Publications without Fulltext
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/3
Browse
82 results
Search Results
Publication Metadata only Spatial and thermal aware methods for efficient workload management in distributed data centers(Elsevier B.V., 2024) N/A; Department of Computer Engineering; Ali, Ahsan; Özkasap, Öznur; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of EngineeringGeographically distributed data centers provide facilities for users to fulfill the demand of storage and computations, where most of the operational cost is due to electricity consumption. In this study, we address the problem of energy consumption of cloud data centers and identify key characteristics of techniques proposed for reducing operational costs, carbon emissions, and financial penalties due to service level agreement (SLA) violations. By considering computer room air condition (CRAC) units that utilize outside air for cooling purposes as well as temperature and space-varying properties, we propose the energy cost model which takes into account temperature ranges for cooling purposes and operations of CRAC units. Then, we propose spatio-thermal-aware algorithms to manage workload using the variation of electricity price, locational outside and within the data center temperature, where the aim is to schedule the incoming workload requests with minimum SLA violations, cooling cost, and energy consumption. We analyzed the performance of our proposed algorithms and compared the experimental results with the benchmark algorithms for metrics of interest including SLA violations, cooling cost, and overall operations cost. Modeling, experiments, and verification conducted on CloudSim with realistic data center scenarios and workload traces show that the proposed algorithms result in reduced SLA violations, save between 15% to 75% of cooling cost and between 3.89% to 39% of the overall operational cost compared to the existing solutions.Publication Metadata only Longitudinal attacks against iterative data collection with local differential privacy(Tubitak Scientific & Technological Research Council Turkey, 2024) Department of Computer Engineering; Gürsoy, Mehmet Emre; Department of Computer Engineering; College of EngineeringLocal differential privacy (LDP) has recently emerged as an accepted standard for privacy -preserving collection of users' data from smartphones and IoT devices. In many practical scenarios, users' data needs to be collected repeatedly across multiple iterations. In such cases, although each collection satisfies LDP individually by itself, a longitudinal collection of multiple responses from the same user degrades that user's privacy. To demonstrate this claim, in this paper, we propose longitudinal attacks against iterative data collection with LDP. We formulate a general Bayesian adversary model, and then individually show the application of this adversary model on six popular LDP protocols: GRR, BLH, OLR, RAPPOR, OUE, and SS. We experimentally demonstrate the effectiveness of our attacks using two metrics, three datasets, and various privacy and domain parameters. The effectiveness of our attacks highlights the privacy risks associated with longitudinal data collection in a practical and quantifiable manner and motivates the need for appropriate countermeasures.Publication Metadata only Bringing order to sparsity: a sparse matrix reordering study on multicore CPUs(Association for Computing Machinery, Inc, 2023) Trotter, James D.; Ekmekçibaşı, Sinan; Langguth, Johannes; Ilic, Aleksandar; Department of Computer Engineering; Torun, Tuğba; Düzakın, Emre; Erten, Didem Unat; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and EngineeringMany real-world computations involve sparse data structures in the form of sparse matrices. A common strategy for optimizing sparse matrix operations is to reorder a matrix to improve data locality. However, it's not always clear whether reordering will provide benefits over the unordered matrix, as its effectiveness depends on several factors, such as structural features of the matrix, the reordering algorithm and the hardware that is used. This paper aims to establish the relationship between matrix reordering algorithms and the performance of sparse matrix operations. We thoroughly evaluate six different matrix reordering algorithms on 490 matrices across eight multicore architectures, focusing on the commonly used sparse matrix-vector multiplication (SpMV) kernel. We find that reordering based on graph partitioning provides better SpMV performance than the alternatives for a large majority of matrices, and that the resulting performance is explained through a combination of data locality and load balancing concerns. © 2023 Owner/Author(s).Publication Metadata only FLAGS simulation framework for federated learning algorithms(Institute of Electrical and Electronics Engineers Inc., 2023) Department of Computer Engineering; Lodhi, Ahnaf Hannan; Shamsizade, Toghrul; Al Asaad, Omar Mohammad; Akgün, Barış; Özkasap, Öznur; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of EngineeringFederated Learning (FL) provides an effective mechanism for distributed learning. However, it is expected to operate in a highly diverse setting with distinct behaviors from the participating nodes as well as dynamic network conditions. The FL performance, therefore, is subject to change due to the highly transitory nature of the overall system. An efficient simulation framework must be flexible to allow a range of participant behaviors, interactions, and environment characteristics. In this demo paper, we present the Federated Learning Algorithm Simulation (FLAGS) framework that we propose as a lightweight FL implementation and testing platform. FLAGS framework allows for a wide range of device