Sürdürülebilir Kalkınma Amaçları

• 5
• 1

• BildiriAçık Erişim2025/r/munzur/2326
  LLM-Based Video Analytics Test Scenario Generation in Smart Cities

  Yilmazer, Merve; Karakose, Mehmet

  Rapid advances in the field of artificial intelligence have made significant contributions to the automation of software development and testing stages. Software created for use in various fields is tested with test scenarios created manually by software test experts or using test automation. Testing large-scale software with these methods complicates the testing phases because it requires increased human intervention and includes complex applications. In this study, an LLM-based scenario generation framework enhanced with prompt engineering is proposed for testing software to be used for video analysis in smart cities and smart campus areas. Thus, software test scenarios are created by strengthening large language models that are fast, flexible and have high learning ability using prompt engineering techniques. Test scenarios produced through LLM reinforced with prompt engineering techniques were evaluated with rarity and reality metrics and it was determined that more robust scenarios were produced compared to randomly generated test scenarios in the relevant field.

  AtıfScopus3·OpenAlex3

  İncele
• MakaleAçık Erişim2025Scopus SJRQ2/r/munzur/873
  A New, Robust, Adaptive, Versatile, and Scalable Abandoned Object Detection Approach Based on DeepSORT Dynamic Prompts, and Customized LLM for Smart Video Surveillance

  Yilmazer, Merve; Karakose, Mehmet

  Video cameras are one of the important elements in ensuring security in public areas. Videos inspected by expert personnel using traditional methods may have a high error rate and take a long time to complete. In this study, a new deep learning-based method is proposed for the detection of abandoned objects, such as bags, suitcases, and suitcases left unsupervised in public areas. Transfer learning-based keyframe detection was first performed to remove unnecessary and repetitive frames from the ABODA dataset. Then, human and object classes were detected using the weights of the YOLOv8l model, which has a fast and effective object detection feature. Abandoned object detection is achieved by tracking classes in consecutive frames with the DeepSORT algorithm and measuring the distance between them. In addition, the location information of the human and object classes in the frames was analyzed by a large language model supported by prompt engineering. Thus, an explanation output regarding the location, size, and estimation rate of the object and human classes was created for the authorities. It is observed that the proposed model produces promising results comparable to the state-of-the-art methods for suspicious object detection from videos with success metrics of 97.9% precision, 97.0% recall, and 97.4% f1-score.

  AtıfScopus5·WoS2·OpenAlex8

  İncele
• BildiriAçık Erişim2024/r/munzur/2173
  A New Hybrid CNN Model for Abnormal Behaviour Detection in Smart Campus

  Yilmazer, Merve; Karakose, Mehmet; Ay, Berhan Turku

  Security and monitoring systems are provided through video cameras in public places such as universities, hospitals, cinemas and theater halls. In smart campuses created by the integration of various sensors and digital technologies, there are many video cameras indoors and outdoors in the campus areas to ensure the safety of students, academics, administrators and visitors. Examining the images recorded with these video cameras in terms of security and detecting abnormal behaviours requires a long time and effort. In this study, a new hybrid convolutional neural network (CNN) model is proposed to detect abnormal behaviors occurring in smart campus areas. In the proposed method, firstly, the features of the UTI public dataset, which includes various student behaviors, are extracted with the hybrid use of InceptionV3 and MobileNetV2 deep transfer learning models. The extracted features of the images were combined and classified by converting them into a single feature vector. 6 different behavior classes, 3 of which are normal and 3 of which are abnormal, have been classified and detected with 92.7 % accuracy. Experimental results show that the proposed method for abnormal behavior detection produces more efficient results than other methods in terms of feature extraction, accuracy and computational costs.

