Computer Science

Permanent URI for this collectionhttps://hdl.handle.net/10679/43

Browse

Now showing 1 - 20 of 88

Open Access
ACNMP: skill transfer and task extrapolation through learning from demonstration and reinforcement learning via representation sharing
(ML Research Press, 2020) Akbulut, M. T.; Öztop, Erhan; Xue, H.; Tekden, A. E.; Şeker, M. Y.; Uğur, E.; Computer Science; ÖZTOP, Erhan
To equip robots with dexterous skills, an effective approach is to first transfer the desired skill via Learning from Demonstration (LfD), then let the robot improve it by self-exploration via Reinforcement Learning (RL). In this paper, we propose a novel LfD+RL framework, namely Adaptive Conditional Neural Movement Primitives (ACNMP), that allows efficient policy improvement in novel environments and effective skill transfer between different agents. This is achieved through exploiting the latent representation learned by the underlying Conditional Neural Process (CNP) model, and simultaneous training of the model with supervised learning (SL) for acquiring the demonstrated trajectories and via RL for new trajectory discovery. Through simulation experiments, we show that (i) ACNMP enables the system to extrapolate to situations where pure LfD fails; (ii) Simultaneous training of the system through SL and RL preserves the shape of demonstrations while adapting to novel situations due to the shared representations used by both learners; (iii) ACNMP enables order-of-magnitude sample-efficient RL in extrapolation of reaching tasks compared to the existing approaches; (iv) ACNMPs can be used to implement skill transfer between robots having different morphology, with competitive learning speeds and importantly with less number of assumptions compared to the state-of-the-art approaches. Finally, we show the real-world suitability of ACNMPs through real robot experiments that involve obstacle avoidance, pick and place and pouring actions.
Open Access
Actor-critic reinforcement learning for bidding in bilateral negotiation
(TÜBİTAK, 2022) Arslan, Furkan; Aydoğan, Reyhan; Computer Science; AYDOĞAN, Reyhan; Arslan, Furkan
Designing an effective and intelligent bidding strategy is one of the most compelling research challenges in automated negotiation, where software agents negotiate with each other to find a mutual agreement when there is a conflict of interests. Instead of designing a hand-crafted decision-making module, this work proposes a novel bidding strategy adopting an actor-critic reinforcement learning approach, which learns what to offer in a bilateral negotiation. An entropy reinforcement learning framework called Soft Actor-Critic (SAC) is applied to the bidding problem, and a self-play approach is employed to train the model. Our model learns to produce the target utility of the coming offer based on previous offer exchanges and remaining time. Furthermore, an imitation learning approach called behavior cloning is adopted to speed up the learning process. Also, a novel reward function is introduced that does take not only the agent’s own utility but also the opponent’s utility at the end of the negotiation. The developed agent is empirically evaluated. Thus, a large number of negotiation sessions are run against a variety of opponents selected in different domains varying in size and opposition. The agent’s performance is compared with its opponents and the performance of the baseline agents negotiating with the same opponents. The empirical results show that our agent successfully negotiates against challenging opponents in different negotiation scenarios without requiring any former information about the opponent or domain in advance. Furthermore, it achieves better results than the baseline agents regarding the received utility at the end of the successful negotiations.
Open Access
Affordance-based altruistic robotic architecture for human–robot collaboration
(Sage, 2019-08) Imre, M.; Öztop, Erhan; Nagai, Y.; Ugur, E.; Computer Science; ÖZTOP, Erhan
This article proposes a computational model for altruistic behavior, shows its implementation on a physical robot, and presents the results of human-robot interaction experiments conducted with the implemented system. Inspired from the sensorimotor mechanisms of the primate brain, object affordances are utilized for both intention estimation and action execution, in particular, to generate altruistic behavior. At the core of the model is the notion that sensorimotor systems developed for movement generation can be used to process the visual stimuli generated by actions of the others, infer the goals behind, and take the necessary actions to help achieving these goals, potentially leading to the emergence of altruistic behavior. Therefore, we argue that altruistic behavior is not necessarily a consequence of deliberate cognitive processing but may emerge through basic sensorimotor processes such as error minimization, that is, minimizing the difference between the observed and expected outcomes. In the model, affordances also play a key role by constraining the possible set of actions that an observed actor might be engaged in, enabling a fast and accurate intention inference. The model components are implemented on an upper-body humanoid robot. A set of experiments are conducted validating the workings of the components of the model, such as affordance extraction and task execution. Significantly, to assess how human partners interact with our altruistic model deployed robot, extensive experiments with naive subjects are conducted. Our results indicate that the proposed computational model can explain emergent altruistic behavior in reference to its biological counterpart and moreover engage human partners to exploit this behavior when implemented on an anthropomorphic robot.
