Top 10 jees.kr Wettbewerber

kiees.or.kr

한국전자파학회 홈페이지에 오신 것을 환영합니다.

janss.kr

Exploration of the lunar poles is accelerating as multiple missions target these regions, with growing interest in studying the environment within permanently shadowed regions (PSRs)—areas at the poles that never receive direct sunlight. To prepare for these exploration activities within PSRs, we determined radiance levels in PSRs of various sizes and derived a conversion factor from ShadowCam radiance units to luminance, which is more suitable for evaluating human factors, as luminance accounts for the wavelength range to which humans are sensitive. Notably, during lunar summer, many PSRs reach luminance levels comparable to those of well-lit buildings for several Earth days each month, while peak winter lighting is typically up to six times dimmer, except in regions where regional shadows predominate and further decrease illumination. As a result, we do not expect artificial light to be needed for missions visiting PSRs during the summer peak lighting period, except for close inspection of samples. In contrast, in winter, diminished ambient lighting may require supplemental illumination for many tasks.

accesson.kr

국가 오픈액세스 플랫폼(AccessON)은 우리나라 연구자 누구나 전 세계의 오픈액세스 논문을 한 곳에서 편리하게 검색하고, 원문을 무료로 이용할 수 있도록 지원합니다.

telecom-paris.hal.science

Machine Learning-based Network Intrusion Detection Systems (ML-based NIDS) rely heavily on the quality of the datasets used for training and evaluation. However, widely used NIDS benchmarks often suffer from poor data diversity, which limits model generalization and undermines the reliability of evaluation protocols. While prior work has acknowledged this limitation, a systematic framework to quantify dataset diversity and analyze its relationship with performance is still missing. To address this gap, we introduce a structured approach for characterizing dataset diversity in ML-based NIDS, grounded in measurement theory. We distinguish three types of diversity-intra-class, inter-class, and domain-shift-and operationalize their measurement using established metrics such as the Vendi Score and the Jensen-Shannon divergence. Our empirical analysis on the CIC-IDS2018 dataset, spanning sixty diversity-controlled train-test experiments, provides new insights into the relationship between diversity and generalization and demonstrates the value of diversity-aware data sampling for improving evaluation reliability.

isy.liu.se

descr