  AtıfScopus2·OpenAlex1

  İncele
• BildiriAçık Erişim2024/r/munzur/2036
  A Deep Learning-Based Approach for Damage Detection in Cultural Heritage Images and Generating Heat Maps

  Ogdu, Cagatay Umut; Yilmazer, Merve; Karakose, Mehmet

  Cultural structures may be damaged and damaged over time due to external factors such as natural and social disasters, which may lead to the loss of national assets if cultural assets are not protected. Therefore, the protection of cultural heritage is of great importance not only for today's generations but also for future. In recent years, deep learning and image processing have made great progress and have become very effective for detecting and analyzing patterns. These techniques can also be used to solve complex problems such as damage detection of structures in the field of cultural heritage. Deep learning methods can be used to determine the current status of structures and detect possible damage by working on images obtained from different angles of structures, while also reducing human errors. In this study, as an important step for the protection of cultural heritage, a detection method was developed using deep learning models on damaged and intact cultural heritage building images. The data set used in the study consists of damaged and intact cultural heritage building images. An attempt was made to determine the model that gave the best results by using pre-trained models with the Transfer Learning method. Heat maps were created using the Grad-CAM method to identify damaged areas on the trained models, thus making it possible to more clearly identify the damaged areas in the image. This method can play an important role in preserving cultural heritage. It can be used to detect damaged areas and direct them to repair.

  AtıfScopus3·OpenAlex4

  İncele
• BildiriAçık Erişim2024/r/munzur/1982
  A New Approach to Detecting Free Parking Spaces Based on YOLOv6 and Keyframe Detection with Video Analytics

  Yilmazer, Merve; Karakose, Mehmet; Tanberk, Senem; Arslan, Samed

  With urbanization and population growth, automobile use has also increased. As a result of this, there is a need to expand parking management and inspection systems to ensure safe and efficient use of parking areas. A new deep learning-based method has been proposed as an alternative to traditional systems to control free spaces in parking areas monitored by CCTV security cameras. A large amount of video data needs to be processed for parking areas recorded with video cameras 24 hours a day, 365 days a year. Repeating frames in videos cause overlearning in deep learning models. It also increases memory and computation cost. For this reason, keyframe detection based on sampling was first performed on the sample video of the Dragon Lake Parking (DLP) dataset and a summary of the dataset was obtained. Then, empty parking areas were detected by YOLOv6 deep neural network. It has been observed that the model can detect empty parking areas at a rate of 96.6% mAP.

  • 
  AtıfScopus7·OpenAlex5

  İncele
• MakaleYayıncıda açık erişim2024Scopus SJRQ3/r/munzur/1911
  Fastener and rail surface defects detection with deep learning techniques

  Yilmazer, Merve; Karakose, Mehmet

  The railways, which are frequently used by countries for both passenger and freight transportation, should be checked periodically. Controls made with classical methods are slow and there are often overlooked faults. This work suggests a novel deep learning-based technique for identifying fastener and railway track surface defects. Within the scope of the proposed method, firstly, the railroad track was observed using an autonomous drone. Shaky images in the recorded video were removed with a video stabilization algorithm. Frames were created and labeled from the video, and rail and fastener regions were detected using the Faster R-CNN deep neural network. Fault detection was performed through ResNet101v2-based classification using different datasets for identifying surface detects in rails and different datasets for the detection of fasteners. The proposed method was experimentally shown to have a 98% accuracy rate for detecting rail surface flaws and a 95% accuracy rate for detecting fastener flaws. A user interface was developed to display the identified faulty images on computers, tablets, and mobile phones via a mobile application. The system, which was previously proposed in a different study, was retrained by going through the video stabilization step, thus improving the fault detection rate, and the method was also included in the user interface module. This study contributes to the processing of ever-increasing video data with deep learning-based methods. It is also anticipated that it will benefit researchers working in the field of railway non-contact fault detection.

  • 
  AtıfScopus6·OpenAlex6

  İncele
• BildiriAçık Erişim2023/r/munzur/2413
  Chat with ChatGPT: Access to cultural heritage with ChatGPT

  Yilmazer, Merve; Karakose, Mehmet

  Cultural heritage, in the most general sense, refers to the historical accumulations from the past to the present. Digital systems are being integrated as an alternative to physical interventions for the management, maintenance and supervision of cultural heritage sites. For these purposes, advanced intelligent systems such as machine learning and deep learning are generally used. In this study, the competence of ChatGPT, an artificial intelligence robot developed by OpenAI with a high learning rate, in the field of cultural heritage is investigated. Questions such as cultural heritage, digital cultural heritage, protection of cultural heritage, etc. were asked to ChatGPT, and the timeliness and adequacy of the answers produced in response to the questions were evaluated. In addition, a comparison of experimental studies in the literature for the preservation and cultural heritage digitalization sites is also included in this study.

