Search

With the rapid advancement of technology, the use of artificial intelligence (AI) is increasing in various sectors such as education, health, security and defense. A critical application of AI is highway management, especially with the rise of autonomous vehicles. The focus of this study is to address the problem of deformations in highway marking lines that pose challenges for autonomous vehicles and affect traffic safety. The research involves using unmanned aerial vehicle (UAV) to create an original image dataset of highway lines. This data set will be processed with image enhancement techniques and deep learning models. The first stage involves cleaning the images from foreign matter. Deep learning models will then identify potential line deformations. These models will be developed and trained for optimum accuracy using various performance metrics. In the study, the mobilenet v3 model, trained with the images in the data set, reached an accuracy rate of 89.58%, the resnet50 v2 model 77.78% and the Convolutional Neural Network model 92.55%. The ultimate goal is to implement a real-time system to accurately detect and report differences in highway lines by combining the UAV with the computer system on the ground. This will ensure timely notification to authorities and help prevent traffic safety problems related to line deformations. This approach demonstrates the practical applications of artificial intelligence in improving road safety and autonomous vehicle navigation. [ABSTRACT FROM AUTHOR]

Cracks in buildings are a source of concern as they may indicate structural problems. Cracks in buildings are one of the major problems with concrete structures, as they affect the appearance of the building, compromise the integrity of the masonry, jeopardize building safety, and reduce the durability of the structure. Cracks in buildings can be a cause for concern and may indicate a potential structural problem that could jeopardize the safety and stability of the building. Understanding the root causes of these cracks is crucial to determining appropriate preventive measures and repair methods. In this study, crack and slope control in buildings was performed with an image processing-based measurement system developed using CNN deep learning algorithms. A dataset of 294 photographs was used for the study. The data were subjected to image processing, preprocessing, and detection with CNN. The accuracy rate is 0.9716 for the VGG-16 architecture and 0.9513 for the Inception-V3 architecture. It was concluded that there is no significant difference between the accuracy rates of the architectures. All vertical and horizontal cracks with a thickness of 2 mm and a continuity of 4 cm were detected. Thus, crack control in buildings can be done quickly and reliably, and building safety will be ensured. [ABSTRACT FROM AUTHOR]

One of the most important technological developments in the field of medicine is Computed Tomography and Magnetic Resonance imaging techniques. This technique allows the size and shape of tumor areas in body tissues to be determined, making it easier for specialists to determine the type of tumor as well as whether it is benign or malignant. Various deep learning-based computer software have been developed to accurately detect tumor areas in tissue. Due to the lack of image data used in deep learning studies, a limitation naturally arises in studies in this field. In order to eliminate the lack of image data in these studies, image augmentation can be performed using deep learning methods as well as data augmentation methods using various image processing techniques. In this study, Generative Adversarial Networks, a deep learning technique, were employed to duplicate brain MR images and generate synthetic images. After the resulting MR images were made usable by undergoing various pre-processing, similarity rates to real images were calculated using metrics such as Peak Signal-to-Noise Ratio, Structural similarity index and Mean Square Error, and by looking at these rates, realistic images were added to the data set and the data set was expanded. [ABSTRACT FROM AUTHOR]

Grasshoppers damage crops and causes millions of tons of food to be destroyed every year. The development of effective and accurate locust identification systems is critical in controlling locust species and preventing food loss. In this study, 11 different plant pest grasshopper species seen in various parts of our country and the world were classified using various convolutional neural network models. The dataset used in the study was obtained by observing the Eastern and Southeastern Anatolia regions of our country. The novelity of this study is that a dataset named GHCD11 has been created for 11 different plant pest grasshopper species in our country. In addition, VGG16, VGG19, ResNet50, DenseNet121, EfficientNet, MobileNet, which are in the Keras library and are widely used in image classification, were used for the automatic classification of 11 different grasshopper species in the study. As a result of experimental studies on the GHCD11 dataset with learning transfer, remarkable classification accuracies in the range of 95% to 99% were obtained. The study is important because it not only presents a novel dataset, but also demonstrates that automatic identification and detection of plant pest grasshopper species can be done with high accuracy using convolutional neural network architectures. [ABSTRACT FROM AUTHOR]

