帮我润色论文。In this paper, we propose a balancing training method to address problems in imbalanced data learning. To this end, we derive a new loss used in the balancing training phase that alleviates the influence of samples that cause an overfitted decision boundary. The proposed loss efficiently improves the performance of any type of imbalance learning methods. In experiments on multiple benchmark data sets, we demonstrate the validity of our method and reveal that the proposed loss outperforms the state-of-the-art cost-sensitive loss methods. Furthermore, since our loss is not restricted to a specific task, model, or training method, it can be easily used in combination with other recent resampling, meta-learning, and cost-sensitive learning methods for class-imbalance problems. Our code is made available at https://github.com/pseulki/IB-Loss.

时间: 2023-02-24 18:02:14 浏览: 395
在本文中,我们提出了一种平衡训练方法,以解决不平衡数据学习中的问题。为此,我们在平衡训练阶段推导出一种新的损失,以减少导致过度拟合决策边界的样本的影响。所提出的损失有效提高了任何类型的不平衡学习方法的性能。在多个基准数据集的实验中,我们证明了我们的方法的有效性,并发现所提出的损失优于最先进的成本敏感损失方法。此外,由于我们的损失不受特定任务、模型或训练方法的限制,它可以轻松与其他最近的重采样、元学习和成本敏感学习方法结合使用,以解决类不平衡问题。我们的代码可在 https://github.com/pseulki/IB-Loss 获得。
相关问题

The human visual cortex is biased towards shape components while CNNs produce texture biased features. This fact may explain why the performance of CNN significantly degrades with low-labeled input data scenarios. In this paper, we propose a frequency re-calibration U-Net (FRCU-Net) for medical image segmentation. Representing an object in terms of frequency may reduce the effect of texture bias, resulting in better generalization for a low data regime. To do so, we apply the Laplacian pyramid in the bottleneck layer of the U-shaped structure. The Laplacian pyramid represents the object proposal in different frequency domains, where the high frequencies are responsible for the texture information and lower frequencies might be related to the shape. Adaptively re-calibrating these frequency representations can produce a more discriminative representation for describing the object of interest. To this end, we first propose to use a channel-wise attention mechanism to capture the relationship between the channels of a set of feature maps in one layer of the frequency pyramid. Second, the extracted features of each level of the pyramid are then combined through a non-linear function based on their impact on the final segmentation output. The proposed FRCU-Net is evaluated on five datasets ISIC 2017, ISIC 2018, the PH2, lung segmentation, and SegPC 2021 challenge datasets and compared to existing alternatives, achieving state-of-the-art results.请详细介绍这段话中的技术点和实现方式

这段话主要介绍了一种针对医学图像分割的新型网络结构——频率重新校准U-Net(FRCU-Net)。该网络结构的核心思想是将物体表示为频率,在低数据情况下降低纹理偏差的影响,从而获得更好的泛化性能。具体实现方式包括以下技术点: 1. 使用Laplacian金字塔将物体表示在不同的频率域中,其中高频率负责纹理信息,而较低的频率可能与物体的形状相关。 2. 通过自适应重新校准这些频率表示,以产生更具有区分性的物体表示。为此,首先提出使用通道注意力机制来捕捉一个特征图集合中各通道之间的关系,然后通过一个非线性函数将金字塔各层的特征提取结果组合起来,以得到最终的分割输出。 3. 在ISIC 2017、ISIC 2018、PH2、肺分割和SegPC 2021数据集上对FRCU-Net进行了评估,并与现有的替代方案进行了比较,取得了最先进的结果。 综上所述,FRCU-Net通过将物体表示为频率,以及使用自适应的频率重新校准和通道注意力机制,实现了对低数据情况下医学图像分割的有效处理。

The major contributions of this paper are summarized as follows: . We investigate a new automotive architecture and implementation method. We propose an extended SAE (Society of Automotive Engineer) Benchmark and the use of DDS middleware as an alternative for the existing architecture. . We detail the implementation of the electronic stability unit based on the extended SAE benchmark. . We propose a new design of the DDS based on the MBD approach. Thus, the implementation of the application and the new DDS block are realized under SIMULINK. We intend to improve DDS's programming approach, facilitate con¯guring and generation of DDS description and take into account the real-time network drivers. . In order to validate our DDS implementation and highlight its contributions in the context of hard real-time automotive systems, we detail latency computation for automotive networks, and we present the implemented algorithm to calculate the Worst Case Response Time (WCRT). We prove that DDS qualities of service on the top of the SAE vehicle application are respected. We also give a comparison of system performance using real time networks FlexRay and Ethernet.

