Publications without Fulltext
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/3
Browse
1703 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Metadata only Self-supervised object-centric learning for videos(Neural information processing systems foundation, 2023) Xie, Weidi; Department of Computer Engineering; Aydemir, Görkay; Güney, Fatma; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of EngineeringUnsupervised multi-object segmentation has shown impressive results on images by utilizing powerful semantics learned from self-supervised pretraining. An additional modality such as depth or motion is often used to facilitate the segmentation in video sequences. However, the performance improvements observed in synthetic sequences, which rely on the robustness of an additional cue, do not translate to more challenging real-world scenarios. In this paper, we propose the first fully unsupervised method for segmenting multiple objects in real-world sequences. Our object-centric learning framework spatially binds objects to slots on each frame and then relates these slots across frames. From these temporally-aware slots, the training objective is to reconstruct the middle frame in a high-level semantic feature space. We propose a masking strategy by dropping a significant portion of tokens in the feature space for efficiency and regularization. Additionally, we address over-clustering by merging slots based on similarity. Our method can successfully segment multiple instances of complex and high-variety classes in YouTube videos.Publication Metadata only Evidence of mitophagy in lens capsule epithelial cells of patients with pseudoexfoliation syndrome(Lippincott Williams and Wilkins, 2024) N/A; Aydemir, Dilara; Sönmez, Sadi Can; Kısakürek, Zeynep Büşra; Gözel, Merve; Karslıoğlu, Melisa Zişan; Güleser, Ümit Yaşar; Şahin, Afsun; Hasanreisoğlu, Murat; Koç University Research Center for Translational Medicine (KUTTAM) / Koç Üniversitesi Translasyonel Tıp Araştırma Merkezi (KUTTAM); Graduate School of Health Sciences; School of Medicine; Koç University HospitalPurpose Pseudoexfoliation Syndrome (PEX) is a condition in which aberrant fibrillary protein builds up in various components of the eye and other extraocular tissues. In this study, we aim to investigate the functionality of intracellular auto-degradative machinery -especially mitophagy- and related genes and proteins in PEX. Methods Anterior lens capsules were obtained from cataracts patients with and without PEX to constitute the PEX group and age-matched controls during microincision cataracts surgery. PINK1-mediated mitophagy markers were evaluated on the transcriptional and translational level via RT-qPCR and immunohistochemistry analysis, respectively. Results The lens epithelial cells of PEX patients were characterized by significantly higher PINK1 gene expression compared to that of the controls (p<0.05). In terms of intensity of staining of expressed proteins, PINK1 (p<0.05), Parkin (p<0.01) and LC3B (p<0.01) were all statistically higher in PEX, compared to the controls. Conclusion Altered auto-degradative response -specifically mitophagy- is a component of increased oxidative stress in PEX patients. The role of this mechanism in emerging complications warrants further research.Publication Metadata only How to detect an inadvertent pregnancy during random start stimulations(Elsevier Inc., 2024) Lawrenz, B; Fatemi, H.M.; Ata, Mustafa Barış; School of MedicineN/APublication Metadata only Implementing the analogous neural network using chaotic strange attractors(Springer Nature, 2024) Department of Electrical and Electronics Engineering; Teğin, Uğur; Department of Electrical and Electronics Engineering; College of EngineeringMachine learning studies need colossal power to process massive datasets and train neural networks to reach high accuracies, which have become gradually unsustainable. Limited by the von Neumann bottleneck, current computing architectures and methods fuel this high power consumption. Here, we present an analog computing method that harnesses chaotic nonlinear attractors to perform machine learning tasks with low power consumption. Inspired by neuromorphic computing, our model is a programmable, versatile, and generalized platform for machine learning tasks. Our mode provides exceptional performance in clustering by utilizing chaotic attractors’ nonlinear mapping and sensitivity to initial conditions. When deployed as a simple analog device, it only requires milliwatt-scale power levels while being on par with current machine learning techniques. We demonstrate low errors and high accuracies with our model for regression and classification-based learning tasks.Publication Metadata only Validating digital traces with survey data: the use case of religiosity(Association for Computing Machinery, Inc, 2024) Department of Sociology;Department of Mathematics; Yörük, Erdem; Atsızelti, Şükrü; Yardı, Melih