SiG-DML-P5: Machine Learning Applications
Wed, 2 Sep, 16:00 - 17:40 Belgium Time (UTC +2)
Location: Balcony II West
Session Type: Poster
Track: SiG-DML - Signal and Data Analytics for Machine Learning

SiG-DML-P5.1: CITRAS-FM: TINY TIME SERIES FOUNDATION MODEL FOR COVARIATE-INFORMED ZERO-SHOT FORECASTING
Yosuke Yamaguchi, Issei Suemitsu, Yuki Kajihara, Wenpeng Wei, Hitachi Ltd., Japan

SiG-DML-P5.2: MITIGATING SPECTRAL BIAS IN NEURAL OPERATORS FOR UNDERWATER TRANSMISSION LOSS PREDICTION
Yifan Sun, Shikai Fang, Chao Zhang, Lei Cheng, Jianlong Li, Zhejiang University, China; Peter Gerstoft, Technical University of Denmark, University of California San Diego, United States

SiG-DML-P5.3: AS‑HybridSN: A Lightweight 3D–2D Architecture for Concentration‑Aware Aflatoxin Quantification in Hyperspectral Pistachio Imaging
Sina Mahroughi, Augusta Nneka Ndu, Hossein Mehrabinejad, Theocharis Ispoglou, John George, Akbar Sheikh-Akbari, Leeds Beckett University, United Kingdom

SiG-DML-P5.4: DATA-EFFICIENT SELF-ADAPTATION FOR TRUSTWORTHY VESSEL MANEUVERING UNDER WIND DISTURBANCES
Vasileios Kanatas, Nikolaos Passalis, Aristotle University of Thessaloniki, Greece; Tongtong Wang, Beatriz Sanguino, Houxiang Zhang, Guoyuan Li, Norwegian University of Science and Technology, Norway; Anastasios Tefas, Aristotle University of Thessaloniki, Greece

SiG-DML-P5.5: LASTR: LANGUAGE-DRIVEN TIME-SERIES SEGMENT RETRIEVAL
Kota Dohi, Harsh Purohit, Tomoya Nishida, Takashi Endo, Yusuke Ohtsubo, Koichiro Yawata, Koki Takeshita, Tatsuya Sasaki, Yohei Kawaguchi, Hitachi, Ltd., Japan

SiG-DML-P5.6: VMDNET: TEMPORAL LEAKAGE-FREE VARIATIONAL MODE DECOMPOSITION FOR ELECTRICITY DEMAND FORECASTING
Weibin Feng, Ran Tao, John Cartlidge, Jin Zheng, University of Bristol, United Kingdom

SiG-DML-P5.7: End-to-End Neural Compression of Ocean Sound Speed Profiles for Operational Nomadic Forecasting
Oscar GAUVRIT, Ronan FABLET, IMT Atlantique, France; Yann STEPHAN, SHOM, France

SiG-DML-P5.8: FEW-SHOT ORDINAL LEARNING FOR DAY-WISE FRESHNESS ESTIMATION WITH HYPERSPECTRAL FISH IMAGES
Kazi Nabiul Alam, Pooneh Bagheri-Zadeh, Akbar Sheikh-Akbari, Leeds Beckett University, United Kingdom

SiG-DML-P5.9: Parameter-Efficient Few-Shot Domain Adaptation for Text-to-Time Series Diffusion Models
Harsh Purohit, Tomoya Nishida, Dohi Kota, Takashi Endo, Masaaki Yamamoto, Yohei Kawaguchi, Hitachi, Japan

SiG-DML-P5.10: PARAMETER-EFFICIENT DOMAIN ADAPTATION OF PHYSICS-INFORMED SELF-ATTENTION BASED GNNS FOR AC POWER FLOW PREDICTION
Redwanul Karim, Changhun Kim, Timon Conrad, Nora Gourmelon, Julian Oelhaf, David Riebesel, Tomás Arias-Vergara, Andreas Maier, Johann Jäger, Siming Bayer, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany