Efficiently detecting outlying behavior in video-game players

Kim, Young Bin; Kang, Seong-Hoon; Lee, Sang Hyeok; Jung, Jang Young; Kam, Hyeong Ryeol; Lee, Jung; Kim, Young Sun; Lee, Joonsoo; Kim, Chang Hun

doi:10.7717/peerj.1502

Cited by 11 publications

(10 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We did not use artificial neural network ( Hernandez-Serna & Jimenez-Segura, 2014 ) since it may suffer from overfitting. The principle of the standard SVM involves setting up two parallel planes so that each is nearest to one of two datasets with the two planes being as far apart as possible ( Kim et al, 2015 ; Modinos et al, 2013 ; Wu & Zhang, 2012 ; Zhang & Wang, 2015 ). The planes are described as which lie midway between the bounding planes provided by …”

Section: Methodsmentioning

confidence: 99%

Morphological analysis of dendrites and spines by hybridization of ridge detection with twin support vector machine

Wang

Chen

et al. 2016

PeerJ

View full text Add to dashboard Cite

Dendritic spines are described as neuronal protrusions. The morphology of dendritic spines and dendrites has a strong relationship to its function, as well as playing an important role in understanding brain function. Quantitative analysis of dendrites and dendritic spines is essential to an understanding of the formation and function of the nervous system. However, highly efficient tools for the quantitative analysis of dendrites and dendritic spines are currently undeveloped. In this paper we propose a novel three-step cascaded algorithm–RTSVM— which is composed of ridge detection as the curvature structure identifier for backbone extraction, boundary location based on differences in density, the Hu moment as features and Twin Support Vector Machine (TSVM) classifiers for spine classification. Our data demonstrates that this newly developed algorithm has performed better than other available techniques used to detect accuracy and false alarm rates. This algorithm will be used effectively in neuroscience research.

show abstract

Section: Methodsmentioning

confidence: 99%

Morphological analysis of dendrites and spines by hybridization of ridge detection with twin support vector machine

Wang

Chen

et al. 2016

PeerJ

View full text Add to dashboard Cite

show abstract

“…They use a rigid registration transform to cope with small out of plane head rotations and change in scale. In [10] authors use the sum of movement variations of landmark points that belong to a certain facial component as input features for a neural network. Other approaches use optical flow estimation techniques applied on a face image directly and use it to detect facial movements.…”

Section: Image Processing Techniques For Facial Expressionsmentioning

confidence: 99%

“…Since a real-time approach is more important than an accurate one for pose estimation, we use a simple geometric method that can estimate the coarse pose of student's head by analyzing the angles of a triangle made by connecting the eyes and the tip of the nose. The same approach is used in [10]. Due to the symmetry of the human face, a triangle formed by connecting the eyes and the tip of the nose in a frontal picture is isosceles.…”

Section: Detection Of Concentration Signs and Facial Expression Analysismentioning

confidence: 99%

Using Computer Vision for Student-Centred Remote Lab in Electronics

Khattar

Luthon

Larroque³

et al. 2016

EDULEARN Proceedings

View full text Add to dashboard Cite

Technology is affecting students' life in different ways. Nowadays, students are more interested in social media, games and Internet of Things. On the other hand, most current teaching techniques appear outdated and uninteresting to students due to the fact that they do not follow the technological advances. For these reasons, students nowadays do not show much interest in education and learning. On the other hand, there is an urgent need for new learning approaches that take into account both the interests of today's students and the technological advances in several fields like telecommunication and gaming. Particularly for STEM curricula (Science, Technology, Engineering, and Math), labs play a crucial role to help students fully understand the material given during lectures. However, traditional hands-on labs are tied to space-time constraints: a student must perform the lab activity in a pre-scheduled time and in a given space. Furthermore, traditional labs are not suited for all students: some students may need more help and more motivating factors in order to take the most of the lab experience and to enhance their learning outcomes. This is not always best done in hands-on labs due to large number of students and to the presence of only one teacher that has to do lots of effort to adapt to each student's needs. Remote labs provide an alternative experience to the traditional lab, eliminating time-space constraints and introducing students to a new way of working by manipulating hardware remotely, which is used frequently in industry (SCADA: Supervisory Control and Data Acquisition). It can also be adapted to each student's needs if one is capable to infer student's mood, emotion and competence. In this paper we present the implementation of a remote lab in electronics, called LaboREM, which takes advantage of the technological advances in telecommunication and takes into consideration what current students are interested in. It is based on three parts: a remote laboratory, a learning management system and a game-like approach. The remote laboratory consists of remotely-controlled measurement devices, plus a simple robotic arm that mimics the student hand to construct electronic circuits. The robotic arm picks up electronics components equipped with magnets and places them on a breadboard. A wide angle camera is installed in order that students see what is physically happening in the lab. The electronic lab activity consists of short-time experiments (mainly tests on active filters) that last less than 5 minutes. The scenario is based on a game-like approach: a treasure hunt and a Top 10. Furthermore, a mini drone that can be controlled by the student remotely complements the static camera to add more immersion to the lab experience. The student can send specific requests to the drone in order to see some electronic instruments in a more interesting way. Moreover image processing and pattern recognition techniques are also used to infer student mood, concentration and motivation. Clues of boredom, lack of ...

show abstract

“…The study also assists in formulating correlation among different online users. Kim et al [42] have developed a technique that can perform identification of outlying behaviour of user. The analytical module design by the authors considers the inputs as movement of users from webcam and that apply multimodal feature for collecting data followed by data refinement.…”

Section: Existing Techniques Of Vamentioning

confidence: 99%

“…Not tested for analytics Aryanfar et al [38] support vector machine and naïve Bayes -Good Recognition rate Not tested for analytics Ayed et al [39] Mining with MapReduce, Wavelets -Reduce processing time -No comparative analysis -No complexity Analysis Cai et al [40] Statistical Analysis Good precision -No comparative analysis -No complexity Analysis Chen et al [41] PeakVizor, Glyph visualization -Interactive detection of user's online behaviour -Doesn't work online -cannot perform classification -No complexity Analysis Kim et al [42] Morphological study of facial expression -ideal for online games -No comparative analysis -No complexity Analysis Mao et al [43] Video traceability Accurate target extraction -Doesn't include high level of data extraction or mining.…”

Section: Existing Techniques Of Vamentioning

confidence: 99%

Insights to Video Analytic Modelling Approach with Future Line of Research

Chandra¹,

Reddy²

2016

IJCA

View full text Add to dashboard Cite

The area of Video analytics has made some significant improvement due to advancement in image processing and datamining techniques. However, the inclination is still towards image contents and less to mined contents owing to many unsolved issues. Although concept of mining is more than 2 decade old, but mining approaches are yet to be standardized in the area of video surveillance system. With evolution of newer set of challenges in video capturing, existing mining models finds itself less applicable due to unstructured format of dynamic frames. Hence, this paper discusses about video analytics and presents a brief discussion of frequently used mining approaches in video as well as discussed some recent studies in this direction in order to scale the degree of effectiveness in existing system. The paper also presents research gap and provided solution as future line of research as a possible way to overcome the research gap.

show abstract

Efficiently detecting outlying behavior in video-game players

Cited by 11 publications

References 41 publications

Morphological analysis of dendrites and spines by hybridization of ridge detection with twin support vector machine

Morphological analysis of dendrites and spines by hybridization of ridge detection with twin support vector machine

Using Computer Vision for Student-Centred Remote Lab in Electronics

Insights to Video Analytic Modelling Approach with Future Line of Research

Contact Info

Product

Resources

About