An online learning platform for teaching, learning, and assessment of programming
- Robinson, Philip E., Carroll, Johnson
- Authors: Robinson, Philip E. , Carroll, Johnson
- Date: 2017
- Subjects: Online learning platform , Automated assessment , Programming
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/236077 , uj:24151 , Citation: Robinson, P.E. & Carroll, J. 2017. An online learning platform for teaching, learning, and assessment of programming.
- Description: Abstract: In this paper the use of an open-source online learning platform to aid in teaching and assessment of computer programming in large classes is discussed. The pedagogical philosophy of how the subject of computer programming is taught is presented. Based on the skills and learning processes that are identified for effective teaching of computer programming, a strategy for employing modern web technology coupled with an automated assessment capability to meet these goals is discussed. The paper describes the technology and implementation of the learning platform and new methods for automated assessment of programming assignments and exams. Finally, the application of the system to achieve the pedagogical goals and the benefits of using the system for teaching large classes is reported.
- Full Text:
- Authors: Robinson, Philip E. , Carroll, Johnson
- Date: 2017
- Subjects: Online learning platform , Automated assessment , Programming
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/236077 , uj:24151 , Citation: Robinson, P.E. & Carroll, J. 2017. An online learning platform for teaching, learning, and assessment of programming.
- Description: Abstract: In this paper the use of an open-source online learning platform to aid in teaching and assessment of computer programming in large classes is discussed. The pedagogical philosophy of how the subject of computer programming is taught is presented. Based on the skills and learning processes that are identified for effective teaching of computer programming, a strategy for employing modern web technology coupled with an automated assessment capability to meet these goals is discussed. The paper describes the technology and implementation of the learning platform and new methods for automated assessment of programming assignments and exams. Finally, the application of the system to achieve the pedagogical goals and the benefits of using the system for teaching large classes is reported.
- Full Text:
Implementation of specifications grading for assessment of programming using an online learning platform
- Robinson, Philip E., Carroll, Johnson
- Authors: Robinson, Philip E. , Carroll, Johnson
- Date: 2017
- Subjects: Computer science education , Specifications grading , Online learning platform
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/${Handle} , uj:24937 , Citation: Robinson, P.E. & Carroll, J. 2017. Implementation of specifications grading for assessment of programming using an online learning platform.
- Description: Abstract: Computer programming is inherently ill-suited to traditional assessment with partial credit, as real-world programming tasks have a binary evaluation scheme (works or does not work) allowing multiple attempts. In this study, the specifications grading paradigm is presented as an alternative method of assessing computer programming in a more authentic manner. The authors propose a specifications grading scheme for an introductory programming course, and describe the implementation of this scheme using a custom online learning platform with automated grading capabilities. A set of criteria are defined for assessing the quality of a grading system and these criteria are used to discuss the merits of the proposed grading system. The authors argue that the proposed system is superior to the traditional assessment models in terms of fostering authentic learning, providing more accurate and reliable assessment, and saving the instructor time.
- Full Text:
- Authors: Robinson, Philip E. , Carroll, Johnson
- Date: 2017
- Subjects: Computer science education , Specifications grading , Online learning platform
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/${Handle} , uj:24937 , Citation: Robinson, P.E. & Carroll, J. 2017. Implementation of specifications grading for assessment of programming using an online learning platform.
- Description: Abstract: Computer programming is inherently ill-suited to traditional assessment with partial credit, as real-world programming tasks have a binary evaluation scheme (works or does not work) allowing multiple attempts. In this study, the specifications grading paradigm is presented as an alternative method of assessing computer programming in a more authentic manner. The authors propose a specifications grading scheme for an introductory programming course, and describe the implementation of this scheme using a custom online learning platform with automated grading capabilities. A set of criteria are defined for assessing the quality of a grading system and these criteria are used to discuss the merits of the proposed grading system. The authors argue that the proposed system is superior to the traditional assessment models in terms of fostering authentic learning, providing more accurate and reliable assessment, and saving the instructor time.
- Full Text:
An online system for monitoring and assessing the programming process
- Robinson, Philip E., Carroll, Johnson
- Authors: Robinson, Philip E. , Carroll, Johnson
- Date: 2016
- Subjects: Computer Science Education , Learning Management System (LMS) , Online Assessment
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/224393 , uj:22603 , Citation: Robinson, P.E. & Carroll, J. 2016. An online system for monitoring and assessing the programming process.
- Description: Abstract: Traditional assessment of programming ability, as well as more recent automated assessment systems, consider only the completed program submitted by the student. We present a system which automatically monitors and assesses the codeproduction process as well as the final product, allowing adaptive feedback and assessment of programming competency. Our assessment system is based on open-source components which provide a full online programming environment and allows for a flexible scripting interface to the assessment process, which can monitor student actions during the programming task. The system was implemented for an introductory programming class of nearly 400 students, and an example of the automated assessment is presented.