Open Access
Aktör tabanlı sistemler için test kapsama kriterleri
(CEUR-WS, 2018) Sözer, Hasan; Gürler, O.; Yılmaz, O.; Computer Science; Tarhan, A.; Erten, M.; SÖZER, Hasan
Aktör tabanlı sistemler, eşzamanlı çalışan ve birbirleri ile asenkron bir şekilde haberleşen aktör isimli otonom elemanlardan oluşmaktadırlar. Asenkron haberleşme sebebiyle aktörler arasında paylaşılan mesajların sıralaması farklılık gösterebilmektedir. Diğer eşzamanlı çalışan sistemlerde olduğu gibi, determinizm yokluğu, aktör tabanlı sistemlerde test ve hata ayıklama süreçlerini zorlaştırmaktadır. Geleneksel test kapsama kriterleri de bu sistemler için etkin olmamaktadır. Bu bildiride, aktör tabanlı sistemler için kullanılabilecek test kapsama kriterleri irdelenmektedir. Literatürde önerilmiş mevcut kriterlere ek olarak yeni kriterler ile, ayrık matematik alanında son zamanlarda yayınlanmış olan çalışmaların aktör tabanlı sistemler için test kapsama kriterleri belirlemek ve değerlendirmek üzere uygulamaları ilk defa bu bildiride ele alınmaktadır. Önerilen kapsama kriterlerine göre değerlendirme yapabilen ve bu kriterleri sağlayacak şekilde test durumlarını otomatik olarak oluşturan bir test altyapısı şu an geliştirme aşamasındadır.
Open Access
Alarm sequence rule mining extended with a time confidence parameter
(2014) Çelebi, Ö. F.; Zeydan, E.; Arı, İsmail; İleri, Ö.; Ergüt, S.; Computer Science; ARI, Ismail
Most mobile telecommunication operators receive an overwhelming number of alarms in their networks. Network support specialists are faced with the challenge of picking the most important alarms in advance that can cause severe damages to the system or disrupt the service. A system that can discover alarm correlations and alarm rules then notify network administrators can significantly increase the efficiency of Network Operation Centers (NOC) of these mobile operators. This paper provides a new alarm correlation, rule discovery, and significant rule selection technique based on analysis of real data collected from a mobile telecom operator. We present a method based on sequential rule mining algorithm with an additional parameter called time-confidence. The time-confident rules found by this method are processed more efficiently in real-time Complex Event Processing (CEP) systems that require exact time-window values during monitoring. Furthermore, compared to traditional sequential rule mining, our proposed method adds another support dimension to eliminate meaningless rules that appear due to wrong settings of minimum support-confidence thresholds with respect to the nature of data.
Open Access
Arabic offensive language on twitter: Analysis and experiments
(Association for Computational Linguistics (ACL), 2021) Mubarak, H.; Rashed, Ammar; Darwish, K.; Samih, Y.; Abdelali, A.; Rashed, Ammar
Detecting offensive language on Twitter has many applications ranging from detecting/predicting bullying to measuring polarization. In this paper, we focus on building a large Arabic offensive tweet dataset. We introduce a method for building a dataset that is not biased by topic, dialect, or target. We produce the largest Arabic dataset to date with special tags for vulgarity and hate speech. We thoroughly analyze the dataset to determine which topics, dialects, and gender are most associated with offensive tweets and how Arabic speakers use offensive language. Lastly, we conduct many experiments to produce strong results (F1 = 83.2) on the dataset using SOTA techniques.
