检索结果-内蒙古大学图书馆

2024 International Conference on Optoelectronic Materials and Devices, ICOMD 2024

作者： Zhang, Quan Qing, Chao Zuo, Chenglin Hu, Jiahui Li, Yan School of Computer Science and Software Engineering Southwest Petroleum University Chengdu610500 China Low Speed Aerodynamics Institute China Aerodynamics Research and Development Center Sichuan Mianyang621000 China Key Laboratory of Icing and Anti/De-Icing China Aerodynamics Research and Development Center Mianyang621000 China Intelligent Oil and Gas Laboratory Southwest Petroleum University Chengdu610500 China

ISBN: (数字)9781510689046

ISBN: (纸本)9781510689039

The uniformity of cloud distribution is a critical metric for evaluating the performance of icing wind tunnels, directly affecting the accuracy of experimental results. To address the challenge of measuring cloud distribution in wind tunnels, this paper proposes a solution based on extinction tomography. A rectangular cross-sectional imaging system was developed specifically for rectangular wind tunnel structures, overcoming the limitations of traditional ring-shaped systems. To resolve the issue of insufficient projections, an iterative reconstruction algorithm combined with regularization techniques was employed for accurate image reconstruction. Additionally, the BM3D denoising algorithm was applied to enhance image quality. The results of simulation experiments demonstrate that the system effectively improves the PSNR and SSIM of reconstructed images under both Gaussian and speckle noise conditions, significantly enhancing the accuracy of cloud distribution measurements. © 2025 SPIE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation

Fine-grained Domain Adaptive Crowd Counting via Point-derive...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yongtuo Liu Dan Xu Sucheng Ren Hanjie Wu Hongmin Cai Shengfeng He School of Computer Science South China University of Technology Institute of Informatics University of Amsterdam Department of Computer Science and Engineering Hong Kong University of Science and Technology School of Computing and Information Systems Singapore Management University

Due to domain shift, a large performance drop is usually observed when a trained crowd counting model is deployed in the wild. While existing domain-adaptive crowd counting methods achieve promising results, they typically regard each crowd image as a whole and reduce domain discrepancies in a holistic manner, thus limiting further improvement of domain adaptation performance. To this end, we propose to untangle domain-invariant crowd and domain-specific background from crowd images and design a fine-grained domain adaption method for crowd counting. Specifically, to disentangle crowd from background, we propose to learn crowd segmentation from point-level crowd counting annotations in a weakly-supervised manner. Based on the derived segmentation, we design a crowd-aware domain adaptation mechanism consisting of two crowd-aware adaptation modules, i.e., Crowd Region Transfer (CRT) and Crowd Density Alignment (CDA). The CRT module is designed to guide crowd features transfer across domains beyond background distractions. The CDA module dedicates to regularising target-domain crowd density generation by its own crowd density distribution. Our method outperforms previous approaches consistently in the widely-used adaptation scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Stochastic Proximal WMMSE for Ergodic Sum Rate Maximization

A Stochastic Proximal WMMSE for Ergodic Sum Rate Maximizatio...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiaotong Zhao Xi Wang Juncheng Wang Qingjiang Shi School of Software Engineering Tongji University Shanghai China Department of Computer Science Hong Kong Baptist University Hong Kong China Shenzhen Research Institute of Big Data Shenzhen China

We consider ergodic weighted sum rate (WSR) maximization in a massive multi-user multiple-input multiple-output system. Existing solutions iteratively minimize the average WSR based on all the historical information, and use bisection search to satisfy the power constraint at each iteration, resulting in both high storage burden and high computational complexity. In contrast, we propose an efficient stochastic proximal weighted minimum mean-square error (SPWMMSE) algorithm, which updates the precoder only based on the current single channel realization, without checking the power constraint at each iteration. Furthermore, we propose a novel proximal term to incorporate all the previous channel and surrogate function information in precoder updates. Our analysis shows that SPWMMSE converges to the stationary point of the original ergodic WSR maximization problem almost surely. Simulation results demonstrate the effectiveness of SPWMMSE over the current best alternatives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Random Distribution Choices on Particle Swarm Optimization: An Initial Analysis 27

Exploring the Impact of Random Distribution Choices on Parti...

引用

27th International Conference on Knowledge Based and Intelligent Information and engineering Sytems, KES 2023

作者： Kolodziejczyk, Joanna Tarasenko, Yuliia Sulikowski, Piotr Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence Methods and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Zolnierska 49 Szczecin71-210 Poland National Institute of Telecommunications ul. Szachowa 1 Warsaw04-894 Poland Department of Information Systems Engineering Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Zolnierska 49 Szczecin71-210 Poland