本文的主要贡献总结如下: 1. 我们研究了一种新的汽车架构和实现方法。我们提出了扩展的SAE(汽车工程师协会)基准以及将DDS中间件作为现有架构的替代方案。 2. 我们详细介绍了基于扩展SAE基准的电子稳定单元的实现。 3. 我们提出了基于MBD方法的DDS的新设计。因此,应用程序的实现和新的DDS块在SIMULINK下完成。我们旨在改进DDS的编程方法,简化DDS描述的配置和生成,并考虑实时网络驱动程序。 4. 为了验证我们的DDS实现并突出其在硬实时汽车系统环境中的贡献,我们详细说明了汽车网络的延迟计算,并介绍了计算最坏情况响应时间(WCRT)的实现算法。我们证明了DDS在SAE车辆应用程序之上的服务质量得到了满足。我们还通过使用实时网络FlexRay和以太网对系统性能进行了比较。
阅读全文

相关推荐

Algorithm 1: The online LyDROO algorithm for solving (P1). input : Parameters V , {γi, ci}Ni=1, K, training interval δT , Mt update interval δM ; output: Control actions 􏰕xt,yt􏰖Kt=1; 1 Initialize the DNN with random parameters θ1 and empty replay memory, M1 ← 2N; 2 Empty initial data queue Qi(1) = 0 and energy queue Yi(1) = 0, for i = 1,··· ,N; 3 fort=1,2,...,Kdo 4 Observe the input ξt = 􏰕ht, Qi(t), Yi(t)􏰖Ni=1 and update Mt using (8) if mod (t, δM ) = 0; 5 Generate a relaxed offloading action xˆt = Πθt 􏰅ξt􏰆 with the DNN; 6 Quantize xˆt into Mt binary actions 􏰕xti|i = 1, · · · , Mt􏰖 using the NOP method; 7 Compute G􏰅xti,ξt􏰆 by optimizing resource allocation yit in (P2) for each xti; 8 Select the best solution xt = arg max G 􏰅xti , ξt 􏰆 and execute the joint action 􏰅xt , yt 􏰆; { x ti } 9 Update the replay memory by adding (ξt,xt); 10 if mod (t, δT ) = 0 then 11 Uniformly sample a batch of data set {(ξτ , xτ ) | τ ∈ St } from the memory; 12 Train the DNN with {(ξτ , xτ ) | τ ∈ St} and update θt using the Adam algorithm; 13 end 14 t ← t + 1; 15 Update {Qi(t),Yi(t)}N based on 􏰅xt−1,yt−1􏰆 and data arrival observation 􏰙At−1􏰚N using (5) and (7). i=1 i i=1 16 end With the above actor-critic-update loop, the DNN consistently learns from the best and most recent state-action pairs, leading to a better policy πθt that gradually approximates the optimal mapping to solve (P3). We summarize the pseudo-code of LyDROO in Algorithm 1, where the major computational complexity is in line 7 that computes G􏰅xti,ξt􏰆 by solving the optimal resource allocation problems. This in fact indicates that the proposed LyDROO algorithm can be extended to solve (P1) when considering a general non-decreasing concave utility U (rit) in the objective, because the per-frame resource allocation problem to compute G􏰅xti,ξt􏰆 is a convex problem that can be efficiently solved, where the detailed analysis is omitted. In the next subsection, we propose a low-complexity algorithm to obtain G 􏰅xti, ξt􏰆. B. Low-complexity Algorithm for Optimal Resource Allocation Given the value of xt in (P2), we denote the index set of users with xti = 1 as Mt1, and the complementary user set as Mt0. For simplicity of exposition, we drop the superscript t and express the optimal resource allocation problem that computes G 􏰅xt, ξt􏰆 as following (P4) : maximize 􏰀j∈M0 􏰕ajfj/φ − Yj(t)κfj3􏰖 + 􏰀i∈M1 {airi,O − Yi(t)ei,O} (28a) τ,f,eO,rO 17 ,建立了什么模型

