Kandemir, Ali; Kılıç, Engin; Yildiz, Faruk; Türkoğlu, Halil İbrahim; Yildirim, Nalan

Plant–pollinator interactions are fundamental to reproductive success, yet remain understudied in the Turkish ecological context, particularly for endemic species. This study investigates pollinator diversity, behavior, and environmental influences in two rare Scrophularia L. species endemic to Erzincan, Türkiye: S. fatmae and S. erzincanica. Field observations conducted between 2019 and 2020 documented floral visitors, visitation frequency, and the role of floral morphology in guiding pollinator behavior. Climatic variables such as temperature, humidity, and wind were also analyzed in relation to pollinator activity. The high-altitude S. fatmae was visited exclusively by Bombus niveatus, which proved effective even under cold and windy conditions, whereas S. erzincanica attracted a more diverse community, including Halictus quadricinctus, Halictus sp., and Lasioglossum pauxillum, the efficiency of pollination was strongly linked to floral architecture; clustered flowers and staminodes enhanced pollinator guidance and cross-pollination. Statistical comparisons further highlighted differences in body size and foraging strategies between pollinator groups. Environmental conditions were shown to significantly limit pollinator activity, with high humidity and low temperatures reducing visitation. Additionally, unexpected warming events accelerated phenology in S. fatmae, indicating potential risks from climate change. Overall, this research provides novel insights into the functional ecology of endemic Scrophularia species, demonstrating how floral traits, pollinator behavior, and environmental variables interact to shape reproductive strategies. These findings contribute to biodiversity conservation efforts and underscore the importance of long-term monitoring under changing climatic conditions.

Akın, Erhan; Bayrak, Ayşe; Tastimur, Canan

In recent years, the use of machine learning models for fault detection has become commonplace. Its goal is to identify and fix problems with permanent magnet synchronous reluctance motors. This research’s primary goal is to identify and categorize errors in their early stages. We classified winding faults using machine learning approaches, such as Independent Component Analysis and Deep Learning models. We could distinguish between vibration and current signals from the engine signals by using Independent Component Analysis (ICA). We experimented on multiple architectures using the convolutional neural network (CNN) architecture we designed from scratch and the Transfer Learning technique, testing two distinct datasets we generated using the signals we got. According to experimental findings, the suggested scratch CNN model performed exceptionally well in classification, achieving 98.6% with current signals and 99.4% with vibration signals.

Akın, Erhan; Tastimur, Canan; Agrikli, Mehmet

Anormallik tespiti, verilerde beklenen davranışı göstermeyen kalıpların elde edilmesine karşılık gelmektedir. Bu uygun olmayan kalıplar, farklı uygulama etki alanlarında anormallikler, istisnalar, aykırı değerler veya kirleticiler olarak adlandırılır. Anormallik tespitinin önemi, çeşitli uygulama alanlarındaki verilerdeki anormalliklerin önemli bilgilere dönüşmesidir. İplik gerginlik sinyalleri incelendiğinde herhangi bir nedenle arıza yaptığı durumlarda bu sinyallerde anormallik durumları gözlemlenmektedir. Bu farklılıktan yola çıkarak iplik bükme makinesinde, bir arıza olup olmadığı önceden tespit edilebilir. Böylece daha büyük bir sorunun önüne geçilmiş olmaktadır. Anormallikleri tespit etmek için literatürde birçok yöntem kullanılmaktadır: Küme Tabanlı Algoritmalar, İstatistiksel Yöntem Algoritmaları vb. Bu çalışmada, bağımsız bileşen analizi kullanılarak, iplik makinelerinde bulunan iplik gerilim sinyalleri incelenmiş ve hatalı sinyal bölgeleri incelenmiştir. belirlenen. Önerilen yöntem diğer yöntemlerle karşılaştırılmış ve önerilen yöntemle en yüksek başarı oranı elde edilmiştir.

Akın, Erhan; Tastimur, Canan

Deep learning, which has seen frequent use in recent studies, has helped solve the problem of classifying objects of many different types and properties. Most studies both create and train a convolutional neural network (CNN) from scratch. The time spent training the network is thus wasted. Transfer learning (TL) is used both to prevent the loss of time due to training the dataset and to more effectively classify small datasets. This study performs classification using a dataset containing eighteen types of fastener. Our study contains three different TL scenarios. Two of them use TL with fine-tuning (FT), while the third does so with feature extraction (FE). The study compares the classification performance of eighteen different pre-trained network models (i.e., one or more versions of EfficientNet, DenseNet, InceptionResNetV2, InceptionV3, MobileNet, ResNet50, Xception, and VGGNet) in detail. When compared to other research in the literature, our first and second scenarios provide excellent implementations of TL-FT, while our third scenario, TL-FE, is hybrid and produces better results than the other two. Furthermore, our findings are superior to those of most previous studies. The models with the best results are DenseNet169 with an accuracy of 0.97 in the TL-FT1 scenario, EfficientNetB0 with 0.96 in TL-FT2, and DenseNet169 with 0.995 in TL-FE.