Open Access
Artificial intelligence techniques for conflict resolution
(Springer, 2021-08) Aydoğan, Reyhan; Baarslag, T.; Gerding, E.; Computer Science; AYDOĞAN, Reyhan
Conflict resolution is essential to obtain cooperation in many scenarios such as politics and business, as well as our day to day life. The importance of conflict resolution has driven research in many fields like anthropology, social science, psychology, mathematics, biology and, more recently, in artificial intelligence. Computer science and artificial intelligence have, in turn, been inspired by theories and techniques from these disciplines, which has led to a variety of computational models and approaches, such as automated negotiation, group decision making, argumentation, preference aggregation, and human-machine interaction. To bring together the different research strands and disciplines in conflict resolution, the Workshop on Conflict Resolution in Decision Making (COREDEMA) was organized. This special issue benefited from the workshop series, and consists of significantly extended and revised selected papers from the ECAI 2016 COREDEMA workshop, as well as completely new contributions.
Open Access
Asset price and direction prediction via deep 2D transformer and convolutional neural networks
(ACM, 2022-11-02) Tuncer, Tuna; Kaya, Uygar; Sefer, Emre; Alacam, Onur; Hoşer, Tuğcan; Computer Science; SEFER, Emre; Tuncer, Tuna; Kaya, Uygar; Alacam, Onur; Hoşer, Tuğcan
Artificial intelligence-based algorithmic trading has recently started to attract more attention. Among the techniques, deep learning-based methods such as transformers, convolutional neural networks, and patch embedding approaches have become quite popular inside the computer vision researchers. In this research, inspired by the state-of-the-art computer vision methods, we have come up with 2 approaches: DAPP (Deep Attention-based Price Prediction) and DPPP (Deep Patch-based Price Prediction) that are based on vision transformers and patch embedding-based convolutional neural networks respectively to predict asset price and direction from historical price data by capturing the image properties of the historical time-series dataset. Before applying attention-based architecture, we have transformed historical time series price dataset into two-dimensional images by using various number of different technical indicators. Each indicator creates data for a fixed number of days. Thus, we construct two-dimensional images of various dimensions. Then, we use original images valleys and hills to label each image as Hold, Buy, or Sell. We find our trained attention-based models to frequently provide better results for ETFs in comparison to the baseline convolutional architectures in terms of both accuracy and financial analysis metrics during longer testing periods.
Open Access
Bandwidth prediction in low-latency media transport
(ACM, 2023-06-16) Bentaleb, A.; Akçay, Mehmet Necmettin; Lim, M.; Beğen, Ali Cengiz; Zimmermann, R.; Computer Science; BEĞEN, Ali Cengiz; Akçay, Mehmet Necmettin
Designing a robust bandwidth prediction algorithm for low-latency media transport that can quickly adapt to varying network conditions is challenging. In this paper, we present the working principles of a hybrid bandwidth predictor (termed BoB, Bang-on-Bandwidth) we developed recently for real-time communications and discuss its use with the new Media-over-QUIC (MOQ) protocol proposals.
Open Access
Bargaining chips: Coordinating one-to-many concurrent composite negotiations
(ACM, 2021) Baarslag, T.; Elfrink, T.; Nassiri Mofakham, F.; Koça, T.; Kaisers, M.; Aydoğan, Reyhan; Computer Science; AYDOĞAN, Reyhan
This study presents Bargaining Chips: a framework for one-to-many concurrent composite negotiations, where multiple deals can be reached and combined. Our framework is designed to mirror the salient aspects of real-life procurement and trading scenarios, in which a buyer seeks to acquire a number of items from different sellers at the same time. To do so, the buyer needs to successfully perform multiple concurrent bilateral negotiations as well as coordinate the composite outcome resulting from each interdependent negotiation. This paper contributes to the state of the art by: (1) presenting a model and test-bed for addressing such challenges; (2) by proposing a new, asynchronous interaction protocol for coordinating concurrent negotiation threads; and (3) by providing classes of multi-deal coordinators that are able to navigate this new one-to-many multi-deal setting. We show that Bargaining Chips can be used to evaluate general asynchronous negotiation and coordination strategies in a setting that generalizes over a number of existing negotiation approaches.
Open Access
The benefits of server hinting when DASHing or HLSing
(ACM, 2022-03-17) Lim, M.; Akçay, Mehmet Necmettin; Bentaleb, A.; Beğen, Ali Cengiz; Zimmermann, R.; Computer Science; BEĞEN, Ali Cengiz; Akçay, Mehmet Necmettin
Streaming clients almost always compete for the available bandwidth and server capacity. Not every client's playback buffer conditions will be the same, though, nor should be the priority with which the server processes the individual requests coming from these clients. In an earlier work, we demonstrated that if clients conveyed their buffer statuses to the server using a Common Media Client Data (CMCD) query argument, the server could allocate its output capacity among all the requests more wisely, which could significantly reduce the rebufferings experienced by the clients. In this paper, we address the same problem using the Common Media Server Data (CMSD) standard that is work-in-progress at the Consumer Technology Association (CTA). In this case, the incoming requests are scheduled based on their CMCD information. For example, the response to a request indicating a healthy buffer status is held/delayed until more urgent requests are handled. When the delayed response is eventually transmitted, the server attaches a new CMSD parameter to indicate how long the delay was. This parameter avoids misinterpretations and subsequent miscalculations by the client's rate-adaptation logic. We implemented the server and client understanding/processing CMCD and CMSD, respectively. Our experiments show that the proposed CMSD parameter effectively eliminates unnecessary downshifting while reducing both the rebuffering rate and duration.
Open Access
BoB: Bandwidth prediction for real-time communications using heuristic and reinforcement learning
(IEEE, 2023) Bentaleb, A.; Akçay, Mehmet Necmettin; Lim, M.; Beğen, Ali Cengiz; Zimmermann, R.; Computer Science; BEĞEN, Ali Cengiz; Akçay, Mehmet Necmettin
Bandwidth prediction is critical in any Real-time Communication (RTC) service or application. This component decides how much media data can be sent in real time. Subsequently, the video and audio encoder dynamically adapts the bitrate to achieve the best quality without congesting the network and causing packets to be lost or delayed. To date, several RTC services have deployed the heuristic-based Google Congestion Control (GCC), which performs well under certain circumstances and falls short in some others. In this paper, we leverage the advancements in reinforcement learning and propose BoB (Bang-on-Bandwidth) — a hybrid bandwidth predictor for RTC. At the beginning of the RTC session, BoB uses a heuristic-based approach. It then switches to a learning-based approach. BoB predicts the available bandwidth accurately and improves bandwidth utilization under diverse network conditions compared to the two winning solutions of the ACM MMSys'21 grand challenge on bandwidth estimation in RTC. An open-source implementation of BoB is publicly available for further testing and research.
Metadata only
Building the Turkish FrameNet
(Global WordNet Association, 2021) Marşan, B.; Kara, N.; Özçelik, M.; Arıcan, B. N.; Cesur, N.; Kuzgun, A.; Sanıyar, E.; Yıldız, Olcay Taner; Computer Science; YILDIZ, Olcay Taner
FrameNet (Lowe, 1997; Baker et al., 1998; Fillmore and Atkins, 1998; Johnson et al., 2001) is a computational lexicography project that aims to offer insight into the semantic relationships between predicate and arguments. Having uses in many NLP applications, FrameNet has proven itself as a valuable resource. The main goal of this study is laying the foundation for building a comprehensive and cohesive Turkish FrameNet that is compatible with other resources like PropBank (Kara et al., 2020) or WordNet (Bakay et al., 2019; Ehsani, 2018; Ehsani et al., 2018; Parlar et al., 2019; Bakay et al., 2020) in the Turkish language.
Open Access
Can social agents efficiently perform in automated negotiation?
