Research Outputs
Permanent URI for this communityhttps://hdl.handle.net/20.500.14288/2
Browse
233 results
Search Results
Publication Metadata only A computational-graph partitioning method for training memory-constrained DNNs(Elsevier, 2021) Wahib, Mohamed; Dikbayir, Doga; Belviranli, Mehmet Esat; N/A; Department of Computer Engineering; Qararyah, Fareed Mohammad; Erten, Didem Unat; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 219274Many state-of-the-art Deep Neural Networks (DNNs) have substantial memory requirements. Limited device memory becomes a bottleneck when training those models. We propose ParDNN, an automatic, generic, and non-intrusive partitioning strategy for DNNs that are represented as computational graphs. ParDNN decides a placement of DNN's underlying computational graph operations across multiple devices so that the devices' memory constraints are met and the training time is minimized. ParDNN is completely independent of the deep learning aspects of a DNN. It requires no modification neither at the model nor at the systems level implementation of its operation kernels. ParDNN partitions DNNs having billions of parameters and hundreds of thousands of operations in seconds to few minutes. Our experiments with TensorFlow on 16 GPUs demonstrate efficient training of 5 very large models while achieving superlinear scaling for both the batch size and training throughput. ParDNN either outperforms or qualitatively improves upon the related work.Publication Metadata only A containerized proof-of-concept implementation of LightChain system(Ieee, 2020) N/A; N/A; Department of Computer Engineering; N/A; Department of Computer Engineering; Department of Computer Engineering; Hassanzadeh-Nazarabadi, Yahya; Nayal, Nazir; Hamdan, Shadi Sameh; Özkasap, Öznur; Küpçü, Alptekin; PhD Student; Faculty Member; Master Student; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; N/A; N/A; 113507; 168060LightChain is the first Distributed Hash Table (DHT)-based blockchain with a logarithmic asymptotic message and memory complexity. In this demo paper, we present the software architecture of our open-source implementation of LightChain, as well as a novel deployment scenario of the entire LightChain system on a single machine aiming at results reproducibility.Publication Metadata only A critical evaluation of recent deep generative sketch models from a human-centered perspective(Institute of Electrical and Electronics Engineers Inc., 2022) Department of Computer Engineering; N/A; Sezgin, Tevfik Metin; Sabuncuoğlu, Alpay; Faculty Member; PhD Student; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; 18632; N/ADrawing a sketch is a uniquely personal process that depends on previous knowledge, experiences, and current mood. Hence, the success of deep generative sketch models depends on user expectations. Yet, the unconditional generation ability of these models does not consider human-centered metrics in the training step. To achieve this kind of training process, we frst need to understand the factors behind human perception on successful generative examples. We designed a user study where we asked twenty-one people from different disciplines to determine these factors. In this study, participants ordered four recent generative models' (Autoencoder, DCGAN, SketchRNN, and Sketchformer) output sketches from most to least recognizable. The results suggest that success in representing the distinct feature of a category is more important than other attributes such as spatial proportions or stroke counts. We shared our code, the interactive notebooks, and feld study results to accelerate further analysis in the area.Publication Metadata only A criticism on popular sketch datasets(Institute of Electrical and Electronics Engineers Inc., 2022) Department of Computer Engineering; N/A; Department of Computer Engineering; Sezgin, Tevfik Metin; Dede, Ezgi; Çelik, Birkan; Faculty Member; Master Student; Student; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; College of Engineering; 18632; N/A; N/ASketching is a tool that people can use without any training and benefit from when communicating, thinking or keeping records. The wide range of uses of sketching has made it a high-potential, promising research topic for human-computer interaction researchers. The first step for the researchers who were working for this purpose was developing sketch recognition models. However, in order to continue these studies, they needed a large amount of sketch data. Creating these datasets is a costly task. For this reason, the cheapest methods that enable to produce a large number of sketches quickly were preferred in the research. Although the required amount of sketching data has been collected thanks to these methods, it is necessary to question their quality and similarity to the sketches created during daily life interactions. In this article, a critical comparison of the most widely used sketch datasets in the literature with the sketches we create during daily life interactions is made. In addition, a new dataset which consists of sketches that are created during human-human interactions is introduced. The study showed that popular sketch datasets do not reflect the quality of sketches we create in our daily life.