Research Outputs
Permanent URI for this communityhttps://hdl.handle.net/20.500.14288/2
Browse
145 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Open Access 3D face recognition by projection based methods(Society of Photo-optical Instrumentation Engineers (SPIE), 2006) DutaĒ§aci, Helin; Sankur, BĆ¼lent; Department of Computer Engineering; Yemez, YĆ¼cel; Faculty Member; Department of Computer Engineering; College of EngineeringIn this paper, we investigate recognition performances of various projection-based features applied on registered 3D scans of faces. Some features are data driven, such as ICA-based features or NNMF-based features. Other features are obtained using DFT or DCT-based schemes. We apply the feature extraction techniques to three different representations of registered faces, namely, 3D point clouds, 2D depth images and 3D voxel. We consider both global and local features. Global features are extracted from the whole face data, whereas local features are computed over the blocks partitioned from 2D depth images. The block-based local features are fused both at feature level and at decision level. The resulting feature vectors are matched using Linear Discriminant Analysis. Experiments using different combinations of representation types and feature vectors are conducted on the 3D-RMA dataset.Publication Open Access 3D spatial organization and network-guided comparison of mutation profiles in Glioblastoma reveals similarities across patients(Public Library of Science, 2019) DinƧer, Cansu; Kaya, TuÄba; TunƧbaÄ, Nurcan; Department of Chemical and Biological Engineering; Department of Computer Engineering; Keskin, Ćzlem; GĆ¼rsoy, Attila; Faculty Member; Department of Chemical and Biological Engineering; Department of Computer Engineering; KoƧ University Research Center for Translational Medicine (KUTTAM) / KoƧ Ćniversitesi Translasyonel Tıp AraÅtırma Merkezi (KUTTAM); College of Engineering; 26605; 8745Glioblastoma multiforme (GBM) is the most aggressive type of brain tumor. Molecular heterogeneity is a hallmark of GBM tumors that is a barrier in developing treatment strategies. In this study, we used the nonsynonymous mutations of GBM tumors deposited in The Cancer Genome Atlas (TCGA) and applied a systems level approach based on biophysical characteristics of mutations and their organization in patient-specific subnetworks to reduce inter-patient heterogeneity and to gain potential clinically relevant insights. Approximately 10% of the mutations are located in "patches" which are defined as the set of residues spatially in close proximity that are mutated across multiple patients. Grouping mutations as 3D patches reduces the heterogeneity across patients. There are multiple patches that are relatively small in oncogenes, whereas there are a small number of very large patches in tumor suppressors. Additionally, different patches in the same protein are often located at different domains that can mediate different functions. We stratified the patients into five groups based on their potentially affected pathways, revealed from the patient-specific subnetworks. These subnetworks were constructed by integrating mutation profiles of the patients with the interactome data. Network-guided clustering showed significant association between each group and patient survival (P-value = 0.0408). Also, each group carries a set of signature 3D mutation patches that affect predominant pathways. We integrated drug sensitivity data of GBM cell lines with the mutation patches and the patient groups to analyze the therapeutic outcome of these patches. We found that Pazopanib might be effective in Group 3 by targeting CSF1R. Additionally, inhibiting ATM that is a mediator of PTEN phosphorylation may be ineffective in Group 2. We believe that from mutations to networks and eventually to clinical and therapeutic data, this study provides a novel perspective in the network-guided precision medicine.Publication Open Access A deep learning approach for data driven vocal tract area function estimation(Institute of Electrical and Electronics Engineers (IEEE), 2018) Department of Computer Engineering; Department of Electrical and Electronics Engineering; Erzin, Engin; Asadiabadi, Sasan; Faculty Member; Department of Computer Engineering; Department of Electrical and Electronics Engineering; College of Sciences; Graduate School of Sciences and Engineering; 34503; N/AIn this paper we present a data driven vocal tract area function (VTAF) estimation using Deep Neural Networks (DNN). We approach the VTAF estimation problem based on sequence to sequence learning neural networks, where regression over a sliding window is used to learn arbitrary non-linear one-to-many mapping from the input feature sequence to the target articulatory sequence. We propose two schemes for efficient estimation of the VTAF; (1) a direct estimation of the area function values and (2) an indirect estimation via predicting the vocal tract boundaries. We consider acoustic speech and phone sequence as two possible input modalities for the DNN estimators. Experimental evaluations are performed over a large data comprising acoustic and phonetic features with parallel articulatory information from the USC-TIMIT database. Our results show that the proposed direct and indirect schemes perform the VTAF estimation with mean absolute error (MAE) rates lower than 1.65 mm, where the direct estimation scheme is observed to perform better than the indirect scheme.Publication Open Access A diversity combination model incorporating an inward bias for interaural time-level difference cue integration in sound lateralization(Multidisciplinary Digital Publishing Institute (MDPI), 2020) N/A; Department of Computer Engineering; Mojtahedi, Sina; Erzin, Engin; Ungan, Pekcan; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; School of Medicine; N/A; 34503; N/AA sound source with non-zero azimuth leads to interaural time level differences (ITD and ILD). Studies on hearing system imply that these cues are encoded in different parts of the brain, but combined to produce a single lateralization percept as evidenced by experiments indicating trading between them. According to the duplex theory of sound lateralization, ITD and ILD play a more significant role in low-frequency and high-frequency stimulations, respectively. In this study, ITD and ILD, which were extracted from a generic head-related transfer functions, were imposed on a complex sound consisting of two low- and seven high-frequency tones. Two-alternative forced-choice behavioral tests were employed to assess the accuracy in identifying a change in lateralization. Based on a diversity combination model and using the error rate data obtained from the tests, the weights of the ITD and ILD cues in their integration were determined by incorporating a bias observed for inward shifts. The weights