这项工作提出了两种统计方法,用于基于通用和用户依赖模型的击键生物识别数据的合成。两种方法在机器人检测任务上均经过验证,使用击键合成数据来更好地训练系统。我们的实验包括一个来自168,000名受试者的1.36亿击球事件的数据集。我们通过定性和定量实验分析了两种合成方法的性能。根据两个监督分类器(支持向量机和长期的短期内存网络)和一个包括人类和生成的样本在内的学习框架,考虑了不同的机器人探测器。我们的结果证明,所提出的统计方法能够生成现实的人类合成击键样品。此外,分类结果表明,在具有大型标记数据的情况下,可以高精度检测这些合成样品。但是,在几次学习方案中,它代表了一个重要的挑战。
translated by 谷歌翻译
The study aims the development of a wearable device to combat the onslaught of covid-19. Likewise, to enhance the regular face shield available in the market. Furthermore, to raise awareness of the health and safety protocols initiated by the government and its affiliates in the enforcement of social distancing with the integration of computer vision algorithms. The wearable device was composed of various hardware and software components such as a transparent polycarbonate face shield, microprocessor, sensors, camera, thin-film transistor on-screen display, jumper wires, power bank, and python programming language. The algorithm incorporated in the study was object detection under computer vision machine learning. The front camera with OpenCV technology determines the distance of a person in front of the user. Utilizing TensorFlow, the target object identifies and detects the image or live feed to get its bounding boxes. The focal length lens requires the determination of the distance from the camera to the target object. To get the focal length, multiply the pixel width by the known distance and divide it by the known width (Rosebrock, 2020). The deployment of unit testing ensures that the parameters are valid in terms of design and specifications.
translated by 谷歌翻译
The findable, accessible, interoperable, and reusable (FAIR) data principles have provided a framework for examining, evaluating, and improving how we share data with the aim of facilitating scientific discovery. Efforts have been made to generalize these principles to research software and other digital products. Artificial intelligence (AI) models -- algorithms that have been trained on data rather than explicitly programmed -- are an important target for this because of the ever-increasing pace with which AI is transforming scientific and engineering domains. In this paper, we propose a practical definition of FAIR principles for AI models and create a FAIR AI project template that promotes adherence to these principles. We demonstrate how to implement these principles using a concrete example from experimental high energy physics: a graph neural network for identifying Higgs bosons decaying to bottom quarks. We study the robustness of these FAIR AI models and their portability across hardware architectures and software frameworks, and report new insights on the interpretability of AI predictions by studying the interplay between FAIR datasets and AI models. Enabled by publishing FAIR AI models, these studies pave the way toward reliable and automated AI-driven scientific discovery.
translated by 谷歌翻译
We propose an analysis-by-synthesis method for fast multi-view 3D reconstruction of opaque objects with arbitrary materials and illumination. State-of-the-art methods use both neural surface representations and neural rendering. While flexible, neural surface representations are a significant bottleneck in optimization runtime. Instead, we represent surfaces as triangle meshes and build a differentiable rendering pipeline around triangle rasterization and neural shading. The renderer is used in a gradient descent optimization where both a triangle mesh and a neural shader are jointly optimized to reproduce the multi-view images. We evaluate our method on a public 3D reconstruction dataset and show that it can match the reconstruction accuracy of traditional baselines and neural approaches while surpassing them in optimization runtime. Additionally, we investigate the shader and find that it learns an interpretable representation of appearance, enabling applications such as 3D material editing.
translated by 谷歌翻译
Building trustworthy, effective, and responsible machine learning systems hinges on understanding how differences in training data and modeling decisions interact to impact predictive performance. In this work, we seek to better understand how we might characterize, detect, and design for data-model synergies. We focus on a particular type of data-model inefficiency, in which adding training data from some sources can actually lower performance evaluated on key sub-groups of the population, a phenomenon we refer to as negative data externalities on group performance. Such externalities can arise in standard learning settings and can manifest differently depending on conditions between training set size and model size. Data externalities directly imply a lower bound on feasible model improvements, yet improving models efficiently requires understanding the underlying data-model tensions. From a broader perspective, our results indicate that data-efficiency is a key component of both accurate and trustworthy machine learning.
translated by 谷歌翻译
生成模型生成的合成数据可以增强医学成像中渴望数据深度学习模型的性能和能力。但是,(1)(合成)数据集的可用性有限,并且(2)生成模型训练很复杂,这阻碍了它们在研究和临床应用中的采用。为了减少此入口障碍,我们提出了Medigan,Medigan是一站式商店,用于验证的生成型号,该型号是开源框架 - 不合骨python图书馆。 Medigan允许研究人员和开发人员仅在几行代码中创建,增加和域名。在基于收集的最终用户需求的设计决策的指导下,我们基于生成模型的模块化组件(i)执行,(ii)可视化,(iii)搜索和排名以及(iv)贡献。图书馆的可伸缩性和设计是通过其越来越多的综合且易于使用的验证生成模型来证明的,该模型由21种模型组成,利用9种不同的生成对抗网络体系结构在4个域中在11个数据集中训练,即乳腺摄影,内窥镜检查,X射线和X射线和X射线镜头,X射线和X型。 MRI。此外,在这项工作中分析了Medigan的3个应用,其中包括(a)启用社区范围内的限制数据共享,(b)研究生成模型评估指标以及(c)改进临床下游任务。在(b)中,扩展了公共医学图像综合评估和报告标准,我们根据图像归一化和特定于放射学特征提取了Fr \'Echet Inception距离变异性。
translated by 谷歌翻译
基于深度学习的计算机辅助检测系统在乳腺癌检测中表现出良好的性能。但是,高密度的乳房显示出较差的检测性能,因为密集组织可以掩盖甚至模拟质量。因此,乳腺癌检测的敏感性可在致密乳房中降低20%以上。此外,与低密度乳房相比,极度致密的病例报告说,患癌症的风险增加。这项研究旨在使用合成高密度的全场数字乳房X线照片(FFDM)作为乳腺质量检测模型训练期间的数据增强来提高高密度乳房的质量检测性能。为此,对使用三个FFDM数据集进行了五个周期一致的GAN(CycleGAN)模型,以高分辨率乳房X线照片中的低密度图像翻译进行了训练。训练图像是由乳房密度双拉德类别分开的,几乎是脂肪的脂肪,双刺是乳房的乳房。我们的结果表明,所提出的数据增强技术在两个不同的测试集中提高了高密度乳房中质量检测的敏感性和精度,并将其作为域适应技术有用。此外,在一项涉及两名专家放射科医生和一名外科肿瘤学家的读者研究中评估了合成图像的临床现实主义。
translated by 谷歌翻译
基于图神经网络(GNN)方法已饱和推荐系统的领域。这些系统的收益很大,显示了通过网络结构解释数据的优势。但是,尽管在建议任务中使用图形结构有明显的好处,但这种表示形式也带来了新的挑战,这些挑战加剧了缓解算法偏见的复杂性。当将GNN集成到下游任务中时,例如建议,缓解偏差可能会变得更加困难。此外,将现有的公平促进方法应用于大型现实世界数据集的棘手性对缓解尝试更加严重的限制。我们的工作着手通过采用现有方法来促进图形上的个人公平性并将其扩展以支持Mini批次或基于子样本的培训,从而填补了这一空白下游建议任务。我们评估了两种流行的GNN方法:图形卷积网络(GCN),该方法在整个图上进行训练,以及使用概率随机步行的图形,以创建用于迷你批次训练的子图,并评估子采样对个人公平性的影响。我们实施了一个由Dong等人提出的称为\ textit {redress}的个人公平概念,该概念使用等级优化来学习单个公平节点或项目,嵌入。我们在两个现实世界数据集上进行了经验证明,图形不仅能够达到可比的精度,而且与GCN模型相比,还可以提高公平性。这些发现对个人的公平促进,GNN和下游形式产生了影响,推荐系统,表明小批量培训通过允许当地的细微努力指导代表性学习中的公平促进过程来促进个人公平促进。
translated by 谷歌翻译
ICECUBE是一种用于检测1 GEV和1 PEV之间大气和天体中微子的光学传感器的立方公斤阵列,该阵列已部署1.45 km至2.45 km的南极的冰盖表面以下1.45 km至2.45 km。来自ICE探测器的事件的分类和重建在ICeCube数据分析中起着核心作用。重建和分类事件是一个挑战,这是由于探测器的几何形状,不均匀的散射和冰中光的吸收,并且低于100 GEV的光,每个事件产生的信号光子数量相对较少。为了应对这一挑战,可以将ICECUBE事件表示为点云图形,并将图形神经网络(GNN)作为分类和重建方法。 GNN能够将中微子事件与宇宙射线背景区分开,对不同的中微子事件类型进行分类,并重建沉积的能量,方向和相互作用顶点。基于仿真,我们提供了1-100 GEV能量范围的比较与当前ICECUBE分析中使用的当前最新最大似然技术,包括已知系统不确定性的影响。对于中微子事件分类,与当前的IceCube方法相比,GNN以固定的假阳性速率(FPR)提高了信号效率的18%。另外,GNN在固定信号效率下将FPR的降低超过8(低于半百分比)。对于能源,方向和相互作用顶点的重建,与当前最大似然技术相比,分辨率平均提高了13%-20%。当在GPU上运行时,GNN能够以几乎是2.7 kHz的中位数ICECUBE触发速率的速率处理ICECUBE事件,这打开了在在线搜索瞬态事件中使用低能量中微子的可能性。
translated by 谷歌翻译
Boll Weevil(Anthonomus Grandis L.)是一种严重的害虫,主要以棉花为食。由于亚热带气候条件,在德克萨斯州的下里奥格兰德山谷等地方,棉花植物可以全年生长,因此,收获期间上一个季节的剩下的种子可以在玉米中的旋转中继续生长(Zea Mays L.)和高粱(高粱双色L.)。这些野性或志愿棉花(VC)植物到达Pinhead平方阶段(5-6叶阶段)可以充当Boll Weevil Pest的宿主。得克萨斯州的鲍尔象鼻虫根除计划(TBWEP)雇用人们在道路或田野侧面生长的风险投资和消除旋转作物的田间生长,但在田野中生长的植物仍未被发现。在本文中,我们证明了基于您的计算机视觉(CV)算法的应用,仅在三个不同的生长阶段(V3,V6)(V3,V6)中检测出在玉米场中生长的VC植物,以检测在玉米场中生长的VC植物的应用。使用无人飞机系统(UAS)遥感图像。使用Yolov5(S,M,L和X)的所有四个变体,并根据分类精度,平均平均精度(MAP)和F1得分进行比较。发现Yolov5s可以在玉米的V6阶段检测到最大分类精度为98%,地图为96.3%,而Yolov5s和Yolov5m的地图为96.3%,而Yolov5m的分类精度为85%,Yolov5m和Yolov5m的分类准确性最小,而Yolov5L的分类精度最少。在VT阶段,在尺寸416 x 416像素的图像上为86.5%。开发的CV算法有可能有效地检测和定位在玉米场中间生长的VC植物,并加快TBWEP的管理方面。
translated by 谷歌翻译