Driver drowsiness detection is an important issue to prevent traffic accidents. 40% of severe traffic accidents are due to drowsiness. Various methods are used for driver drowsiness detection. One of the driver drowsiness detection method is driver drowsiness detection based on the analysis of signals such as EEG and ECG. Another driver drowsiness detection method is driver drowsiness detection based on vehicle-driver interaction. The last driver drowsiness detection method used in the study is driver drowsiness detection from images. This method is more advantageous than the other two methods in terms of cost and usability because no driver intervention required. Classical image processing techniques and deep learning algorithms are used for driver drowsiness detection from images. Recent driver drowsiness detection studies are based on deep learning models. In addition, the model to be developed will need to be able to work on mobile devices in order to ensure widespread use. In the study, Convolutional Neural Networks were used for driver drowsiness detection on mobile devices. In order to increase the success rate of the model, the pre-trained model was reused with the transfer learning technique. The model developed for the training consists of 14 layers and 1,236,217 parameters. The dataset consists of two categories, open-eye and closed-eye images. The developed model achieved 95.65% accuracy, 95.86% precision, 94.32% recall and 95.17% f1 score which achieved better results than previous studies. A dataset of 2425 images was used to train the model. [ABSTRACT FROM AUTHOR]

Nowadays, trade based on logistics and sea transportation has gained importance. Considering the traffic related to this, the classification and discrimination of ship types are important in terms of transportation and storage costs, and safety. The classification of ships performing different tasks on the sea is handled in this study, and a ship image dataset has been created in order to make a high accuracy ship classification thanks to deep learning methods. It is preferred in our deep learning study in comparison to the classical machine learning method, as the features are semantically richer as the higher level, while expressing content from the dataset. It was created by the acquisition of various ship images thanks to the web scraping method. YOLOv5 and Xception deep learning models were trained to obtain the most appropriate classification performance. As a result of the experiments, an accuracy rate of approximately between 96% and 99% was achieved with both models. Scientific findings and discussion are included in our study as well. [ABSTRACT FROM AUTHOR]

Pistachio is a product with high commercial value and Turkey has a serious production and export potential in this field. The harvesting and sorting of these products is as important process as their cultivation. Classification of pistachios according to their outer shell color after harvest is one of the important processes that must be done before presenting the pistachio to market. In this study, deep learning techniques were used to sort the pistachios according to their outer color. The data set required for the extract process was obtained using an industrial experimental setup. The AlexNet structure was trained and tested with these data sets. The network structure was trained and tested for two different percentages (70%, 15%, 15% and 60%, 20%, 20%) and three different data numbers to investigate the effect of training, validation and test data in different percentages and numbers on test accuracy. The highest test accuracy was calculated as 98.44% by using of 60%, 20%, 20% percentages and 580x2, 193x2 and 193x2 data for training, validation and testing, respectively. Classification process has been performed with deep learning techniques with high accuracy. Network structures trained with the developed industrial data set are at a level to obtain high accuracy in industrial sorting machines. [ABSTRACT FROM AUTHOR]

The duration of the smart intersection system lights is determined automatically according to the nearest busy. The vehicle at the intersection with the camera is calculated by the image processing process. optimizing the signaling time in traffic signaling. It will be passed to be passed by a system that can be reached later. Also the system can be entered with this remote central management. Manually switch to roads. In this study, it is a smart intersection system used with special permission from Malatya Metropolitan Municipality transportation units. These studies and the benefits they have provided are highlighted. In addition, DARKNET's real-time object detection YOLOV3 deep learning model is used within the scope of in-vehicle realtime traffic system from data images on websites for traffic. The vehicles are placed in the targeted and future-determined database. Positive signaling with information from the designed Process-Based Intersection Management System. Agricultural bounty takes advantage of little stealing gases to be grown to take advantage of time and small items. A clean environment will be created. [ABSTRACT FROM AUTHOR]

Hand-crafted features are efficient methods for image processing, recognition, and computer vision. However, the advancements in data size and image resolution lead to inconvenience in feature extraction. Moreover, they are unstable, method-dependent, and computationally intensive due to high dimensions. Especially, big data on image datasets causes unpredictable long process. It is a definite necessity to adjust the feature extraction algorithms to computer-assisted methods for image processing. Generative representational learning algorithms have been emerging approaches with the advantages of Deep Learning. In this study, I proposed employing Deep Belief Networks (DBN) for breast cancer diagnosis on ROI images. DBN models were iterated on different image sizes to evaluate the impact of dimensionality on ROI images. The proposed DBN model has achieved performance rates of 96.32%, 96.68%, 95.93%, and 96.40% for accuracy, specificity, sensitivity, and precision, respectively. Consequently, the proposed DBN with detailed representational learning is an efficient and robust algorithm for the classification of breast cancer and healthy tissues on mammograms by the advantage of generative architectures. [ABSTRACT FROM AUTHOR]

