4 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 4 / 4
Yayın Neural network steering control algorithm for autonomous ground vehicles having signal time delay(SAGE Publications Ltd, 2024-03) Dinçmen, ErkinAn adaptive neural network–based steering control algorithm is proposed for yaw rate tracking of autonomous ground vehicles with in-vehicle signal time delay. The control system consists of two neural networks: the observer neural network and the controller neural network. The observer neural network adapts itself to the system dynamics during the training phase. Once trained, the observer neural network cooperates with the controller neural network, which constantly adapts itself during the control task. In this way, an adaptive and intelligent control structure is proposed. Through simulation studies, it has been shown that while a proportional-integral-derivative type steering controller fails to perform its control task in case of steering signal delay, the proposed control algorithm manages to adapt itself according to the control problem and achieves reference yaw rate tracking. The robustness of the control algorithm according to the signal delay magnitude has been demonstrated by simulation studies. A rigorous Lyapunov stability analysis of the control algorithm is also presented.Yayın Optimisation of pedestrian detection system using FPGA-CPU hybrid implementation for vehicle industry(Inderscience Enterprises Ltd., 2019) Özcan, Ahmet Remzi; Tavşanoǧlu, Ahmet VedatImproved image processing and developing technologies are rapidly expanding the application areas of image processing systems. In recent years, pedestrian detection systems have become one of the major safety technologies used in the automotive industry. This paper presents an optimised real-time pedestrian detection system using an FPGA-CPU based hybrid design. The histograms of oriented gradients (HOG) algorithm, which is extensively used for feature extraction in pedestrian detection applications, was implemented on a low-end FPGA. In the study, the original HOG descriptors are designed in low complexity without sacrificing performance. The obtained features were classified on a low-power single board computer with support vector machine (SVM). Tests with the INRIA pedestrian database show that the proposed model has high potential for use as a real-time low-cost pedestrian detection system in practice.Yayın On extensions, Lie-Poisson systems, and dissipation(Heldermann Verlag, 2022-07-06) Esen, Oğul; Özcan, Gökhan; Sütlü, SerkanLie-Poisson systems on the dual spaces of unified products are studied. Having been equipped with a twisted 2-cocycle term, the extending structure framework allows not only to study the dynamics on 2-cocycle extensions, but also to (de)couple mutually interacting Lie-Poisson systems. On the other hand, symmetric brackets; such as the double bracket, the Cartan-Killing bracket, the Casimir dissipation bracket, and the Hamilton dissipation bracket are worked out in detail. Accordingly, the collective motion of two mutually interacting irreversible dynamics, as well as the mutually interacting metriplectic flows, are obtained. The theoretical results are illustrated in three examples. As an infinite-dimensional physical model, decompositions of the BBGKY hierarchy are presented. As for the finite-dimensional examples, the coupling of two Heisenberg algebras, and the coupling of two copies of 3D dynamics are studied.Yayın Retinal disease diagnosis in OCT scans using a foundational model(Springer Science and Business Media Deutschland GmbH, 2025) Nazlı, Muhammet Serdar; Turkan, Yasemin; Tek, Faik Boray; Toslak, Devrim; Bulut, Mehmet; Arpacı, Fatih; Öcal, Mevlüt CelalThis study examines the feasibility and performance of using single OCT slices from the OCTA-500 dataset to classify DR (Diabetic Retinopathy) and AMD (Age-Related Macular Degeneration) with a pre-trained transformer-based model (RETFound). The experiments revealed the effective adaptation capability of the pretrained model to the retinal disease classification problem. We further explored the impact of using different slices from the OCT volume, assessing the sensitivity of the results to the choice of a single slice (e.g., “middle slice”) and whether analyzing both horizontal and vertical cross-sectional slices could improve outcomes. However, deep neural networks are complex systems that do not indicate directly whether they have learned and generalized the disease appearance as human experts do. The original dataset lacked disease localization annotations. Therefore, we collected new disease classification and localization annotations from independent experts for a subset of OCTA-500 images. We compared RETFound’s explainability-based localization outputs with these newly collected annotations and found that the region attributions aligned well with the expert annotations. Additionally, we assessed the agreement and variability between experts and RETFound in classifying disease conditions. The Kappa values, ranging from 0.35 to 0.69, indicated moderate agreement among experts and between the experts and the model. The transformer-based RETFound model using single or multiple OCT slices, is an efficient approach to diagnosing AMD and DR.
