Publications

Selection Of The Most Suitable Parameters For Classification Of Hazelnut Fruit Using Shufflenet Deep Learning Algorithm

Published in BZT Turan, 2025

This study investigates the use of the ShuffleNet deep learning algorithm to classify hazelnut fruits into good, bad, and inner categories, achieving high accuracy with a dataset of 15,770 images. Among the optimizers tested, ShuffleNet with ADAM demonstrated the best performance, with 99.89% training accuracy, 99.96% test accuracy, and superior metrics including 0.9997 precision, 1 specificity, and 0.9998 F1-score. Read more

Comparison of the Performance of Resnet-50 and Shufflenet Deep Learning Algorithms in Classification of Hazelnut Fruit

Published in BZT Turan, 2025

This study proposes an automatic classification system for hazelnut fruit using deep learning, comparing the performance of ResNet-50 and ShuffleNet algorithms on a dataset of 15,770 hazelnut images. ShuffleNet, with its lower resource demands, is recommended for real-time analysis due to its comparable accuracy (99.94% in testing) to ResNet-50 (99.97% in testing). Read more

A New Routing Objective Function for IETF 6TiSCH Protocol

Published in IEEE, 2022

In this paper; A new parent selection function is proposed for RPL running on top of IETF 6TiSCH protocol stack, which, for each node, takes into account the number of neighbors and the traffic through these routing nodes. Our tests showed a significant improvement in terms of the total number of parent switches and packet delivery rates. Read more

Enabling space time division multiple access in IETF 6TiSCH protocol

Published in TUBITAK, 2019

Here the integration of a low-complexity directional antenna system with IETF 6TiSCH protocol is investigated with the aim of creating a 6TiSCH solution with higher spatial reuse. 6TiSCH nodes equipped with such smart directional antennas can schedule bandwidth resources not only in time and frequency domain but also in spatial (space) domain. Read more

Computer Vision Technology On Food Science

Published in Karaelmas, 2017

Computer vision is a science that extracts useful information about an object from an observed image or image sequence automatically by analyzing in theoretical and algorithmic bases. Computer vision systems are increasingly used for detection of the surface defects, contamination, and quality inspection of the foods in the food industry. Read more

A survey on semantic Web and big data technologies for social network analysis

Published in IEEE, 2016

Social Network Analysis (SNA) has become a very important and increasingly popular topic among researchers in recent years especially after emerging Semantic Web and Big Data technologies. This survey focuses on recently developed systems for SNA and summarizes the state-of-the-art technologies used by them and points out to future research directions. Read more

A Scalable Approach for Sentiment Analysis of Turkish Tweets and Linking Tweets to News

Published in IEEE, 2016

We present a framework for sentiment analysis on tweets related to news items. Given a set of tweets and news items, our framework classifies tweets as positive or negative and links them to the related news items. For the classification of tweets we use three of the most used machine learning methods, namely Naive Bayes, Complementary Naive Bayes, and Logistic Regression, and for linking tweets to news items, Natural Language Processing (NLP) techniques are used, including Zemberek NLP library for stemming and morphological analysis and then bag-of-words method for mapping. Read more