Sürdürülebilir Kalkınma Amaçları
Yazarlar
Yayınlar
- MakaleYalnız künye2026Scopus SJRQ1Efficient ensemble learning with multi-scale fusion based deep neural network for skin lesion classification
Reis, Hatice Catal; Turk, Veysel
Melanoma, a type of skin cancer, is a severe skin cancer that is critical for early diagnosis but difficult to detect. Deep learning is promising in melanoma diagnosis because it can automatically analyze visual features and perform end-to-end learning. However, achieving the optimum balance between performance and computational efficiency for the effective use of these models in clinical applications is an important research topic. In this study, three innovative methods are proposed for skin cancer detection: PADSCNet, P-DEFF, and M–DEFF. The PADSCNet is an effective neural network developed with CNN and multi-head attention techniques, designed with fusion methods, and stands out with its minimum number of parameters despite being quite deep. The P-DEFF and M–DEFF are based on ensemble learning techniques; P-DEFF was developed with a single deep learning model, and M–DEFF was developed with multiple pre-trained deep learning models. The proposed approaches were tested on the Skin Cancer: Malignant vs. Benign dataset, which was pre-processed using image enhancement techniques. According to the experimental results, PADSCNet achieved accuracy rates of 88.12 %, P-DEFF 93.75 %, and M–DEFF 95.00 %. In additional experiments conducted with the PADSCNet model, 93.12 % accuracy rates were achieved in the CNN for Melanoma Detection Dataset, and 95.00 % accuracy rates were achieved in the PH2 dataset. These findings show that the proposed methods are effective in skin cancer detection and can achieve successful results in clinical applications.
AtıfScopus4WoS3OpenAlex4
İncele - MakaleAçık Erişim2025Scopus SJRQ2Enhancing part-based gait recognition via ensemble learning and feature fusion
Yaprak, Büşranur; Gedikli, Eyüp
Gait, a behavior-based biometric feature, has gained increasing popularity in human identification, particularly in surveillance systems, due to its ability to function without physical contact or explicit consent. Traditional silhouette-based methods have demonstrated that different body parts exhibit distinct movement patterns during walking, thereby enhancing recognition accuracy. In this study, we propose an improved part-based gait recognition approach by leveraging ensemble learning on local body regions. The Gait Energy Image (GEI) is segmented into five horizontal parts, and ensemble learning is applied to the convolutional neural network (CNN) responsible for their processing. A separate MetaModel is trained for each body part to integrate the part-based features obtained from ensemble learning and synthesize the most discriminative ones. Additionally, a part-removal process is introduced to mitigate the effects of appearance-based variations by analyzing absolute differences between images with and without variations. The aggregated most distinctive features contribute to robust recognition. We evaluate our proposed approach on the CASIA-B, CASIA-C, and Outdoor-Gait datasets, and experimental results indicate that ensemble learning significantly enhances part-based gait recognition performance under various appearance variations, outperforming several state-of-the-art methods. The datasets and source code are available at https://github.com/busrakckugurlu/Enhancing-Part-based-Gait-Recognition-via-Ensemble-Learning-and-Feature-Fusion/tree/main.
AtıfScopus9WoS3OpenAlex7İncele - MakaleAçık Erişim2024Scopus SJRQ1Fusion of transformer attention and CNN features for skin cancer detection
Reis, Hatice Catal; Turk, Veysel
Melanoma is a skin cancer that spreads quickly and has serious risks. Early diagnosis is essential, but since the symptoms of skin lesions in the early stages are vague and similar, they can be difficult for specialists to detect. Therefore, machine learning-based alternative diagnostic methods can be developed in addition to existing ones. This study proposes a new deep learning model, a modified lightweight vision transformer (ViT) architecture, and a hybrid framework developed with an integrated deep learning model and an Ensemble Learning (EL) model for the early-stage diagnosis of skin lesions. The proposed deep learning model was developed based on convolution layers and transformers. The model is called multi-head attention block depthwise separable convolution network (MABSCNET). The proposed hybrid framework was developed by combining modern deep learning and EL models pre-trained with the ImageNet dataset along with the MABSCNET model. In the experimental process, the effectiveness of the proposed methods was evaluated on the ISIC 2020 dataset. Additionally, additional experiments were conducted on ISIC 2018 and a Kaggle dataset to analyze the proposed hybrid framework's classification performance. Image enhancement techniques were used in the datasets. In the ISIC 2020 dataset, the MABSCNET model reached 78.63 % accuracy, the ViT model obtained 76.50 %, and the hybrid framework reached 92.74 % accuracy. Moreover, the proposed hybrid framework achieved 100 % on the ISIC 2018 dataset and 94.24 % on the Kaggle dataset.
AtıfScopus62WoS37OpenAlex51İncele - MakaleYalnız künye2021Scopus SJRQ1A reduced variance unsupervised ensemble learning algorithm based on modern portfolio theory
Ünlü, Ramazan; Xanthopoulos, Petros
Unsupervised ensemble learning or consensus clustering has gained popularity due to its ability to combine multiple clustering solutions into a single solution that is robust and often performs better than the individual ones. There have been several approaches to consensus clustering including voting and weighted voting algorithmic schemes. Although there have been several algorithms for adjusting the weights of a consensus clustering all of them are tuned based on some performance characteristic associated with clustering accuracy. In this paper, we propose a method for incorporating weights by taking into consideration the intra algorithmic variability i.e. algorithms that provide solutions with very different performance upon multiple runs. The methodology is inspired by modern portfolio theory and more specifically from Markowitz model for asset allocation where one is trying to identify the most efficient portfolio through the solution of a convex optimization problem. Here, efficiency is defined as the minimum amount of risk for an expected return. We apply this method to different datasets and compare with respect to performance and robustness. The proposed scheme appears to achieve competitive average performance with very low variability.
AtıfScopus13WoS7OpenAlex15İncele