behaviors and cooperative mechanisms, enabling rapid testing of multiple FL algorithms. © 2023 IEEE.Publication Metadata only Prototyping products using web-based AI tools: designing a tangible programming environment with children(Association Computing Machinery, 2022) Department of Computer Engineering; Sabuncuoğlu, Alpay; 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 Engineering; Graduate School of Sciences and EngineeringA wide variety of children's products such as mobile apps, toys, and assistant systems now have integrated smart features. Designing such AI-powered products with children, the users, is essential. Using high-fidelity prototypes can be a means to reveal children's needs and behaviors with AI-powered systems. Yet, a prototype that can show unpredictable features similar to the final AI-powered product can be expensive. A more manageable and inexpensive solution is using web-based AI prototyping tools such as Teachable Machine. In this work, we developed a Teachable Machine-powered game-development environment to inform our tangible programming environment's design decisions. Using this kind of an AI-powered high-fidelity prototype in the research process allowed us to observe children in a very similar setting to our final AI-powered product and extract design considerations. This paper reports our experience of prototyping AI-powered solutions with children and shares our design considerations for children's self-made tangible representations.Publication Metadata only Gamu blue: a practical tool for game theory security equilibria(Institute of Electrical and Electronics Engineers Inc., 2024) Yıldız, Burcu; Department of Computer Engineering; Taweel, Ameer; Küpçü, Alptekin; Department of Computer Engineering; College of EngineeringThe application of game theory in cybersecurity enables strategic analysis, adversarial modeling, and optimal decision-making to address security threats' complex and dynamic nature. Previous studies by Abraham et al. and Biçer et al. presented various definitions of equilibria to examine the security aspects of games involving multiple parties. Nonetheless, these definitions lack practical and easy-to-use implementations. Our primary contribution is addressing this gap by developing Gamu Blue, an easy-to-use tool with implementations for computing the equilibria definitions including k-resiliency, l-repellence, t-immunity, (l, t)-resistance, and m-stability. © 2024 IEEE.Publication Metadata only Machine learning methods for alarm prediction in industrial informatics: review and benchmark(Springer Science and Business Media Deutschland Gmbh, 2023) Department of Computer Engineering; Görgülü, Hamza; Özkasap, Öznur; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of EngineeringAlarm systems are important assets for plant safety and efficiency in a variety of industries, including power and utility, process and manufacturing, oil and gas, and communications. Especially in the process-based industry, alarm systems collect a huge amount of data in the field that requires operators to take action carefully. However, existing industrial alarm systems suffer from poor performance, mostly with alarm overloading and alarm flooding. Therefore, this problem creates an opportunity to implement machine learning models in order to predict upcoming alarms in the industry. In this way, the operators can take the necessary actions automatically while they are using their capacity for other unpredicted alarms. This study provides an overview of alarm prediction methods used in industrial alarm systems with the context of their classification types. In addition, a comparative analysis was conducted between two state-of-the-art deep learning models, namely Long Short-Term Memory (LSTM) and Transformer, through a benchmarking process. The experimental results of both models were evaluated and contrasted to identify their respective strengths and weaknesses. Moreover, this study identifies research gaps in alarm prediction, which can guide future research for better alarm management systems.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 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 Omnidirectional image quality assessment with local-global vision transformers(Elsevier, 2024) Elfkir, Mohamed Hedi; Imamoglu, Nevrez; Ozcinar, Cagri; Erdem, Erkut; Department of Computer Engineering; Tofighi, Nafiseh Jabbari; Erdem, Aykut; 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); Graduate School of Sciences and Engineering; College of EngineeringWith the rising popularity of omnidirectional images (ODIs) in virtual reality applications, the need for specialized image quality assessment (IQA) methods becomes increasingly critical. Traditional IQA approaches, designed for rectilinear images, often fail to evaluate ODIs accurately due to their 360 -degree scene representation. Addressing this, we introduce the Local - Global Transformer for 360 -degree Image Quality Assessment (LGT360IQ). This novel framework features dual branches tailored to mimic top -down and bottom -up visual attention mechanisms, adapted for the spherical characteristics of ODIs. The local branch processes tangent viewports from salient regions within the equirectangular projection image, extracting detailed features for granular quality assessment. In parallel, the global branch utilizes a task -dependent token sampling strategy for holistic image feature processing and quality score prediction. This integrated approach combines local and global information, offering an effective IQA method for ODIs. Our extensive evaluation across three benchmark ODI datasets, CVIQ, OIQA, and ODI, demonstrates LGT360IQ superior performance and establishes its role in advancing the field of IQA for omnidirectional images.