unit that can process high-capacity data, which can also be used for FPGA encoding algorithms. In this study, multiplication algorithms were analyzed and high-capacity adders that constitute high-speed multiplier and look-up tables were designed by using Very High-Speed Integrated Circuit Hardware Description Language (VHDL). The designed circuit/multiplier was synthesized with ISE Design Suite 14.7 software. The simulation results were obtained through ModelSIM and ISIM programs.
加密算法使用非常大的密钥值来提供更高的安全性。为了实时处理大容量数据，我们需要先进的硬件结构。如今，与以前的设计方法相比，使用现场可编程门阵列（FPGA）可以更容易地设计出所需的硬件解决方案。在过去十年中，FPGA 的速度、容量和设计工具都得到了改进。因此，可以用较低的成本设计和生产能够处理大容量数据的硬件。 本研究的目的是创建可处理大容量数据的高速运算单元的组件，该组件也可用于 FPGA 编码算法。 本研究分析了乘法算法，并使用极高速集成电路硬件描述语言（VHDL）设计了构成高速乘法器和查找表的大容量加法器。使用 ISE Design Suite 14.7 软件对设计的电路/乘法器进行了综合。仿真结果通过 ModelSIM 和 ISIM 程序获得。
{"title":"High-Capacity Multiplier Design Using Look Up Table","authors":"Kenan Baysal, Deniz Taşkin","doi":"10.35377/saucis...1229353","DOIUrl":"https://doi.org/10.35377/saucis...1229353","url":null,"abstract":"Encryption algorithms work with very large key values to provide higher security. In order to process high-capacity data in real-time, we need advanced hardware structures. Today, when compared to the previous designing methods, the required hardware solutions can be designed more easily by using Field Programmable Gate Array (FPGA). Over the past decade, FPGA speeds, capacities, and design tools have been improved. Thus, the hardware that can process data with high capacity can be designed and produced with lower costs. The purpose of this study is to create the components of a high-speed arithmetic unit that can process high-capacity data, which can also be used for FPGA encoding algorithms. In this study, multiplication algorithms were analyzed and high-capacity adders that constitute high-speed multiplier and look-up tables were designed by using Very High-Speed Integrated Circuit Hardware Description Language (VHDL). The designed circuit/multiplier was synthesized with ISE Design Suite 14.7 software. The simulation results were obtained through ModelSIM and ISIM programs.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139283512","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 : 2023-08-31DOI: 10.35377/saucis...1339150
Can Yüzkollar
Image hashing is an algorithm used to represent an image with a unique value. Hashing methods, which are generally developed to search for similar examples of an image, have gained a new dimension with the use of deep network structures and better results have started to be obtained with the methods. The developed deep network models generally consider hash functions independently and do not take into account the correlation between them. In addition, most of the existing data-dependent hashing methods use pairwise/triplet similarity metrics that capture data relationships from a local perspective. In this study, the Central similarity metric, which can achieve better results, is adapted to the deep reinforcement learning method with sequential learning strategy, and successful results are obtained in learning binary hash codes. By taking into account the errors of previous hash functions in the deep reinforcement learning strategy, a new model is presented that performs interrelated and central similarity based learning.