  AtıfScopus6·OpenAlex4

  İncele
• BildiriAçık Erişim2023/r/munzur/2349
  Yolov5 Based Fault Detection Approach in Railway Components

  Yilmazer, Merve; Karakose, Mehmet

  For safe transportation on the railway, the faults occurring in its components must be detected and repaired. Recently, fault detection methods have been developed on railway visual data using methods such as image processing, machine learning and deep learning. Especially since deep learning-based algorithms have a self-learning structure, the data used in model training and testing significantly affect the performance of the model. In the proposed method within the scope of this study, railway visual data were obtained using autonomous drone. YOLOv5 deep neural network is trained to detect faults that may occur in various components such as rail, fastener, sleeper and ballast in the railway. In order to increase the efficiency of the model, images obtained under different lighting conditions were included in the data set. In addition, by using the OpenCV library, the video stabilization process and the vibrations that occur during data acquisition in the video are eliminated. Thus, with the proposed method, it has been shown that the errors due to many components in the railway can be detected with a mAP rate of 94.5%.

  • 
  AtıfScopus5·OpenAlex3

  İncele
• MakaleAçık Erişim2022/r/munzur/5834
  Mask R-CNN Derin Sinir Ağı ile Demiryolu Hattı Bileşenlerinde Çoklu Hata Tespiti

  Karaköse, Mehmet; Aydin, Ilhan; Akın, Erhan; Yilmazer, Merve

  Demiryolu birçok yolcunun aynı anda seyahat edebilmesine olanak tanıyan aynı zamanda yük taşımacılığında da sıklıkla kullanılan bir ulaşım çeşididir. Ulaşımda kazalar ve aksamalar meydana gelmemesi için hattın periyodik olarak kontrolünün sağlanması ve hatalı bileşenlerin belirlenerek onarılması gerekmektedir. Raylı ulaşım sistemlerinin güvenliğinin sağlanması için yapılan manuel denetimlere alternatif olarak, son zamanlarda görüntü işleme algoritmaları ve derin öğrenme algoritmaları kullanılarak temassız, hızlı ve güvenilir sonuçlar veren hata tespit yöntemleri geliştirilmiştir. Bu çalışmada sağlıklı olan traversler ve travers üzerinde meydana gelen çeşitli hataların tespit edilmesine yönelik Mask R-CNN derin sinir ağı mimarisi kullanılarak yeni bir yöntem önerildi. Üç farklı hata türü ve sağlıklı travers olmak üzere toplamda dört farklı sınıf etiketi ile etiketlenen gerçek demiryolu görüntüleri kullanılarak model eğitimi ve eğitilen modelin test edilmesi sağlandı. Değerlendirme metrikleri hesaplanarak modelin başarı performansı ölçüldü. Sağlıklı ve hatalı olan traversleri belirlemede modelin doğruluğu %95 olarak belirlendi.

  • 
  AtıfOpenAlex4·TR Dizin1

  İncele
• MakaleAçık Erişim2022Scopus SJRQ3/r/munzur/3023
  A New Rail Surface Defects Detection Approach Using 3D Laser Cameras Based on ResNet50

  Santur, Yunus; Yilmazer, Merve; Karakose, Mehmet; Akin, Erhan

  Rail transportation systems, which are used as one of the most common means of transportation worldwide, should be regularly inspected to prevent accidents that may occur. The rail condition monitoring can be performed in high accuracy and real time using computer vision, deep learning algorithms today. In this study, a new deep learning based approach using 3D laser cameras for rail inspection is presented. In the proposed approach, two 3D laser cameras placed on a real train, seeing the rail line from the left and right surfaces were used. These data consisting of sensitive distance value constitute the input data of the ResNet50 transfer learning model. The training was carried out on Nvidia Cuda supported graphics processing units using ResNet50 Convolutional Neural Network. During the test phase, the operation speed and accuracy rate of the method was measured by repeating the process on real-time rail profiles. The accuracy rate was calculated as 94%. As a result a new approach is presented based on deep learning using 3D laser cameras for rail inspection is presented.

  • 
  AtıfScopus12·WoS8·OpenAlex9

  İncele