(MDPI, 2021-07) Sanchez-Anguix, V.; Tunalı, O.; Aydoğan, Reyhan; Julian, V.; Computer Science; AYDOĞAN, Reyhan
In the last few years, we witnessed a growing body of literature about automated negotiation. Mainly, negotiating agents are either purely self-driven by maximizing their utility function or by assuming a cooperative stance by all parties involved in the negotiation. We argue that, while optimizing one’s utility function is essential, agents in a society should not ignore the opponent’s utility in the final agreement to improve the agent’s long-term perspectives in the system. This article aims to show whether it is possible to design a social agent (i.e., one that aims to optimize both sides’ utility functions) while performing efficiently in an agent society. Accordingly, we propose a social agent supported by a portfolio of strategies, a novel tit-for-tat concession mechanism, and a frequency-based opponent modeling mechanism capable of adapting its behavior according to the opponent’s behavior and the state of the negotiation. The results show that the proposed social agent not only maximizes social metrics such as the distance to the Nash bargaining point or the Kalai point but also is shown to be a pure and mixed equilibrium strategy in some realistic agent societies.
Open Access
Catching the moment with LoL + in twitch-like low-latency live streaming platforms
(IEEE, 2022) Bentaleb, A.; Akçay, Mehmet Necmettin; Lim, M.; Beğen, Ali Cengiz; Zimmermann, R.; Computer Science; BEĞEN, Ali Cengiz; Akçay, Mehmet Necmettin
Our earlier Low-on-Latency (dubbed as LoL) solution offered an accurate bandwidth prediction and rate adaptation algorithm tailored for live streaming applications that targeted an end-to-end latency of up to two seconds. While LoL was a significant step forward in multi-bitrate low-latency live streaming, further experimentation and testing showed that there was room for improvement in three areas. First, LoL used hard-coded parameters computed from an offline training process in the rate adaptation algorithm and this was seen as a significant barrier in LoL's wide deployment. Second, LoL's objective was to maximize a collective QoE function. Yet, certain use cases have specific objectives besides the singular QoE and this had to be accommodated. Third, the adaptive playback speed control failed to produce satisfying results in some scenarios. Our goal in this paper is to address these areas and make LoL sufficiently robust to deploy. We refer to the enhanced solution as LoL+ which has been integrated to the official dash.js player in v3.2.0.
Open Access
Common media client data (CMCD): Initial findings
(Association for Computing Machinery, Inc, 2021-07-16) Bentaleb, A.; Lim, M.; Akçay, Mehmet Necmettin; Beğen, Ali Cengiz; Zimmermann, R.; Computer Science; BEĞEN, Ali Cengiz; Akçay, Mehmet Necmettin
In September 2020, the Consumer Technology Association (CTA) published the CTA-5004: Common Media Client Data (CMCD) specification. Using this specification, a media client can convey certain information to the content delivery network servers with object requests. This information is useful in log association/analysis, quality of service/experience monitoring and delivery enhancements. This paper is the first step toward investigating the feasibility of CMCD in addressing one of the most common problems in the streaming domain: efficient use of shared bandwidth by multiple clients. To that effect, we implemented CMCD functions on an HTTP server and built a proof-of-concept system with CMCD-Aware dash.js clients. We show that even a basic bandwidth allocation scheme enabled by CMCD reduces rebuffering rate and duration without noticeably sacrificing the video quality.
Open Access
Common media server data (CMSD) - update on implementations and validation of key use cases
(ACM, 2023-06-16) Pham, S.; Law, W.; Beğen, Ali Cengiz; Silhavy, D.; Berthelot, B.; Arbanowski, S.; Steglich, S.; Computer Science; BEĞEN, Ali Cengiz
The CTA-5006 (Common Media Server Data, CMSD) specification establishes a uniform method for media servers to exchange data with each media object response. The aim is to enhance distribution efficiency, performance, and ultimately, the user experience. We provide an overview of CMSD implementations and focus on integrating CMSD into the dash.js reference player. Three use cases are evaluated to demonstrate the advantages of CMSD, including leveraging edge server throughput estimates to improve initial bitrate selection and low-latency live streaming, prefetching manifests and segments to improve startup delay, and allowing an edge server to suggest a playback bitrate to improve the collective experience. The outcomes from the initial implementations confirm the benefits of using CMSD.