- Full Text:
- Authors: Robinson, Philip E. , Carroll, Johnson
- Date: 2016
- Subjects: Computer Science Education , Learning Management System (LMS) , Online Assessment
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/224393 , uj:22603 , Citation: Robinson, P.E. & Carroll, J. 2016. An online system for monitoring and assessing the programming process.
- Description: Abstract: Traditional assessment of programming ability, as well as more recent automated assessment systems, consider only the completed program submitted by the student. We present a system which automatically monitors and assesses the codeproduction process as well as the final product, allowing adaptive feedback and assessment of programming competency. Our assessment system is based on open-source components which provide a full online programming environment and allows for a flexible scripting interface to the assessment process, which can monitor student actions during the programming task. The system was implemented for an introductory programming class of nearly 400 students, and an example of the automated assessment is presented.
- Full Text:
Foreground segmentation in atmospheric turbulence degraded video sequences to aid in background stabilization
- Robinson, Philip E., Nel, Andre L.
- Authors: Robinson, Philip E. , Nel, Andre L.
- Date: 2016
- Subjects: Atmospheric turbulence , Video stabilization , Background subtraction
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/217644 , uj:21665 , Citation: Robinson, P.E. & Nel, A.L. 2016. Foreground segmentation in atmospheric turbulence degraded video sequences to aid in background stabilization.
- Description: Abstract: Video sequences captured over a long range through the turbulent atmosphere contain some degree of atmospheric turbulence degradation (ATD). Stabilization of the geometric distortions present in video sequences containing ATD and containing objects undergoing real motion is a challenging task. This is due to the difficulty of discriminating what visible motion is real motion and what is caused by ATD warping. Due to this, most stabilization techniques applied to ATD sequences distort real motion in the sequence. In this study we propose a new method to classify foreground regions in ATD video sequences. This classification is used to stabilize the background of the scene while preserving objects undergoing real motion by compositing them back into the sequence. A hand annotated dataset of three ATD sequences is produced with which the performance of this approach can be quantitatively measured and compared against the current state-of-the-art.
- Full Text:
- Authors: Robinson, Philip E. , Nel, Andre L.
- Date: 2016
- Subjects: Atmospheric turbulence , Video stabilization , Background subtraction
- Language: English
- Type: Article
- Identifier: http://hdl.handle.net/10210/217644 , uj:21665 , Citation: Robinson, P.E. & Nel, A.L. 2016. Foreground segmentation in atmospheric turbulence degraded video sequences to aid in background stabilization.
- Description: Abstract: Video sequences captured over a long range through the turbulent atmosphere contain some degree of atmospheric turbulence degradation (ATD). Stabilization of the geometric distortions present in video sequences containing ATD and containing objects undergoing real motion is a challenging task. This is due to the difficulty of discriminating what visible motion is real motion and what is caused by ATD warping. Due to this, most stabilization techniques applied to ATD sequences distort real motion in the sequence. In this study we propose a new method to classify foreground regions in ATD video sequences. This classification is used to stabilize the background of the scene while preserving objects undergoing real motion by compositing them back into the sequence. A hand annotated dataset of three ATD sequences is produced with which the performance of this approach can be quantitatively measured and compared against the current state-of-the-art.
- Full Text:
Blind deconvolution of Gaussian blurred images containing additive white Gaussian noise
- Robinson, Philip E., Roodt, Yuko
- Authors: Robinson, Philip E. , Roodt, Yuko
- Date: 2013
- Subjects: Gaussian blur , Gaussian noise , Bind deconvolution
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16753 , uj:15807 , Robinson, P.E. & Roodt, Y. Blind deconvolution of Gaussian blurred images containing additive white Gaussian noise. IEEE International Conference on Industrial Technology (ICIT 2013), 2013, pp. 1092-1097.
- Description: Abstract: Image restoration algorithms are used to reconstruct the information that is suppressed when an observed image is subjected to blurring. These algorithms generally assume that knowledge of the nature of the distortion and noise contained in an observed image is available. When this information is not available and has to be directly estimated from the image being processed the problem becomes one of blind deconvolution. This paper makes use of a novel blur identification technique and a noise identification technique to perform blind deconvolution on single images that have been degraded by a Gaussian blur and contain additive white Gaussian noise.
- Full Text:
- Authors: Robinson, Philip E. , Roodt, Yuko
- Date: 2013
- Subjects: Gaussian blur , Gaussian noise , Bind deconvolution
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16753 , uj:15807 , Robinson, P.E. & Roodt, Y. Blind deconvolution of Gaussian blurred images containing additive white Gaussian noise. IEEE International Conference on Industrial Technology (ICIT 2013), 2013, pp. 1092-1097.