Another example is the SRIOV_NET_VF resource class, which is provided by SRIOV-enabled network interface cards. In the case of multiple SRIOV-enabled NICs on a compute host, different qualitative traits may be tagged to each NIC. For example, the NIC called enp2s0 might have a trait “CUSTOM_PHYSNET_PUBLIC” indicating that the NIC is attached to a physical network called “public”. The NIC enp2s1 might have a trait “CUSTOM_PHYSNET_INTRANET” that indicates the NIC is attached to the physical network called “Intranet”. We need a way of representing that these NICs each provide SRIOV_NET_VF resources but those virtual functions are associated with different physical networks. In the resource providers data modeling, the entity which is associated with qualitative traits is the resource provider object. Therefore, we require a way of representing that the SRIOV-enabled NICs are themselves resource providers with inventories of SRIOV_NET_VF resources. Those resource providers are contained on a compute host which is a resource provider that has inventory records for other types of resources such as VCPU, MEMORY_MB or DISK_GB. This spec proposes that nested resource providers be created to allow for distinguishing details of complex components of some resource providers. During review the question came up about “rolling up” amounts of these nested providers to the root level. Imagine this scenario: I have a NIC with two PFs, each of which has only 1 VF available, and I get a request for 2 VFs without any traits to distinguish them. Since there is no single resource provider that can satisfy this request, it will not select this root provider, even though the root provider “owns” 2 VFs. This spec does not propose any sort of “rolling up” of inventory, but this may be something to consider in the future. If it is an idea that has support, another BP/spec can be created then to add this behavior.

Recall that to solve (P2) in the tth time frame, we observe ξt 􏰗 {hti, Qi(t), Yi(t)}Ni=1, consisting of the channel gains {hti}Ni=1 and the system queue states {Qi(t),Yi(t)}Ni=1, and accordingly decide the control action {xt, yt}, including the binary offloading decision xt and the continuous resource allocation yt 􏰗 􏰄τit, fit, eti,O, rit,O􏰅Ni=1. A close observation shows that although (P2) is a non-convex optimization problem, the resource allocation problem to optimize yt is in fact an “easy” convex problem if xt is fixed. In Section IV.B, we will propose a customized algorithm to efficiently obtain the optimal yt given xt in (P2). Here, we denote G􏰀xt,ξt􏰁 as the optimal value of (P2) by optimizing yt given the offloading decision xt and parameter ξt. Therefore, solving (P2) is equivalent to finding the optimal offloading decision (xt)∗, where (P3) : 􏰀xt􏰁∗ = arg maximize G 􏰀xt, ξt􏰁 . (20) xt ∈{0,1}N In general, obtaining (xt)∗ requires enumerating 2N offloading decisions, which leads to significantly high computational complexity even when N is moderate (e.g., N = 10). Other search based methods, such as branch-and-bound and block coordinate descent [29], are also time-consuming when N is large. In practice, neither method is applicable to online decision- making under fast-varying channel condition. Leveraging the DRL technique, we propose a LyDROO algorithm to construct a policy π that maps from the input ξt to the optimal action (xt)∗, i.e., π : ξt 􏰕→ (xt)∗, with very low complexity, e.g., tens of milliseconds computation time (i.e., the time duration from observing ξt to producing a control action {xt, yt}) when N = 10.,为什么要使用深度强化学习

最新推荐

recommend-type

SCI论文写作框架及英文常用句型模板.pdf

- 描述方法时,可以采用:"We propose a new … model and … algorithm that enables us to …" 或 "In this paper, we describe improved … models for …"。 - 结果部分,例如:"This paper reports results ...
recommend-type

无人机巡检利器-YOLOv11电力设备缺陷检测与定位优化.pdf

想深入掌握目标检测前沿技术?Yolov11绝对不容错过!作为目标检测领域的新星,Yolov11融合了先进算法与创新架构,具备更快的检测速度、更高的检测精度。它不仅能精准识别各类目标,还在复杂场景下展现出卓越性能。无论是学术研究,还是工业应用,Yolov11都能提供强大助力。阅读我们的技术文章,带你全方位剖析Yolov11,解锁更多技术奥秘!
recommend-type

COMSOL模拟土石混合体孔隙渗流中的细颗粒迁移运动:多场多相介质耦合分析,基于COMSOL模拟的土石混合体孔隙渗流中的细颗粒迁移运动研究,COMSOL孔隙渗流下的细颗粒迁移运动 对土石混合体进行了

