Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
9 results
Search Results
Publication Metadata only Assistive Visual Tool: Enhancing Safe Navigation with Video Remapping in AR Headsets(SPRINGER INTERNATIONAL PUBLISHING AG, 2025) Sadeghzadeh, Arezoo; Islam, Md Baharul; Uddin, Md Nur; Aydin, Tarkan; DelBue, A; Canton, C; Pont-Tuset, J; Tommasi, T; Bahcesehir University; State University System of Florida; Florida Gulf Coast UniversityVisual Field Loss (VFL) is characterized by blind spots or scotomas that poses detrimental impact on fundamental movement activities of individuals. Addressing the challenges (e.g., low video quality, content loss, high levels of contradiction, and limited mobility assessment) faced by existing Extended Reality (XR) systems as vision aids, we introduce a groundbreaking method that enriches the real-time navigation using Augmented Reality (AR) glasses. Our novel vision aid employs advanced video processing techniques to enhance visual perception in individuals with moderate to severe VFL, bridging the gap to healthy vision. A unique optimal video remapping function, tailored to our selected AR glasses characteristics, dynamically maps live video content to the largest intact region of the Visual Field (VF) map. Our method preserves video quality, minimizing blurriness and distortion. Through a comprehensive empirical user study involving 29 subjects with artificially induced scotomas, statistical analyses of object counting and multi-tasking walking track tests demonstrate the promising performance of our method in enhancing visual awareness and navigation capability in real-time.Publication Metadata only Machine Vision-Based Expert System for Automated Skin Cancer Detection(SPRINGER INTERNATIONAL PUBLISHING AG, 2022) Junayed, Masum Shah; Jeny, Afsana Ahsan; Rada, Lavdie; Islam, Md Baharul; BritoLoeza, C; MartinGonzalez, A; CastanedaZeman, V; Safi, A; Bahcesehir University; Daffodil International UniversitySkin cancer is the most frequently occurring kind of cancer, accounting for about one-third of all cases. Automatic early detection without expert intervention for a visual inspection would be of great help for society. The image processing and machine learning methods have significantly contributed to medical and biomedical research, resulting in fast and exact inspection in different problems. One of such problems is accurate cancer detection and classification. In this study, we introduce an expert system based on image processing and machine learning for skin cancer detection and classification. The proposed approach consists of three significant steps: pre-processing, feature extraction, and classification. The pre-processing step uses the grayscale conversion, Gaussian filter, segmentation, and morphological operation to represent skin lesion images better. We employ two feature extractors, i.e., the ABCD scoring method (asymmetry, border, color, diameter) and gray level co-occurrence matrix (GLCM), to extract cancer-affected areas. Finally, five different machine learning classifiers such as logistic regression (LR), decision tree (DT), k-nearest neighbors (KNN), support vector machine (SVM), and random forest (RF) used to detect and classify skin cancer. Experimental results show that random forest exceeds all other classifiers achieving an accuracy of 97.62% and 0.97 Area Under Curve (AUC), which is state-of-the-art on the experimented open-source dataset PH2.Publication Metadata only Neural Architecture Search Using Differential Evolution in MAML Framework for Few-Shot Classification Problems(SPRINGER INTERNATIONAL PUBLISHING AG, 2023) Gulcu, Ayla; Kus, Zeki; DiGaspero, L; Festa, P; Nakib, A; Pavone, M; Bahcesehir UniversityModel-Agnostic Meta-Learning (MAML) algorithm is an optimization based meta-learning algorithm which aims to find a good initial state of the neural network that can then be adapted to any novel task using a few optimization steps. In this study, we take MAML with a simple four-block convolution architecture as our baseline, and try to improve its few-shot classification performance by using an architecture generated automatically through the neural architecture search process. We use differential evolution algorithm as the search strategy for searching over cells within a predefined search space. We have performed our experiments using two well-known few-shot classification datasets, mini-ImageNet and FC100 dataset. For each of those datasets, the performance of the original MAML is compared to the performance of our MAML-NAS model under both 1-shot 5-way and 5-shot 