Feature recognition in 3D surface models using self-organizing maps
- Authors: Buhr, Richard Otto
- Date: 2008-11-18T09:06:20Z
- Subjects: Self-organizing maps , Neural networks (Computer science) , Computer vision
- Type: Thesis
- Identifier: uj:14724 , http://hdl.handle.net/10210/1729
- Description: M.Ing. , This project investigates the use of Self-Organizing Maps (SOM) for feature recognition and analysis in 3D objects. Object data was generated to simulate data obtained from 3D scanning and trained using SOM. The trained data was analysed using speci cally developed software. The feature recognition and analysis process can be summarized as follows: a 3D object le is converted to a pure 3D data le, this data le is trained using the SOM algorithm after which the output is analyzed using a 3D object viewer and SOM data display.
- Full Text:
- Authors: Buhr, Richard Otto
- Date: 2008-11-18T09:06:20Z
- Subjects: Self-organizing maps , Neural networks (Computer science) , Computer vision
- Type: Thesis
- Identifier: uj:14724 , http://hdl.handle.net/10210/1729
- Description: M.Ing. , This project investigates the use of Self-Organizing Maps (SOM) for feature recognition and analysis in 3D objects. Object data was generated to simulate data obtained from 3D scanning and trained using SOM. The trained data was analysed using speci cally developed software. The feature recognition and analysis process can be summarized as follows: a 3D object le is converted to a pure 3D data le, this data le is trained using the SOM algorithm after which the output is analyzed using a 3D object viewer and SOM data display.
- Full Text:
A proposed sector wide risk model based on enterprise wide risk management
- Authors: Buhr, Richard Otto
- Date: 2012-06-04
- Subjects: Risk management , Risk assessment , Crisis management
- Type: Thesis
- Identifier: uj:2331 , http://hdl.handle.net/10210/4789
- Description: D.Ing. , For executive management to guide an enterprise, strategic planning is essential. Using Enterprise Wide Risk Management (EWRM) as an input to Scenario Analysis (SA) for Strategic Planning (SP) allows for improved accuracy over conventional methods. This would allow for greater realism from the executive management perspective of possible outcomes in scenario modelling by providing a solid quantitative base founded on real operational information. Emerging regulatory legislation for corporates also require quantitative risk management in the enterprise for reporting and rating purposes, providing a wealth of information for scenario modelling purposes. From the outset this research focuses on the industrial sectors in South Africa, though the model could be applied to any industry sector internationally. The core of any industrial enterprise is made up of the Operational Support Systems (OSS) that provide the hardware and software infrastructure to operate the business. The smooth operation and efficient handling of any unforeseen events in the OSS impacts the very survival of the en- terprise in a highly competitive environment. The development of an OSS risk management (RM) strategy to provide an efficient and effective way to recognise, classify and mitigate the risks involved in OSS is thus crucial to any enterprise that seeks to remain competitive. To implement this RM strategy and provide information regarding likely loss events, a quantitative risk model is required to simulate different scenarios. This research investigates the development of a Sector Wide Risk Model (SWRM) to simulate stress events in an industry sector and their impact on sector members.
- Full Text:
- Authors: Buhr, Richard Otto
- Date: 2012-06-04
- Subjects: Risk management , Risk assessment , Crisis management
- Type: Thesis
- Identifier: uj:2331 , http://hdl.handle.net/10210/4789
- Description: D.Ing. , For executive management to guide an enterprise, strategic planning is essential. Using Enterprise Wide Risk Management (EWRM) as an input to Scenario Analysis (SA) for Strategic Planning (SP) allows for improved accuracy over conventional methods. This would allow for greater realism from the executive management perspective of possible outcomes in scenario modelling by providing a solid quantitative base founded on real operational information. Emerging regulatory legislation for corporates also require quantitative risk management in the enterprise for reporting and rating purposes, providing a wealth of information for scenario modelling purposes. From the outset this research focuses on the industrial sectors in South Africa, though the model could be applied to any industry sector internationally. The core of any industrial enterprise is made up of the Operational Support Systems (OSS) that provide the hardware and software infrastructure to operate the business. The smooth operation and efficient handling of any unforeseen events in the OSS impacts the very survival of the en- terprise in a highly competitive environment. The development of an OSS risk management (RM) strategy to provide an efficient and effective way to recognise, classify and mitigate the risks involved in OSS is thus crucial to any enterprise that seeks to remain competitive. To implement this RM strategy and provide information regarding likely loss events, a quantitative risk model is required to simulate different scenarios. This research investigates the development of a Sector Wide Risk Model (SWRM) to simulate stress events in an industry sector and their impact on sector members.
- Full Text:
- «
- ‹
- 1
- ›
- »