When Clicks Reveal Student Frustration: A Sensor-Free Analytics Approach with Adaptive Thresholds

Massive Open Online Courses (MOOCs) attract thousands of participants who each exercise autonomy by engaging with resources and with other participants to whatever degree they wish. When analyzing participants’ patterns of engagement in MOOCs it is possible to notice that certain participants exhibit high levels of participation, actively engaging with others in forums. This study focuses on characterizing these highly active participants, and understanding their contributions back to the network in a MOOC designed for teachers’ professional development. Connectivism is used as theoretical lens to describe super-posters’ engagement in forums. Data from participants’ demographics, click-data, and forum posts are used to identify these highly active users. Qualitative content analysis is used to categorize the content of their posts, and social network analysis is used to represent their patterns of engagement. Results show that super-posters are generators of engagement, repurposing the content learned from the MOOC and feeding-forward new resources to the network. Super-posters can be seen as representatives of participation inequality in forums. They position themselves as the most prestigious and most influential nodes in the networks created by participants as they engage in forums. In some networks super-posters served as bridges, connecting people from different discussion threads and helping information to flow through the network. This study provides to MOOC designers and MOOC instructors an affordable method to identify and classify super-posters in any MOOC. Findings of this study could be used by MOOC designers and MOOC instructors to develop pedagogical interventions to give these participants a special role in the next MOOC cohort, which may foster engagement in MOOC forums and nurture the cyclical process of learning described in Connectivism. Regarding implications for research, this study attends the need for qualitative methods when analyzing participants’ engagement in MOOC forums and contributes to our knowledge of participation inequality. It also extends the literature of super-posters by showing their characterization in a MOOC focused on teachers’ professional development.

본 논문에서는 2차원 바코드 영상을 위한 적응적 이진화 방법을 제안한다. 적응형 이진화 방법은 조명의 영향을 최소화하여 이진화를 수행하는 기술이다. 적응적 이진화 방법은 주로 문서 영상에 맞게 발전되어 왔다. 기존 방법들은 적응적 이진화에서 사용되는 박스에 대한 크기 설정 문제를 가지고 있다. 이 문제로 기존 방법들은 이차원 바코드 영상 인식에 적용하기에 부적절하다. 문제점을 극복하기 위해 먼저 박스크기와 기존 방법들의 문제점을 분석하고, 이를 기반으로 적분영상을 사용한 새로운 적응형 이진화 방법을 소개한다. 제안한 방법의 성능 입증을 위해 기존의 방법과 속도, 성능 비교 실험을 수행하였고 실험 결과는 기존 방법보다 우수함을 입증하였다. In this paper, we propose an adaptive thresholding method to binarize two-dimensional barcode images. Adaptive thresholding methods that minimize light effects convert an original image into a binary image. The methods are applied to document image binarization. The methods, however, have problems of determining box size used in adaptive thresholding. thus, they inappropriate to use in recognition of two-dimensional barcode images. To overcome the problem, we analysis the problem and propose a new adaptive threshold method using the integral image. To show the effectiveness of our method, we compared our method with the well-known existing methods in terms of visual quality and processing time. The experimental result indicates that the proposed method is superior to the existing method.

This paper presents a robust adaptive moving human detection and recognition method in videos. The human detection method consists of modified moving average background model with supportive secondary model and an adaptive threshold selection model based on Gaussian distribution. The moving average background model is used for background modeling and the background subtraction system is used to provide foreground image through difference image between current image and background model. The adaptive threshold method is used to simultaneously update the system to environment changes. The modified human model consists of five parts with robust features to facilitate human recognition process. For recognition purpose Support Vector Machine has been used as classifier. Experimental results show the effectiveness of proposed system.