Objective: The aim of this study is to develop a high-performance model and web-based clinical decision making method to successfully distinguish and classify COVID-19 from bacterial pneumonia, viral pneumonia and healthy controls with lung ultrasound (LUS) videos using appropriate video processing techniques and artificial intelligence (AI) methods development of the support system. Material and Methods: In this study, the open source LUS video dataset at https://github.com/jannisborn/covid19_ultrasound was used. The dataset includes 32 healthy controls, 24 COVID-19, 24 bacterial pneumonia and 12 viral pneumonia class videos. In the video processing stage, 300 image frames were taken from the videos in each class. The images were divided into 80% (960) training and 20% (240) test datasets. In the modeling phase, the convolutional neural network (CNN) method, one of the deep neural network architectures in the keras library, was used. Accuracy, sensitivity, specificity, precision, Matthews' correlation coefficient and F1 score criteria are given to evaluate the performance of the model. A web-based system has been developed that can successfully detect COVID-19 using the, with the help of the AI-based model, Python Flask Library. Results: The accuracy in the test dataset was calculated as 93.39% for healthy control, COVID-19 and viral pneumonia, and 95.07% for bacterial pneumonia. Conclusion: According to the performance criteria values obtained with the video processing-based CNN model, it can be said that the developed system gives very successful predictions in the diagnosis of COVID-19, bacterial pneumonia and viral pneumonia. [ABSTRACT FROM AUTHOR]

The skin, in which our body is completely covered, both provides the heat balance of our body and protects our body against external factors. Skin cancer, which occur as a result of the uncontrolled proliferation of cells on the skin surface, are one of the most common types of cancer in the world. Early detection of skin cancer means early treatment of the disease. With early diagnosis, patients can be cured earlier and mortality rates can be reduced. The hardest part of skin cancer diagnosis is that skin lesions are very similar to each other. Therefore, it is of great importance that skin cancer can be diagnosed and classified as benign or malignant tumor. In this study, Convolutional Neural Network were used to determine whether skin cancer is benign or malignant. Separate results are obtained with Alexnet, Resnet50, Densenet201 and Googlenet. Then the performance rates of the models used have been compared. The highest accuracy rate was achieved with the Resnet50 model with 83.49%. Then, the results were obtained with the proposed hybrid model. In the proposed hybrid model, the accuracy rate was 84.11%. This rate is an important value for early diagnosis and treatment of the disease. [ABSTRACT FROM AUTHOR]

Objective: Since COVID-19 is a worldwide pandemic, COVID-19 detection using a convolutional neural network (CNN) has been an extraordinary research technique. In the reported studies, many models that can predict COVID-19 based on deep learning methods using various medical images have been created; however, clinical decision support systems have been limited. The aim of this study is to develop a successful deep learning model based on X-ray images and a computer-assisted, fast, free and web-based diagnostic tool for accurate detection of COVID-19. Methods: In this study a 15-layer CNN model was used to detect COVID-19 using X-ray images, which outperformed many previously published CNN models in terms of classification. The model performance is evaluated according to Accuracy, Matthews Correlation Coefficient (MCC), F1 Score, Specificity, Sensitivity (Recall), Youden's Index, Precision (Positive Predictive Value: PPV), Negative Predictive Value (NPV), and Confusion Matrix (Classification matrix). In the second phase of the study, the computer-aided diagnostic tool for COVID-19 disease was developed using Python Flask library, JavaScript and Html codes. Results: The model to diagnose COVID-19 has an average accuracy of 98.68 % in the training set and 96.98 % in the testing set. Among the evaluation metrics, the minimum value is 93.4 % for MCC and Youden's index, and the maximum value is 97.8 for sensitivity and NPV. A higher sensitivity value means a lower false negative (FN) value, and a low FN value is an encouraging outcome for COVID-19 cases. This conclusion is crucial because minimizing the overlooked cases of COVID-19 (false negatives) is one of the main goals of this research. Conclusions: In this period when COVID-19 is spreading rapidly around the world, it is thought that the free and web-based COVID-19 X-Ray clinical decision support tool can be a very effective and fast diagnostic tool. The computer-aided system can assist physicians and radiologists in making clinical decisions about the disease, as well as provide support in diagnosis, follow-up, and prognosis. The developed computer-assisted diagnosis tool can be publicly accessed at http://biostatapps.inonu.edu.tr/CSYX/.. [ABSTRACT FROM AUTHOR]

