Publications without Fulltext
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/3
Browse
32 results
Search Results
Publication Metadata only Graph domain adaptation with localized graph signal representations(Elsevier GMBH, 2024) Pilavci, Yusuf Yigit; Guneyi, Eylem Tugce; Vural, Elif; Cengiz, Cemil; ; Graduate School of Sciences and Engineering;In this paper we propose a domain adaptation algorithm designed for graph domains. Given a source graph with many labeled nodes and a target graph with few or no labeled nodes, we aim to estimate the target labels by making use of the similarity between the characteristics of the variation of the label functions on the two graphs. Our assumption about the source and the target domains is that the local behavior of the label function, such as its spread and speed of variation on the graph, bears resemblance between the two graphs. We estimate the unknown target labels by solving an optimization problem where the label information is transferred from the source graph to the target graph based on the prior that the projections of the label functions onto localized graph bases be similar between the source and the target graphs. In order to efficiently capture the local variation of the label functions on the graphs, spectral graph wavelets are used as the graph bases. Experimentation on various data sets shows that the proposed method yields quite satisfactory classification accuracy compared to reference domain adaptation methods.Publication Metadata only HyperE2VID: improving event-based video reconstruction via hypernetworks(IEEE-Inst Electrical Electronics Engineers Inc, 2024) Ercan, Burak; Eker, Onur; Sağlam, Canberk; Erdem, Erkut; Department of Computer Engineering; Erdem, Aykut; Department of Computer Engineering; Koç Üniversitesi İş Bankası Enfeksiyon Hastalıkları Uygulama ve Araştırma Merkezi (EHAM) / Koç University İşbank Center for Infectious Diseases (KU-IS CID); College of Engineering;Event-based cameras are becoming increasingly popular for their ability to capture high-speed motion with low latency and high dynamic range. However, generating videos from events remains challenging due to the highly sparse and varying nature of event data. To address this, in this study, we propose HyperE2VID, a dynamic neural network architecture for event-based video reconstruction. Our approach uses hypernetworks to generate per-pixel adaptive filters guided by a context fusion module that combines information from event voxel grids and previously reconstructed intensity images. We also employ a curriculum learning strategy to train the network more robustly. Our comprehensive experimental evaluations across various benchmark datasets reveal that HyperE2VID not only surpasses current state-of-the-art methods in terms of reconstruction quality but also achieves this with fewer parameters, reduced computational requirements, and accelerated inference times.Publication Metadata only AffectON: Incorporating affect into dialog generation(IEEE-Inst Electrical Electronics Engineers Inc, 2023) Bucinca, Zana; Department of Computer Engineering; Yemez, Yücel; Erzin, Engin; Sezgin, Tevfik Metin; Department of Computer Engineering; Koç Üniversitesi İş Bankası Yapay Zeka Uygulama ve Araştırma Merkezi (KUIS AI)/ Koç University İş Bank Artificial Intelligence Center (KUIS AI); College of EngineeringDue to its expressivity, natural language is paramount for explicit and implicit affective state communication among humans. The same linguistic inquiry (e.g., How are you?) might induce responses with different affects depending on the affective state of the conversational partner(s) and the context of the conversation. Yet, most dialog systems do not consider affect as constitutive aspect of response generation. In this article, we introduce AffectON, an approach for generating affective responses during inference. For generating language in a targeted affect, our approach leverages a probabilistic language model and an affective space. AffectON is language model agnostic, since it can work with probabilities generated by any language model (e.g., sequence-to-sequence models, neural language models, n-grams). Hence, it can be employed for both affective dialog and affective language generation. We experimented with affective dialog generation and evaluated the generated text objectively and subjectively. For the subjective part of the evaluation, we designed a custom user interface for rating and provided recommendations for the design of such interfaces. The results, both subjective and objective demonstrate that our approach is successful in pulling the generated language toward the targeted affect, with little sacrifice in syntactic coherence.Publication Metadata only Large language model-based chatbots in higher education(Wiley, 2024) Eryilmaz, Merve; Yetisen, Ail K.; Ozcan, Aydogan; Department of Mechanical Engineering; Yığcı, Defne; Taşoğlu, Savaş; Department of Mechanical Engineering; School of Medicine; College of EngineeringLarge language models (LLMs) are artificial intelligence (AI) platforms capable of analyzing and mimicking natural language processing. Leveraging deep learning, LLM capabilities have been advanced significantly, giving rise to generative chatbots such as