The world is marching towards digital communication and digital video surveillance is an indispensable part of it. Moving object detection and face detection play an important role in the video surveillance applications. It is a part of security oriented applications such as traffic systems, hospitals, banks. Background subtraction algorithm is used in order to detect the foreground. Due to the light intensity variations in dynamically changing environment, background subtraction module needs an adaptive threshold value for each input video frame. The pixel values above the threshold value are detected as foreground pixels. The range of adaptive threshold values usually varies from 10 to 85 in the proposed work. This gives a better detection capability in moving object detection wherein PSNR of 32.39 is obtained when two detected images with and without adaptive threshold are chosen as inputs to the PSNR block. Face detection is treated as an extension module of moving object detection wherein the input face image is subtracted from the test image with the help of adaptive threshold but finally the matching unit is the additional component which decides the match based on the global threshold value which is chosen as 183000 here. Here, instead of detecting the moving body, only face is considered for detection. Since real time videos need to be processed using FPGA kits, an area efficient moving object and face detection system is designed using Spartan 6 FPGA kit. The number of slice registers used has reduced from 365 to 320 in case of moving object detection, from 861 to 537 in case of face detection. The results obtained reveal that the use of adaptive threshold concept results in better detection process with PSNR of 32.39.

Single sensor digital color cameras capture only one of the three primary colors at each pixel and a process called color demosaicking (CDM) is used to reconstruct the full color images. Most CDM algorithms assume the existence of high local spectral redundancy in estimating the missing color samples. However, for images with sharp color transitions and high color saturation, such an assumption may be invalid and visually unpleasant CDM errors will occur. In this paper, we exploit the image nonlocal redundancy to improve the local color reproduction result. First, multiple local direc- tional estimates of a missing color sample are computed and fused according to local gradients. Then, nonlocal pixels similar to the esti- mated pixel are searched to enhance the local estimate. An adaptive thresholding method rather than the commonly used nonlocal means filtering is proposed to improve the local estimate. This allows the final reconstruction to be performed at the structural level as op- posed to the pixel level. Experimental results demonstrate that the proposed local directional interpolation and nonlocal adaptive thresh- olding method outperforms many state-of-the-art CDM methods in reconstructing the edges and reducing color interpolation artifacts, leading to higher visual quality of reproduced color images. © 2011

In the paper, a practical method for road detection is proposed. Many features of vehicle are introduced to detect the preceding vehicles. According to the characteristics of lane marks and vehicles, the improved Sobel operator convolution kernel is introduced in the image preprocessing to enhance the robustness of the algorithm. In order to be feasible to the change of illumination and road conditions, the adaptive double threshold method is introduced to get the binary image, the edges which are needed during detection of lane marks and front vehicles are extracted with Hough Transformation and SUSAN algorithm based on adaptive threshold in different contrast ratio. In order to apply the information to implement the lane departure warming system and forward collision warming system, both distances from host vehicle to left and right lane lines and preceding vehicles are estimated according to the inverse projection. Experiment results indicate that this algorithm is feasible for different road conditions and can realize the detection and tracking of the lane lines and vehicles with robustness and efficiency simultaneously.

<span>Segmentation of blood vessels (BVs) from retinal image is one of the important steps in developing a computer-assisted retinal diagnosis system and has been widely researched especially for implementing automatic BV segmentation methods. This paper proposes an improvement to an existing retinal BV (RBV) segmentation method by combining the trainable B-COSFIRE filter with adaptive thresholding methods. The proposed method can automatically configure its selectivity given a prototype pattern to be detected. Its segmentation performance is comparable to many published methods with the advantage of robustness against noise on retinal background. Instead of using grid search to find the optimal threshold value for a whole dataset, adaptive thresholding (AT) is used to determine the threshold for each retinal image. Two AT methods investigated in this study were ISODATA and Otsu’s method. The proposed method was validated using 40 images from two benchmark datasets for retinal BV segmentation validation, namely DRIVE and STARE. The validation results indicated that the segmentation performance of the proposed unsupervised method is comparable to the original B-COSFIRE method and other published methods, without requiring the availability of ground truth data for new dataset. The Sensitivity and Specificity values achieved for DRIVE and STARE are 0.7818, 0.9688, 0.7957 and 0.9648, respectively.</span>

Fault detection in a grid-connected photovoltaic system using adaptive thresholding method

When using thresholding method to segment an image, a fixed threshold is not suitable if the background is uneven. Here, we propose a new adaptive thresholding method using variational theory. The method requires only one parameter to be selected and the adaptive threshold surface can be found automatically from the original image.

