检索结果-内蒙古大学图书馆

9th International Conference on Cloud Computing and Internet of Things, CCIOT 2024

作者： Pu, Tongyu Zeng, Kai Bai, Fenhua Zhang, Chi Zhang, Xiaohui Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming China

ISBN: (纸本)9798400717161

Preserving privacy has become crucial in the field of location-based services (LBS) to leverage their full potential while protecting users from untrustworthy LBS providers. Given that LBS users typically use resource-constrained mobile devices, many existing privacy-preserving methods focus on anonymization. However, these methods have certain limitations regarding privacy protection and efficiency. This paper introduces a novel Privacy-preserving LBS scheme to address these issues. We develop an efficient query mechanism where users send encrypted distance queries to the server. The server then employs a PFR-tree and homomorphic encryption to filter Points of Interest (POIs) in a hierarchical manner. The PFR-tree quickly eliminates irrelevant regions based on their locations, minimizing unnecessary computations and enhancing query efficiency. Experimental results indicate that this PFR-tree-based scheme significantly reduces query time compared to traditional methods without a PFR tree, especially as the number of POIs increases, demonstrating superior performance and efficiency in scenarios with many POIs. This approach effectively meets privacy protection needs for indoor navigation in cloud environments while maintaining high efficiency and security. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A Columnar Storage Cone Search Method for Massive Astronomical Data 5

A Columnar Storage Cone Search Method for Massive Astronomic...

引用

5th International Conference on information science, Parallel and Distributed Systems, ISPDS 2024

作者： Liu, Yu-Hai Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9798350352719

In recent years, with the continuous advancement of astronomical instrument manufacturing technology, astronomical observation data has shown an exponential growth trend, and traditional database technologies are no longer able to meet the storage and retrieval performance requirements. To address the challenges of storing massive astronomical data and efficient cone search, a solution utilizing columnar storage is proposed, leveraging the separate storage of each attribute column in columnar storage for independent retrieval to enhance data read efficiency. Building upon this, a specialized cone search area retrieval method tailored for columnar storage mode is introduced to reduce data read and computation in cone search, further enhancing retrieval efficiency. © 2024 IEEE.

关键词： Storage efficiency

来源：评论

学校读者我要写书评

暂无评论

Adversarial dual decision-based model for event-related opinion sentence recognition

引用

Multimedia Tools and Applications 2024年 1-18页

作者： Xiang, Yan Qin, Yuan Yu, Zhengtao Huang, Yuxin Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China

Event-related opinion sentences recognition aims to mine the valuable comments discussing about the specific event from the mass of microblogs comments. It’s difficult to label sufficient comments for a new microblogs event, and domain adaptation methods are suitable for this task, which can transfer the knowledge from the source domain(labeled event) to the target domain (unlabeled event). However, existing domain adaptation models do not make full use of the domain invariance to realize categories alignments of the two domains. Therefore, we propose a adversarial dual decision model for opinion sentences recognition, which takes advantage of the domain invariance that the opinion sentences are correlated with the event description. The proposed model has two generators to obtain different event-correlated features, and two classifiers to make dual decisions based on the two features. Through the adversarial process of generators and classifiers, the model completes the category feature alignment and realizes the opinion sentences recognition for the new event. The comparative experiment results show that our model outperforms the state-of-the-art models on six opinion sentences recognition tasks. In addition, we verify the effectiveness of each component of our model by ablation experiments. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A CNNSENet-PSO-SVM approach for multi-classification of mass spectrometry

Journal of Biotech Research

引用

Journal of Biotech Research 2024年 18卷 252-261页

作者： Wu, Liping Pan, Jiayao Xiang, Cheng Yang, Zhou Li, Yong Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming China Faculty of Life Sciences and Technology Kunming University of Science and Technology Yunnan Kunming China Zunyi Medical University Guizhou Zunyi China