{"title":"Sequential and Correlated Image Hash Code Generation with Deep Reinforcement Learning","authors":"Can Yüzkollar","doi":"10.35377/saucis...1339150","DOIUrl":"https://doi.org/10.35377/saucis...1339150","url":null,"abstract":"Image hashing is an algorithm used to represent an image with a unique value. Hashing methods, which are generally developed to search for similar examples of an image, have gained a new dimension with the use of deep network structures and better results have started to be obtained with the methods. The developed deep network models generally consider hash functions independently and do not take into account the correlation between them. In addition, most of the existing data-dependent hashing methods use pairwise/triplet similarity metrics that capture data relationships from a local perspective. In this study, the Central similarity metric, which can achieve better results, is adapted to the deep reinforcement learning method with sequential learning strategy, and successful results are obtained in learning binary hash codes. By taking into account the errors of previous hash functions in the deep reinforcement learning strategy, a new model is presented that performs interrelated and central similarity based learning.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132912590","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 : 2023-08-28DOI: 10.35377/saucis...1309103
Seda Yilmaz, Ihsan Hakan Selvi
The development of technology increases data traffic and data size day by day. Therefore, it has become very important to collect and interpret data. This study, it is aimed to analyze the car sales data collected using web scraping techniques by using machine learning algorithms and to create a price estimation model. The data needed for analysis was collected using Selenium and BeautifulSoup and prepared for analysis by applying various data preprocessing steps. Lasso regression and PCA analysis were used for feature selection and size reduction, and the GridSearchCV method was used for hyperparameter tuning. The results were evaluated with machine learning algorithms. Random Forest, K-Nearest Neighbor, Gradient Boost, AdaBoost, Support Vector and XGBoost regression algorithms were used in the analysis. The obtained analysis results were evaluated together with Mean Square Error (MSE), Root Mean Square Error (RMSE) and Coefficient of Determination (R-square). When the results for data set 1 were examined, the model that gave the best results was XGBoost Regression with 0.973 R2, 0.026 MSE and 0.161 RMSE values. When the results for data set 2 were examined, the model that gave the best results was K-Nearest Neighbor Regression with 0.978 R2, 0.021 MSE and 0.145 RMSE values.
{"title":"Price Prediction Using Web Scraping and Machine Learning Algorithms in the Used Car Market","authors":"Seda Yilmaz, Ihsan Hakan Selvi","doi":"10.35377/saucis...1309103","DOIUrl":"https://doi.org/10.35377/saucis...1309103","url":null,"abstract":"The development of technology increases data traffic and data size day by day. Therefore, it has become very important to collect and interpret data. This study, it is aimed to analyze the car sales data collected using web scraping techniques by using machine learning algorithms and to create a price estimation model. The data needed for analysis was collected using Selenium and BeautifulSoup and prepared for analysis by applying various data preprocessing steps. Lasso regression and PCA analysis were used for feature selection and size reduction, and the GridSearchCV method was used for hyperparameter tuning. The results were evaluated with machine learning algorithms. \u0000Random Forest, K-Nearest Neighbor, Gradient Boost, AdaBoost, Support Vector and XGBoost regression algorithms were used in the analysis. The obtained analysis results were evaluated together with Mean Square Error (MSE), Root Mean Square Error (RMSE) and Coefficient of Determination (R-square). When the results for data set 1 were examined, the model that gave the best results was XGBoost Regression with 0.973 R2, 0.026 MSE and 0.161 RMSE values. When the results for data set 2 were examined, the model that gave the best results was K-Nearest Neighbor Regression with 0.978 R2, 0.021 MSE and 0.145 RMSE values.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133094233","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 : 2023-08-10DOI: 10.35377/saucis...1309970
A. Saygılı
The COVID-19 pandemic, caused by a novel coronavirus, has become a global epidemic. Although the reverse transcription-polymerase chain reaction (RT-PCR) test is the current gold standard for detecting the virus, its low reliability has led to the use of CT and X-ray imaging in diagnostics. As limited vaccine availability necessitates rapid and accurate detection, this study applies k-means and fuzzy c-means segmentation to CT and X-ray images to classify COVID-19 cases as either diseased or healthy for CT scans and diseased, healthy, or non-COVID pneumonia for X-rays. Our research employs four open-access, widely-used datasets and is conducted in four stages: preprocessing, segmentation, feature extraction, and classification. During feature extraction, we employ the Gray-Level Co-Occurrence Matrix (GLCM), Local Binary Pattern (LBP), and Histogram of Oriented Gradients (HOG). In the classification process, our approach involves utilizing k-Nearest Neighbor (kNN), Support Vector Machines (SVM), and Extreme Learning Machines (ELM) techniques. Our research achieved a sensitivity rate exceeding 99%, which is higher than the 60-70% sensitivity rate of PCR tests. As a result, our study can serve as a decision support system that can help medical professionals make rapid and precise diagnoses with a high level of sensitivity.