Plants, which are a part of nature, are used for different reasons, such as alternative medicine as well as adding beauty to our environment. In such cases requiring expertise, the misinformation spread among the public and the use of poisonous plants considering that they are medicinal causes problems that can go up to death. In this study, it is aimed to solve these problems through a system that determines the species of leaves in leaf images using artificial intelligence techniques. Convolutional Neural Network (CNN), one of the most widely used artificial intelligence techniques, has been used recently. Its multi-layer structure, having many parameters and being able to learn features without requiring too much pre-processing is one of the reasons why it is used in many studies. In this study, the training of the convolutional neural network was carried out separately with 5 different data sets consisting of leaf images with a fixed background, and the effect of these training parameters on training was investigated. A combined data set consisting of 270 species obtained by combining these data sets was created. A general purpose leaf classification model is obtained with convolutional neural network. The results obtained by the classification process were compared with the studies in the literature. [ABSTRACT FROM AUTHOR]

Bees are one of the oldest living species in the world, having a major impact on the development of living species. The continuity of plants at the bottom of the food chain is directly related to the pollination of bees. Bees are a global insurance because of this characteristic. For this reason, it is very important to check the health status of bees. Depending on the technology developed nowadays, it is possible to control the health status of bees remotely with real-time image processing applications. In the study, feature extraction methods, which are the strengths of deep learning, were executed from two different arms and aggressive changes in images were detected. In the classification process; Instead of Softmax classifier based on probability calculation, multi-layer feedback artificial neural network (MLFB-ANN) model has been used. The success of the designed system has also been compared with the Softmax classifier. As a result of experimental studies, 93.07% success rate can be achieved with Softmax classifier for six different bee diseases on the same data set, while 95.04% success rate has been obtained with the developed system. In this study, a hybrid method based on deep learning methods was proposed for the classification of bee diseases and successful results were obtained. [ABSTRACT FROM AUTHOR]

Deep learning, one of the most popular topics of recent years, is frequently used in the biomedical field. Disease and fracture detection, data estimation, tissue and organ segmentation, and many other applications are successfully carried out with deep learning algorithms. However, while these applications are valid for human medicine, veterinary medicine is left behind. So, the deficiency in the literature about animal's X-Ray images processing has been the biggest motivation for this study. In this work, a comprehensive dataset containing dog X-Rays taken from Ankara Metropolitan Municipality Stray Animals Temporary Nursing Home, was processed with deep learning algorithms. It is aimed to determine the type of long bone. Like many other studies, Convolutional Neural Networks'(CNN) architectures are utilized in this study, too. Transfer learning was carried out with AlexNet, GoogLeNet and VGG-19 deep learning models, and the classification performance was tested with Support Vector Machines (SVM). [ABSTRACT FROM AUTHOR]

Security camera systems especially in public areas such as airports, courthouses or sports facilities etc. are used to find fugitive persons or detect suspicious behaviors manually under the monitoring of an operator. In hallway-like sections in public facilities, repeated appearances of an unknown ordinary person in a short span of time can be defined as suspicious behavior. However, the fact that multiple cameras are monitored by a single operator makes it harder to detect suspicious behaviors especially in crowded fields. Therefore, support decision systems are required to support operator. If individuals are detected on images automatically and their appearances on the camera are recorded on a database by giving them a temporary identity, suspicious behaviors can be reported to an operator as a support decision system. For this reason, two different methods are used together as a hybrid solution in the study; a MTCNN based facial detection is used on the real time security camera images that currently provide face images, and an identification method, created with facial landmarks produced with a deep learning algorithm that was trained with res-net, was used on the obtained person's face images. It has been presented that suspicious behaviors can be detected by interpreting the temporary identity information that was obtained. The success of the application was experimentally tested, and the causes of success and failures in the results were discussed. [ABSTRACT FROM AUTHOR]

Although the architectural design process is carried out with the collaboration of experts who are experienced in many different areas from the main preferences to the detailing stage, the major decisions such as plan organization, mass design etc. are taken by the architect. Computer Aided Design (CAD) programs are generally effective after the major decisions of the design are taken. For this reason, it is common for the main decisions, taken during the design process, to be changed during the analysis of the structural system. In order to prevent this, in the early stages of architectural design, earthquake system awareness and structural system design should be included as an design input; as, the failure of the structural system which did not considered well in the architectural design phase leads to unexpected revisions in the implementation project phase and thus leads to serious losses in both time and cost. The aim of this study is to create an Irregularity Control Assistant (IC Assitant) that can provide architects general information about the appropriateness of structural system decisions to earthquake regulations in the early stages of design process by using the deep learning and image processing methods. In this way, correct decisions will be made in the early stages of the design and unexpected revisions that may occur during the implementation project phase will be prevented. [ABSTRACT FROM AUTHOR]