Open Access
A comparison of topologically associating domain callers over mammals at high resolution
(BioMed Central Ltd, 2022-04-12) Sefer, Emre; Computer Science; SEFER, Emre
Background: Topologically associating domains (TADs) are locally highly-interacting genome regions, which also play a critical role in regulating gene expression in the cell. TADs have been first identified while investigating the 3D genome structure over High-throughput Chromosome Conformation Capture (Hi-C) interaction dataset. Substantial degree of efforts have been devoted to develop techniques for inferring TADs from Hi-C interaction dataset. Many TAD-calling methods have been developed which differ in their criteria and assumptions in TAD inference. Correspondingly, TADs inferred via these callers vary in terms of both similarities and biological features they are enriched in. Result: We have carried out a systematic comparison of 27 TAD-calling methods over mammals. We use Micro-C, a recent high-resolution variant of Hi-C, to compare TADs at a very high resolution, and classify the methods into 3 categories: feature-based methods, Clustering methods, Graph-partitioning methods. We have evaluated TAD boundaries, gaps between adjacent TADs, and quality of TADs across various criteria. We also found particularly CTCF and Cohesin proteins to be effective in formation of TADs with corner dots. We have also assessed the callers performance on simulated datasets since a gold standard for TADs is missing. TAD sizes and numbers change remarkably between TAD callers and dataset resolutions, indicating that TADs are hierarchically-organized domains, instead of disjoint regions. A core subset of feature-based TAD callers regularly perform the best while inferring reproducible domains, which are also enriched for TAD related biological properties. Conclusion: We have analyzed the fundamental principles of TAD-calling methods, and identified the existing situation in TAD inference across high resolution Micro-C interaction datasets over mammals. We come up with a systematic, comprehensive, and concise framework to evaluate the TAD-calling methods performance across Micro-C datasets. Our research will be useful in selecting appropriate methods for TAD inference and evaluation based on available data, experimental design, and biological question of interest. We also introduce our analysis as a benchmarking tool with publicly available source code.
Open Access
Conflict-based negotiation strategy for human-agent negotiation
(Springer, 2023-12) Keskin, Mehmet Onur; Buzcu, Berk; Aydoğan, Reyhan; Computer Science; AYDOĞAN, Reyhan; Keskin, Mehmet Onur; Buzcu, Berk
Day by day, human-agent negotiation becomes more and more vital to reach a socially beneficial agreement when stakeholders need to make a joint decision together. Developing agents who understand not only human preferences but also attitudes is a significant prerequisite for this kind of interaction. Studies on opponent modeling are predominantly based on automated negotiation and may yield good predictions after exchanging hundreds of offers. However, this is not the case in human-agent negotiation in which the total number of rounds does not usually exceed tens. For this reason, an opponent model technique is needed to extract the maximum information gained with limited interaction. This study presents a conflict-based opponent modeling technique and compares its prediction performance with the well-known approaches in human-agent and automated negotiation experimental settings. According to the results of human-agent studies, the proposed model outpr erforms them despite the diversity of participants’ negotiation behaviors. Besides, the conflict-based opponent model estimates the entire bid space much more successfully than its competitors in automated negotiation sessions when a small portion of the outcome space was explored. This study may contribute to developing agents that can perceive their human counterparts’ preferences and behaviors more accurately, acting cooperatively and reaching an admissible settlement for joint interests.
Open Access
Creating domain dependent Turkish WordNet and SentiNet
(Global WordNet Association, 2021) Arıcan, B. N.; Özçelik, M.; Aslan, D. B.; Sarmış, E.; Parlar, S.; Yıldız, Olcay Taner; Computer Science; YILDIZ, Olcay Taner
A WordNet is a thesaurus that has a structured list of words organized depending on their meanings. WordNet represents word senses, all meanings a single lemma may have, the relations between these senses, and their definitions. Another study within the domain of Natural Language Processing is sentiment analysis. With sentiment analysis, data sets can be scored according to the emotion they contain. In the sentiment analysis we did with the data we received on the Tourism WordNet, we performed a domain-specific sentiment analysis study by annotating the data. In this paper, we propose a method to facilitate Natural Language Processing tasks such as sentiment analysis performed in specific domains via creating a specific-domain subset of an original Turkish dictionary. As the preliminary study, we have created a WordNet for the tourism domain with 14,000 words and validated it on simple tasks.

Browse

Browsing by Rights "info:eu-repo/semantics/openAccess"