返回
聖五風采

The 22nd International Conference on Advanced Data Mining and Applications 2026

發佈時間:2026-11-13
The 22nd International Conference on Advanced Data Mining and Applications 2026 - 1
預覽(滑鼠經過縮圖可切換;點擊可放大)
1 / 5
上一頁
第 1 / 1 頁
下一頁

  

【學生研究走進國際學術會議|ADMA 2026】☀️

      我校學生羅康裕、高梓博及林平治,在程淑鍵老師指導下,赴香港參與第二十二屆先進數據挖掘及應用國際會議(ADMA 2026),以海報分享團隊研究成果。

      本屆會議由香港理工大學及香港科技大學學者擔任大會主席,程序委員會主席則來自香港理工大學、清華大學及澳洲昆士蘭大學。

      團隊以太陽能發電為題,探討發電量快速變化及部分感測資料缺失時,預測範圍的可靠性,並運用多個電站的數據比較不同校準方法。團隊論文經同行評審獲接納,已由 Springer 正式出版,收錄於《Lecture Notes in Artificial Intelligence》(LNAI)系列的 ADMA 2026 會議論文集。

      從研究展示到與參會者交流,同學累積了學術表達與研究實踐的經驗,也看見數學建模與數據科學在課堂以外的應用。期待同學繼續保持好奇,以數據和證據探索更多問題!


      Hong U Lo, Zibo Gao and Peng Chi Lam from CDSJ5 presented a research poster at ADMA 2026, the 22nd International Conference on Advanced Data Mining and Applications, in Hong Kong. The team was supervised by their teacher, Sok Kin Cheng.

      Academics from The Hong Kong Polytechnic University and The Hong Kong University of Science and Technology serve as the conference’s General Chairs, with Program Chairs from The Hong Kong Polytechnic University, Tsinghua University and The University of Queensland, Australia.

      The team investigated the reliability of solar power prediction intervals during rapid changes in power output and partial loss of sensor inputs. Using data from multiple power stations, they compared calibration methods. Their paper was accepted following peer review and has been published by Springer in the ADMA 2026 proceedings, part of the Lecture Notes in Artificial Intelligence (LNAI) series.

      By presenting their work and exchanging ideas with other participants, the students gained experience in research and academic communication, while exploring applications of mathematical modelling and data science beyond the classroom. We look forward to seeing them continue to ask questions and explore problems through data and evidence.

📖 論文 / Paper

      "When Solar Power Changes Fast: A Multi-site Audit of Prediction-Interval Reliability Under Ramp Events and Sensor Degradation"

[閱讀論文 / Read the paper](https://link.springer.com/chapter/10.1007/978-981-92-7741-4_26)