知识图（kgs）以（头，谓词，尾部） - 轨道的形式存储信息。为了增强具有新知识的公斤，研究人员提出了kg完成（kgc）任务的模型，例如链接预测；即，回答（H; P;？）或（？; P; t）查询。这种模型通常在固定测试集上使用平均指标进行评估。尽管对于跟踪进度有用，但平均的单分数指标无法透露模型到底学到的或未能学习的内容。为了解决这个问题，我们提出了KGXBoard：一个交互式框架，用于对有意义的数据子集进行精细颗粒评估，每个框架都测试了KGC模型的个人和可解释功能。在我们的实验中，我们强调了使用KGXBoard发现的发现，这是无法通过标准平均单分数指标来检测到的。

Artificial Intelligence (AI) has become commonplace to solve routine everyday tasks. Because of the exponential growth in medical imaging data volume and complexity, the workload on radiologists is steadily increasing. We project that the gap between the number of imaging exams and the number of expert radiologist readers required to cover this increase will continue to expand, consequently introducing a demand for AI-based tools that improve the efficiency with which radiologists can comfortably interpret these exams. AI has been shown to improve efficiency in medical-image generation, processing, and interpretation, and a variety of such AI models have been developed across research labs worldwide. However, very few of these, if any, find their way into routine clinical use, a discrepancy that reflects the divide between AI research and successful AI translation. To address the barrier to clinical deployment, we have formed MONAI Consortium, an open-source community which is building standards for AI deployment in healthcare institutions, and developing tools and infrastructure to facilitate their implementation. This report represents several years of weekly discussions and hands-on problem solving experience by groups of industry experts and clinicians in the MONAI Consortium. We identify barriers between AI-model development in research labs and subsequent clinical deployment and propose solutions. Our report provides guidance on processes which take an imaging AI model from development to clinical implementation in a healthcare institution. We discuss various AI integration points in a clinical Radiology workflow. We also present a taxonomy of Radiology AI use-cases. Through this report, we intend to educate the stakeholders in healthcare and AI (AI researchers, radiologists, imaging informaticists, and regulators) about cross-disciplinary challenges and possible solutions.

The monitoring of machine conditions in a plant is crucial for production in manufacturing. A sudden failure of a machine can stop production and cause a loss of revenue. The vibration signal of a machine is a good indicator of its condition. This paper presents a dataset of vibration signals from a lab-scale machine. The dataset contains four different types of machine conditions: normal, unbalance, misalignment, and bearing fault. Three machine learning methods (SVM, KNN, and GNB) evaluated the dataset, and a perfect result was obtained by one of the methods on a 1-fold test. The performance of the algorithms is evaluated using weighted accuracy (WA) since the data is balanced. The results show that the best-performing algorithm is the SVM with a WA of 99.75\% on the 5-fold cross-validations. The dataset is provided in the form of CSV files in an open and free repository at https://zenodo.org/record/7006575.

FSS(Few-shot segmentation)~aims to segment a target class with a small number of labeled images (support Set). To extract information relevant to target class, a dominant approach in best performing FSS baselines removes background features using support mask. We observe that this support mask presents an information bottleneck in several challenging FSS cases e.g., for small targets and/or inaccurate target boundaries. To this end, we present a novel method (MSI), which maximizes the support-set information by exploiting two complementary source of features in generating super correlation maps. We validate the effectiveness of our approach by instantiating it into three recent and strong FSS baselines. Experimental results on several publicly available FSS benchmarks show that our proposed method consistently improves the performance by visible margins and allows faster convergence. Our codes and models will be publicly released.

Artificial Intelligence (AI) is having a tremendous impact across most areas of science. Applications of AI in healthcare have the potential to improve our ability to detect, diagnose, prognose, and intervene on human disease. For AI models to be used clinically, they need to be made safe, reproducible and robust, and the underlying software framework must be aware of the particularities (e.g. geometry, physiology, physics) of medical data being processed. This work introduces MONAI, a freely available, community-supported, and consortium-led PyTorch-based framework for deep learning in healthcare. MONAI extends PyTorch to support medical data, with a particular focus on imaging, and provide purpose-specific AI model architectures, transformations and utilities that streamline the development and deployment of medical AI models. MONAI follows best practices for software-development, providing an easy-to-use, robust, well-documented, and well-tested software framework. MONAI preserves the simple, additive, and compositional approach of its underlying PyTorch libraries. MONAI is being used by and receiving contributions from research, clinical and industrial teams from around the world, who are pursuing applications spanning nearly every aspect of healthcare.

静止状态fMRI是一种成像方式，它通过信号变化揭示了大脑活动的定位，这就是所谓的静息状态网络（RSN）。该技术正在在神经外科预制范围内广受欢迎，以可视化功能区域并评估区域活动。 RS-FMRI网络的标签需要主题的专业知识并且耗时，因此需要自动分类算法。尽管AI在医学诊断中的影响表现出了很大的进步。在临床环境中部署和维护它们是未满足的需求。我们提出了一条端到端可重复的管道，该管道将RS-FMRI的图像处理结合在基于云的工作流程中，同时使用深度学习来自动化RSN的分类。我们已经构建了可重现的Azure机器学习基于云的医学成像概念管道，用于fMRI分析，集成了流行的FMRIB软件库（FSL）工具包。为了证明使用大型数据集的临床应用，我们比较了三个神经网络体系结构，以分类从处理后的RS-FMRI中得出的更深型RSN。这三种算法是：MLP，基于2D投影的CNN和一个完全3D CNN分类网络。每种网络都在RS-FMRI背面项目的独立组件上训练，每种分类方法的精度> 98％。

在安全至关重要的应用中，深度神经网络的使用越来越多，就需要训练有素的模型。当前大多数校准技术解决了分类问题，同时着重于改善对内域预测的校准。在许多决策系统中占据相似的空间和重要性的视觉对象探测器的校准几乎没有关注。在本文中，我们研究了当前对象检测模型的校准，尤其是在域移位下。为此，我们首先引入了插件的火车时间校准损失以进行对象检测。它可以用作辅助损失函数，以改善检测器的校准。其次，我们设计了一种新的不确定性量化机制来进行对象检测，该机制可以隐式校准常用的基于自我训练的域自适应检测器。我们在研究中包括单阶段和两阶段对象探测器。我们证明，我们的损失改善了具有明显边缘的内域和室外检测的校准。最后，我们展示了我们技术在校准不同域移动方案中的域自适应对象探测器方面的实用性。

深度神经网络（DNNS）的边缘训练是持续学习的理想目标。但是，这受到训练所需的巨大计算能力的阻碍。硬件近似乘数表明，它们在获得DNN推理加速器中获得资源效率的有效性；但是，使用近似乘数的培训在很大程度上尚未开发。为了通过支持DNN培训的近似乘数来构建有效的资源加速器，需要对不同DNN体系结构和不同近似乘数进行彻底评估。本文介绍了近似值，这是一个开源框架，允许使用模拟近似乘数快速评估DNN训练和推理。近似值与TensorFlow（TF）一样用户友好，仅需要对DNN体系结构的高级描述以及近似乘数的C/C ++功能模型。我们通过使用GPU（AMSIM）上的基于基于LUT的近似浮点（FP）乘数模拟器来提高乘数在乘数级别的模拟速度。近似值利用CUDA并有效地将AMSIM集成到张量库中，以克服商业GPU中的本机硬件近似乘数的缺乏。我们使用近似值来评估使用LENET和RESNETS体系结构的小型和大型数据集（包括Imagenet）的近似乘数的DNN训练的收敛性和准确性。与FP32和BFLOAT16乘数相比，评估表明测试准确性相似的收敛行为和可忽略不计的变化。与训练和推理中基于CPU的近似乘数模拟相比，GPU加速近似值快2500倍以上。基于具有本地硬件乘数的高度优化的闭合源Cudnn/Cublas库，原始张量量仅比近似值快8倍。

近年来，人们对建立面孔和名人声音之间的关联的兴趣越来越大，从而利用YouTube的视听信息。先前的工作采用公制学习方法来学习适合关联匹配和验证任务的嵌入式空间。尽管显示出一些进展，但由于依赖距离依赖的边缘参数，运行时训练的复杂性差以及对精心制作的负面采矿程序的依赖，这种制剂是限制性的。在这项工作中，我们假设一个丰富的表示形式以及有效但有效的监督对于实现面部voice关联任务的歧视性关节嵌入空间很重要。为此，我们提出了一种轻巧的插件机制，该机制利用这两种方式中的互补线索以通过正交性约束来根据其身份标签形成丰富的融合杂物并将其簇形成。我们将我们提出的机制作为融合和正交投影（FOP）创造，并在两个流网络中实例化。在Voxceleb1和Mav-Celeb数据集上评估了总体结果框架，其中包括许多任务，包括跨模式验证和匹配。结果表明，我们的方法对当前的最新方法有利，而我们提出的监督表述比当代方法所采用的方法更有效。此外，我们还利用跨模式验证和匹配任务来分析多种语言对面部声音协会的影响。代码可用：\ url {https://github.com/msaadsaeed/fop}

原产地目的地（O-D）旅行需求预测是运输中的基本挑战。最近，时空深度学习模型展示了提高预测准确性的巨大潜力。但是，很少有研究能够解决细粒O-D矩阵中的不确定性和稀疏问题。这提出了一个严重的问题，因为许多零偏离了确定性深度学习模型的基础的高斯假设。为了解决这个问题，我们设计了一个空间零膨胀的负二项式神经网络（Stzinb-gnn），以量化稀疏旅行需求的不确定性。它使用扩散和时间卷积网络分析空间和时间相关性，然后将其融合以参数化行进需求的概率分布。使用两个具有各种空间和时间分辨率的现实世界数据集对STZINB-GNN进行了检查。结果表明，由于其高精度，紧密的置信区间和可解释的参数，尤其是在高时空分辨率下，Stzinb-GNN比基准模型的优越性。 STZINB-GNN的稀疏参数对各种运输应用具有物理解释。