Enhancing Dimensionality Prediction in Hybrid Metal Halides via Feature Engineering and Class-Imbalance Mitigation
Department of Physics and Astronomy, Middle Tennessee State University（物理与天文学系，中田纳西州立大学）；Department of Chemical and Biological Engineering, University of Colorado（化学与生物工程系，科罗拉多大学）；Department of Mechanical Engineering and Materials Science, Duke University（机械工程与材料科学系，杜克大学）；National Center for Computational Sciences Division, Oak Ridge National Laboratory（计算科学中心 division，橡树岭国家实验室）
Mariia Karabin, Isaac Armstrong, Leo Beck, Paulina Apanel, Markus Eisenbach, David B. Mitzi, Hanna Terletska, Hendrik Heinz
We present a machine learning framework for predicting the structural dimensionality of hybrid metal halides (HMHs), including organic-inorganic perovskites, using a combination of chemically-informed feature engineering and advanced class-imbalance handling techniques. The dataset, consisting of 494 HMH structures, is highly imbalanced across dimensionality classes (0D, 1D, 2D, 3D), posing significant challenges to predictive modeling. This dataset was later augmented to 1336 via the Synthetic Minority Oversampling Technique (SMOTE) to mitigate the effects of the class imbalance. We developed interaction-based descriptors and integrated them into a multi-stage workflow that combines feature selection, model stacking, and performance optimization to improve dimensionality prediction accuracy. Our approach significantly improves F1-scores for underrepresented classes, achieving robust cross-validation performance across all dimensionalities.
Model-agnostic Mitigation Strategies of Data Imbalance for Regression
Department of Computing Science（计算科学系）；Carl von Ossietzky Universität Oldenburg（卡尔·冯·奥西特齐克大学奥尔登堡分校）；Department for Civil Engineering, Geoinformation and Health Technology（土木工程、地理信息与健康技术系）；Jade University of Applied Science（亚德大学应用科学学院）；Energy Division, OFFIS - Institute of Information Technology, Oldenburg, Germany（能源部门，OFFIS信息技术研究所，德国奥尔登堡）
From Data to Decision: A Multi-Stage Framework for Class Imbalance Mitigation in Optical Network Failure Analysis
Aston Institute of Photonic Technologies（阿斯顿光电技术研究所）；Aston University（阿斯顿大学）；Scuola Superiore Sant’Anna（圣安娜高等学院）；Nokia, Optical Networks（诺基亚光网络部门）；Instituto de Telecomunicações（电信研究所）；Instituto Superior Técnico（技术高级学院）
School of Engineering and Physical Sciences, Heriot-Watt University（赫瑞瓦特大学工程与物理科学学院）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）；University of Cambridge（剑桥大学）；SeeByte Ltd.（SeeByte有限公司）
NeuBM: Mitigating Model Bias in Graph Neural Networks through Neutral Input Calibration
School of Computing and Information Technology, Great Bay University（大海湾大学计算机与信息学院）；Dongguan Key Laboratory for Intelligence and Information Technology（东莞智能与信息科技重点实验室）；Department of Computer Science, University of California, Los Angeles（加州大学洛杉矶分校计算机科学系）
Class Uncertainty: A Measure to Mitigate Class Imbalance
Dept. of Computer Engineering, METU, Ankara, Turkey（METU 计算机工程系，土耳其安卡拉）；LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS, Marne-la-Vallée, France（LIGM，巴黎理工学院，法国图瓦兹-埃菲尔大学，CNRS，法国马尔奈-拉瓦勒）；Five AI Ltd., United Kingdom（Five AI 有限公司，英国）；Center for Robotics and Artificial Intelligence (ROMER), METU, Ankara, Turkey（机器人与人工智能中心（ROMER），METU，土耳其安卡拉）
Enhanced Breast Cancer Tumor Classification using MobileNetV2: A Detailed Exploration on Image Intensity, Error Mitigation, and Streamlit-driven Real-time Deployment
Viterbi School of Engineering（维特比工程学院）；College of Engineering（工程学院）；University of Southern California（南加州大学）；Rochester Institute of Technology（罗切斯特理工学院）；Northeastern University（东北大学）；School of Arts & Sciences（艺术与科学学院）；State University of New York Plattsburgh（纽约州立大学普拉茨堡分校）
Equitable Length of Stay Prediction for Patients with Learning Disabilities and Multiple Long-term Conditions Using Machine Learning
Loughborough University（拉夫堡大学）；Swansea University Medical School（斯旺西大学医学院）；University of Leicester（莱斯特大学）；Leicestershire Partnership NHS Trust（莱斯特郡合作 NHS 信托机构）
