检索结果-内蒙古大学图书馆

ieee International symposium on Information Theory (ISIT)

作者： Lou, Hao Farnoud (Hassanzadeh), Farzad Univ Virginia Elect & Comp Engn Charlottesville VA 22903 USA

ISBN: (纸本)9781538682098

data deduplication has gained attention in large-scale storage systems due to the explosive growth in digital data. Recently, the information-theoretic aspects of conventional deduplication algorithms have been studied and novel algorithms with better performance have been proposed. In this paper, we study the performances of variable-length deduplication and multi-chunk deduplication algorithms from the point of view of information theory. We consider a source model in which source strings are composed of repeated blocks with each data block containing a constant number of substitution edits. We show that over the proposed source model, the variable-length deduplication algorithm can achieve asymptotically arbitrarily large compression ratio and the multi-chunk deduplication algorithm is order optimal under mild conditions.

关键词： Explosives data models Information theory

来源：评论

学校读者我要写书评

暂无评论

Visual Saliency Prediction for Augmented Reality Videos

Visual Saliency Prediction for Augmented Reality Videos

引用

ieee International symposium on Circuits and Systems (ISCAS)

作者： Zongyi Xie Huiyu Duan Yuxin Zhu Pengfei Wang Xiongkuo Min Guangtao Zhai Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350356830

ISBN: (纸本)9798350356847

Augmented Reality (AR) is an emerging technology that allows users to perceive both virtual-world contents and real-world scenes simultaneously. It has numerous applications in industrial manufacturing, entertainment, gaming, education, etc. In AR environments, the visual confusion phenomenon caused by the overlay of augmented content and real backgrounds is evident, yet the understanding and research of visual saliency under the AR visual confusion condition remains limited. This paper primarily analyzes the interaction between real-world scenes and AR content, explores human visual saliency when using AR devices. First, we conduct a large-scale eye-tracking experiment based on a head-mounted AR device, and construct an AR saliency dataset containing 2160 videos, with corresponding collected eye movement data. Through qualitative analysis of the visual attention heat maps, we conclude that visual confusion significantly influences visual attention in AR video. Additionally, we quantitatively evaluate the performance of a series of classical saliency models and deep neural network saliency models on the dataset constructed in this project. For better predicting saliency in AR, we propose a general saliency prediction model, InternSal, which achieves state-of-the-art performance compared to other methods. The database and codes will be released to facilitate future research.

关键词： Performance evaluation visualization Multimedia systems Gaze tracking Predictive models Manufacturing Integrated circuit modeling Heat maps Augmented reality Videos

来源：评论

学校读者我要写书评

暂无评论

Process decomposition and distributed fault detection of large-scale industrial processes 7

Process decomposition and distributed fault detection of lar...

引用

7th ieee International symposium on Advanced Control of Industrial Processes (AdCONIP)

作者： Yin, Xunyuan Qin, Yan Chen, Hongtian Du, Wenli Liu, Jinfeng Huang, Biao Nanyang Technol Univ Sch Chem & Biomed Engn Singapore 637459 Singapore Univ Alberta Dept Chem & Mat Engn Edmonton AB T6G 1H9 Canada East China Univ Sci & Technol Key Lab Smart Mfg Energy Chem Proc Minist Educ Shanghai 200237 Peoples R China

ISBN: (数字)9781665471749

ISBN: (纸本)9781665471749

In this work, a data-driven distributed process monitoring problem is considered. A process decomposition approach is proposed by leveraging community structure detection to decompose variables into subsystems optimally via finding a maximal value of the metric of modularity. A two-layer distributed monitoring scheme is developed where local estimators are designed based on the configured subsystems of variables using canonical correlation analysis. Inner-subsystem interactions and inter-subsystem interactions are tackled by the two layers separately. The proposed method is applied to a simulated wastewater treatment process.

关键词： Process monitoring Measurement Correlation Fault detection Process control Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

A MULTI-TASK MULTIPLE INSTANCE LEARNING ALGORITHM TO ANALYZE large WHOLE SLIDE IMAGES FROM BRIGHT CHALLENGE 2022

A MULTI-TASK MULTIPLE INSTANCE LEARNING ALGORITHM TO ANALYZE...

引用

ieee International symposium on Biomedical Imaging Challenges (ieee ISBIC)

作者： Marini, Niccolo Wodzinski, Marek Atzori, Manfredo Mueller, Henning Univ Appl Sci Western Switzerland Informat Syst Inst Sierre Switzerland Univ Geneva Dept Comp Sci Geneva Switzerland AGH Univ Sci & Technol Dept Measurement & Elect Krakow Poland Univ Padua Dept Neurosci Padua Italy Univ Geneva Med Fac Geneva Switzerland

ISBN: (纸本)9781665451727

Malignant lesions in breast tissue specimen whole slide images (WSIs), may lead to a dangerous diagnosis, such as cancer. However, WSIs analysis is time-consuming and expensive, requiring the work of expert pathologists. This paper aims to present a method for the 2022 BRIGHT Challenge, that involves the analysis of breast WSIs. The organizers provided over 550 breast WSIs and over 3900 regions of interest (ROIs) to develop and validate methods for breast cancer images. The method presented in this work is based on a Multiple Instance Learning instance-based Convolutional Neural Network (CNN), allowing the combination of strongly-annotated data (from ROIs) and weakly-annotated data (from WSIs) via the optimization of a multi-task loss function. Furthermore, during the CNN training, the input patches are clustered and filtered according to their entropy, to reduce the non-informative content used to train the model. The CNN reaches an averaged F1-score = 0.63 +/- 0.02 on the 3-class classification task and averaged F1-score = 0.39 +/- 0.08 on the 6-class classification task, considering the validation partition;an averaged F1-score = 0.65 on the cancer risk classification task and averaged F1-score = 0.45 on the sub-typing cancer risk classification task, considering the best result achieved on the test partition. These results show that Multiple Instance Learning instance-based CNNs may represent a good resource to tackle this kind of problem.

关键词： Deep Learning Image classification BRIGHT Breast cancer Multiple Instance Learning

来源：评论

学校读者我要写书评

暂无评论

Proceedings - 2021 ieee 14th Pacific visualization symposium, PacificVis 2021

Proceedings - 2021 IEEE 14th Pacific Visualization Symposium...

引用

14th ieee Pacific visualization symposium, PacificVis 2021

ISBN: (纸本)9781665439312

The proceedings contain 29 papers. The topics discussed include: an extension of empirical orthogonal functions for the analysis of time-dependent 2D scalar field ensembles;visual analytics methods for interactively exploring the campus lifestyle;know-what and know-who: document searching and exploration using topic-based two-mode networks;Louvain-based multi-level graph drawing;supporting the discovery process in the literature review workflow for novice researchers;unravelling the human perspective and considerations for urban data visualization;visualization of topic transitions in SNSs using document embedding and dimensionality reduction;and stable visual summaries for trajectory collections.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explainable AI applied to the analysis of the climatic behavior of 11 years of Meteosat Water Vapor images

Explainable AI applied to the analysis of the climatic behav...

引用

ieee symposium Series on Computational Intelligence (ieee SSCI)

作者： Valdes, Julio J. Pou, Antonio Natl Res Council Canada Digital Technol Res Ctr Ottawa ON Canada Autonomous Univ Madrid Dept Ecol Madrid Spain

ISBN: (纸本)9781665487689

large stocks of meteorological satellite images contain important climatic information of the last decades. This paper explores the capabilities of three Explainable AI procedures (Occlusion, XRAI and SHAP) as tools to analyze and uncover patterns in the mid to upper troposphere Water Vapor dynamics, and their relationships with yearly seasons. The data consisted of 4140 daily Meteosat satellite images on the WV6.2 band between 2010 to 2020 and the base model was a convolutional neural network targeting season prediction. The results show that each explanation procedure highlights different aspects of the atmospheric processes and are appropriate for different purposes: Occlusion for studying the general traits of the 11 years time period covered by the images, XRAI for detecting and following dynamic patterns for short spans of time, and SHAP for detailed geographical expressions of atmospheric processes. All together Explainable AI exhibits an important potential for the study of atmospheric and climate change, which should be further investigated.

关键词： explainable AI climate change atmospheric patterns water vapor images convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Towards a Conversational User Interface for Aiding Researchers with Reproducibility

Towards a Conversational User Interface for Aiding Researche...

