This study proposes a multi-domain approach to improve the performance of a hazardous chemical concentration detection model, enhancing classification accuracy. The proposed method incorporates frequency and wavelet domains to extract diverse features, and by combining features from these three domains, the model can learn more comprehensively, enabling more precise predictions. Experimental results show that the model using the multi-domain approach achieved a significant performance improvement compared to the time-domain-only model. The overall accuracy increased from 84.82% to 89.29%, an improvement of approximately 4.5%.
한국어
본 연구는 유해 화학 물질 농도 검출 모델의 성능 향상을 위해 멀티 도메인(Multi-domain) 방식을 제안 하여 분류 성능을 개선한다. 제안된 방식은 주파수 및 웨이블릿(Wavelet) 도메인을 추가로 활용하여 다양한 특징 을 추출하며, 세 가지 도메인에서 얻은 특징들을 결합함으로써 모델이 복합적인 학습을 수행하여 더욱 정교한 예 측이 가능하다. 연구 결과, 멀티 도메인 방식을 사용한 모델은 시간 도메인만을 사용한 모델에 비해 상당한 성능 향상을 보였으며, 전체 정확도는 시간 도메인만 사용한 경우 84.82%에서 멀티 도메인 방식을 적용했을 때 89.29% 로 약 4.5% 향상되었다.
목차
요약 Abstract Ⅰ. 서론 Ⅱ. 관련 연구 Ⅲ. 시스템 설계 3.1 시스템의 전체적 구성 3.2 Multi Domain Feature 추출 3.3 Multi Domain Feature 결합 3.4 모델 설계 Ⅳ. 성능 평가 4.1 구현 4.2 성능 평가 Ⅴ. 결론 REFERENCES
Ever since next generation convergence technology became one of the most important industries in the nation, computing professionals have encountered a growing number of challenges. Along with scholars and colleagues in related fields, they have gathered in avariety of forums and meetings over the last few decades to share their knowledge, experiences and the outcome of their research. These exchanges have led to the founding of the International Next-generation Convergence technology (INCA) on December 1, 2015. INCA was registered as an incorporated association under the Ministry of Information and Communications. The main purpose of the organization is to improve our society by achieving the highest capability possible in next generation convergence technology.
간행물
간행물명
차세대융합기술학회논문지 [The Journal of Next-generation Convergence Technology Association]