Browsing by Subject "Active learning"

Now showing 1 - 11 of 11

Open Access
Active learning in context-driven stream mining with an application to ımage mining
(Institute of Electrical and Electronics Engineers, 2015-11) Tekin, C.; Schaar, Mihaela van der
We propose an image stream mining method in which images arrive with contexts (metadata) and need to be processed in real time by the image mining system (IMS), which needs to make predictions and derive actionable intelligence from these streams. After extracting the features of the image by preprocessing, IMS determines online the classifier to use on the extracted features to make a prediction using the context of the image. A key challenge associated with stream mining is that the prediction accuracy of the classifiers is unknown, since the image source is unknown; thus, these accuracies need to be learned online. Another key challenge of stream mining is that learning can only be done by observing the true label, but this is costly to obtain. To address these challenges, we model the image stream mining problem as an active, online contextual experts problem, where the context of the image is used to guide the classifier selection decision. We develop an active learning algorithm and show that it achieves regret sublinear in the number of images that have been observed so far. To further illustrate and assess the performance of our proposed methods, we apply them to diagnose breast cancer from the images of cellular samples obtained from the fine needle aspirate of breast mass. Our findings show that very high diagnosis accuracy can be achieved by actively obtaining only a small fraction of true labels through surgical biopsies. Other applications include video surveillance and video traffic monitoring.
Open Access
An assessment of the effects of teaching methods on academic performance of students in accounting courses
(Routledge, 2010) Hosal-Akman, N.; Simga-Mugan, C.
This study explores the effect of teaching methods on the academic performance of students in accounting courses. The study was carried out over two semesters at a well-known university in Turkey in principles of financial accounting and managerial accounting courses. Students enrolled in the courses were assigned to treatment and control groups. Treatment group students solved assigned problems or cases in groups in class, while in the control group the instructor lectured on and solved the problems and cases. The results of the study show that there was no significant difference in the academic performance of the treatment and control group students in either course.
Open Access
Do computer games enhance learning about conflicts? A cross-national inquiry into proximate and distant scenarios in Global Conflicts
(Pergamon Press, 2015) Kampf, R.; Cuhadar E.
Interactive conflict resolution and peace education have developed as two major lines of practice to tackle intractable inter-group conflicts. Recently, new media technologies such as social media, computer games, and online dialogue are added to the existing set of tools used for peace education. However, a debate is emerging as to how effective they are in motivating learning and teaching skills required for peace building. We take issue with this question and have conducted a study investigating the effect of different conflict contexts on student learning. We have designed a cross-national experimental study with Israeli-Jewish, Palestinian, and Guatemalan undergraduate students using the Israeli-Palestinian and Guatemalan scenarios in the computer game called "Global Conflicts." The learning effects of these scenarios were systematically analyzed using pre- and post-test questionnaires. The study indicated that Israeli-Jews and Palestinians acquired more knowledge from the Guatemalan game than Guatemalans acquired from the Israeli-Palestinian game. All participants acquired knowledge about proximate conflicts after playing games about these scenarios, and there were insignificant differences between the three national groups. Israeli-Jews and Palestinians playing the Israeli-Palestinian game changed their attitudes about this conflict, while Guatemalans playing the Guatemalan game did not change their attitudes about this case. All participants changed their attitudes about distant conflicts after playing games about these scenarios. © 2014 Elsevier Ltd.
Open Access
Entropy-functional-based online adaptive decision fusion framework with application to wildfire detection in video
(IEEE, 2012-01-09) Gunay, O.; Toreyin, B. U.; Kose, K.; Çetin, A. Enis
In this paper, an entropy-functional-based online adaptive decision fusion (EADF) framework is developed for image analysis and computer vision applications. In this framework, it is assumed that the compound algorithm consists of several subalgorithms, each of which yields its own decision as a real number centered around zero, representing the confidence level of that particular subalgorithm. Decision values are linearly combined with weights that are updated online according to an active fusion method based on performing entropic projections onto convex sets describing subalgorithms. It is assumed that there is an oracle, who is usually a human operator, providing feedback to the decision fusion method. A video-based wildfire detection system was developed to evaluate the performance of the decision fusion algorithm. In this case, image data arrive sequentially, and the oracle is the security guard of the forest lookout tower, verifying the decision of the combined algorithm. The simulation results are presented.
