Results 31 to 40 of about 6,023 (236)
Evaluating the determinants of support for police militarization among officers
Politics &Policy, Volume 51, Issue 4, Page 636-660, August 2023., 2023 Abstract We evaluate the determinants of officer support for their agency participating in the 1033 Program: a program that facilitates the flow of military hardware to local law enforcement agencies. In doing so, we provide insight into why officers demand such equipment, which, in turn, may partially explain patterns of program participation and ...
Ryan M. Welch +3 more
wiley +1 more source
Policy Studies Journal, Volume 51, Issue 3, Page 551-571, August 2023., 2023 Abstract How political actors choose which politics to focus on helps shape the outcome of the policy process. While the policy agenda of the federal government has received widespread attention, there is much less known about the policy agendas of the U.S. states. In this paper, we describe how and why states choose to have similar agendas. We rely on
David A. M. Peterson +4 more
wiley +1 more source
Zhongguo cuzhong zazhi, 2022 目的 建立基于机器学习的血糖异常急性缺血性卒中患者的预后预测模型，比较传统logistic模型与机器学习模型的预测效能。 方法 以中国国家卒中登记研究Ⅲ（China national stroke registration study III，CNSR-Ⅲ）血糖异常急性缺血性卒中患者为研究对象，采用病例报告表收集患者的人口学信息、既往病史、实验室检查、头颅影像学检查、卒中病因分型等临床资料。采用分层10折交叉验证划分训练集（3325例）和测试集（369例），基于随机森林、梯度提升决策树（
杨佳蕾, 陈思玎, 孟霞, 姜勇, 王拥军
doaj +1 more source
Wildlife Letters, Volume 1, Issue 1, Page 32-41, March 2023., 2023 AF‐TigerNet automatically detects the position of Amur tigers and determines detection confidence. Overall network structure of AF‐TigerNet consists of the backbone, neck, and head. The backbone is the modified CSPNet which outputs C3–C5 feature maps to the neck with the channel numbers 64 (C3), 128 (C4), and 256 (C5).
Bohan Liu, Zhilin Qu
wiley +1 more source
大数据, 2022 随着机器学习技术的广泛应用，数据安全问题时有发生，人们对数据隐私保护的需求日渐显现，这无疑降低了不同实体间共享数据的可能性，导致数据难以共享，形成“数据孤岛”。联邦学习可以有效解决“数据孤岛”问题。联邦学习本质上是一种分布式的机器学习，其最大的特点是将用户数据保存在用户本地，模型联合训练过程中不会泄露各参与方的原始数据。尽管如此，联邦学习在实际应用中仍然存在许多安全隐患，需要深入研究。对联邦学习可能受到的攻击及相应的防御措施进行系统性的梳理。首先根据联邦学习的训练环节对其可能受到的攻击和威胁进行分类 ...
吴建汉, 司世景, 王健宗, 肖京
doaj +1 more source
Nailfold capillaroscopy and deep learning in diabetes 甲襞毛细血管镜检测与深度学习在糖尿病中的应用
Journal of Diabetes, Volume 15, Issue 2, Page 145-151, February 2023., 2023 Highlights Nailfold capillary images were obtained by performing nailfold video capillaroscopy in 120 adult patients with and without diabetes. Over 5000 photographs were analyzed using machine‐learning approaches, and these models were clearly able to distinguish people based on diabetes status.
Reema Shah +6 more
wiley +1 more source
Catalyzing success in community‐based conservation
Conservation Biology, Volume 37, Issue 1, February 2023., 2023 Abstract Efforts to devolve rights and engage Indigenous Peoples and local communities in conservation have increased the demand for evidence of the efficacy of community‐based conservation (CBC) and insights into what enables its success. We examined the human well‐being and environmental outcomes of a diverse set of 128 CBC projects.
Brandie Fariss +5 more
wiley +1 more source
The Photogrammetric Record, Volume 37, Issue 180, Page 366-384, December 2022., 2022 Abstract Registration of 3D spatial data and models is a fundamental task in applications such as mapping, positioning and virtual/augmented reality. Most of the existing 3D registration methods such as iterative closest point (ICP) and recent learning‐based methods are dedicated to point cloud registration, and rely heavily on point‐wise ...
Yuan Zhao +3 more
wiley +1 more source
Methods in Ecology and Evolution, Volume 13, Issue 7, Page 1429-1435, July 2022., 2022 Abstract Over the past two decades, accelerometer (ACC) data have been increasingly used to study animal behaviours and energetics. However, the large amount of raw ACC data can be a burden to device storage and power consumption and in many cases may also require device retrieval for data collection.
Hui Yu +4 more
wiley +1 more source
智能科学与技术学报, 2023 针对具有不确定性四旋翼无人机姿态跟踪问题，提出了基于极值搜索的鲁棒控制方法。首先，建立四旋翼无人机非线性姿态模型，并考虑模型参数的不确定性，设计鲁棒控制器来确保跟踪误差动态的有界性。然后，将鲁棒控制器与无模型学习算法结合，设计基于学习的控制器，从而自动迭代地调整鲁棒控制器的反馈增益，并在线优化期望性能成本函数。最后，通过MATLAB进行数值仿真，所述控制方法的系统稳态跟踪误差相较于经典鲁棒控制方法降低了0.246，证明了所述方法鲁棒性和优越性。
郭大力, 赵中原, 罗子娟
doaj +1 more source