Standardization of Criteria across Multiple Evaluators to Detect Objects

2023-01-13T08:10:26+00:00

For a typical object detection task with machine learning technique, there has an absolute correct label on which a mechanical model is constructed. However, there are many tasks in which labels vary with evaluators because they have different criteria for discrimination. It happens when the detection criteria are vague and undefined among evaluators. This problem is avoided by constructing an individual model, but it is not recommended from a long-term perspective, because the model depends on a specific evaluator.

This paper proposes a method to standardize the evaluator's criteria. The method is verified in the image detection task of asteroid powders in paint material as an example of ambiguity in the criteria.

The performance and variance of detection with the proposed method are compared with conventional ones to evaluate whether it allows us to standardize the evaluators’ criteria. It turns out a clear reduction in the variance of evaluators’ detection results without significant degradation of the performance for all evaluators. It is confirmed this method standardizes the criteria across multiple evaluators. In addition, the paper discusses how to obtain manuals formally expressing the standardized criteria with text mining.

Scrutinizing UML Teaching and Learning Modeling Tools

2023-01-06T16:05:06+00:00

The purpose of this paper was to identify, synthesize, and analyze the modeling tools, especially those that support UML modeling and interactive learning methods for Software Engineering and Information Systems Design courses. The goals were to guide both professors and students to choose the proper modeling tools to support software engineering courses objectives. The research identified many successful modeling tools that can help students use what is suitable for learning UML modeling and contribute to engaging students in modeling. Moreover, this research used the meta-ethnography method for synthesizing qualitative results in the area of software engineering, especially modeling. Group of modelling tools have been chosen for this paper based on their usages popularity and successfulness in producing high quality design models. The contribution of this paper is highlighting and defining the strengths, weakness, and limitations of each studied tool.

Transactions on Engineering and Computing Sciences

Standardization of Criteria across Multiple Evaluators to Detect Objects

Scrutinizing UML Teaching and Learning Modeling Tools