检索结果-内蒙古大学图书馆

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Sridharan, S. Satheeshkumar, K. Rajesh, R. Deivasigamani, Sugitha Department of Computer Science and Engineering Nagapattinam India

ISBN: (纸本)9798350375190

data mining is an endeavor to identify patterns, correlations, similarities, and links among massive datasets in order to uncover hidden, intriguing information. The goal of clustering is to arrange data sets that share similar attributes into groups, or clusters. The gene data are enormous, complex, and contain information on gene expression simultaneously, making it difficult to manage the unmanageable amount of data. The massive volume of data makes cluster analysis and interpretation difficult. Self-organizing maps are thought to be a helpful method for evaluating and visualizing high dimensional gene data for machine learning algorithms. An instrument for the best cluster mining in gene samples is the Firefly algorithm. This approach helps to improve visualization and suggests a fresh angle for identifying reliable clusters from the massive amounts of gene expression data. The results of this work yield the most accurate and optimal clusters from the large gene data sets. © 2024 ieee.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Revisiting JPEG2000 for efficient and adaptable virtual microscopy 20

Revisiting JPEG2000 for efficient and adaptable virtual micr...

引用

20th International symposium on Medical Information Processing and analysis

作者： Iregui, Marcela Cano, Fabian Ortiz, Bayron Alvarez-Jimenez, Charlems Romero, Eduardo Victorino, Jorge Univ Mil Nueva Granada ACCEDER Res Grp Bogota Colombia Univ Nacl Colombia Cim Lab Res Grp Bogota Colombia

ISBN: (纸本)9798331528669;9798331528652

Digital pathology is still far from actual clinic applications, among others because the dominant Whole Slide Image (WSI) format structures information as a pyramid of the WSI at different resolutions. Both the construction of the pyramid and its navigation are relatively inefficient in terms of the required needs of actual cloud applications with many users interacting. This paper presents a novel strategy that boosts the intrinsic advantages of the JPEG2000 format with real pathology cases, making it possible natural JPEG2000 integration with existing WSI viewers. Unlike traditional methods that rely on pyramidal image representations, the proposed approach eliminates the dependency on such intermediary structures, highly improving the digital pathology workflow. Experimental results demonstrate a substantial reduction of 86% in storage space while server-client data exchange is improved in a 30% when comparing with the traditional pyramidal approach.

关键词： JPEG2000 Telepathology Remote visualization Whole Slide Images

来源：评论

学校读者我要写书评

暂无评论

THE POTENTIAL OF LOW-FREQUENCY POLARIMETRIC SAR data FOR SOIL CARBON CONTENT RETRIEVAL IN THE ARCTIC

THE POTENTIAL OF LOW-FREQUENCY POLARIMETRIC SAR DATA FOR SOI...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Yi, Yonghong Tabatabaeenejad, Alireza Fluhrer, Anke Jagdhuber, Thomas Moghaddam, Mahta Kimball, John S. Miller, Charles E. Tongji Univ Coll Surveying & Geo Informat Shanghai Peoples R China Aerosp Corp El Segundo CA USA Univ Augsburg lnst Geog Augsburg Germany Univ Southern Calif Dept Elect & Comp Engn Los Angeles CA USA Univ Montana Numer Terradynam Simulat Grp Missoula MT USA Caltech Jet Prop Lab Pasadena CA USA

ISBN: (纸本)9798350320107

Accurate soil carbon data are important for understanding the permafrost response and potential carbon release to future climate change. However, there is a large discrepancy in current soil organic carbon (SOC) estimates in the Arctic, where sparse measurements are unable to capture SOC complexity over the vast and remote region. Polarimetric Synthetic Aperture Radar (SAR) data are sensitive to roughness and moisture conditions of soil and vegetation, and may provide useful information on surface and profile SOC properties ( Yi et al., 2021 , 2022 ). The NASA Arctic Boreal Vulnerability Experiment (ABoVE) airborne campaign acquired an abundance of full-polarimetric P- and L-band SAR data across Alaska and western Canada ( Miller et al., 2019 ), which provides opportunities to test new remote sensing applications. The main objective of this study is to investigate the potential of low-frequency polarimetric SAR data for regional SOC retrieval in the Arctic through data analysis and modeling. We chose the Alaska North Slope as our study area due to more in-situ data available in this area. © 2023 ieee.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Identification of Load Model Parameters Based on data-driven Approach and Its Application in Transient Stability Preventive Control 6

Dynamic Identification of Load Model Parameters Based on Dat...

