• Journal of IKEEE
• /
• v.19 no.2
• /
• pp.186-192
• /
• 2015

This paper proposes an automatic generation technology of test case based on API in source code for software's quality improvement. The proposed technology is comprised of four processes which are analyzing source code by using the Doxygen open source tool, defining API specification by using analyzed results, creating test design, generating a test case by adapting Pairwise test technology. Analyzing source code by using the Doxygen open source tool is the phase in which API information in source code such as the API name, input parameter and return parameter are extracted. Defined API specification by using analyzed results is the phase where API informations, which is needed to generate test case, are defined as a form of database by SQLite database on the basis of extracted API information. Creating test design is the phase in which the scenario is designed in order to be composed as database by defining threshold of input and return parameters and setting limitations based on the defined API. Generating a test case by adapting Pairwise test technique is the phase where real test cases are created and changed into database by adapting Pairwise technique on the base of test design information. To evaluate the efficiency of proposed technology, the research was conducted by begin compared to specification based test case creation. The result shows wider test coverage which means the more cases were created in the similar duration of time. The reduction of manpower and time for developing products is expected by changing the process of quality improving in software developing from man-powered handwork system into automatic test case generation based on API of source code.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.1
• /
• pp.69-75
• /
• 2023

In recent years, there has been a growing interest in deep learning-based animal pose estimation, especially in the areas of animal behavior analysis and healthcare. However, existing animal pose estimation techniques do not perform well when body parts are occluded or not present. In particular, the occlusion of dog tail or ear might lead to a significant degradation of performance in pet behavior and emotion recognition. In this paper, to solve this intractable problem, we propose a simple yet novel framework for pet pose estimation where pet pose is predicted on an outpainted image where some body parts hidden outside the input image are reconstructed by the image inpainting network preceding the pose estimation network, and we performed a preliminary study to test the feasibility of the proposed approach. We assessed CE-GAN and BAT-Fill for image outpainting, and evaluated SimpleBaseline for pet pose estimation. Our experimental results show that pet pose estimation on outpainted images generated using BAT-Fill outperforms the existing methods of pose estimation on outpainting-less input image.

• Proceedings of the KIPE Conference
• /
• 2009.11a
• /
• pp.105-110
• /
• 2009

The On Line Electric Vehicles(OLEV) that can pick up inductive power from underground coils on driving with high efficiency have been developed this year, and is now proposed in this paper. The IPS(Inductive Power Supply) system consists of power supply inverters, power supply rails, pick up modules, and a regulator. There are 3 generations of IPS have been developed so far, and the $4^{th}$ generation IPS is being developed. The $1^{st}$ generation has been demonstrated this Feb. 27, which is equipped with mechanically auto tracking pick-up module with 1cm air gap, and showed 80% power efficiency. The $2^{nd}$ generation IPS applied to an 120kW (average)/240kW(peak) motor powered electric bus has 17cm air gap with 72% power efficiency. For the $2^{nd}$ generation IPS, the Power supply inverter has 440V, 3phase input and 200A @ 20kHz output. The test power supply rail of 240m long is segmented by 60m each, where newly developed core structure and power cable are constructed under the road covered with asphalt of 5cm thickness. The pick-up modules which consist of core, winding wire, and rectifiers are fixed to the bottom of the bus which can carry more than 40 passengers and can pick up max. 60kW. To remove parasitic component and to transfer maximum power between them resonant circuit topology is applied to the primary and secondary sides. The EMF level is below 62.5mG at 1.75m from the center of the road to meet the regulation. Several effective ways of reducing EMF levels have been developed. In addition, effective ways to solve problems related high frequency power cables buried in ground and it's proof from soil have been studied also. This development shows that the IPS system is capable of supplying enough power to the pick-up of OLEV and can reduce battery size, weight and cost, which means the IPS with OLEV is one of the best candidate for EV.

• Journal of The Korean Association For Science Education
• /
• v.44 no.3
• /
• pp.231-248
• /
• 2024

This study developed a chatbot for first-year high school students, employing open-source software and the Korean Sentence-BERT model for AI-powered document classification. The chatbot utilizes the Sentence-BERT model to find the six most similar Q&A pairs to a student's query and presents them in a carousel format. The initial dataset, built from online resources, was refined and expanded based on student feedback and usability throughout over the operational period. By the end of the 2023 academic year, the chatbot integrated a total of 30,819 datasets and recorded 3,457 student interactions. Analysis revealed students' inclination to use the chatbot when prompted by teachers during classes and primarily during self-study sessions after school, with an average of 2.1 to 2.2 inquiries per session, mostly via mobile phones. Text mining identified student input terms encompassing not only science-related queries but also aspects of school life such as assessment scope. Topic modeling using BERTopic, based on Sentence-BERT, categorized 88% of student questions into 35 topics, shedding light on common student interests. A year-end survey confirmed the efficacy of the carousel format and the chatbot's role in addressing curiosities beyond integrated science learning objectives. This study underscores the importance of developing chatbots tailored for student use in public education and highlights their educational potential through long-term usage analysis.