ABSTRACTFew studies have investigated epistemic positioning in online postgraduate courses. Such courses in US contexts rely heavily on asynchronous online discussion forums. This study investigates how postgraduate students’ patterned use of personal experience tellings functioned in the construction of their epistemic positioning (as ‘expert’ or ‘novice’) as they participated in these forums. Analysis is focused on two patterns observed across the data: (a) making assessments of the course content and activities and (b) engaging in troubles telling. By examining how students’ epistemic stance-taking is displayed through these patterned interactions, this study finds that participants’ sharing of personal experiences online functions to make visible their epistemic positioning regarding what is treated as ‘learnable’ in ways that are not possible in face-to-face classrooms. These findings have relevance for what counts as valuable ways of participating in online educational discussions.

Open wikis such as WikiEducator (WE) (http://www.wikieducator.org/Main_Page) lie at the intersection of two significant applications of learning technology: open educational resources (OERs), which are freely available materials that can be shared, modified, adapted, and reused in diverse learning contexts; and collaborative authoring environments. This chapter presents a case study of the use of open wikis in a single online postgraduate course in the College of Education at Massey University (New Zealand). The case discussion includes an illustration of the use of open wiki technology at WikiEducator within the course from two different points of view: the use of wikis as a presentation tool by the course teaching staff; and as a production tool by learners seeking to create OERs as part of an instructional design project. The chapter also links the challenges and opportunities associated with these points of view to wider possibilities and pressures attending the terrain in which contemporary higher education is situated.

We examined the ethical implications of a mythical online student with a carefully concealed real identity who took part in an online post-graduate course. The mythical online student took part in all student activities and provided co-students with cognitive and technical support as a covert second facilitator; consequently, students found scaffolding unobtrusive and integrated the unknown virtual student into the learning community. We explored the ethical implication of undisclosed identity and analyzed Students’ reaction to the disclosure of the mythical student after the course. The study confirmed our success in creating a convincing virtual student, but this success precipitated some shock, disbelief, and dismay. Most students accepted the presence of a virtual student, but some felt betrayed because her real identity was hidden. Recommendations for implementing such a virtual tool ethically are advanced, along with suggestions for teaching situations that may benefit from its use.

People need to engage in lifelong learning to be part of the knowledge society, while educational institutions cannot formally provide continuous ongoing, personally defined learning that addresses immediate workplace-based needs. Designing a formal online post-graduate course around a soccer game metaphor, we incorporated the characteristics of informal lifelong learning, namely peer facilitated and collaborative processes, formative and reflective assessment, learning community and open-ended curriculum driven by learner-determined goals. Students used the metaphor in their social discussions to denote collaborative learning, community, personal purposes and transformative reflective learning. The metaphor familiarised and prepared students for lifelong informal learning by bridging the gap from formal learning.

The role of e-learning in the existing and challenging educational era is crucial. However, it is necessary to overcome some drawbacks such as feelings of isolation and a lack of emotional contact. In this sense, emotion management is a key driver of student satisfaction in e-learning, which is significantly related to students’ motivation, learning, cognitive strategies, self-regulation, and personality antecedents in the classroom. This article examines an online postgraduate course in financial statements auditing, describing the resources used by the e-tutor to conduct affective tutorials, reduce students’ feelings of isolation, increase student involvement, and achieve success in e-learning. The results of a survey administered to 125 students over the period 2015 to 2020 indicate that students who receive emotional support have higher levels of satisfaction with the course in terms of all satisfaction indicators. In addition, female e-learning students are more satisfied with intensive e-tutor monitoring overall but are less gratified by non-face-to-face e-tools. Our study responds to the calls in the 2021–2027 Digital Education Action Plan to improve and reset education and training for the digital age.

The method of wavelet thresholding for removing noise, or denoising, has been researched extensively due to its effectiveness and simplicity. Much of the work has been concentrated on finding the best uniform threshold or best basis. However, not much has been done to make this method adaptive to spatially changing statistics which is typical of a large class of images. This work proposes a spatially adaptive wavelet thresholding method based on context modeling, a common technique used in image compression to adapt the coder to the non-stationarity of images. We model each coefficient as a random variable with the generalized Gaussian prior with unknown parameters. Context modeling is used to estimate the parameters for each coefficient, which are then used to adapt the thresholding strategy. Experimental results show that spatially adaptive wavelet thresholding yields significantly superior image quality and lower MSE than optimal uniform thresholding.