Particle Swarm Optimization (PSO) is a robust stochastic optimization algorithm for solving complex and constrained optimization problems. This paper aims to systematically investigate the influence of diverse random number distributions on the learning parameters of PSO and evaluate the algorithm's sensitivity based on these parameters. To this end, several exhaustive numerical experiments were conducted on several test functions, including asymmetric Sphere, Easom, and Csendes. Initially, appropriate random distributions were identified for the learning parameters and proceeded to compare these distributions using all potential combinations. The sensitivity of PSO to these parameters was evaluated using the mean best score, the relative proximity of the best particle to the theoretical optimum, and the average objective function evaluations. The most significant contribution of this research lies in the insights derived from the experimental data. The discovery was that highly skewed and long-tailed distributions such as Chi, Chi-square, Lomax, and Exponential often underperform. On the other hand, distributions that are bounded proportionally to the problem domain consistently surpass the performance of the standard uniform distribution. These findings significantly enhance the understanding of PSO algorithms and provide valuable guidelines for their practical deployment. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Particle Swarm Optimization random number distribution stochastic optimization

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Detection of Malicious Volt-VAr Control Parameters in Smart Inverters

arXiv

引用

arXiv 2023年

作者： Saber, Ahmad Mohammad Youssef, Amr Svetinovic, Davor Zeineldin, Hatem El-Saadany, Ehab Electrical Engineering and Computer Science Department Khalifa University Abu Dhabi United Arab Emirates Concordia Institute for Information Systems Engineering MontrealQC Canada

Distributed Volt-Var Control (VVC) is a widely used control mode of smart inverters. However, necessary VVC curve parameters are remotely communicated to the smart inverter, which opens doors for cyberattacks. If VVC curves of an inverter are maliciously manipulated, the attacked inverter's reactive power injection will oscillate, causing undesirable voltage oscillations to manifest in the distribution system, which, in turn, threatens the system's stability. In contrast with previous works which proposed methods to mitigate the oscillations after they are already present in the system, this paper presents an intrusion detection method to detect malicious VVC curves once they are communicated to the inverter. The proposed method utilizes a Multi-Layer Perceptron (MLP) that is trained on features extracted from only the local measurements of the inverter. After a smart inverter is equipped with the proposed method, any communicated VVC curve will be verified by the MLP once received. If the curve is found to be malicious, it will be rejected, thus preventing unwanted oscillations beforehand. Otherwise, legitimate curves will be permitted. The performance of the proposed scheme is verified using the 9-bus Canadian urban benchmark distribution system simulated in PSCAD/EMTDC environment. Our results show that the proposed solution can accurately detect malicious VVC curves. © 2023, CC BY-NC-SA.

关键词： Distributed power generation

来源：评论

学校读者我要写书评

暂无评论

The impact of Mânuka-dominated riparian on lake’s water quality – a multi-source remote sensing approach

The impact of Mânuka-dominated riparian on lake’s water qu...

引用

Machine Intelligence for GeoAnalytics and Remote Sensing (MIGARS), International Conference on

作者： Simna Rassak Alvaro Orsi Albert Bifet María Jesús Gutiérrez Ginés Kristin Bohm Kevin I-Kai Wang Akshat Bisht Department of Computer Science Institute of Environmental Science and Research(ESR) University of Waikato Hillcrest Hamilton New Zealand Institute of Environmental Science and Research(ESR) Auckland New Zealand Department of Computer Science University of Waikato Hillcrest Hamilton New Zealand Institute of Environmental Science and Research(ESR) Porirua New Zealand Department of Electrical Computer and Software Engineering University of Auckland Auckland Central Auckland New Zealand University of Auckland Auckland Central Auckland New Zealand

ISBN: (数字)9798350389678

ISBN: (纸本)9798350389685

Mânuka trees in riparian plantings on lake banks can improve water quality and its ecosystem. In this study, we used multisource remote sensing data analysis on a mânuka experiment plot in Lake Waikare catchment to understand the role of Mânuka trees in mitigating pollution and climate change effects. We evaluate experiment plots with and without Mânuka trees. We compare soil moisture sensors in both these areas and calculate soil water retention and soil loss.

关键词： Soil moisture Ecosystems Vegetation mapping Vegetation Water quality Lakes Water pollution

来源：评论

学校读者我要写书评

暂无评论

A Novel Adaptive Perturbation-Based Method for Long-Tailed Open Sets Recognition

SSRN

引用

SSRN 2023年

作者： Ngueilbaye, Alladoumbaye Zhang, Qin Yang, Hongye Zhang, Xiaolin Zhang, Peng Chen, Xiaojun Huang, Joshua Zhexue Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

Real-world data often have a long-tailed and open-ended distribution. A reliable practical machine learning system need to learn from the majority classes and also generalize to minority *** achieve this, acknowledge the minority and the novel class samples, and avoid misclassifying them into one of the majority classes are of great significance. Long-tailed Open Set Recognition aims to learn from the naturally distributed long-tailed and open-ended data, by using the easy-gained head class samples to learn the fundamental information, and also try to improve the out-of-distribution generalization ability by identifying the tail class and open-set class samples as novelty to avoid the misclassification. The key challenges for long-tailed open set recognition is the tail and open-set sensitivity, since they can be easily biased towards dominant classes and perform ineffectively on close-set dataset classes. Inspired by techniques on open set recognition, in this paper, we propose a Class-aware Input Preprocessing (CLAIP) approach to improve the detection of the Out-of-distribution samples by perturbing the input images. In this approach, we employ two techniques to leverage its performance. First, we introduce the middle class samples as auxiliary data during the network training process to force each category's boundaries. Second, we add a Class-aware Input Preprocessing module that can be easily plugged into the testing process by perturbing the salient regions of the input images to further improve the out-of-distribution generalization. The experimental results show that CLAIP achieves high quality and significant performance compared to the existing solutions. © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Implementation of IoT and WSN Technologies for Health Monitoring 1st

Implementation of IoT and WSN Technologies for Health Monito...