Mass spectrometry (MS) is a technique used to determine the mass of molecules or atoms within a sample and their relative abundance. It can identify unknown compounds by comparing their mass spectra to known spectra in databases, which helps the determinations of the molecular formula and structure of the compound. However, the current cost of commercially available software is high, and there are relatively few applications of machine learning and deep learning methods in mass spectrometry recognition. To tackle these issues, a convolutional neural network within squeeze and excitation net-particle swarm optimization-support vector machine (CNNSENet-PSO-SVM) was proposed for multi-classification of mass spectrometry data. The method aimed to provide an effective and accurate mass spectra multi-classification method combining machine learning with deep learning to identify unknown mass spectra in mass spectral libraries. The approach involved preprocessing the original molecular compound mass spectrometry dataset using mass-to-charge ratio and intensity values as input and employing CNN for feature extraction. A channel attention mechanism module, SENet, was integrated within CNN to enhance feature extraction capabilities. Subsequently, the extracted feature vectors were fed into SVM with parameters optimized using the PSO algorithm for classification. Compared to traditional methods, the proposed model achieved an accuracy rate of 90.55% on the test set, demonstrating its potential for analyzing small molecular compound MS data. © (2023), (Bio Tech System). All Rights Reserved.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Research on MEC computing offload strategy for joint optimization of delay and energy consumption

引用

Mathematical Biosciences and engineering 2024年第6期21卷 6336-6358页

作者： Ni, Mingchang Zhang, Guo Yang, Qi Yin, Liqiong Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650504 China Kunming Iron & Steel Holding Co. Ltd. Kunming650302 China

The decision-making process for computational offloading is a critical aspect of mobile edge computing, and various offloading decision strategies are strongly linked to the calculated latency and energy consumption of the mobile edge computing system. This paper proposes an offloading scheme based on an enhanced sine-cosine optimization algorithm (SCAGA) designed for the "edge-end" architecture scenario within edge computing. The research presented in this paper covers the following aspects: (1) Establishment of computational resource allocation models and computational cost models for edge computing scenarios;(2) Introduction of an enhanced sine and cosine optimization algorithm built upon the principles of Levy flight strategy sine and cosine optimization algorithms, incorporating concepts from roulette wheel selection and gene mutation commonly found in genetic algorithms;(3) Execution of simulation experiments to evaluate the SCAGA-based offloading scheme, demonstrating its ability to effectively reduce system latency and optimize offloading utility. Comparative experiments also highlight improvements in system latency, mobile user energy consumption, and offloading utility when compared to alternative offloading schemes. © 2024 the Author(s).

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Detection of Flare-related Decaying and Decayless Kink Oscillations Using Jerk-aware Motion Magnification

引用

Research in Astronomy and Astrophysics 2022年第11期22卷 130-136页

作者： Xiaowei Guo Bo Liang Song Feng Wei Dai Yunfei Yang Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China

Kink oscillations of coronal loops are often influenced by external events and this results in various changes of the *** the changes can provide valuable information for understanding kink *** observation focuses on a flare region acquired by the Atmospheric Imaging Assembly on the Solar Dynamics Observatory spacecraft on 2016 March *** are a bunch of arched loops and an open loop near the ***,their oscillations show very low *** we used the jerk-aware motion method to magnify the weak *** found that before the flare onset at 02:59 UT,there were some large loops above the arched loops being raised *** properties of the weak oscillations show clear *** the one hand,the oscillations in the arched loops were decayless initially,but both their amplitude and period increased after 02:30 UT and before the flare *** enhanced,the oscillations decayed with *** the other hand,the oscillations in the open loop were nearly constant before and after 02:30 UT,but their period *** means that the changes in periods and amplitudes of oscillations are likely associated with the loops raised before the flare.

关键词： Sun:corona Sun:oscillations Sun:flares waves

来源：评论

学校读者我要写书评

暂无评论

MSF-TransUNet: A Multi-Scale Fusion Approach for Precise Cardiac Image Segmentation 24

MSF-TransUNet: A Multi-Scale Fusion Approach for Precise Car...

引用

4th International Conference on Artificial Intelligence, Big Data and Algorithms, CAIBDA 2024

作者： Zhang, Nuorui Li, Jingtao Faculty of Information Engineering and Automation Kunming University of Science & Technology Kunming Yunnan China

