Digital Library[ Search Result ]
An Evaluation Method for Generalization Errors of CNN using Training Data
http://doi.org/10.5626/JOK.2021.48.3.284
Even with high-performance CNNs, generalization errors, which are the errors on test datasets that are expected in the real world, are often high. This generalization error must be reduced so that the model can maintain its learned performance in the real world. This paper defines a response set as a neuron set that is frequently activated for each model class learned from the training dataset with high data diversity. Also, the differences in generalization errors due to the data diversity of the test dataset are considered. The difference is defined as a relative generalization error. In the current work, an evaluation method for CNN generalization error using only the training dataset is proposed by using the relationship between the CNN class response set and the relative generalization error. The case study confirms that the response set ratio is related to the relative generalization error and demonstrates the effectiveness of the evaluation method for generalization errors of CNN using training data.
Patterns of Detecting Feature Interaction in Autonomous Car
Young Woo Lee, Heung Seok Chae
http://doi.org/10.5626/JOK.2019.46.10.1001
In a system with multiple features working together, unexpected behaviors may arise due to feature interaction. An interaction detection method that only considers the dependencies between a system"s components can cause false positives, because interactions are considered to occur between features that are not actually performed simultaneously. In addition, it does not take into account for the interactions that result from the association, such as speed and direction. This paper proposes a pattern with which to detect interaction based on time-series data of the system. In case studies, I classified interaction types by combining interaction attributes, mapped the patterns to identify each interaction, and then performed interaction detection based on the time series data of an autonomous car. For the ACC, OA, LKA, and EVA features of the autonomous car, interactions between speed and direction variables were detected using a non-continuous partitioning pattern and a repetitive partitioning pattern. The interaction resulting from the association between direction and speed variables was detected using a partition conflict pattern.
Study of State Machine Diagram Robustness Testing using Casual Relation of Events
Seon Yeol Lee, Heung Seok Chae
Studies of fault injection into state machine diagram have been studied for generating robustness test cases. Conventional studies have, however, tended to inject too many faults into diagrams because they only have considered structural aspects of diagrams. In this paper, we propose a method that aims to reduce the number of injected fault without a decrease in effectivenss of robustness test. A proposed method is demonstrated using a microwave oven sate machine diagram and evaluated using a hash table state machine diagram. The result of the evaluation shows that the number of injected faults is decreased by 43% and the number of test cases is decreased by 63% without a decrease in effectiveness of hash table robustness test.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr