Machine-part interaction classification is a key capability required by Cyber-Physical Systems (CPS), a pivotal enabler of Smart Manufacturing (SM). While previous relevant studies on the subject have primarily focused on time series classification, change point detection is equally important because it provides temporal information on changes in behavior of the machine. In this work, we address point detection and time series classification for machine-part interactions with a deep Convolutional Neural Network (CNN) based framework. The CNN in this framework utilizes a two-stage encoder-classifier structure for efficient feature representation and convenient deployment customization for CPS. Though data-driven, the design and optimization of the framework are Subject Matter Expertise (SME) guided. An SME defined Finite State Machine (FSM) is incorporated into the framework to prohibit intermittent misclassifications. In the case study, we implement the framework to perform machine-part interaction classification on a milling machine, and the performance is evaluated using a testing dataset and deployment simulations. The implementation achieved an average F1-Score of 0.946 across classes on the testing dataset and an average delay of 0.24 seconds on the deployment simulations.
Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
School of Computer Science & Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)（华中科技大学与平安产险联合实验室）；Ping An Property & Casualty Insurance Company of China, Ltd.（中国平安财产保险股份有限公司）；The Chinese University of Hong Kong（香港中文大学）
Tübingen AI Center, University of Tübingen（图宾根大学图宾根人工智能中心）；University of Cambridge（剑桥大学）；Munich Center for ML, Technical University of Munich（慕尼黑工业大学慕尼黑机器学习中心）
Convolutional neural networks: a magic bullet for gravitational-wave detection?
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck ETH Center for Learning Systems（马克斯·普朗克-ETH学习系统中心）；University of Cambridge（剑桥大学）；University of Portsmouth（朴茨茅斯大学）；Max Planck Institute for Gravitational Physics（马克斯·普朗克引力物理研究所）
Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization
University of Amsterdam（阿姆斯特丹大学）；Informatics Institute, University of Amsterdam（阿姆斯特丹大学信息学院）；Amsterdam Machine Learning Lab (AMLab), University of Amsterdam（阿姆斯特丹大学机器学习实验室）
Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving
Center for Applied Autonomous Sensor Systems (AASS)（应用自主传感器系统中心）；Örebro University（奥雷布罗大学）；Computer Vision Laboratory（计算机视觉实验室）；Linköping University（利德斯霍尔大学）
Merging-Diverging Hybrid Transformer Networks for Survival Prediction in Head and Neck Cancer
School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）；Institute of Translational Medicine, Shanghai Jiao Tong University（上海交通大学转化医学研究院）；Royal Prince Alfred Hospital（皇家阿尔弗雷德王子医院）；Med-X Research Institute, Shanghai Jiao Tong University（上海交通大学Med-X研究院）
Visual Spatial Learning: Single-Field Spatial Interpolation Using Convolutional Neural Networks
Centro de Matemática (CMAT), Universidade do Minho（数学中心（CMAT），明霍大学）；DEI-FEUP & INESC TEC, Universidade do Porto（FEUP-DEI与INESC TEC，波尔图大学）；Instituto Português do Mar e da Atmosfera, I. P. (IPMA, I. P.), Lisboa, Portugal（葡萄牙海洋与大气研究所（IPMA, I. P.），里斯本，葡萄牙）；Centro de Ciências do Mar e do Ambiente (MARE), Évora, Portugal（海洋与环境科学中心（MARE），埃维拉，葡萄牙）
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
Arizona State University（亚利桑那州立大学）；Mayo Clinic（梅奥诊所）
从头开始训练深度卷积神经网络（CNN）是很困难的，因为它需要大量的标记训练数据和大量的专业知识来确保适当的收敛。一个有希望的替代方案是微调CNN，该CNN已经使用例如大量标记的自然图像进行了预训练。然而，自然图像和医学图像之间的实质性差异可能会反对这种知识转移。在本文中，我们试图回答医学图像分析背景下的以下中心问题：\emph{Can the use of pre-trained deep CNNs with sufficient fine-tuning eliminate the need for training a deep CNN from scratch?}为了解决这个问题，我们考虑了3个专业的4种不同的医学成像应用（放射学、心脏病学和胃肠病学），涉及3种不同成像模式的分类、检测和分割，并研究了从头开始训练的深度CNN的性能如何与以逐层方式微调的预训练CNN进行比较。我们的实验一致表明，（1）使用具有足够微调的预训练的CNN优于或在最坏情况下表现得与从头开始训练的CNN一样好;（2）微调的CNN比从头开始训练的CNN对训练集的大小更鲁棒;（3）浅调或深调都不是特定应用的最佳选择;以及（4）我们的逐层微调方案可以提供一种实用的方法，以根据可用数据的量来达到当前应用的最佳性能。
COVID-Net US: A Tailored, Highly Efficient, Self-Attention Deep Convolutional Neural Network Design for Detection of COVID-19 Patient Cases from Point-of-care Ultrasound Imaging
University of Waterloo（滑铁卢大学）；National Research Council Canada（加拿大国家研究委员会）；Oakville Trafalgar Memorial Hospital（奥克维尔特拉法加纪念医院）；McMaster University（麦克马斯特大学）；Waterloo Artificial Intelligence Institute（滑铁卢人工智能研究所）
TB-Net: A Tailored, Self-Attention Deep Convolutional Neural Network Design for Detection of Tuberculosis Cases from Chest X-ray Images
University of Waterloo（滑铁卢大学）；Waterloo Artificial Intelligence Institute（滑铁卢人工智能研究所）；DarwinAI Corp.（DarwinAI公司）；Niagara Health（尼亚加拉健康中心）；McMaster University（麦克马斯特大学）；Thunder Bay Regional Health Sciences Centre（桑德贝地区健康科学中心）；Northern Ontario School of Medicine（北安大略医学院）
Multi-scale fully convolutional neural networks for histopathology image segmentation: from nuclear aberrations to the global tissue architecture
University Medical Center Hamburg-Eppendorf（汉堡埃彭多夫大学医学中心）；Center for Biomedical Artificial Intelligence (bAIome)（生物医学人工智能中心（bAIome））；Department of Computational Neuroscience（计算神经科学系）；I. Department of Internal Medicine（第一内科）；Department of Pathology（病理学系）；Department for Interdisciplinary Endoscopy（跨学科内镜检查科）