COMSOL模拟土石混合体孔隙渗流中的细颗粒迁移运动:多场多相介质耦合分析,基于COMSOL模拟的土石混合体孔隙渗流中的细颗粒迁移运动研究,COMSOL孔隙渗流下的细颗粒迁移运动。 对土石混合体进行了数值仿真,考虑了土石混合体孔隙变化,细颗粒侵蚀,骨架结构变形,此问题是一个多场(渗流场、变形场、应力场、损伤场)多相介质(土颗粒集合体,块石,空隙,孔隙)耦合的复杂问题。 ,COMSOL; 细颗粒迁移; 孔隙渗流; 土石混合体; 多场多相介质耦合。,COMSOL模拟土石混合体多场多相介质渗流与变形耦合效应研究
recommend-type

电力系统11节点无功补偿仿真研究:功率因数和谐波观察,线路阻抗参数可调,基于Matlab2018b及以上版本,电力系统11节点无功补偿仿真研究:功率因数和谐波观察,线路阻抗参数化调整,基于Matlab

电力系统11节点无功补偿仿真研究:功率因数和谐波观察,线路阻抗参数可调,基于Matlab2018b及以上版本,电力系统11节点无功补偿仿真研究:功率因数和谐波观察,线路阻抗参数化调整,基于Matlab 2018b及以上版本,电力系统11个节点无功补偿仿真,功率因数和谐波可观察,线路阻抗参数可改,matlab2018b及以上(可改版) ,电力系统仿真; 无功补偿; 功率因数; 谐波观察; 线路阻抗参数可改; MATLAB2018b及以上,MATLAB仿真平台:电力系统节点无功补偿及功率因数、谐波观测研究
recommend-type

Spring Websocket快速实现与SSMTest实战应用

标题“websocket包”指代的是一个在计算机网络技术中应用广泛的组件或技术包。WebSocket是一种网络通信协议,它提供了浏览器与服务器之间进行全双工通信的能力。具体而言,WebSocket允许服务器主动向客户端推送信息,是实现即时通讯功能的绝佳选择。 描述中提到的“springwebsocket实现代码”,表明该包中的核心内容是基于Spring框架对WebSocket协议的实现。Spring是Java平台上一个非常流行的开源应用框架,提供了全面的编程和配置模型。在Spring中实现WebSocket功能,开发者通常会使用Spring提供的注解和配置类,简化WebSocket服务端的编程工作。使用Spring的WebSocket实现意味着开发者可以利用Spring提供的依赖注入、声明式事务管理、安全性控制等高级功能。此外,Spring WebSocket还支持与Spring MVC的集成,使得在Web应用中使用WebSocket变得更加灵活和方便。 直接在Eclipse上面引用,说明这个websocket包是易于集成的库或模块。Eclipse是一个流行的集成开发环境(IDE),支持Java、C++、PHP等多种编程语言和多种框架的开发。在Eclipse中引用一个库或模块通常意味着需要将相关的jar包、源代码或者配置文件添加到项目中,然后就可以在Eclipse项目中使用该技术了。具体操作可能包括在项目中添加依赖、配置web.xml文件、使用注解标注等方式。 标签为“websocket”,这表明这个文件或项目与WebSocket技术直接相关。标签是用于分类和快速检索的关键字,在给定的文件信息中,“websocket”是核心关键词,它表明该项目或文件的主要功能是与WebSocket通信协议相关的。 文件名称列表中的“SSMTest-master”暗示着这是一个版本控制仓库的名称,例如在GitHub等代码托管平台上。SSM是Spring、SpringMVC和MyBatis三个框架的缩写,它们通常一起使用以构建企业级的Java Web应用。这三个框架分别负责不同的功能:Spring提供核心功能;SpringMVC是一个基于Java的实现了MVC设计模式的请求驱动类型的轻量级Web框架;MyBatis是一个支持定制化SQL、存储过程以及高级映射的持久层框架。Master在这里表示这是项目的主分支。这表明websocket包可能是一个SSM项目中的模块,用于提供WebSocket通讯支持,允许开发者在一个集成了SSM框架的Java Web应用中使用WebSocket技术。 综上所述,这个websocket包可以提供给开发者一种简洁有效的方式,在遵循Spring框架原则的同时,实现WebSocket通信功能。开发者可以利用此包在Eclipse等IDE中快速开发出支持实时通信的Web应用,极大地提升开发效率和应用性能。
recommend-type

