Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
Search Results
Conference Paper Magnetic Levitation-Based Endothelial Cell Sorting(Institute of Electrical and Electronics Engineers Inc., 2023) Tekin, Hüseyin Cumhur; Kecili, S.; Tekin, H.C.; 01. Izmir Institute of Technology; 03.01. Department of Bioengineering; 03. Faculty of EngineeringCell sorting for rare cells is crucial for diagnostic purposes. Circulating Endothelial Cells (CECs) can be used as cardiovascular disease markers. Due to the rareness of the CECs in the blood, an accurate, easy, cost and time-effective sorting method is a need. Magnetic levitation is a promising technique for observing differences in the average height of endothelial and white blood cells which does not require any labeling. This study aims to show that the magnetic levitation principle can be used for sorting endothelial cells from the blood. By using paramagnetic medium concentrations of 10 mM and 50 mM, the average levitation height between HUVECs used as a model endothelial cells and U937 cells used as model of white blood cells was measured as 65 μm and 32 μm, respectively. Since there is a significant difference in levitation height for HUVECs and U937 cells, magnetic levitation technology exhibits promising potential for the precise sorting of endothelial cells. © 2023 IEEE.Conference Object Citation - Scopus: 2Lane Change Detection With an Ensemble of Image-Based and Video-Based Deep Learning Models(Institute of Electrical and Electronics Engineers Inc., 2023) Nalcakan, Y.; Baştanlar, Yalın; Bastanlar, Y.; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyPrediction of lane-changing maneuvers of surrounding vehicles is important for autonomous vehicles to understand the scene properly. This research proposes a vision-based technique that only requires a single in-car RGB camera. The surrounding vehicles' maneuvers are classified as right/left lane-change or no lane change conforming to most lane change detection studies in the literature. The usual practice in previous studies is feeding individual video frames into CNN to extract features and afterward using an LSTM to classify the sequence of features. Differently, in our study, we exploit the power of ensembling the prediction results of two methods. The first one uses a small feature vector containing the image coordinates of the target vehicle and classifies it with an LSTM. The second method works with a simplified scene representation video (only the target vehicle and ego-lane highlighted) and it is based on a self-supervised contrastive video representation learning scheme. Since maneuver labeling is not required in the self-supervised learning step this enables the use of a relatively large dataset. After the self-supervised training, the model is fine-tuned with a labeled dataset. Our experimental study on a well-known lane change detection dataset reveals that both of the mentioned methods by themselves achieve state-of-the-art results and ensembling them increases the classification accuracy even more. © 2023 IEEE.Conference Object Software Product Line Testing Based on Event Sequence Graphs With Feature Expressions(Institute of Electrical and Electronics Engineers Inc., 2023) Kaya, D.O.; Tuğlular, Tuğkan; Tuglular, T.; Belli, Fevzi; Belli, F.; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologySoftware Product Line testing is by its nature challenging, especially due to the exponential rise in the number of assets that need to be verified. Scalability and efficient verification, two challenges that model-based SPL testing must deal with, are discussed in this paper. An approach to automatically obtaining test suites for software product lines is proposed as a solution to these challenges. By exploiting Event Sequence Graphs with Feature Expressions, which concisely depict the Software Product Line behavior, the proposed approach automatically generates test sequences for different product configurations. The presented approach is applied to the illustrative case studies from the literature. © 2023 IEEE.