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 Metadata only A diversity combination model incorporating an inward bias for interaural time-level difference cue integration in sound lateralization(MDPI, 2020) N/A; N/A; Department of Computer Engineering; N/A; Mojtahedi, Sina; Erzin, Engin; Ungan, Pekcan; PhD Student; 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 Metadata only A genome-wide functional screen identifies enhancer and protective genes for amyloid beta-peptide toxicity(Multidisciplinary Digital Publishing Institute (MDPI), 2023) Picon-Pages, Pol; Bosch-Morato, Monica; Subirana, Laia; Rubio-Moscardo, Francisca; Guivernau, Biuse; Fanlo-Ucar, Hugo; Herrera-Fernandez, Victor; Vicente, Ruben; Fernandez-Fernandez, Jose M.; Garcia-Ojalvo, Jordi; Oliva, Baldomero; Posas, Francesc; de Nadal, Eulalia; Munoz, Francisco J.; N/A; N/A; N/A; Department of Computer Engineering; Department of Computer Engineering; Zeylan, Melisa Ece; Şenyüz, Simge; Gürsoy, Attila; Keskin, Özlem; PhD Student; Master Student; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; N/A; 8745; 26605Alzheimer's disease (AD) is known to be caused by amyloid beta-peptide (A beta) misfolded into beta-sheets, but this knowledge has not yet led to treatments to prevent AD. To identify novel molecular players in A beta toxicity, we carried out a genome-wide screen in Saccharomyces cerevisiae, using a library of 5154 gene knock-out strains expressing A beta(1-42). We identified 81 mammalian orthologue genes that enhance A beta(1-42) toxicity, while 157 were protective. Next, we performed interactome and text-mining studies to increase the number of genes and to identify the main cellular functions affected by A beta oligomers (oA beta). We found that the most affected cellular functions were calcium regulation, protein translation and mitochondrial activity. We focused on SURF4, a protein that regulates the store-operated calcium channel (SOCE). An in vitro analysis using human neuroblastoma cells showed that SURF4 silencing induced higher intracellular calcium levels, while its overexpression decreased calcium entry. Furthermore, SURF4 silencing produced a significant reduction in cell death when cells were challenged with oA beta(1-42), whereas SURF4 overexpression induced A beta(1-42) cytotoxicity. In summary, we identified new enhancer and protective activities for A beta toxicity and showed that SURF4 contributes to oA beta(1-42) neurotoxicity by decreasing SOCE activity.Publication Metadata only A hybrid edge-assisted machine learning approach for detecting heart disease(Institute of Electrical and Electronics Engineers (IEEE), 2022) Otoum, Safa; N/A; Department of Computer Engineering; Hayyolalam, Vahideh; Özkasap, Öznur; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 113507Various resources are provided by cloud computing over the Internet, which enable plenty of applications to be employed to offer different services for industries. However, cloud computing due to the relying on a central server/datacenter has limitations such as high latency and response time, which are so crucial in real time applications like healthcare systems. To solve this, edge computing paradigm paves the way and provides pioneering solutions by moving the computational and storage resources closer to the end users. Edge computing by facilitating the realtime applications becomes more suitable for healthcare systems. This paper uses edge technology for detecting heart disease in patients utilizing a hybrid machine learning method. Although there exist some works in this area, there is still a need for improving the prediction accuracy. To this end, this paper proposes a metaheuristic-based feature selection method using Black Widow Optimization (BWO) algorithm, and then, applies different classifiers on the selected features. The experimental results show that AdaBoost classifier along with BWO-based feature selection by 90.11 % accuracy outperforms other experimental methods, such as KNN, SVM, DT, and RF.Publication Metadata only A mobile application for symptom management in patients with breast cancer(Oncology Nursing Society, 2022) Seven M.; N/A; N/A; Department of Computer Engineering; N/A; Paşalak, Şeyma İnciser; Bağçivan, Gülcan; Özkasap, Öznur; Selçukbiricik, Fatih; PhD Student; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Health Sciences; School of Nursing; College of Engineering; School of Medicine; 125009; 261422; 113507; 202015OBJECTIVES: To evaluate the effect of a symptom management mobile application on quality of life and symptom severity in women with breast cancer undergoing chemotherapy. SAMPLE & SETTING: This parallel randomized pilot study consisted of women with breast cancer admitted to oncology outpatient clinics between November 2019 and January 2021 in Turkey. METHODS & VARIABLES: Participants (N = 40) were randomly assigned to the intervention (n = 20) or control group (n = 20). The intervention group used the mobile application in conjunction with usual care. The control group received usual care. Participants were assessed during the first, third, and last chemotherapy cycles. Data were collected using the European Organisation for Research and Treatment of Cancer Quality-of-Life Questionnaire–Core 30 and the Edmonton Symptom Assessment System. RESULTS: During the study, the decrease in general health and physical functioning and the increase in the severity of depression/sadness in the intervention group were statistically lower than in the control group. IMPLICATIONS FOR NURSING: The use of a mobile application for symptom management may promote general well-being and physical function and may alleviate symptoms of depression/sadness in women with breast cancer undergoing chemotherapy. Further studies are needed to evaluate the application in clinical settings with larger groups.