Publications without Fulltext
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/3
Browse
5 results
Search Results
Publication Metadata only Through the glance mug: a familiar artefact to support opportunistic search in meetings(Assoc Computing Machinery, 2018) N/A; Department of Psychology; Department of Electrical and Electronics Engineering; N/A; N/A; N/A; Department of Psychology; Department of Media and Visual Arts; Börütecene, Ahmet; Bostan, İdil; Akyürek, Ekin; Sabuncuoğlu, Alpay; Temuzkuşu, İlker; Genç, Çağlar; Göksun, Tilbe; Özcan, Oğuzhan; PhD Student; Undergraduate Student; Undergraduate Student; PhD Student; Researcher; PhD Student; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; Department of Psychology; Department of Media and Visual Arts; KU Arçelik Research Center for Creative Industries (KUAR) / KU Arçelik Yaratıcı Endüstriler Uygulama ve Araştırma Merkezi (KUAR); KU Arçelik Research Center for Creative Industries (KUAR) / KU Arçelik Yaratıcı Endüstriler Uygulama ve Araştırma Merkezi (KUAR); N/A; N/A; KU Arçelik Research Center for Creative Industries (KUAR) / KU Arçelik Yaratıcı Endüstriler Uygulama ve Araştırma Merkezi (KUAR); KU Arçelik Research Center for Creative Industries (KUAR) / KU Arçelik Yaratıcı Endüstriler Uygulama ve Araştırma Merkezi (KUAR); N/A; 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; College of Engineering; Graduate School of Sciences and Engineering; N/A; Graduate School of Social Sciences and Humanities; College of Social Sciences and Humanities; College of Social Sciences and Humanities; N/A; N/A; N/A; N/A; N/A; N/A; 47278; 12532During collocated meetings, the spontaneous need for information, called opportunistic search, might arise while conversing. However, using smartphones to look up information might be disruptive, disrespectful or even embarrassing in social contexts. We propose an alternative instrument for this practice: Glance Mug, A touch-sensitive mug prototype that listens to the conversation and displays browsable content-driven results on its inner screen. We organized 15 pairs of one-to-one meetings between students to gather user reflections. the user study revealed that the mug has the potential for supporting instant search and affords sufficient subtlety to conceal user actions. Yet, it provoked some anxiety for the users in maintaining eye contact with their partners. Our main contributions are the context-aware mug concept tested in a real-life setting and the analysis through Hornecker and Buur's Tangible interaction Framework that discusses its design space, and its impact on the users and social interaction.Publication Metadata only Online anomaly detection with nested trees(IEEE-Inst Electrical Electronics Engineers Inc, 2016) Gökçesu, Kaan; Şimşek, Mustafa; Kozat, Süleyman S.; N/A; Department of Media and Visual Arts; Delibalta, İbrahim; Baruh, Lemi; PhD Student; Faculty Member; Department of Media and Visual Arts; Graduate School of Social Sciences and Humanities; College of Social Sciences and Humanities; N/A; 36113We introduce an online anomaly detection algorithm that processes data in a sequential manner. At each time, the algorithm makes a new observation, produces a decision, and then adaptively updates all its parameters to enhance its performance. The algorithm mainly works in an unsupervised manner since in most real-life applications labeling the data is costly. Even so, whenever there is a feedback, the algorithm uses it for better adaptation. The algorithm has two stages. In the first stage, it constructs a score function similar to a probability density function to model the underlying nominal distribution (if there is one) or to fit to the observed data. In the second state, this score function is used to evaluate the newly observed data to provide the final decision. The decision is given after the well-known thresholding. We construct the score using a highly versatile and completely adaptive nested decision tree. Nested soft decision trees are used to partition the observation space in a hierarchical manner. We adaptively optimize every component of the tree, i.e., decision regions and probabilistic models at each node as well as the overall structure, based on the sequential performance. This extensive in-time adaptation provides strong modeling capabilities; however, it may cause overfitting. To mitigate the overfitting issues, we first use the intermediate nodes of the tree to produce several subtrees, which constitute all the models from coarser to full extend, and then adaptively combine them. By using a real-life dataset, we show that our algorithm significantly outperforms the state of the art.Publication Metadata only Online text classification for real life tweet analysis(Institute of Electrical and Electronics Engineers (IEEE), 2016) Yar, Ersin; Kozat, Süleyman S.; N/A; Department of Media and Visual Arts; Delibalta, İbrahim; Baruh, Lemi; PhD Student; Faculty Member; Department of Media and Visual Arts; Graduate School of Social Sciences and Humanities; College of Social Sciences and Humanities; N/A; 36113In this paper, we study multi-class classification of tweets, where we introduce highly efficient dimensionality reduction techniques suitable for online processing of high dimensional feature vectors generated from freely-worded text. As for the real life case study, we work on tweets in the Turkish language, however, our methods are generic and can be used for other languages as clearly explained in the paper. Since we work on a real life application and the tweets are freely worded, we introduce text correction, normalization and root finding algorithms. Although text processing and classification are highly important due to many applications such as emotion recognition, advertisement selection, etc., online