ISBN: (纸本)9798400710247

Cardiac image segmentation is crucial in the detection and treatment of cardiovascular disorders. The complexity of cardiac anatomy, morphological variations under different pathological conditions, and inconsistencies in imaging quality pose significant challenges to existing medical image segmentation methods. In order to tackle these difficulties, this work presents the MSF-TransUNet, an innovative structure specifically developed for the purpose of segmenting cardiac images. This model harnesses the synergistic capabilities of Convolutional Neural Networks (CNNs) and Transformer architectures to tackle the intricacies of cardiac anatomy and variations in imaging conditions. The MSF-TransUNet incorporates an Efficient Pyramid Squeeze Attention Network (EPSANet) as its encoder, enhancing multi-scale feature representation and long-range channel dependencies. Additionally, a Multi-Scale Fusion Module (MSFM) is developed to integrate multi-scale features from various encoder layers within the skip connections, utilizing convolution operations and the SCSE attention mechanism for efficient feature fusion. To overcome the challenges of cardiac structural complexity and data imbalance, the model introduces an Adaptive t-vMF Dice Loss, dynamically adjusting similarity metrics to enhance segmentation performance across different categories and regions. Extensive evaluations on two widely used cardiac image segmentation datasets, CAMUS and ACDC, demonstrate that the MSF-TransUNet outperforms existing state-of-the-art models on several metrics. Notably, our model achieves average Dice coefficients of 0.9243 and 0.9206, showcasing its flexibility and accuracy in handling scenarios with poor image quality or complex cardiac anatomy. © 2024 Copyright held by the owner/author(s).

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A classification method for compound mass spectrum data based on the Flex-Bootstrap method and Resnet network 43

A classification method for compound mass spectrum data base...

引用

43rd Chinese Control Conference, CCC 2024

作者： Pan, Jiayao Wu, Li Ping Li, Yong Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China

ISBN: (纸本)9789887581581

Aiming at the low accuracy of mass spectrum data recognition due to the subjectivity of artificial feature extraction and the limitation of a single sample and unbalanced mass spectrum data in current research, a classification method based on the fusion of the Flex-Bootstrap and Residual Network models is proposed and compared with the DNN model and the fusion model of CNN and DNN. The Flex-Bootstrap method and Resnet fusion model used the Flex-Bootstrap method to expand the combined mass spectrum data perform sparse sequence representation and use the extracted feature vectors to construct the Resnet model. Compared with the traditional classification methods, the proposed method achieves better results in classifying small molecule compounds by mass spectrum data. The accuracy of the test set is increased to 98.894%, and the loss function value is reduced to 0.0502. This model effectively solves the problem of underfitting when using the DNN and the fusion models of CNN and DNN for data classification and improves the prediction accuracy and search efficiency for the mass spectrum database. © 2024 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Influence of Vapour-Liquid Channel Distribution on the Performance of Flat-Plate Heat Pipes 5

Influence of Vapour-Liquid Channel Distribution on the Perfo...

引用

5th International Conference on Smart Grid and Energy engineering, SGEE 2024

作者： Zhu, Chenyu Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China

ISBN: (纸本)9798331530686

With the progress of technology and the development of industrialisation, power electronic equipment is developing towards high performance and miniaturisation, and its heat dissipation needs are gradually increasing. Efficient thermal management technology plays an important role in the stable operation of power electronic equipment. Flat-plate heat pipe(FHP)s utilise the principle of internal phase change, and are characterised by the absence of external power drive and high thermal conductivity, which helps to reduce the overall energy consumption and extend the service life of power electronic systems. Improving the performance of FHP has become a hot research topic. In this paper, we analyse the heat transfer principle of FHP and find that a reasonable vapour-liquid channel ratio has an important influence on the efficiency of vapour-liquid two-phase flow, thus improving the heat exchange capability of FHP. To this end, we change the vapour-liquid channel ratio by changing the wick width, set up an experimental test platform, and find that the FHP with a vapour-liquid channel ratio of 160% has the optimal heat exchange capability. © 2024 IEEE.

关键词： device optimisation energy saving performance testing thermal management

来源：评论

学校读者我要写书评

暂无评论

Predictive Study of Uniformity of Variable Frequency Microwave Heating Based on PSO-SVM

Predictive Study of Uniformity of Variable Frequency Microwa...

引用

2024 International Conference on Optics, Electronics, and Communication engineering, OECE 2024

作者： Yang, Biao Yang, Ying Liu, Bingyan Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming China

ISBN: (纸本)9781510685437

Due to the complexity of temporal and spatial characteristics during microwave heating, the unpredictability of the magnetic field makes it difficult to accurately predict the heating effect by traditional modeling methods. Aiming at the problems of uneven material temperature distribution and unpredictable heating results during microwave heating, a variable frequency strategy is proposed to improve the heating uniformity and estimate the heating effect using a support vector machine. Firstly, this paper proposes variable frequency heating to move the hot spot position according to the fixed frequency heating effect. Then the particle swarm optimization (PSO) algorithm support vector machine (SVM) model is introduced to predict the uniformity index of variable microwave heating. The numerical calculation results show that the proposed method has accurate prediction results for the heating results of the variable strategy. © 2024 SPIE.

关键词： Particle swarm optimization (PSO)

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：