引用

1st International Conference on Computing and Emerging Technologies, ICCET 2023

作者： Mazhar, Tehseen Iqbal, Muhammad Iqbal, Muhammad Ghadi, Yazeed Yasin Rehman, Ateeq Ur Abbasi, Waseem Department of Computer Science Virtual University of Pakistan Lahore54000 Pakistan Institute of Computing and Information Technology Gomal University Dera Ismail Khan29220 Pakistan Department of Computer Science and Software Engineering Al Ain Universit Abu Dhabi15322 United Arab Emirates Department of Electrical Engineering Government College University Lahore54000 Pakistan Department of Computer Science and IT Superior University Sargodha Pakistan

ISBN: (纸本)9783031776168

IoT-based applications make innovative use of millions of sensors. Research has risen in the medical and technological fields in the previous ten years. The Internet of Things impacts the development of medical research. Improved medical care is possible because the Internet of Things can link sensors, medical equipment, and remote healthcare professionals. Patient treatment has been enhanced in terms of effectiveness, cost, accessibility, and safety. Due to COVID-19, receiving medical treatment in the convenience of one’s home is more important than ever. To enhance healthcare, internet of things devices is utilized to monitor patients. His article examines how the Internet of Things has improved, enabling technology, healthcare services, and healthcare-related challenges. IoT system concerns are also taken into consideration. This effort aims to help future researchers understand the topic better by giving a thorough overview of all of HIoT’s many uses. The applications, technology, and challenges of the healthcare industry are all examined in this article. As a result, the IoT has the potential to improve healthcare’s effectiveness and ability to treat patients. The idea put out in this article is that the Internet of Things may be made widely used, lucrative, and easily available everywhere. The integration provides a faster calculation. The last section includes a number of practical recommendations and suggestions for implementing the IoT healthcare system during COVID-19 and future severe pandemics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Crowdsensed Data-oriented Distributed and Secure Spatial Query Scheme

Crowdsensed Data-oriented Distributed and Secure Spatial Que...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Yuxi Li Fucai Zhou Jingjing Chen Dong Ji School of Computer Science and Engineering Northeastern University Shenyang China Software College Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Focusing on the privacy concerns and leakage abuse of sensory data collection in mobile crowdsensing (MCS) environment, we propose a crowdsensed data-oriented distributed and secure spatial query scheme while ensuring data privacy as long as query patterns. To cater to the demands of real-world MCS workloads, we designed a distributed multi-layer architecture and leveraged distributed hash functions(DHT) and broadcast encryption(BE) to achieve load-balancing and enforce access control. Our scheme incorporates a recently developed cryptographic tool–function secret sharing (FSS) to safeguard the query pattern and sensory data from potential compromises at the server *** analysis demonstrates that our scheme achieves affordable query complexity while satisfying adaptive $\mathcal{L}$-semantic security. Encouraging experimental results substantiate the efficacy of our scheme, the growth rates of query cost diminishes as the number of records and participants increases. These findings emphasize the suitability of our scheme for crowdsensing applications with fine-grained access control requirements and establish it as an efficient cryptographic tool that holds promise for diverse MCS applications.

关键词： Access control Data privacy Costs Crowdsensing Focusing Data collection Complexity theory

来源：评论

学校读者我要写书评

暂无评论

2021 Monthly Rice Production in Chinese Coastal Provinces 3

2021 Monthly Rice Production in Chinese Coastal Provinces

引用

3rd International Conference on Big Data Analytics and Practices, IBDAP 2022

作者： Parmar, Ajeet Munasinghe, Thilanka Tubbs, Heidi Anyamba, Assaf Rensselaer Polytechnic Institute Department of Electrical Computer and Systems Engineering Troy United States Rensselaer Polytechnic Institute Department of Information Technology and Web Science Troy United States Oak Ridge National Laboratory Geospatial Science and Human Security Division Oak Ridge United States

ISBN: (数字)9781665469388

ISBN: (纸本)9781665469388

This paper explores the dynamics of rice production in the Chinese provinces of Liaoning, Jilin, Heilongjiang, Shanghai, Jiangsu, and Zhejiang and seeks to predict monthly rice production in the months of April through October using precipitation and Normalized Difference Vegetation Index as the predictor variables available. We utilize ridge and lasso regression models to predict the rice yield. Results indicate that a lasso regression model with an R2 value of 0.9991501 with an adjusted R2 value of 0.9991502 and a ridge regression model with an R2 value of 0.9865443 with an adjusted R2 value of 0.9870637 are possible. The lasso regression model does not account for all predictor variables while the ridge regression model does. Both models could be expanded upon to include more observations. © 2022 IEEE.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：