Can; Duruşan, Fırat; Etgü, Tolga; College of Social Sciences and Humanities; Graduate School of Social Sciences and Humanities; College of SciencesThis paper tests the validity of a digital trace database (Politus) obtained from Twitter, with a recently conducted representative social survey, focusing on the use case of religiosity in Turkey. Religiosity scores in the research are extracted using supervised machine learning under the Politus project. The validation analysis depends on two steps. First, we compare the performances of two alternative tweet-To-user transformation strategies, and second, test for the impact of resampling via the MRP technique. Estimates of the Politus are examined at both aggregate and region-level. The results are intriguing for future research on measuring public opinion via social media data.Publication Metadata only Event-triggered reinforcement learning based joint resource allocation for ultra-reliable low-latency V2X communications(Institute of Electrical and Electronics Engineers Inc., 2024) Department of Electrical and Electronics Engineering; Ergen, Sinem Çöleri; Khan, Nasir; Department of Electrical and Electronics Engineering; College of Engineering; Graduate School of Sciences and EngineeringFuture 6G-enabled vehicular networks face the challenge of ensuring ultra-reliable low-latency communication (URLLC) for delivering safety-critical information in a timely manner. Existing resource allocation schemes for vehicle-toeverything (V2X) communication systems primarily rely on traditional optimization-based algorithms. However, these methods often fail to guarantee the strict reliability and latency requirements of URLLC applications in dynamic vehicular environments due to the high complexity and communication overhead of the solution methodologies. This paper proposes a novel deep reinforcement learning (DRL) based framework for the joint power and block length allocation to minimize the worst-case decoding-error probability in the finite block length (FBL) regime for a URLLC-based downlink V2X communication system. The problem is formulated as a non-convex mixed-integer nonlinear programming problem (MINLP). Initially, an algorithm grounded in optimization theory is developed based on deriving the joint convexity of the decoding error probability in the block length and transmit power variables within the region of interest. Subsequently, an efficient event-triggered DRL based algorithm is proposed to solve the joint optimization problem. Incorporating event-triggered learning into the DRL framework enables assessing whether to initiate the DRL process, thereby reducing the number of DRL process executions while maintaining reasonable reliability performance. The DRL framework consists of a twolayered structure. In the first layer, multiple deep Q-networks (DQNs) are established at the central trainer for block length optimization. The second layer involves an actor-critic network and utilizes the deep deterministic policy-gradient (DDPG)-based algorithm to optimize the power allocation. Simulation results demonstrate that the proposed event-triggered DRL scheme can achieve 95% of the performance of the joint optimization scheme while reducing the DRL executions by up to 24% for different network settings.Publication Metadata only Vilma: a zero-shot benchmark for linguıstic and temporal grounding in video-language models(International Conference on Learning Representations, ICLR, 2024) Pedrotti, Andrea; Dogan, Mustafa; Cafagna, Michele; Parcalabescu, Letitia; Calixto, Iacer; Frank, Anetteh; Gatt, Albert; Department of Electrical and Electronics Engineering; Kesen, İlker; Erdem, Aykut; Department of Electrical and Electronics Engineering; Koç Üniversitesi İş Bankası Yapay Zeka Uygulama ve Araştırma Merkezi (KUIS AI)/ Koç University İş Bank Artificial Intelligence Center (KUIS AI); Graduate School of Sciences and Engineering; College of EngineeringWith the ever-increasing popularity of pretrained Video-Language Models (VidLMs), there is a pressing need to develop robust evaluation methodologies that delve deeper into their visio-linguistic capabilities. To address this challenge, we present VILMA), a task-agnostic benchmark that places the assessment of fine-grained capabilities of these models on a firm footing. Task-based evaluations, while valuable, fail to capture the complexities and specific temporal aspects of moving images that VidLMs need to process. Through carefully curated counterfactuals, VILMA offers a controlled evaluation suite that sheds light on the true potential of these models, as well as their performance gaps compared to human-level understanding. VILMA also includes proficiency tests, which assess basic capabilities deemed essential to solving the main counterfactual tests. We show that current VidLMs' grounding abilities are no better than those of vision-language models which use static images. This is especially striking once