- Description: Abstract: Image restoration algorithms are used to reconstruct the information that is suppressed when an observed image is subjected to blurring. These algorithms generally assume that knowledge of the nature of the distortion and noise contained in an observed image is available. When this information is not available and has to be directly estimated from the image being processed the problem becomes one of blind deconvolution. This paper makes use of a novel blur identification technique and a noise identification technique to perform blind deconvolution on single images that have been degraded by a Gaussian blur and contain additive white Gaussian noise.
- Full Text:
Adaptive multi-scale retinex algorithm for contrast enhancement of real world scenes
- Robinson, Philip E., Lau, Wing J.
- Authors: Robinson, Philip E. , Lau, Wing J.
- Date: 2012
- Subjects: Contrast enhancement , Multi-scale retinex algorithm , Retinex theory
- Type: Article
- Identifier: uj:4673 , http://hdl.handle.net/10210/10438
- Description: Contrast enhancement is a classic image restoration technique that traditionally has been performed using forms of histogram equalization. While effective these techniques often introduce unrealistic tonal rendition in real-world scenes. This paper explores the use of Retinex theory to perform contrast enhancement of real-world scenes. We propose an improvement to the Multi-Scale Retinex algorithm which enhances its ability to perform dynamic range compression while not introducing halo artifacts and greying. The algorithm is well suited to be implemented on the GPU and by doing so real-time processing speeds are achieved.
- Full Text:
- Authors: Robinson, Philip E. , Lau, Wing J.
- Date: 2012
- Subjects: Contrast enhancement , Multi-scale retinex algorithm , Retinex theory
- Type: Article
- Identifier: uj:4673 , http://hdl.handle.net/10210/10438
- Description: Contrast enhancement is a classic image restoration technique that traditionally has been performed using forms of histogram equalization. While effective these techniques often introduce unrealistic tonal rendition in real-world scenes. This paper explores the use of Retinex theory to perform contrast enhancement of real-world scenes. We propose an improvement to the Multi-Scale Retinex algorithm which enhances its ability to perform dynamic range compression while not introducing halo artifacts and greying. The algorithm is well suited to be implemented on the GPU and by doing so real-time processing speeds are achieved.
- Full Text:
Robust single image noise estimation from approximate local statistics
- Roodt, Yuko, Clarke, Wimpie, Robinson, Philip E., Nel, André
- Authors: Roodt, Yuko , Clarke, Wimpie , Robinson, Philip E. , Nel, André
- Date: 2012
- Subjects: Gaussian noise , Imaging sensors
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16706 , uj:15802 , Roodt, Y., Robinson, P.E. & Nel, A. Robust single image noise estimation from approximate local statistics. Proceedings of the Twenty-Third Annual Symposium of the Pattern Recognition Association of South Africa, November 2012, pp 47-53.
- Description: Abstract: A novel method for estimating the variance and standard deviation of the additive white Gaussian noise contained in an image will be presented. Only a single image is used to estimate the noise properties. Local image outliers are discarded, this allows us to separate the additive zero mean white Gaussian noise contained in a noisy image from the original image structure. Local variance estimates can then be calculated from the extracted noise. These local variance estimates are weak and can be influenced by misclassified image information. Robust statistics are then used to fuse the weak local variance estimates to obtain a robust global noise variance estimate. This method of estimating the noise properties is computationally efficient and provides reliable estimation results in synthetic and real-world imagery. The accuracy and processing complexity of the proposed algorithm will be compared against the current state-of-the-art noise estimators.
- Full Text:
- Authors: Roodt, Yuko , Clarke, Wimpie , Robinson, Philip E. , Nel, André
- Date: 2012
- Subjects: Gaussian noise , Imaging sensors
- Language: English
- Type: Conference proceedings
- Identifier: http://hdl.handle.net/10210/16706 , uj:15802 , Roodt, Y., Robinson, P.E. & Nel, A. Robust single image noise estimation from approximate local statistics. Proceedings of the Twenty-Third Annual Symposium of the Pattern Recognition Association of South Africa, November 2012, pp 47-53.
- Description: Abstract: A novel method for estimating the variance and standard deviation of the additive white Gaussian noise contained in an image will be presented. Only a single image is used to estimate the noise properties. Local image outliers are discarded, this allows us to separate the additive zero mean white Gaussian noise contained in a noisy image from the original image structure. Local variance estimates can then be calculated from the extracted noise. These local variance estimates are weak and can be influenced by misclassified image information. Robust statistics are then used to fuse the weak local variance estimates to obtain a robust global noise variance estimate. This method of estimating the noise properties is computationally efficient and provides reliable estimation results in synthetic and real-world imagery. The accuracy and processing complexity of the proposed algorithm will be compared against the current state-of-the-art noise estimators.
- Full Text:
- «
- ‹
- 1
- ›
- »