引用

6th Asia Energy and Electrical Engineering symposium (AEEES)

作者： Zhou, Ying Liu, Baozhu Lu, Guangming Zhang, Lulu Wang, Jiecong Ma, Jing North China Elect Power Univ Sch Elect & Elect Engn Beijing Peoples R China China Elect Power Res Inst Elect Power Syst Res Inst Beijing Peoples R China

ISBN: (纸本)9798350373486;9798350373479

This article proposes a power system transient stability preventive control method that considers data-driven identification of the distribution network dynamic load model. Firstly, the distribution network and its internal loads connected to each node of the large power grid are equivalently transformed into a dynamic synthetic load model (SLM), and the dominant parameters in the model are extracted. Based on a deep belief network (DBN), the dominant parameters are dynamically identified;Secondly, integrate the identified model into the large power grid and generate data-driven transient stability constraints based on DBN;Establish a transient stability preventive control optimal power flow model with the objective function of comprehensively adjusting generator output and minimizing the total cost of load, considering multiple constraints such as data-driven transient stability margin, and solve it using the NSGA-II algorithm;Finally, the effectiveness of the proposed method was verified through simulation analysis of an improved ieee 39 nodes system.

关键词： transient stability preventive control parameter identification data driven synthesis load model

来源：评论

学校读者我要写书评

暂无评论

MLIP: MEDICAL LANGUAGE-IMAGE PRE-TRAINING WITH MASKED LOCAL REPRESENTATION LEARNING 21

MLIP: MEDICAL LANGUAGE-IMAGE PRE-TRAINING WITH MASKED LOCAL ...

引用

21st ieee International symposium on Biomedical Imaging (ISBI)

作者： Liu, Jiarun Zhou, Hong-Yu Li, Cheng Huang, Weijian Yang, Hao Liang, Yong Shi, Guangming Zheng, Hairong Wang, Shanshan Chinese Acad Sci Shenzhen Inst Adv Technol Paul C Lauterbur Res Ctr Biomed Imaging Shenzhen Peoples R China Peng Cheng Lab Shenzhen Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Pazhou Lab Huangpu Guangzhou Peoples R China

ISBN: (纸本)9798350313345;9798350313338

Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in natural datasets. Besides, medical image-text pairs often involve numerous complex fine-grained correspondences. This paper aims to enhance the data efficiency by introducing multiple-to-multiple local relationship modeling to capture denser supervision. More specifically, we propose a medical language-image pre-training (MLIP) framework, which exploits the limited image-text medical data more efficiently through sentence-patch matching. Furthermore, we introduce a masked contrastive learning strategy with semantic integrity estimation to reduce redundancy in images while preserving the underlying semantics. Our evaluation results show that MLIP outperforms previous work in zero/few-shot classification and few-shot segmentation tasks by a large margin.

关键词： Language-image pre-training masked contrastive learning sentence-patch matching medical image analysis

来源：评论

学校读者我要写书评

暂无评论

Measuring Perceptual Color Differences of Smartphone Photographs

引用

ieee TRANSACTIONS ON PATTERN analysis AND MACHINE INTELLIGENCE 2023年第8期45卷 10114-10128页