classification and regression algorithms over text are limited due to need for high dimensional vectors to represent natural text inputs. We overcome such limitations by showing that randomized projections and piecewise linear models can be efficiently leveraged to significantly reduce the computational cost for feature vector extraction from the tweets. Hence, we can perform multi-class tweet classification and regression in real time. We demonstrate our results over tweets collected from a real life case study where the tweets are freely-worded, e.g., with emoticons, shortened words, special characters, etc., and are unstructured. We implement several well-known machine learning algorithms as well as novel regression methods and demonstrate that we can significantly reduce the computational complexity with insignificant change in the classification and regression performance./ Öz: Serbestçe kelimelere dökülmüş metinden üretilen yüksek boyutlu öznitelik vektörlerinin çevrimiçi işlenmesine uygun son derece etkin boyut azaltıcı tekniklerin tanıtıldıgı bu bildiride tweetlerin çok sınıflı sınıflandırması incelenmektedir. Gerçek hayat çalışması olarak, Türk dilindeki tweetler üzerinde çalışılmaktadır. Ancak, kullanılan yöntemler bildiride açıklandığı üzere geneldir ve diğer diller içinde kullanılabilir. Gerçek hayat uygulaması üzerinde çalışıldığından ve tweetlerin serbestçe yazılmış olmasından dolayı, metin düzeltme, düzgeleme ve kök bulma algoritmaları uygulanır. Metin işleme ve sınıflandırma duygu tanıması, reklam seçimi vb. gibi birçok uygulamada yüksek derecede önemli olmasına rağmen çevrimiçi metin sınıflandırma ve regresyon algoritmaları doğal metin girdilerini gösterimlemek için yüksek boyutlu vektörlere olan ihtiyaçtan dolayı sınırlıdır. Bu gibi kısıtlamaların üstesinden özellik vektörü özütlemesi için hesaplama maliyetini ciddi ölçüde azaltan rasgeleleştirilmiş izdüşümler ve parçalı doğrusal modelleri etkin bir biçimde kullanılarak gelinebilir. Bu sayede, gerçek zamanlı çok sınıflı tweet sınıflandırması ve regresyonu yapılabilir. Sonuçlar gerçek bir hayat çalışmasından toplanan serbestçe yazılmış yani ifadeler, kısaltılmış kelimeler, özel karakterler vb. ile ve düzensiz olan tweetler kullanılarak gösterilmektedir. Özgün regresyon yöntemleri ile iyi bilinen makine öğrenimi algoritmaları uygulanır ve sınıflandırma ve regresyon performansında önemli değişiklik olmadan hesaplama karma¸sıklığın önemli ölçüde azaltıldığı gös- terilir.Publication Metadata only Mathematical model of causal inference in social networks(Institute of Electrical and Electronics Engineers (IEEE), 2016) Simsek, Mustafa; Delibalta, Ibrahim; Kozat, Suleyman S.; Department of Media and Visual Arts; Baruh, Lemi; Faculty Member; Department of Media and Visual Arts; College of Social Sciences and Humanities; 36113In this article, we model the effects of machine learning algorithms on different Social Network users by using a causal inference framework, making estimation about the underlying system and design systems to control underlying latent unobservable system. In this case, the latent internal state of the system can be a wide range of interest of user. For example, it can be a user's preferences for some certain products or affiliation of the user to some political parties. We represent these variables using state space model. In this model, the internal state of the system, e.g. the preferences or affiliations of the user is observed using user's connections with the Social Networks such as Facebook status updates, shares, comments, blogs, tweets etc./ Öz: Bu makalede makine öğrenmesi algoritmalarının sosyal medya esas gözlemlenemeyen durumun değiştirilmesi için gerekli algoritmalar dizayn ettik. Burada sistemin gizli iç durumu bir kişinin bir ürüne olan bağlılığını ya da siyasi parti bağlılık- larını temsil edebilir. Biz sistemin bu gizli iç durumunu durum uzay modeli kullanarak modelledik. Bu modellemede sistemin iç durumunu sosyal medya kullanıcısının tercih ya da bağlılık- larını, Facebook durum güncellemeleri, paylaşımları, yorumları, blogları ve tweet’lerini kullanarak elde ettik. Esas sistem tüketici tercihlerinden siyasi parti tercihlerine birçok alanda kullanılabilmesine rağmen biz sosyal medya kullanıcılarının tercihlerini modellemekle ilgileneceğiz.Publication Metadata only Viewfinder: supporting the installation and reconfiguration of multi-camera motion capture systems with a mobile application(Assoc Computing Machinery, 2017) Batis, Emmanuel; Bylund, Mathias; Fjeld, Morten; N/A; N/A; Department of Media and Visual Arts; Baytaş, Mehmet Aydın; Çay, Damla; Yantaç, Asım Evren; PhD Student; PhD Student; Faculty Member; Department of Media and Visual Arts; Graduate School of Social Sciences and Humanities; Graduate School of Social Sciences and Humanities; College of Social Sciences and Humanities; N/A; N/A; 52621We present ViewFinder, a cross-platform mobile application to support the installation and reconfiguration of marker-based motion capture systems with multiple cameras. ViewFinder addresses a common issue when installing or reconfiguring motion capture systems: that system components such as cameras and the host computer can be physically separate and/or difficult to reach, requiring personnel to maneuver between them frequently and laboriously. ViewFinder allows setup technicians or end users to visualize the output of each camera in the system in a variety of ways in real time, on a smartphone or tablet, while also providing a means to make adjustments to system parameters such as exposure or marker thresholds on the fly. The app has been designed and evaluated through a process observing user-centered design principles, and effectively reduces the amount of work involved in installing and reconfiguring motion capture systems.