{"title":"Rapid and Precise Identification of COVID-19 through Segmentation and Classification of CT and X-ray Images","authors":"A. Saygılı","doi":"10.35377/saucis...1309970","DOIUrl":"https://doi.org/10.35377/saucis...1309970","url":null,"abstract":"The COVID-19 pandemic, caused by a novel coronavirus, has become a global epidemic. Although the reverse transcription-polymerase chain reaction (RT-PCR) test is the current gold standard for detecting the virus, its low reliability has led to the use of CT and X-ray imaging in diagnostics. As limited vaccine availability necessitates rapid and accurate detection, this study applies k-means and fuzzy c-means segmentation to CT and X-ray images to classify COVID-19 cases as either diseased or healthy for CT scans and diseased, healthy, or non-COVID pneumonia for X-rays. Our research employs four open-access, widely-used datasets and is conducted in four stages: preprocessing, segmentation, feature extraction, and classification. During feature extraction, we employ the Gray-Level Co-Occurrence Matrix (GLCM), Local Binary Pattern (LBP), and Histogram of Oriented Gradients (HOG). In the classification process, our approach involves utilizing k-Nearest Neighbor (kNN), Support Vector Machines (SVM), and Extreme Learning Machines (ELM) techniques. Our research achieved a sensitivity rate exceeding 99%, which is higher than the 60-70% sensitivity rate of PCR tests. As a result, our study can serve as a decision support system that can help medical professionals make rapid and precise diagnoses with a high level of sensitivity.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122216141","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 : 2023-07-26DOI: 10.35377/saucis...1314638
Ahmet Furkan Sönmez, Serap Cakar, Feyza Cerezci, Muhammed Kotan, I. Delibasoglu, Guluzar Cit
Skin cancer has emerged as a grave health concern leading to significant mortality rates. Diagnosis of this disease traditionally relies on specialist dermatologists who interpret dermoscopy images using the ABCD rule. However, the integration of computer-aided diagnosis technologies is gaining popularity as a means to assist clinicians in accurate skin cancer diagnosis, overcoming potential challenges associated with human error. The objective of this research is to develop a robust system for the detection of skin cancer by employing machine learning algorithms for skin lesion classification and detection. The proposed system utilizes Convolutional Neural Network (CNN), a highly accurate and efficient deep learning technique well-suited for image classification tasks. By using the power of CNN, this system effectively classifies various skin diseases in dermoscopic images associated with skin cancer The MNIST HAM10000 dataset, comprising 10015 images, serves as the foundation for this study. The dataset encompasses seven distinct skin diseases falling within the realm of skin cancer. In this study, diverse transfer learning methods were used and evaluated to enhance the performance of the system. By comparing and analyzing these approaches, the study aimed to identify the most effective strategies for accurate skin disease classification in dermoscopic images.