5-way settings. The results reveal that MAML-NAS results in better or at least comparable accuracy values for both of the datasets in all settings. More importantly, this performance is achieved by much simpler architectures, that is architectures requiring less floating-point operations.Publication Metadata only Toward Automatic Water Pollution Analysis: A Machine Learning Approach for Water-Quality Monitoring Through Pattern Classification of Water Crystallization(SPRINGER INTERNATIONAL PUBLISHING AG, 2022) Rada, Lavdie; Tanriverdi, Yusuf Baran; Kara, Omer Ekmel; Hemond, Elizabeth M.; Tezel, Ulas; BritoLoeza, C; MartinGonzalez, A; CastanedaZeman, V; Safi, A; Bahcesehir University; Bogazici UniversityHeavy metal contamination in drinking water and water resources is one of the problems generated by increasing water demand and growing industrialization. Heavy metals can be toxic to humans and other living beings when their intake surpasses a certain threshold. Generally, heavy metal contamination analysis of water resources requires qualified experts with specialized equipment. In this paper, we introduce a method for citizen-based water-quality monitoring through simple pattern classification of water crystallization using a smartphone and portable microscope. This work is a first step toward the development of a Water Expert System smartphone application that will provide the ability to analyze water resource contamination remotely by sending images to the database and receiving an automatic analysis of the sample via machine learning software. In this study, we show the ability of the method to detect Fe 2 mg/1 L, 5 mg/L,10 mg/L polluted distilled water compared with other heavy metals (Al, Pb) pollution. The experimental results show that the classification used method has an accuracy greater than 90%.Publication Metadata only Advancing WebRTC QoE Assessment with Machine Learning in Real-World Wi-Fi Scenarios(IEEE, 2024) Argin, Berke; Demir, Mehmet Ozgun; Salik, Elif Dilek; Onalan, Aysun Gurur; Batum, Oyku Han; Soyak, Ece Gelal; Bahcesehir UniversityVideo conferencing applications play a key role in enabling use cases like remote working, education, and potentially the metaverse. From the perspective of Internet service providers, predicting the end user's Quality of Experience (QoE) in such applications is critical in allocating the right resources to ensure consistently high QoE. This work addresses the estimation of user QoE from link-layer performance metrics such as transferred packets, queue size, signal strength, and channel occupancy for WebRTC-supported applications. Our study entails collecting a data set capturing various Wi-Fi scenarios in practical environments and training machine learning models on this data to estimate the perceived QoE. Our findings demonstrate improvement in prediction accuracy compared to earlier models and QoE representations, furthermore, we also investigate the explainability of the models with the help of SHAP values.Publication Metadata only Strategies for the Utilization of Virtual Reality Technologies in the First Year of Architectural Education(SPRINGER INTERNATIONAL PUBLISHING AG, 2021) Ceylan, Salih; Lane, HC; Zvacek, S; Uhomoibhi, J; Bahcesehir UniversityThe first year of architectural education is a crucial period in which students get introduced to the ambiguous nature of architecture and build the foundations of their professional career. It has a dense structure, theoretical and technical courses gathered around the design studio which is the core of architectural education. Its dynamic and flexible nature makes architectural education open for innovations and the implementation of emerging technologies. Accordingly, digital technologies that have a strong relationship with the profession of architecture, also have firm effects on architectural education. Even though it is not common among architectural education institutions around the globe, emerging digital technologies may have a role in the first year of architectural curriculum. One of the digital technologies that can be utilized in the first year of architectural education in virtual reality technologies as they provide an additional medium for experiencing architectural products and alternative methods for designing them. This paper investigates the necessity and potential benefits ofVRtechnologies in the first year of architectural education. Based on a case study conducted among freshman students, the VR technologies prove themselves useful. The paper also presents various methods and strategies, and their potential