Kurumun Atıf Alan Makalesi
Atıf Alan Yayın
Multiclass classification of dry beans using computer vision and machine learning techniques
Scopus
Toplam 346 atıf DOI
There is a wide range of genetic diversity of dry bean which is the most produced one among the edible legume crops in the world. Seed quality is definitely influential in crop production. Therefore, seed classification is essential for both marketing and production to provide the principles of sustainable agricultural systems. The primary objective of this study is to provide a method for obtaining uniform seed varieties from crop production, which is in the form of population, so the seeds are not certified as a sole variety. Thus, a computer vision system was developed to distinguish seven different registered varieties of dry beans with similar features in order to obtain uniform seed classification. For the classification model, images of 13,611 grains of 7 different registered dry beans were taken with a high-resolution camera. A user-friendly interface was designed using the MATLAB graphical user interface (GUI). Bean images obtained by computer vision system (CVS) were subjected to segmentation and feature extraction stages, and a total of 16 features; 12 dimension and 4 shape forms, were obtained from the grains. Multilayer perceptron (MLP), Support Vector Machine (SVM), k-Nearest Neighbors (kNN), Decision Tree (DT) classification models were created with 10-fold cross validation and performance metrics were compared. Overall correct classification rates have been determined as 91.73%, 93.13%, 87.92% and 92.52% for MLP, SVM, kNN and DT, respectively. The SVM classification model, which has the highest accuracy results, has classified the Barbunya, Bombay, Cali, Dermason, Horoz, Seker and Sira bean varieties with 92.36%, 100.00%, 95.03%, 94.36%, 94.92%, 94.67% and 86.84%, respectively. With these results, the demands of the producers and the customers are largely met about obtaining uniform bean varieties.
Atıf Kaynağı
Atıf Yapan Yayın
Hybrid Feature-Based Two-Stage Framework for Audio Deepfake Detection and Generative Model Attribution
Scopus
Havuzumuzda
Rapid advances in technology have made it difficult to distinguish fake voices from natural human voices, bringing serious security risks such as fraud and manipulation. While most studies in the current literature focus solely on binary classifications that question the authenticity of the voice, tracking studies that identify the source of the fake voice and issues of data imbalance are often overlooked. Since accurate source attribution is critical for forensic investigation and preventing misuse, this study proposes a two-stage hierarchical detection system to address both detection and attribution challenges. The system is evaluated on a comprehensive dataset containing real voices and fake voices generated by eight different models, including FlashSpeech, VALLE, and OpenAI. To tackle class imbalance and improve generalization, the study utilizes a 2189-dimensional hybrid feature vector derived from models like YAMNet, Wav2Vec 2.0, and Resemblyzer, combined with 17 different data augmentation techniques that enhance the model's representational power. In the comparative experiments involving nine machine learning algorithms, the SVM (RBF Kernel) model achieved the highest accuracy of 97.97% in the first stage, while Logistic Regression demonstrated the best performance in the second stage with 93.98% accuracy. Considering the averaged accuracy across both stages, SVM (RBF Kernel) exhibited the strongest overall performance with 95.51%. These results demonstrate that the proposed hierarchical approach, coupled with hybrid feature extraction and data augmentation, offers an effective solution for cybersecurity and digital forensics, particularly in preventing the misuse of synthetic voice generation and in digital content verification processes.
Atıf Yapan Makale Bilgileri
Kurumlar (1)
Selçuk Üniversitesi
Selçuklu, Turkey