Generative Pre-trained Transformer (GPT). GPT-1 was initially released by OpenAI in 2018. ChatGPT's release in 2022 marked a global record of speed in technology uptake, attracting more than 100 million users in two months. Consequently, the utility of LLMs in fields including engineering, healthcare, and education has been explored. The potential of LLM-based chatbots in higher education has sparked significant interest and ignited debates. LLMs can offer personalized learning experiences and advance asynchronized learning, potentially revolutionizing higher education, but can also undermine academic integrity. Although concerns regarding AI-generated output accuracy, the spread of misinformation, propagation of biases, and other legal and ethical issues have not been fully addressed yet, several strategies have been implemented to mitigate these limitations. Here, the development of LLMs, properties of LLM-based chatbots, and potential applications of LLM-based chatbots in higher education are discussed. Current challenges and concerns associated with AI-based learning platforms are outlined. The potentials of LLM-based chatbot use in the context of learning experiences in higher education settings are explored. The use of large language models (LLMs) in higher education can facilitate personalized learning experiences, advance asynchronized learning, and support instructors, students, and researchers across diverse fields. The development of regulations and guidelines that address ethical and legal issues is essential to ensure safe and responsible adaptation of LLM-based tools in real-world educational settings.Publication Metadata only Experimental estimation of gap thickness and electrostatic forces between contacting surfaces under electroadhesion(Wiley, 2024) Martinsen, Orjan Grottem; Pettersen, Fred-Johan; Colgate, James Edward; Department of Mechanical Engineering; Aliabbasi, Easa; Başdoğan, Çağatay; Department of Mechanical Engineering; Graduate School of Sciences and Engineering; College of EngineeringElectroadhesion (EA) is a promising technology with potential applications in robotics, automation, space missions, textiles, tactile displays, and some other fields where efficient and versatile adhesion is required. However, a comprehensive understanding of the physics behind it is lacking due to the limited development of theoretical models and insufficient experimental data to validate them. This article proposes a new and systematic approach based on electrical impedance measurements to infer the electrostatic forces between two dielectric materials under EA. The proposed approach is applied to tactile displays, where skin and voltage-induced touchscreen impedances are measured and subtracted from the total impedance to obtain the remaining impedance to estimate the electrostatic forces between the finger and the touchscreen. This approach also marks the first instance of experimental estimation of the average air gap thickness between a human finger and a voltage-induced capacitive touchscreen. Moreover, the effect of electrode polarization impedance on EA is investigated. Precise measurements of electrical impedances confirm that electrode polarization impedance exists in parallel with the impedance of the air gap, particularly at low frequencies, giving rise to the commonly observed charge leakage phenomenon in EA. A novel and systematic approach is introduced, leveraging electrical impedance measurements to infer electrostatic forces between two dielectric materials under electroadhesion (EA). This innovative approach holds promise for diverse applications spanning robotics, automation, space missions, textiles, and tactile displays. Furthermore, this study sheds light on the physics of EA, offering valuable insights with implications for the design of electroadhesive devices.Publication Metadata only Performance measures for video object segmentation and tracking(IEEE-Inst Electrical Electronics Engineers Inc, 2004) Erdem, Çiğdem Eroğlu; Sankur, Bülent; Department of Electrical and Electronics Engineering; Tekalp, Ahmet Murat; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; 26207We propose measures to evaluate quantitatively the performance of video object segmentation and tracking methods without ground-truth (GT) segmentation maps. The proposed measures are based on spatial differences of color and motion along the boundary of the estimated video object plane and temporal differences between the color histogram of the current object plane and its predecessors. They can be used to localize (spatially and/or temporally) regions where segmentation results are good or bad; and/or they can be combined to yield a single numerical measure to indicate the goodness of the boundary segmentation and tracking results over a sequence. The validity of the proposed performance measures without GT have been demonstrated by canonical correlation analysis with another set of measures with GT on a set of sequences (where GT information is available). Experimental results are presented to evaluate the segmentation maps obtained from various sequences using different segmentation approaches.Publication Metadata only Guest editorial special issue on toward securing Internet of Connected Vehicles (IoV) from