Open Access
Fire detection in video using LMS based active learning
(Springer, 2009) Günay, O.; Taşdemir K.; Töreyin, B. U.; Çetin, A. Enis
In this paper, a video based algorithm for fire and flame detection is developed. In addition to ordinary motion and color clues, flame flicker is distinguished from motion of flame colored moving objects using Markov models. Irregular nature of flame boundaries is detected by performing temporal wavelet analysis using Hidden Markov Models as well. Color variations in fire is detected by computing the spatial wavelet transform of moving fire-colored regions. Boundary of flames are represented in wavelet domain and irregular nature of the boundaries of fire regions is also used as an indication of the flame flicker. Decisions from sub-algorithms are linearly combined using an adaptive active fusion method. The main detection algorithm is composed of four sub-algorithms (i) detection of fire colored moving objects, (ii) temporal, and (iii) spatial wavelet analysis for flicker detection and (iv) contour analysis of fire colored region boundaries. Each algorithm yields a continuous decision value as a real number in the range [-1, 1] at every image frame of a video sequence. Decision values from sub-algorithms are fused using an adaptive algorithm in which weights are updated using the least mean square (LMS) method in the training (learning) stage.
Open Access
Introducing sustainability to interior design students through industry collaboration
(Emerald Group Publishing Limited, 2014) Afacan, Yasemin
Purpose: The purpose of this study was to introduce a sustainability course to interior design students and explore how working with industry could address challenges with integrating sustainability education into and ensuring student motivation in non-studio courses. Design/methodology/approach: This is a case study presenting qualitative evaluation from the 15-week "IAED 342 Sustainable Design for Interiors" course with a sample of 98 third-year interior architecture students at Bilkent University, Turkey. Findings: The findings were analyzed from the perspectives of two processes learning and working with industry. The results revealed that an active learning environment and industry collaboration positively influenced students' awareness of sustainable design, increased their ability to integrate sustainability knowledge to design studio projects and improved academic outcomes. Originality/value: This study is a unique effort by the Department of Interior Architecture and Environmental Design at Bilkent University by being the first to introduce a sustainability course and create a responsive and social learning environment through industry collaboration. The results of the study highlighted that better outcomes are achieved by working directly with industry than by performing theoretical exercises. © Emerald Group Publishing Limited.
Open Access
Online adaptive decision fusion framework based on projections onto convex sets with application to wildfire detection in video
(S P I E - International Society for Optical Engineering, 2011-07-06) Gunay, O.; Toreyin, B. U.; Çetin, A. Enis
In this paper, an online adaptive decision fusion framework is developed for image analysis and computer vision applications. In this framework, it is assumed that the compound algorithm consists of several sub-algorithms, each of which yields its own decision as a real number centered around zero, representing the confidence level of that particular sub-algorithm. Decision values are linearly combined with weights that are updated online according to an active fusion method based on performing orthogonal projections onto convex sets describing sub-algorithms. It is assumed that there is an oracle, who is usually a human operator, providing feedback to the decision fusion method. A video-based wildfire detection system is developed to evaluate the performance of the algorithm in handling the problems where data arrives sequentially. In this case, the oracle is the security guard of the forest lookout tower verifying the decision of the combined algorithm. Simulation results are presented.