作者： Wang, Zhihua Xu, Keshuo Yang, Yang Dong, Jianlei Gu, Shuhang Xu, Lihao Fang, Yuming Ma, Kede Shenzhen MSU BIT Univ Guangdong Lab Machine Percept & Intelligent Comp Shenzhen 518115 Peoples R China City Univ Hong Kong Dept Comp Sci Kowloon Hong Kong Peoples R China Jiangxi Univ Finance & Econ Sch Informat Management Nanchang 330013 Jiangxi Peoples R China Guangdong OPPO Mobile Telecommun Corp Ltd Dongguan 523860 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 610056 Peoples R China Hangzhou Dianzi Univ Sch Digital Media & Art Design Hangzhou 310005 Peoples R China

Measuring perceptual color differences (CDs) is of great importance in modern smartphone photography. Despite the long history, most CD measures have been constrained by psychophysical data of homogeneous color patches or a limited number of simplistic natural photographic images. It is thus questionable whether existing CD measures generalize in the age of smartphone photography characterized by greater content complexities and learning-based image signal processors. In this article, we put together so far the largest image dataset for perceptual CD assessment, in which the photographic images are 1) captured by six flagship smartphones, 2) altered by Photoshop, 3) post-processed by built-in filters of the smartphones, and 4) reproduced with incorrect color profiles. We then conduct a large-scale psychophysical experiment to gather perceptual CDs of 30,000 image pairs in a carefully controlled laboratory environment. Based on the newly established dataset, we make one of the first attempts to construct an end-to-end learnable CD formula based on a lightweight neural network, as a generalization of several previous metrics. Extensive experiments demonstrate that the optimized formula outperforms 33 existing CD measures by a large margin, offers reasonable local CD maps without the use of dense supervision, generalizes well to homogeneous color patch data, and empirically behaves as a proper metric in the mathematical sense. Our dataset and code are publicly available at https://***/hellooks/CDNet.

关键词： Image color analysis Photography Measurement visualization Lighting Colored noise Color Color difference color perception smartphone photography image signal processing

来源：评论

学校读者我要写书评

暂无评论

INTEGRATION OF THE OPEN data CUBE ON COMMON CLOUD FRAMEWORKS

INTEGRATION OF THE OPEN DATA CUBE ON COMMON CLOUD FRAMEWORKS

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Baptist, Joshua R. Yetkin, Oguz Terry, Brian Killough, Brian Gowda, Sanjay Analyt Mech & Associates Inc Hampton VA 23666 USA Killough Serv LTD Poquoson VA USA

ISBN: (纸本)9798350320107

The Open data Cube (ODC) [1, 2, 3] is an open-source geospatial data management and analysis software package growing in popularity. With increased popularity there is increased demand for the computational power and storage capabilities required to analyze large spatial and temporal datasets. Cloud resource providers have bolstered their computational and satellite data offerings, simplifying access and management so that average users are able to tailor systems to their specific needs. Consequently, there exists substantial community interest in the comparative capabilities and technological performance of different cloud providers. Making informed choices in cloud providers offerings is crucial for optimizing geospatial data management and processing to meet user-specific needs. In this paper we begin to evaluate the deployment and performance of the ODC, standard notebooks, and datasets, to better determine functional differences. Our work finds that datasets saved in the local environment execute operations significantly faster than from the cloud, Google Earth Engine (GEE) has longer execution times when the metadata for a given asset is indexed locally, and that more thorough benchmarking is required to better understand the end-to-end performance of EO processes on the cloud.

关键词： Open data Cube Cloud Earth Observation GIS Satellite Imagery

来源：评论

学校读者我要写书评

暂无评论

MAPPING AND MONITORING EARTHQUAKE-INDUCED UNSTABLE SLOPES IN PAKISTAN BY MEANS OF MT-INSAR

MAPPING AND MONITORING EARTHQUAKE-INDUCED UNSTABLE SLOPES IN...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Shahzada, Naeem Ding, Xiaoli Hong Kong Polytech Univ Dept Land Surveying & Geoinformat Hung Hom Kowloon Hong Kong Peoples R China Hong Kong Polytech Univ Res Inst Land & Space RILS Kowloon Hung Hom Hong Kong Peoples R China