virtual vehicle hijacking(Institute of Electrical and Electronics Engineers (IEEE), 2019) Cao, Yue; Kaiwartya, Omprakash; Song, Houbing; Lloret, Jaime; Ahmad, Naveed; Department of Electrical and Electronics Engineering; Ergen, Sinem Çöleri; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; 7211N/APublication Metadata only Lossless watermarking for image authentication: a new framework and an implementation(IEEE-Inst Electrical Electronics Engineers Inc, 2006) Çelik, Mehmet Utku; Sharma, Gaurav; Department of Electrical and Electronics Engineering; Tekalp, Ahmet Murat; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; 26207We present a novel framework for lossless (invertible) authentication watermarking, which enables zero-distortion reconstruction of the un-watermarked images upon verification. As opposed to earlier. lossless authentication methods that required reconstruction of the original image prior to validation, the new framework allows validation of the watermarked images before recovery of the original image. This reduces computational requirements in situations when either the verification step fails or the zero-distortion reconstruction is not needed. For verified images, integrity of the reconstructed image is ensured by the uniqueness of the reconstruction procedure. The framework also enables public(-key) authentication without granting access to the perfect original and allows for efficient tamper localization. Effectiveness of the framework is demonstrated by implementing the framework using hierarchical image authentication along with lossless generalized-least significant bit data embedding.Publication Metadata only Using synthetic data for person tracking under adverse weather conditions(Elsevier, 2021) Kerim, Abdulrahman; Çelikcan, Ufuk; Erdem, Erkut; Department of Computer Engineering; Erdem, Aykut; Faculty Member; Department of Computer Engineering; College of Engineering; 20331Robust visual tracking plays a vital role in many areas such as autonomous cars, surveillance and robotics. Recent trackers were shown to achieve adequate results under normal tracking scenarios with clear weather conditions, standard camera setups and lighting conditions. Yet, the performance of these trackers, whether they are corre-lation filter-based or learning-based, degrade under adverse weather conditions. The lack of videos with such weather conditions, in the available visual object tracking datasets, is the prime issue behind the low perfor-mance of the learning-based tracking algorithms. In this work, we provide a new person tracking dataset of real-world sequences (PTAW172Real) captured under foggy, rainy and snowy weather conditions to assess the performance of the current trackers. We also introduce a novel person tracking dataset of synthetic sequences (PTAW217Synth) procedurally generated by our NOVA framework spanning the same weather conditions in varying severity to mitigate the problem of data scarcity. Our experimental results demonstrate that the perfor-mances of the state-of-the-art deep trackers under adverse weather conditions can be boosted when the avail-able real training sequences are complemented with our synthetically generated dataset during training. (c) 2021 Elsevier B.V. All rights reserved.Publication Metadata only Interpretable embeddings from molecular simulations using Gaussian mixture variational autoencoders(IOP Publishing Ltd, 2020) Bereau, Tristan; Rudzinski, Joseph F.; Bozkurt, Yasemin; PhD Student; Graduate School of Sciences and Engineering; N/AExtracting insight from the enormous quantity of data generated from molecular simulations requires the identification of a small number of collective variables whose corresponding low-dimensional free-energy landscape retains the essential features of the underlying system. Data-driven techniques provide a systematic route to constructing this landscape, without the need for extensive a priori intuition into the relevant driving forces. In particular, autoencoders are powerful tools for dimensionality reduction, as they naturally force an information bottleneck and, thereby, a low-dimensional embedding of the essential features. While variational autoencoders ensure continuity of the embedding by assuming a unimodal Gaussian prior, this is at odds with the multi-basin free-energy landscapes that typically arise from the identification of meaningful collective variables. In this work, we incorporate this physical intuition into the prior by employing a Gaussian mixture variational autoencoder (GMVAE), which encourages the separation of metastable states within the embedding. The GMVAE performs dimensionality reduction and clustering within a single unified framework, and is capable of identifying the inherent dimensionality of the input data, in terms of the number of Gaussians required to categorize the data. We illustrate our approach on two toy models, alanine dipeptide, and a challenging disordered peptide ensemble, demonstrating the enhanced clustering effect of the GMVAE prior compared to standard VAEs. The resulting embeddings appear to be promising representations for constructing Markov state models, highlighting the transferability of the dimensionality reduction from static equilibrium properties to dynamics.