Publications without Fulltext
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/3
Browse
36 results
Search Results
Publication Metadata only A kernel-based multilayer perceptron framework to identify pathways related to cancer stages(Springer International Publishing Ag, 2023) Mokhtaridoost, Milad; Department of Industrial Engineering; Soleimanpoor, Marzieh; Gönen, Mehmet; Department of Industrial Engineering; Graduate School of Sciences and Engineering; College of EngineeringStandard machine learning algorithms have limited knowledge extraction capability in discriminating cancer stages based on genomic characterizations, due to the strongly correlated nature of high-dimensional genomic data. Moreover, activation of pathways plays a crucial role in the growth and progression of cancer from early-stage to latestage. That is why we implemented a kernel-based neural network framework that integrates pathways and gene expression data using multiple kernels and discriminates early- and late-stages of cancers. Our goal is to identify the relevant molecular mechanisms of the biological processes which might be driving cancer progression. As the input of developed multilayer perceptron (MLP), we constructed kernel matrices on multiple views of expression profiles of primary tumors extracted from pathways. We used Hallmark and Pathway Interaction Database (PID) datasets to restrict the search area to interpretable solutions. We applied our algorithm to 12 cancer cohorts from the Cancer Genome Atlas (TCGA), including more than 5100 primary tumors. The results showed that our algorithm could extract meaningful and disease-specific mechanisms of cancers. We tested the predictive performance of our MLP algorithm and compared it against three existing classification algorithms, namely, random forests, support vector machines, and multiple kernel learning. Our MLP method obtained better or comparable predictive performance against these algorithms.Publication Metadata only Corporate network analysis based on graph learning(Springer International Publishing Ag, 2023) Atan, Emre; Duymaz, Ali; Sarisozen, Funda; Aydin, Ugur; Koras, Murat; Department of Computer Engineering;Department of Industrial Engineering; Akgün, Barış; Gönen, Mehmet; College of EngineeringWe constructed a financial network based on the relationships of the customers in our database with our other customers or other bank customers using our large-scale data set of money transactions. There are two main aims in this study. Our first aim is to identify the most profitable customers by prioritizing companies in terms of centrality based on the volume of money transfers between companies. This requires acquiring new customers, deepening existing customers and activating inactive customers. Our second aim is to determine the effect of customers on related customers as a result of the financial deterioration in this network. In this study, while creating the network, a data set was created over money transfers between companies. Here, text similarity algorithms were used while trying to match the company title in the database with the title during the transfer. For customers who are not customers of our bank, information such as IBAN numbers are assigned as unique identifiers. We showed that the average profitability of the top 30% customers in terms of centrality is five times higher than the remaining customers. Besides, the variables we created to examine the effect of financial disruptions on other customers contributed an additional 1% Gini coefficient to the model that the bank is currently using even if it is difficult to contribute to a strong model that already works with a high Gini coefficient.Publication Metadata only Learning Markov Chain Models from sequential data under local differential privacy(Springer Science and Business Media Deutschland Gmbh, 2024) Department of Computer Engineering; Güner, Efehan; Gürsoy, Mehmet Emre; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of EngineeringMarkov chain models are frequently used in the analysis and modeling of sequential data such as location traces, time series, natural language, and speech. However, considering that many data sources are privacy-sensitive, it is imperative to design privacy-preserving methods for learning Markov models. In this paper, we propose Prima for learning discrete-time Markov chain models under local differential privacy (LDP), a state-of-the-art privacy standard. In Prima, each user locally encodes and perturbs their sequential record on their own device using LDP protocols. For this purpose, we adapt two bitvector-based LDP protocols (RAPPOR and OUE); and furthermore, we develop a novel extension of the GRR protocol called AdaGRR. We also propose to utilize custom privacy budget allocation strategies for perturbation, which enable uneven splitting of the privacy budget to better preserve utility in cases with uneven sequence lengths. On the server-side, Prima uses a novel algorithm for estimating Markov probabilities from perturbed data. We experimentally evaluate Prima using three real-world datasets, four utility metrics, and under various combinations of privacy budget and budget allocation strategies. Results show that Prima enables learning Markov chains under LDP with high utility and low error compared to Markov chains learned without privacy constraints.Publication Metadata only Geolocation risk scores for credit scoring models(Springer Science and Business Media Deutschland Gmbh, 2024) Ünal, Erdem; Aydın, Uğur; Koraş, Murat; Department of Computer Engineering;Department of Industrial Engineering; Akgün, Barış; Gönen, Mehmet; College of EngineeringCustomer location is considered as one of the most informative demographic data for predictive modeling. It has been widely used in various sectors including finance. Commercial banks use this information in the evaluation of their credit scoring systems. Generally, customer city and district are used as demographic features. Even if these features are quite informative, they are not fully capable of capturing socio-economical heterogeneity of customers within cities or districts. In this study, we introduced a micro-region approach alternative to this district or city approach. We created features based on characteristics of micro-regions and developed predictive credit risk models. Since models only used micro-region specific data, we were able to apply it to all possible locations and calculate risk scores of each micro-region. We showed their positive contribution to our regular credit risk models.Publication Metadata only Building quadtrees for spatial data under local differential privacy(Springer Science and Business Media Deutschland Gmbh, 2023) Department of Computer Engineering; Alptekin, Ece; Gürsoy, Mehmet Emre; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of EngineeringSpatial decompositions are commonly used in the privacy literature for various purposes such as range query answering, spatial indexing, count-of-counts histograms, data summarization, and visualization. Among spatial decomposition techniques, quadtrees are a popular and well-known method. In this paper, we study the problem of building quadtrees for spatial data under the emerging notion of Local Differential Privacy (LDP). We first propose a baseline solution inspired