of the two cues were found to change with the azimuth of the sound source. While the ILD appears to be the optimal cue for the azimuths near the midline, the ITD and ILD weights turn to be balanced for the azimuths far from the midline.Publication Open Access A gated fusion network for dynamic saliency prediction(Institute of Electrical and Electronics Engineers (IEEE), 2022) Kocak, Aysun; Erdem, Erkut; Department of Computer Engineering; Erdem, Aykut; Faculty Member; Department of Computer Engineering; College of Engineering; 20331Predicting saliency in videos is a challenging problem due to complex modeling of interactions between spatial and temporal information, especially when ever-changing, dynamic nature of videos is considered. Recently, researchers have proposed large-scale data sets and models that take advantage of deep learning as a way to understand what is important for video saliency. These approaches, however, learn to combine spatial and temporal features in a static manner and do not adapt themselves much to the changes in the video content. In this article, we introduce the gated fusion network for dynamic saliency (GFSalNet), the first deep saliency model capable of making predictions in a dynamic way via the gated fusion mechanism. Moreover, our model also exploits spatial and channelwise attention within a multiscale architecture that further allows for highly accurate predictions. We evaluate the proposed approach on a number of data sets, and our experimental analysis demonstrates that it outperforms or is highly competitive with the state of the art. Importantly, we show that it has a good generalization ability, and moreover, exploits temporal information more effectively via its adaptive fusion scheme.Publication Open Access A task set proposal for automatic protest information collection across multiple countries(Springer, 2019) Department of Sociology; Department of Computer Engineering; HĆ¼rriyetoÄlu, Ali; YƶrĆ¼k, Erdem; Yoltar, ĆaÄrı; YĆ¼ret, Deniz; GĆ¼rel, Burak; DuruÅan, Fırat; Mutlu, Osman; Teaching Faculty; Faculty Member; Researcher; Faculty Member; Faculty Member; Researcher; Department of Sociology; Department of Computer Engineering; Graduate School of Social Sciences and Humanities; Graduate School of Sciences and Engineering; N/A; 28982; N/A; 179996; 219277; N/A; N/AWe propose a coherent set of tasks for protest information collection in the context of generalizable natural language processing. The tasks are news article classification, event sentence detection, and event extraction. Having tools for collecting event information from data produced in multiple countries enables comparative sociology and politics studies. We have annotated news articles in English from a source and a target country in order to be able to measure the performance of the tools developed using data from one country on data from a different country. Our preliminary experiments have shown that the performance of the tools developed using English texts from India drops to a level that are not usable when they are applied on English texts from China. We think our setting addresses the challenge of building generalizable NLP tools that perform well independent of the source of the text and will accelerate progress in line of developing generalizable NLP systems.Publication Open Access Adaptive reference levels in a level-crossing analog-to-digital converter(Hindawi, 2008) Guan, Karen M.; Singer, Andrew C.; Department of Computer Engineering; Kozat, SĆ¼leyman Serdar; Faculty Member; Department of Computer Engineering; College of EngineeringLevel-crossing analog-to-digital converters (LC ADCs) have been considered in the literature and have been shown to efficiently sample certain classes of signals. One important aspect of their implementation is the placement of reference levels in the converter. The levels need to be appropriately located within the input dynamic range, in order to obtain samples efficiently. In this paper, we study optimization of the performance of such an LC ADC by providing several sequential algorithms that adaptively update the ADC reference levels. The accompanying performance analysis and simulation results show that as the signal length grows, the performance of the sequential algorithms asymptotically approaches that of the best choice that could only have been chosen in hindsight within a family of possible schemes.Publication Open Access AffectON: incorporating affect into dialog generation(Institute of Electrical and Electronics Engineers (IEEE), 2020) Bucinca, Zana; Department of Computer Engineering; Yemez, YĆ¼cel; Erzin, Engin; Sezgin, Tevfik Metin; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; College of Engineering; 107907; 34503; 18632Due 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 paper, 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 Open Access AI-KU: using co-occurrence modeling for semantic similarity(Association for Computational Linguistics (ACL), 2014) Department of Computer Engineering; BaÅkaya, Osman; Department of Computer Engineering; College of EngineeringIn this paper, we describe our unsupervised method submitted to the Cross-Level Semantic Similarity task in Semeval 2014 that computes semantic similarity between two different sized text fragments. Our method models each text fragment by using the co-occurrence statistics of either occurred words or their substitutes. The co-occurrence modeling step provides dense, low-dimensional embedding for each fragment which allows us to calculate semantic similarity using various similarity metrics. Although our current model avoids the syntactic information, we achieved promising results and outperformed all baselines.Publication Open Access Alpha-beta-conspiracy search(International Computer Games Association (ICGA), 2002) McAllester, David A.; Department of Computer Engineering; YĆ¼ret, Deniz; Faculty Member; Department of Computer Engineering; College of Engineering; 179996We introduce a variant of alpha-beta search in which each node is associated with two depths rather than one. The purpose of alpha-beta search is to find strategies for each player that together establish a value for the root position. A max strategy establishes a lower bound and the min strategy establishes an upper bound. It has long been observed that forced moves should be searched more deeply. Here we make the observation that in the max strategy we are only concerned with the forcedness of max moves and in the min strategy we are only concerned with the forcedness of min moves. This leads to two measures of depth - one for each strategy - and to a two-depth variant of alpha-beta called ABC search. The two-depth approach can be formally derived from conspiracy theory and the structure of the ABC procedure is justified by two theorems relating ABC search and conspiracy numbers.