• Weight update skipping: Reducing training time for artificial neural networks 

  Safayenikoo, P.; Aktürk, İsmail (IEEE, 2021-11-15)

  Artificial Neural Networks (ANNs) are known as state-of-the-art techniques in Machine Learning (ML) and have achieved outstanding results in data-intensive applications, such as recognition, classification, and segmentation. ...

• Do not predict – Recompute! How value recomputation can truly boost the performance of invisible speculation 

  Sakalis, C.; Chowdhury, Z.; Wadle, S.; Aktürk, İsmail; Ros, A.; Sjalander, M.; Kaxiras, S.; Karpuzcu, U. (IEEE, 2021-09)

  Recent architectural approaches that address speculative side-channel attacks aim to prevent software from exposing the microarchitectural state changes of transient execution. The Delay-on-Miss technique is one such ...

• ANAC 2018: Repeated multilateral negotiation league 

  Aydoğan, Reyhan; Fujita, K.; Baarslag, T.; Jonker, C. M.; Ito, T. (Springer, 2020)

  This is an extension from a selected paper from JSAI2019. There are a number of research challenges in the field of Automated Negotiation. The Ninth International Automated Negotiating Agent Competition encourages participants ...

• Challenges and main results of the automated negotiating agents competition (ANAC) 2019 

  Aydoğan, Reyhan; Baarslag, T.; Fujita, K.; Mell, J.; Gratch, J.; de Jonge, D.; Mohammad, Y.; Nakadai, S.; Morinaga, S.; Osawa, H.; Aranha, C.; Jonker, C. M. (Springer, 2020)

  The Automated Negotiating Agents Competition (ANAC) is a yearly-organized international contest in which participants from all over the world develop intelligent negotiating agents for a variety of negotiation problems. ...

• Towards automated aircraft maintenance inspection. A use case of detecting aircraft dents using mask r-cnn 

  Bouarfa, S.; Doğru, Anıl; Arizar, R.; Aydoğan, Reyhan; Serafico, J. (American Institute of Aeronautics and Astronautics Inc, AIAA, 2020)

  Deep learning can be used to automate aircraft maintenance visual inspection. This can help increase the accuracy of damage detection, reduce aircraft downtime, and help prevent inspection accidents. The objective of this ...

• Forecasting multivariate time-series data using LSTM and mini-batches 

  Khodabakhsh, Athar; Arı, İsmail; Bakır, M.; Alagoz, S. M. (Springer, 2020)

  Multivariate time-series data forecasting is a challenging task due to nonlinear interdependencies in complex industrial systems. It is crucial to model these dependencies automatically using the ability of neural networks ...

• Not all mistakes are equal 

  Şensoy, M.; Saleki, Maryam; Julier, S.; Aydoğan, Reyhan; Reid, J. (The ACM Digital Library, 2020)

  In many tasks, classifiers play a fundamental role in the way an agent behaves. Most rational agents collect sensor data from the environment, classify it, and act based on that classification. Recently, deep neural networks ...

• Extraction of novel features based on histograms of mfccs used in emotion classification from generated original speech dataset 

  Pakyurek, M.; Atmış, Mahir; Kulac, S.; Uludag, U. (Kauno Technologijos Universitetas, 2020-02-17)

  This paper introduces two significant contributions: one is a new feature based on histograms of MFCC (Mel-Frequency Cepstral Coefficients) extracted from the audio files that can be used in emotion classification from ...

• SeCaS: Secure capability sharing framework for IoT devices in a structured P2P network 

  Aktypi, A.; Çakmakçı, Kübra Kalkan; Rasmussen, K. B. (The ACM Digital Library, 2020-03-16)

  The emergence of the internet of Things (IoT) has resulted in the possession of a continuously increasing number of highly heterogeneous connected devices by the same owner. To make full use of the potential of a personal ...

• Description-aware fashion image inpainting with convolutional neural networks in coarse-to-fine manner 

  Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (The ACM Digital Library, 2020-04-14)

  Inpainting a particular missing region in an image is a challenging vision task, and promising improvements on this task have been achieved with the help of the recent developments in vision-related deep learning studies. ...

• Objective and subjective QoE evaluation for adaptive point cloud streaming 

  Van Der Hooft, J.; Vega, M. T.; Timmerer, C.; Beğen, Ali Cengiz; De Turck, F.; Schatz, R. (IEEE, 2020-05)

  Volumetric media has the potential to provide the six degrees of freedom (6DoF) required by truly immersive media. However, achieving 6DoF requires ultra-high bandwidth transmissions, which real-world wide area networks ...

• Foreword 

  Toni, L.; Beğen, Ali Cengiz; Alay, O.; Timmerer, C. (The ACM Digital Library, 2020-05)

  N/A

• When they go high, we go low: low-latency live streaming in dash.js with LoL 

  Lim, M.; Akçay, Mehmet Necmettin; Bentaleb, A.; Beğen, Ali Cengiz; Zimmermann, R. (The ACM Digital Library, 2020-05)

  Live streaming remains a challenge in the adaptive streaming space due to the stringent requirements for not just quality and rebuffering, but also latency. Many solutions have been proposed to tackle streaming in general, ...

• Metadata-based user interface design for enhanced content access and viewing 

  Karmis, A. A.; Derya, A.; Beğen, Ali Cengiz (The ACM Digital Library, 2020-05)

  The nature of viewing is changing due to the huge volumes of content being produced including user content generated by amateurs and the proliferation of personalized services. The type of content being produced is not ...

• HTTP adaptive streaming over multiple network interfaces 

  Kara, Burak; Öztürk, Kemal Sarp; Beğen, Ali Cengiz (The ACM Digital Library, 2020-05)

  Enhancing user experience in streaming applications is an important problem. Delivering the best quality possible for the given network conditions is not an easy task. In the case of a streaming client running in a multi-homed ...

• Language inference with multi-head automata through reinforcement learning 

  Şekerci, Alper; Köken, Özlem Salehi (IEEE, 2020)

  The purpose of this paper is to use reinforcement learning to model learning agents which can recognize formal languages. Agents are modeled as simple multi-head automaton, a new model of finite automaton that uses multiple ...

• Evaluating the performance of apple’s low-latency HLS 

  Durak, Kerem; Akçay, Mehmet Necmettin; Erinç, Yiğit Kemal; Pekel, Boran; Beğen, Ali Cengiz (IEEE, 2020-09-21)

  In its annual developers conference in June 2019, Apple has announced a backwards-compatible extension to its popular HTTP Live Streaming (HLS) protocol to enable low-latency live streaming. This extension offers new ...

• Prioritization of test cases with varying test costs and fault severities for certification testing 

  Dirim, S.; Sözer, Hasan (IEEE, 2020-10)

  We present an industrial case study on the application of test case prioritization techniques in the context of certification testing in consumer electronics domain. Test execution times and fault severities are subject ...

• High-level representations through unconstrained sensorimotor learning 

  Öztürkçü, Özgür Baran; Uğur, E.; Öztop, E. (IEEE, 2020-10-26)

  How the sensorimotor experience of an agent can be organized into abstract symbol-like structures to enable effective planning and control is an open question. In the literature, there are many studies that start by assuming ...

• DPSec: A blockchain-based data plane authentication protocol for SDNs 

  Latah, Majd; Çakmakçı, Kübra Kalkan (IEEE, 2020-11-02)

  Software-Defined Networking (SDN) is a promising networking architecture that enables central management along with network programmability. However, SDN brings additional security threats due to untrusted control and data ...

View more