Open Access
Pathologically chronic pain and pain avoidance behavior within predictive processing framework
(2021-06) Demirkaya, Eyşan
Pain as the most enquired philosophical theme is a complex experience, which includes sensation, emotion, motivation, cognition, and social interaction. However, there is not a single overarching philosophical theory that accounts for all the dimensions of pain. The most overlooked discussion of pain is on its motivational aspect; yet, it is indispensable for an integrated understanding of pain. Also, its least debated area is the substantial relation between pathologically chronic pain and action. In this thesis, I attempt to investigate why physiologically acute pain outlasts its purposes to transform into pathologically chronic pain and why pathologically chronic pain is accompanied by pain avoidance behavior by drawing inferences from the explore-exploit dilemma. I also examine the related pain theories addressing their failures in answering these questions. I conclude that analyzing pathologically chronic pain and pain avoidance behavior within predictive processing framework (1) provides an active learning account for pathologically chronic pain, (2) ensures an active inference account for pain avoidance behavior, (3) allows an active learning account for pain avoidance behavior only if certain conditions are met, and (4) points out the disparate action strategies are accountable for pathologically acute pain, pain avoidance behavior, and physiologically acute pain.
Open Access
RELEAF: an algorithm for learning and exploiting relevance
(Cornell University, 2015-02) Tekin, C.; Schaar, Mihaela van der
Recommender systems, medical diagnosis, network security, etc., require on-going learning and decision-making in real time. These -- and many others -- represent perfect examples of the opportunities and difficulties presented by Big Data: the available information often arrives from a variety of sources and has diverse features so that learning from all the sources may be valuable but integrating what is learned is subject to the curse of dimensionality. This paper develops and analyzes algorithms that allow efficient learning and decision-making while avoiding the curse of dimensionality. We formalize the information available to the learner/decision-maker at a particular time as a context vector which the learner should consider when taking actions. In general the context vector is very high dimensional, but in many settings, the most relevant information is embedded into only a few relevant dimensions. If these relevant dimensions were known in advance, the problem would be simple -- but they are not. Moreover, the relevant dimensions may be different for different actions. Our algorithm learns the relevant dimensions for each action, and makes decisions based in what it has learned. Formally, we build on the structure of a contextual multi-armed bandit by adding and exploiting a relevance relation. We prove a general regret bound for our algorithm whose time order depends only on the maximum number of relevant dimensions among all the actions, which in the special case where the relevance relation is single-valued (a function), reduces to O~(T2(2√−1)); in the absence of a relevance relation, the best known contextual bandit algorithms achieve regret O~(T(D+1)/(D+2)), where D is the full dimension of the context vector.
Open Access
Video based wildfire detection at night
(ELSEVIER, 2009-05-06) Günay, O.; Taşdemir K.; Töreyin, B. U.; Çetin, A. Enis
There has been an increasing interest in the study of video based fire detection algorithms as video based surveillance systems become widely available for indoor and outdoor monitoring applications. A novel method explicitly developed for video based detection of wildfires at night (in the dark) is presented in this paper. The method comprises four sub-algorithms: (i) slow moving video object detection, (ii) bright region detection, (iii) detection of objects exhibiting periodic motion, and (iv) a sub-algorithm interpreting the motion of moving regions in video. Each of these sub-algorithms characterizes an aspect of fire captured at night by a visible range PTZ camera. Individual decisions of the sub-algorithms are combined together using a least-mean-square (LMS) based decision fusion approach, and fire/nofire decision is reached by an active learning method.
Open Access
Wildfire detection using LMS based active learning
(IEEE, 2009-04) Töreyin, B. Uğur; Çetin, A. Enis
A computer vision based algorithm for wildfire detection is developed. The main detection algorithm is composed of four sub-algorithms detecting (i) slow moving objects, (ii) gray regions, (iii) rising regions, and (iv) shadows. Each algorithm yields its own decision as a real number in the range [-1,1] at every image frame of a video sequence. Decisions from subalgorithms are fused using an adaptive algorithm. In contrast to standard Weighted Majority Algorithm (WMA), weights are updated using the Least Mean Square (LMS) method in the training (learning) stage. The error function is defined as the difference between the overall decision of the main algorithm and the decision of an oracle, who is the security guard of the forest look-out tower. ©2009 IEEE.