{"title":"Deep Learning-Based Classification of Dermoscopic Images for Skin Lesions","authors":"Ahmet Furkan Sönmez, Serap Cakar, Feyza Cerezci, Muhammed Kotan, I. Delibasoglu, Guluzar Cit","doi":"10.35377/saucis...1314638","DOIUrl":"https://doi.org/10.35377/saucis...1314638","url":null,"abstract":"Skin cancer has emerged as a grave health concern leading to significant mortality rates. Diagnosis of this disease traditionally relies on specialist dermatologists who interpret dermoscopy images using the ABCD rule. However, the integration of computer-aided diagnosis technologies is gaining popularity as a means to assist clinicians in accurate skin cancer diagnosis, overcoming potential challenges associated with human error. The objective of this research is to develop a robust system for the detection of skin cancer by employing machine learning algorithms for skin lesion classification and detection. The proposed system utilizes Convolutional Neural Network (CNN), a highly accurate and efficient deep learning technique well-suited for image classification tasks. By using the power of CNN, this system effectively classifies various skin diseases in dermoscopic images associated with skin cancer The MNIST HAM10000 dataset, comprising 10015 images, serves as the foundation for this study. The dataset encompasses seven distinct skin diseases falling within the realm of skin cancer. In this study, diverse transfer learning methods were used and evaluated to enhance the performance of the system. By comparing and analyzing these approaches, the study aimed to identify the most effective strategies for accurate skin disease classification in dermoscopic images.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124621106","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 : 2023-07-17DOI: 10.35377/saucis...1311014
B. Eren, İ. Cesur
Predicting engine efficiency for environmental sustainability is crucial in the automotive industry. Accurate estimation and optimization of engine efficiency aid in vehicle design decisions, fuel efficiency enhancement, and emission reduction. Traditional methods for predicting efficiency are challenging and time-consuming, leading to the adoption of artificial intelligence techniques like artificial neural networks (ANN). Neural networks can learn from complex datasets and model intricate relationships, making them promise for accurate predictions. By analyzing engine parameters such as fuel type, air-fuel ratio, speed, load, and temperature, neural networks can identify patterns influencing emission levels. These models enable engineers to optimize efficiency and reduce harmful emissions. ANN offers advantages in predicting efficiency by learning from vast amounts of data, extracting meaningful patterns, and identifying complex relationships. Accurate predictions result in better performance, fuel economy, and reduced environmental impacts. Studies have successfully employed ANN to estimate engine emissions and performance, showcasing its reliability in predicting engine characteristics. By leveraging ANN, informed decisions can be made regarding engine design, adjustments, and optimization techniques, leading to enhanced fuel efficiency and reduced emissions. Predicting engine efficiency using ANN holds promise for achieving environmental sustainability in the automotive sector.
{"title":"Predicting Effective Efficiency of the Engine for Environmental Sustainability: A Neural Network Approach","authors":"B. Eren, İ. Cesur","doi":"10.35377/saucis...1311014","DOIUrl":"https://doi.org/10.35377/saucis...1311014","url":null,"abstract":"Predicting engine efficiency for environmental sustainability is crucial in the automotive industry. Accurate estimation and optimization of engine efficiency aid in vehicle design decisions, fuel efficiency enhancement, and emission reduction. Traditional methods for predicting efficiency are challenging and time-consuming, leading to the adoption of artificial intelligence techniques like artificial neural networks (ANN). Neural networks can learn from complex datasets and model intricate relationships, making them promise for accurate predictions. By analyzing engine parameters such as fuel type, air-fuel ratio, speed, load, and temperature, neural networks can identify patterns influencing emission levels. These models enable engineers to optimize efficiency and reduce harmful emissions. ANN offers advantages in predicting efficiency by learning from vast amounts of data, extracting meaningful patterns, and identifying complex relationships. Accurate predictions result in better performance, fuel economy, and reduced environmental impacts. Studies have successfully employed ANN to estimate engine emissions and performance, showcasing its reliability in predicting engine characteristics. By leveraging ANN, informed decisions can be made regarding engine design, adjustments, and optimization techniques, leading to enhanced fuel efficiency and reduced emissions. Predicting engine efficiency using ANN holds promise for achieving environmental sustainability in the automotive sector.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125897256","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}
With urbanization, population, and consumption on the rise, urban waste generation is steadily increasing. Consequently, waste management systems have become integral to city life, playing a critical role in resource efficiency and environmental protection. Inadequate waste management systems can adversely affect the environment, human health, and the economy. Accurate and rapid automatic waste classification poses a significant challenge in recycling. Deep learning models have achieved successful image classification in various fields recently. However, the optimal determination of many hyperparameters is crucial in these models. In this study, we developed a deep learning model that achieves the best classification performance by optimizing the depth, width, and other hyperparameters. Our six-layer Convolutional Neural Network (CNN) model with the lowest depth and width produced a successful result with an accuracy value of 89% and an F1 score of 88%. Moreover, several state-of-the-art CNN models such as VGG19, DenseNet169, ResNet101, Xception, InceptionV3, RegnetX008, RegnetY008, EfficientNetV2S trained with transfer learning and fine-tuning. Extensive experimental work has been done to find the optimal hyperparameters with GridSearch. Our most comprehensive DenseNet169 model, which we trained with fine-tuning, provided an accuracy value of 96.42% and an F1 score of 96%. These models can be successfully used in a variety of waste classification automation.