电力电子技术的智能化:数据中心的智能电源管理

# 摘要 本文探讨了智能电源管理在数据中心的重要性,从电力电子技术基础到智能化电源管理系统的实施,再到技术的实践案例分析和未来展望。首先,文章介绍了电力电子技术及数据中心供电架构,并分析了其在能效提升中的应用。随后,深入讨论了智能化电源管理系统的组成、功能、监控技术以及能
recommend-type

通过spark sql读取关系型数据库mysql中的数据

Spark SQL是Apache Spark的一个模块,它允许用户在Scala、Python或SQL上下文中查询结构化数据。如果你想从MySQL关系型数据库中读取数据并处理,你可以按照以下步骤操作: 1. 首先,你需要安装`PyMySQL`库(如果使用的是Python),它是Python与MySQL交互的一个Python驱动程序。在命令行输入 `pip install PyMySQL` 来安装。 2. 在Spark环境中,导入`pyspark.sql`库,并创建一个`SparkSession`,这是Spark SQL的入口点。 ```python from pyspark.sql imp
recommend-type

新版微软inspect工具下载:32位与64位版本

根据给定文件信息,我们可以生成以下知识点: 首先,从标题和描述中,我们可以了解到新版微软inspect.exe与inspect32.exe是两个工具,它们分别对应32位和64位的系统架构。这些工具是微软官方提供的,可以用来下载获取。它们源自Windows 8的开发者工具箱,这是一个集合了多种工具以帮助开发者进行应用程序开发与调试的资源包。由于这两个工具被归类到开发者工具箱,我们可以推断,inspect.exe与inspect32.exe是用于应用程序性能检测、问题诊断和用户界面分析的工具。它们对于开发者而言非常实用,可以在开发和测试阶段对程序进行深入的分析。 接下来,从标签“inspect inspect32 spy++”中,我们可以得知inspect.exe与inspect32.exe很有可能是微软Spy++工具的更新版或者是有类似功能的工具。Spy++是Visual Studio集成开发环境(IDE)的一个组件,专门用于Windows应用程序。它允许开发者观察并调试与Windows图形用户界面(GUI)相关的各种细节,包括窗口、控件以及它们之间的消息传递。使用Spy++,开发者可以查看窗口的句柄和类信息、消息流以及子窗口结构。新版inspect工具可能继承了Spy++的所有功能,并可能增加了新功能或改进,以适应新的开发需求和技术。 最后,由于文件名称列表仅提供了“ed5fa992d2624d94ac0eb42ee46db327”,没有提供具体的文件名或扩展名,我们无法从这个文件名直接推断出具体的文件内容或功能。这串看似随机的字符可能代表了文件的哈希值或是文件存储路径的一部分,但这需要更多的上下文信息来确定。 综上所述,新版的inspect.exe与inspect32.exe是微软提供的开发者工具,与Spy++有类似功能,可以用于程序界面分析、问题诊断等。它们是专门为32位和64位系统架构设计的,方便开发者在开发过程中对应用程序进行深入的调试和优化。同时,使用这些工具可以提高开发效率,确保软件质量。由于这些工具来自Windows 8的开发者工具箱,它们可能在兼容性、效率和用户体验上都经过了优化,能够为Windows应用的开发和调试提供更加专业和便捷的解决方案。
recommend-type

如何运用电力电子技术实现IT设备的能耗监控

# 摘要 随着信息技术的快速发展,IT设备能耗监控已成为提升能效和减少环境影响的关键环节。本文首先概述了电力电子技术与IT设备能耗监控的重要性,随后深入探讨了电力电子技术的基础原理及其在能耗监控中的应用。文章详细分析了IT设备能耗监控的理论框架、实践操作以及创新技术的应用,并通过节能改造案例展示了监控系统构建和实施的成效。最后,本文展望了未来能耗监控技术的发展趋势,同时
recommend-type

2635.656845多位小数数字,js不使用四舍五入保留两位小数,然后把结果千分位,想要的结果是2,635.65;如何处理

在JavaScript中,如果你想要将2635.656845这个数字精确地保留两位小数,并且去掉多余的千分位,可以使用`toFixed()`函数结合字符串切片的方法来实现。不过需要注意的是,`toFixed()`会返回一个字符串,所以我们需要先转换它。 以下是一个示例: ```javascript let num = 2635.656845; // 使用 toFixed() 保留两位小数,然后去掉多余的三位 let roundedNum = num.toFixed(2).substring(0, 5); // 如果最后一个字符是 '0',则进一步判断是否真的只有一位小数 if (round