from a state-of-the-art method from the centralized DP literature and adapt it to LDP. Motivated by the observation that the baseline solution causes large noise accumulation due to its iterative strategy, we then propose a novel solution which utilizes a single data collection step from users, propagates density estimates to all nodes, and finally performs structural corrections to the quadtree. We experimentally evaluate the baseline solution and the proposed solution using four real-world location datasets and three utility metrics. Results show that our proposed solution consistently outperforms the baseline solution, and furthermore, the resulting quadtrees provide high accuracy in practical tasks such as spatial query answering under conventional privacy levels.Publication Metadata only Topics in assistive technologies and inclusion for older people: introduction to the special thematic session(Springer Science and Business Media Deutschland GmbH, 2024) Hallewell Haslwanter, Jean D.; Panek, Paul; Department of Media and Visual Arts; Subaşı, Özge; Department of Media and Visual Arts; College of Social Sciences and HumanitiesThis special session aims to carry forward discussions on Active Assisted Living (AAL), focusing on both new technologies for older adults and the various social aspects of their development. The papers cover different aspects of the special theme. Some detail the creation or introduction of tailored technologies to meet the specific needs of seniors, including monitor technologies and an interactive system. Others explore methods like co-design and new heuristics to ensure these systems truly address real-world needs. While yet others focus on topics of concern, such as ageist biases of computer science graduates and designing living spaces to better allow existing technologies to be integrated. Overall, the papers recognize the unique challenges of developing systems for older adults while acknowledging the diversity within this age group.Publication Metadata only Learning from the users for spatio-temporal data visualization explorations on social events(Springer Int Publishing Ag, 2016) N/A; Department of Media and Visual Arts; Çay, Damla; Yantaç, Asım Evren; PhD Student; Faculty Member; Department of Media and Visual Arts; KU Arçelik Research Center for Creative Industries (KUAR) / KU Arçelik Yaratıcı Endüstriler Uygulama ve Araştırma Merkezi (KUAR); Graduate School of Social Sciences and Humanities; College of Social Sciences and Humanities; N/A; 52621The amount of volunteered geographic information is on the rise through geo-tagged data on social media. While this growth opens new paths for designers and developers to form new geographical visualizations and interactive geographic tools, it also engenders new design and visualization problems. We now can turn any kind of data into daily useful information to be used during our daily lives. This paper is about exploration of novel visualization methods for spatio-temporal data related to what is happening in the city, planned or unplanned. We, hereby evaluate design students' works on visualizing social events in the city and share the results as design implications. Yet we contribute by presenting intuitive visualization ideas for social events, for the use of interactive media designers and developers who are developing map based interactive tools.Publication Metadata only Nonintrusive AMR asynchrony for communication optimization(Springer International Publishing Ag, 2017) Nguyen, Tan; Zhang, Weiqun; Almgren, Ann; Shalf, John; N/A; Department of Computer Engineering; Farooqi, Muhammad Nufail; Erten, Didem Unat; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 219274Adaptive Mesh Refinement (AMR) is a well known method for efficiently solving partial differential equations. A straightforward AMR algorithm typically exhibits many synchronization points even during a single time step, where costly communication often degrades the performance. This problem will be even more pronounced on future supercomputers containing billion way parallelism, which will raise the communication cost further. Re-designing AMR algorithms to avoid synchronization is not a viable solution due to the large code size and complex control structures. We present a nonintrusive asynchronous approach to hiding the effects of communication in an AMR application. Specifically, our approach reasons about data dependencies automatically using domain knowledge about AMR applications, allowing asynchrony to be discovered with only a modest amount of code modification. Using this approach, we optimize the synchronous AMR algorithm in the BoxLib software framework without severely affecting the productivity of the application programmer We observe around 27-31% performance improvement for an advection solver on the Hazel Hen supercomputer using 12288 cores.Publication Metadata only A second-order adaptive network model for organizational learning and usage of mental models for a team of match officials(2022) Kuilboer, Sam; Sieraad, Wesley; van Ments, Laila; Treur, Jan; Department of Computer Engineering; Canbaloğlu, Gülay; Undergraduate Student; Department of Computer Engineering; College of Engineering; N/AThis paper describes a multi-level adaptive network model for mental processes making use of shared mental models in the context of organizational learning in team-related performances. The paper describes the value of using shared mental models to illustrate the concept of organizational learning, and factors that influence team performances by using the analogy of a team of match officials during a game of football and show their behavior in a simulation of the shared mental model. The paper discusses potential elaborations of the different studied concepts, as well as implications of the paper in the domain of teamwork and team performance, and in terms of organizational learning.Publication Metadata only Per-GOP bitrate adaptation for H.264 compressed video sequences(Springer-Verlag Berlin, 2006) De Martin, Juan Carlos; Department of Computer Engineering; N/A; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; De Vito, Fabio; Özçelebi, Tanır; Civanlar, Mehmet Reha; Tekalp, Ahmet Murat; Other; PhD Student; Faculty Member; Faculty Member; Department of Computer Engineering; Department of Electrical and Electronics Engineering; College of Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; N/A; 16372; 26207In video transmission over packet data networks, it may be desirable to adapt the coding rate according to bandwidth availability. Classical approaches to rate adaptation are bitstream switching, requiring the storage of several pre-coded versions of a video, or layered (scalable) video coding, which has coding efficiency and/or complexity penalties. In this paper we propose a new GOP-level rate adaptation scheme for a single stream, variable target bitrate H.264 encoder; this allows each group of pictures (GOP) to be encoded at a specified bitrate. We first compare the performance of the standard H.264 rate control algorithm with the proposed one in the case of constant target bitrate. Then, we present results on how close the new technique can track a specified per-GOP target bitrate schedule. Results show that the proposed approach can obtain the desired target rates with less than 5% error.