{"title":"Optimization of Several Deep CNN Models for Waste Classification","authors":"Samet Ulutürk, Mahir Kaya, Yasemin ÇETİN KAYA, Onur Altintaş, B. Turan","doi":"10.35377/saucis...1257100","DOIUrl":"https://doi.org/10.35377/saucis...1257100","url":null,"abstract":"With urbanization, population, and consumption on the rise, urban waste generation is steadily increasing. Consequently, waste management systems have become integral to city life, playing a critical role in resource efficiency and environmental protection. Inadequate waste management systems can adversely affect the environment, human health, and the economy. Accurate and rapid automatic waste classification poses a significant challenge in recycling. Deep learning models have achieved successful image classification in various fields recently. However, the optimal determination of many hyperparameters is crucial in these models. In this study, we developed a deep learning model that achieves the best classification performance by optimizing the depth, width, and other hyperparameters. Our six-layer Convolutional Neural Network (CNN) model with the lowest depth and width produced a successful result with an accuracy value of 89% and an F1 score of 88%. Moreover, several state-of-the-art CNN models such as VGG19, DenseNet169, ResNet101, Xception, InceptionV3, RegnetX008, RegnetY008, EfficientNetV2S trained with transfer learning and fine-tuning. Extensive experimental work has been done to find the optimal hyperparameters with GridSearch. Our most comprehensive DenseNet169 model, which we trained with fine-tuning, provided an accuracy value of 96.42% and an F1 score of 96%. These models can be successfully used in a variety of waste classification automation.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126520471","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 : 2023-05-27DOI: 10.35377/saucis...1273536
Murat Koca, İ. Avcı, Mohammed Abdulkareem Shakir AL-HAYANİ
The financial losses of vulnerable and insecure websites are increasing day by day. The proposed system in this research presents a strategy based on factor analysis of website categories and accurate identification of unknown information to classify safe and dangerous websites and protect users from the previous one. Probability calculations based on Naive Bayes and other powerful approaches are used throughout the website classification procedure to evaluate and train the website classification model. According to our study, the Naive Bayes approach was benign and showed successful results compared to other tests. This strategy is best optimized to solve the problem of distinguishing secure websites from unsafe ones. The vulnerability data categorization training model included in this datasheet had a better degree of precision. In this study, the best accuracy probability of 96% was achieved in Naive Bayes' NSL-KDD data set categorization
{"title":"Classification of Malicious URLs Using Naive Bayes and Genetic Algorithm","authors":"Murat Koca, İ. Avcı, Mohammed Abdulkareem Shakir AL-HAYANİ","doi":"10.35377/saucis...1273536","DOIUrl":"https://doi.org/10.35377/saucis...1273536","url":null,"abstract":"The financial losses of vulnerable and insecure websites are increasing day by day. The proposed system in this research presents a strategy based on factor analysis of website categories and accurate identification of unknown information to classify safe and dangerous websites and protect users from the previous one. Probability calculations based on Naive Bayes and other powerful approaches are used throughout the website classification procedure to evaluate and train the website classification model. According to our study, the Naive Bayes approach was benign and showed successful results compared to other tests. This strategy is best optimized to solve the problem of distinguishing secure websites from unsafe ones. The vulnerability data categorization training model included in this datasheet had a better degree of precision. In this study, the best accuracy probability of 96% was achieved in Naive Bayes' NSL-KDD data set categorization","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115646721","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：