Image processing applications in real-time systems have become a popular topic in recent years. Deep learning methods, one of the sub-branches of artificial intelligence, and image processing algorithms used in the field of object detection from images can be used together. In this way, applications are developed in many areas such as autonomous cars, autonomous unmanned aerial vehicles, assist robot technologies, assistant technologies for disabled and elderly individuals. This study aims to detect the tactile paving surfaces with deep learning methods in order to design an assistive technology system that can be used by visually impaired individuals, autonomous vehicles and robots. Contrary to traditional image processing algorithms, deep learning methods and image processing algorithms are used together in this study. The YOLO-V3 model, which is one of the best methods of object detection, is combined with the DenseNet model to create the YOLOV3-Dense model. YOLO-V2, YOLO-V3 and YOLOV3Dense models were trained on the Marmara Tactile Paving Surface (MDPY) dataset, which was created by the researchers and included 4580 images and their performances were compared with each other on the test dataset. It was observed that YOLOV3-Dense model is better than other models in detecting tactile paving surface with 89% F1-score, 92% mean average Precision(mAP) and 81% IoU values. [ABSTRACT FROM AUTHOR]

It is important for the sensitivity of ecological balance that image processing methods and techniques give better results day by day. This article deals with the classification of flower images which are the basic elements of ecological balance. Recently the use of deep learning methods on flower images has increased. In this study, the dataset available on the internet was used for the classification of flower images. The dataset consists of 4326 images. In the obtained dataset, convolutional neural network (CNN), one of the deep learning models, was used for feature extraction. The CNN architectures AlexNet, VGG-16 and VGG-19 are used in this study. The common feature of the three models is that they have a fully connected layer that give 1000 features. The features obtained from flower images were classified with support vector machines (SVM) and the results were compared. As a result of the comparison, the best classification performance was achieved with VGG-16 architecture. Obtained classification accuracy rate is 86.56%. In the next phase, 1000 features obtained from the last fully connected layer of CNN architectures were combined and 3000 feature set were created. Then, the most efficient 300 features were selected from the 3000 set of features using the Maximum Information Coefficient (MIC), Ridge regression, and Recursive Feature Elimination (RFE) feature selection methods. The most efficient features extracted by feature selection methods were reclassified by SVM method. The classification success rate increased by approximately 4.54% to 91.10%. In this study, it has been observed that using CNN architectures and feature selection methods are effective in the classification of flower images. [ABSTRACT FROM AUTHOR]

Recently, rapid developments in image processing have gained different perspective in deep learning models. Deep learning models continue to contribute to the areas of human health. Pneumonia is one of the diseases that people may encounter in any period of their lives. Pneumonia accounts for about 18% of infectious diseases. In some cases, this disease can cause death. In this study, lung x-ray images were used for the diagnosis of pneumonia. The convolutional neural network (CNN) from deep learning models was used for feature extraction in the resulting image set. The results of CNN with different classifiers were compared. As a result of the comparison, a success rate of approximately 95.8% was obtained with support vector machines (SVM). In the early diagnosis of deadly diseases such as pneumonia, deep learning models were found to be faster and more accurate. This study has shown that feature extraction with CNN provides better results in terms of performance than current methods in biomedical field. [ABSTRACT FROM AUTHOR]

Recent developments in image processing have contributed to the advancement of rapidly developing technological systems. In particular, work on image processing in the health field has further increased its popularity. Whether it is medical images or images on the other side, although the success of existing methods is ensured, the deeper learning model is a model that contributes more in terms of time and performance compared to existing methods. Highperformance results can be obtained on multi-layered images with deep learning model while the existing methods are operated on single layer images. The most important feature of deep learning is that it can process the operations on the image in a single pass and discover the parameters that need to be entered manually. Moreover, as technology companies try to deepen their learning and increase their competitive power among themselves, the methods they have built on deep learning in the scientific sense have begun to be preferred over existing methods. It is envisaged that the data sets in the biomedical field, which is one of the limited access areas of the dataset, to be obtained quickly in the recent times will contribute more to the image processing studies in this area together with the deep learning model. [ABSTRACT FROM AUTHOR]