benefits for the implementation of VR technologies into the different domains of first year architectural curriculum.Publication Metadata only Picture Fuzzy Cost-Effectiveness Analysis in Health Care(SPRINGER INTERNATIONAL PUBLISHING AG, 2024) Haktanir, Elif; Kahraman, C; Onar, SC; Cebi, S; Oztaysi, B; Tolga, AC; Sari, IU; Bahcesehir UniversityCost-effectiveness analysis is a way of making a budget in order to minimize the cost and maximize the service outcome, by making the best and most effective choice among the alternative ways to achieve the planned goals. This method, which is generally used in the field of health care, is handled with picture fuzzy sets in this study, and the uncertainties of the decision makers are reflected more realistically and consistently. The method developed with the proposed new equations can be used in many different areas where decisions need to be made under cost constraints. The developed method is illustrated step by step with the application in the field of SMA disease.Publication Metadata only Towards Stereoscopic Video Deblurring Using Deep Convolutional Networks(SPRINGER INTERNATIONAL PUBLISHING AG, 2021) Imani, Hassan; Islam, Md Baharul; Bebis, G; Athitsos, V; Yan, T; Lau, M; Li, F; Shi, C; Yuan, X; Mousas, C; Bruder, G; Bahcesehir UniversityThese days stereoscopic cameras are commonly used in daily life, such as the new smartphones and emerging technologies. The quality of the stereo video can be affected by various factors (e.g., blur artifact due to camera/object motion). For solving this issue, several methods are proposed for monocular deblurring, and there are some limited proposed works for stereo content deblurring. This paper presents a novel stereoscopic video deblurring model considering the consecutive left and right video frames. To compensate for the motion in stereoscopic video, we feed consecutive frames from the previous and next frames to the 3D CNN networks, which can help for further deblurring. Also, our proposed model uses the stereoscopic other view information to help for deblurring. Specifically, to deblur the stereo frames, our model takes the left and right stereoscopic frames and some neighboring left and right frames as the inputs. Then, after compensation for the transformation between consecutive frames, a 3D Convolutional Neural Network (CNN) is applied to the left and right batches of frames to extract their features. This model consists of the modified 3D U-Net networks. To aggregate the left and right features, the Parallax Attention Module (PAM) is modified to fuse the left and right features and create the output deblurred frames. The experimental results on the recently proposed Stereo Blur dataset show that the proposed method can effectively deblur the blurry stereoscopic videos.Publication Metadata only PoseTED: A Novel Regression-Based Technique for Recognizing Multiple Pose Instances(SPRINGER INTERNATIONAL PUBLISHING AG, 2021) Jeny, Afsana Ahsan; Junayed, Masum Shah; Islam, Md Baharul; Bebis, G; Athitsos, V; Yan, T; Lau, M; Li, F; Shi, C; Yuan, X; Mousas, C; Bruder, G; Bahcesehir UniversityPose estimation for multiple people can be viewed as a hierarchical set predicting challenge. Algorithms are needed to classify all persons according to their physical components appropriately. Pose estimation methods are divided into two categories: (1) heatmap-based, (2) regression-based. Heatmap-based techniques are susceptible to various heuristic designs and are not end-to-end trainable, while regression-based methods involve fewer intermediary non-differentiable stages. This paper presents a novel regression-based multi-instance human pose recognition network called PoseTED. It utilizes the well-known object detector YOLOv4 for person detection, and the spatial transformer network (STN) used as a cropping filter. After that, we used a CNN-based backbone that extracts deep features and positional encoding with an encoder-decoder transformer applied for keypoint detection, solving the heuristic design problem before regression-based techniques and increasing overall performance. A prediction-based feed-forward network (FFN) is used to predict several key locations' posture as a group and display the body components as an output. Two available public datasets are tested in this experiment. Experimental results are shown on the COCO andMPII datasets, with an average precision (AP) of 73.7% on the COCO val. dataset, 72.7% on the COCO test dev. dataset, and 89.7% on the MPII datasets, respectively. These results are comparable to the state-of-the-art methods.