查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Support Vector Machine s is the subject of a report. According to news originating from Nanjing, People ’s Republic of China, by NewsRx correspondents, research stated, “Forest fires t hreaten global ecosystems, socio-economic structures, and public safety. Accurat ely assessing forest fire susceptibility is critical for effective environmental management.” Our news journalists obtained a quote from the research from the Ministry of Edu cation, “Supervised learning methods dominate this assessment, relying on a subs tantial dataset of forest fire occurrences for model training. However, obtainin g precise forest fire location data remains challenging. To address this issue, semi-supervised learning emerges as a viable solution, leveraging both a limited set of collected samples and unlabeled data containing environmental factors fo r training. Our study employed the transductive support vector machine (TSVM), a key semi-supervised learning method, to assess forest fire susceptibility in sc enarios with limited samples. We conducted a comparative analysis, evaluating it s performance against widely used supervised learning methods. The assessment ar ea for forest fire susceptibility lies in Dayu County, Jiangxi Province, China, renowned for its vast forest cover and frequent fire incidents. We analyzed and generated maps depicting forest fire susceptibility, evaluating prediction accur acies for both supervised and semi-supervised learning methods across various sm all sample scenarios (e.g., 4, 8, 12, 16, 20, 24, 28, and 32 samples). Our findi ngs indicate that TSVM exhibits superior prediction accuracy compared to supervi sed learning with limited samples, yielding more plausible forest fire susceptib ility maps. For instance, at sample sizes of 4, 16, and 28, TSVM achieves predic tion accuracies of approximately 0.8037, 0.9257, and 0.9583, respectively. In co ntrast, random forests, the top performers in supervised learning, demonstrate a ccuracies of approximately 0.7424, 0.8916, and 0.9431, respectively, for the sam e small sample sizes. Additionally, we discussed three key aspects: TSVM paramet er configuration, the impact of unlabeled sample size, and performance within ty pical sample sizes.”
NETL
NSTL