the performance on proficiency tests is factored in. Our benchmark serves as a catalyst for future research on VidLMs, helping to highlight areas that still need to be explored.Publication Metadata only Contrast improvement through a Generative Adversarial Network (GAN) by utilizing a dataset obtained from a line-scanning confocal microscope(SPIE, 2024) Department of Physics; Kiraz, Alper; Morova, Berna; Bavili, Nima; Ketabchi, Amir Mohammad; Department of Physics; Koç University Research Center for Translational Medicine (KUTTAM) / Koç Üniversitesi Translasyonel Tıp Araştırma Merkezi (KUTTAM); College of Sciences; Graduate School of Sciences and EngineeringConfocal microscopy offers enhanced image contrast and signal-to-noise ratio compared to wide-field illumination microscopy, achieved by effectively eliminating out-of-focus background noise. In our study, we initially showcase the functionality of a line-scanning confocal microscope aligned through the utilization of a Digital Light Projector (DLP) and a rolling shutter CMOS camera. In this technique, a sequence of illumination lines is projected onto a sample using a DLP and focusing objective (50X, NA=0.55). The reflected light is imaged with the camera. Line-scanning confocal imaging is accomplished by synchronizing the illumination lines with the rolling shutter of the sensor, leading to a substantial enhancement of approximately 50% in image contrast. Subsequently, this setup is employed to create a dataset comprising 500 pairs of images of paper tissue. This dataset is employed for training a Generative Adversarial Network (cGAN). Roughly 45% contrast improvement was measured in the test images for the trained network, in comparison to the ground-truth images.Publication Metadata only Investigating the involvement of fibroblast growth factors in adipose tissue thermogenesis(Istanbul University Press, 2024) Department of Molecular Biology and Genetics; Kır, Serkan; Department of Molecular Biology and Genetics; College of ScienceObjective: Thermogenesis in white and brown adipose tissues can be induced by various stimuli, including cold exposure, β-adrenergic stimulation, and tumor growth. Fibroblast growth factor (FGF) 21 has emerged as an important mediator of thermogenesis. This study investigated the involvement of other FGF family members in the regulation of adipose tissue thermogenesis. Materials and Methods: Mice were exposed to cold and administrated a β-adrenergic agonist (CL-316,243) to stimulate a thermogenic response in adipose tissues. Stromavascular fractions isolated from white and brown adipose tissues were cultured and differentiated into primary adipocytes. These cells were treated with recombinant FGFs. Changes in the expression levels of thermogenic genes and FGFs were determined by real-time quantitative PCR. Results: Cold exposure stimulated thermogenic gene expression in the adipose tissue, which was accompanied by the upregulation of certain FGFs. Ffg9 and Fgf21 were prominently induced in white and brown adipose tissues. β-adrenergic stimulation also upregulated thermogenic genes in adipocytes. Fgf21 was identified as the main responder to the β-adrenergic pathway. The administration of recombinant FGFs to cultured primary white and brown adipocytes induced thermogenic genes, including uncoupling protein-1 (Ucp1). FGF2, FGF9, and FGF21 triggered the most significant Ucp1-inducing effects in these cells. Conclusion: FGF21 is as a prominent inducer of thermogenesis in adipose tissue and a promising therapeutic target against cardiovascular and metabolic diseases. FGF2 and FGF9 potently promote thermogenic gene expression in adipocytes. Therefore, their therapeutic targeting should be considered to enhance energy metabolism in adipose tissues.Publication Metadata only Immunotherapy for lung cancer(Turkiye Klinikleri, 2023) Karadurmuş,N.; Akyürek,N.; Aydiner,A.; Savaş,R.; Sönmez,Ö.; Şendur,M.A.N.; Oyan,B.; Yalman,D.; Yilmaz,M.U.; Yilmaz,Ü.; Göker,E.; Yumuk, Perran Fulden; School of MedicineLung cancer is one of the leading causes of cancer-related deaths in men and women. Similar to the approach with other cancer types, lung cancer staging is crucial in planning an effective treatment plan and predicting patient prognosis. Effective immunotherapies for patients with non-small cell lung cancer and non-genomic driver mutations are rapidly evolving. Moreover, anti-programmed death re-ceptor-1 (PD-1)/programmed death ligand 1 (PD-L1)-based treatments have become the first-line standard of care. Despite shortcomings, PD-L1 expression level seems currently to be a relatively reliable predictor of the clinical efficacy of treatment with anti-PD-1/PD-L1 anti-bodies. However, additional biomarkers are required to better personalize treatment options for these patients. This review aimed to increase awareness of lung cancer and immunotherapy treatment options, depending on patient and disease stage characteristics.