ISBN: (纸本)9798350360332;9798350360325

The study tested interferometric point target analysis (IPTA) on Sentinel-1A terrain observation with progressive scans SAR (TOPSAR) images between January 2016 and December 2018 to analyze the spatio-temporal distribution of earthquake-induced active unstable slopes in the surrounding region of the epicenter of the 2005 Kashmir earthquake in northern Pakistan. The results reveal dozens of unstable slopes with an average deformation rate varying between -35 mm/year and 10 mm/year along the line of sight (LOS) direction. A large number of unstable slopes showed relatively faster movements, with a rate between -35 and -25 mm/year. The study also found that the temporal behaviors of downslope movement are correlated with local precipitation. Rainwater finds its pathways through joints and cracks of rocks, speeding up slope destabilization. The study emphasizes the need for continuous monitoring and investigation of earthquake-induced slope stability to accurately delineate and investigate the sliding surfaces of unstable slopes with multi-sensor and multi-orbit data for effective mitigation measures.

关键词： Unstable slopes multi-temporal interferometric SAR (MT-InSAR) persistent scatterers interferometric point target analysis Pakistan Senntinel-1

来源：评论

学校读者我要写书评

暂无评论

Demand-driven Information Flow analysis of WebView in Android Hybrid Apps 34

Demand-driven Information Flow Analysis of WebView in Androi...

引用

34th ieee International symposium on Software Reliability Engineering (ISSRE)

作者： Tiwari, Abhishek Prakash, Jyoti Hammer, Christian Univ Passau Passau Germany

ISBN: (纸本)9798350315943

Android hybrid apps augment native apps with web and inter-language communication capabilities. These apps facilitate the integration of web components, including JavaScript, into native apps. Besides, they allow a two-way communication where JavaScript can utilize functionality shared by the native side (Java). However, due to operational differences between Java and JavaScript, the semantics of this communication are complex. Tracking information flows via this communication channel, i.e., between these heterogeneous platforms, becomes intricate. Multiple approaches have been proposed to analyze hybrid apps. However, most of them focus on specific classes of web-induced vulnerabilities or provide rudimentary tracking of specific information flows via this communication channel. This work proposes a demand-driven analysis to comprehensively track information flow violations from the native side to JavaScript and vice-versa. To this end, our framework selectively creates data flow summaries of the shared native-side code based on its usage in the corresponding JavaScript code. We demonstrate the efficacy of our approach by applying it to various benchmarks and large-scale apps.

关键词： Android Hybrid Apps Information flow analysis Static analysis

来源：评论

学校读者我要写书评

暂无评论

Rapid and Flexible Yield analysis Powered by large-Scale Language Model 30

Rapid and Flexible Yield Analysis Powered by Large-Scale Lan...

引用

30th International symposium on Semiconductor Manufacturing, ISSM 2024

作者： Sawai, Yutaka Okuyama, Suguru Ono, Yusuke Omori, Masahito Ueda, Yuto Rohm Co. Ltd. Power Devices Business Unit Fukuoka Japan Rohm Co. Ltd. Power Devices Business Unit Kyoto Japan GenerativeX Co. Ltd. Tokyo Japan

ISBN: (纸本)9798331510589

Semiconductor device manufacturing involves numerous processes, making it challenging for even experienced engineers to comprehensively analyze yield issues. This study introduces a novel framework for identifying and addressing factors influencing specific characteristics based on simplified production descriptions, such as "a specific product's characteristic deteriorated during a defined period."The framework consists of four layers: input, selection, analysis, and interpretation, with significant innovations in the selection and interpretation layers. In the selection layer, large language models (LLM) utilize metadata from analytical tables to infer column attributes, facilitating the precise determination of columns for row filtration and target variable identification. In the interpretation layer, process information and correlation analysis results are synthesized to propose actionable process improvements or assess risks, grounded in semiconductor engineering principles. The proposed approach highlights the potential of integrating LLM with domain-specific methodologies to efficiently support yield improvement analysis and accurately interpret production data. © 2024 ieee.

关键词： large language model machine learning prompt engineering Yield 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：