引用

ieee symposium on Visual Languages and Human Centric Computing (VL/HCC)

作者： Lázaro Costa HASLab / INESC TEC Faculdade de Engenharia Universidade do Porto Portugal

ISBN: (数字)9798350366136

ISBN: (纸本)9798350376920

In science, it is very important to be able to recreate the same computing environment to reproduce the same results achieved by previous scientific experiments. However, it is challenging to create a shareable package with the same environment using the same programming languages, frameworks, or data sources due to the diversity of researchers’ knowledge and the variety of computational environments used. In this work, I propose designing and constructing a conversational user interface that allows researchers to upload experiment files and clarify the necessary information via text communication to create a reproducible experiment package. My approach uses an integrated large Language Model (LLM) that allows the platform to infer, whenever possible, some information (e.g., the programming language used, the main file to be executed, the parameters needed to be inserted when executing) to reduce the amount of information asked to the user. With this work, I intend to use an LLM to guide the researcher through this procedure, thereby reducing the time spent and the number of interactions required to create a reproducible package.

关键词： Computer languages visualization Soft sensors large language models User interfaces Reproducibility of results

来源：评论

学校读者我要写书评

暂无评论

Modeling Driver's Visual Fixation Behavior Using White-Box Representations

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第9期23卷 15434-15449页

作者： Tang, Xing Yu, Jie Su, Yan Nanjing Univ Sci & Technol Dept Mech Engn Nanjing 210094 Peoples R China

Driving is a highly dynamic task requiring extensive and fast processing of visuospatial information in brief time intervals, while experienced drivers can efficiently perform this task. Therefore, investigating the human-like visual fixation behavior shows much potential in developing the advanced driving assistance systems and efficient autonomous vehicles. Literature shows that driver's visual fixation behavior is guided by a combination of top-down and bottom-up mechanisms. Currently, existing excellent computational frameworks rely heavily on the deep neural network's strong feature extraction ability, which is inherently task-unaware. These black-box models are limited in strengthening the guidance of task-aware top-down factors in governing the fixation behavior. Furthermore, using the black-box model to fit the training data directly decreases its interpretability. In this paper, we encourage to adopt the white-box method. By researching the findings in the intersection of neuroscience and psychology, we propose to identify two white-box representations for driving separately: the information selection representation including salience, effort, expectancy, and value, and the driving task-aware representation highlighting sub-task and speed. We present a novel computational framework to incorporate all the above factors to predict driver's visual fixation systematically. On the BDDA dataset, we have conducted the extensive quantitative evaluation and qualitative analysis to validate the effectiveness. Its performance surpasses the previous state-of-the-art by +11.3% in the Pearson's Correlation Coefficient, especially by a large margin of +24.5% and +28.8% in the turning operations. The ablation study further demonstrates the influence of each component in our framework. Moreover, the trained model has been deployed on the DR(eye)VE dataset to verify the generalization ability, demonstrating the potential of domain adaptation.

关键词： visualization Task analysis Vehicles Training Roads Computational modeling Adaptation models Human-like visual fixation task-aware top-down white-box representation BDDA

来源：评论

学校读者我要写书评

暂无评论

A LUNG-PARENCHYMA-CONTRAST HYBRID NETWORK FOR EGFR GENE MUTATION PREDICTION IN LUNG CANCER 19

A LUNG-PARENCHYMA-CONTRAST HYBRID NETWORK FOR EGFR GENE MUTA...

引用

19th ieee International symposium on Biomedical Imaging (ieee ISBI)

作者： Liu, Meili Wang, Shuo Yu, He Zhu, Yongbei Wang, Liusu Zhang, Mingyu Wu, Zhangjie Li, Xiaohu Li, Weimin Tian, Jie Beihang Univ Beijing Adv Innovat Ctr Big Data Based Precis Med Sch Engn Med Beijing Peoples R China Sichuan Univ West China Hosp Dept Resp & Crit Care Med Chengdu Peoples R China Anhui Med Univ Affiliated Hosp 1 Dept Radiol Hefei Peoples R China

ISBN: (纸本)9781665429238

Epidermal growth factor receptor (EGFR) mutation status is critical for lung cancer treatment planning. Current identification relies on invasive biopsy and expensive gene sequencing. Recent studies revealed that CT images combined with deep learning can be used to non-invasively predict EGFR mutation status. However, how to enable the network to focus on the lung parenchyma area and extract discriminative features needs further exploration. In this study, we proposed a lung-parenchyma-contrast (LPC) hybrid network that: 1) uses a fully automatic whole-lung analysis method and enables the model to focus on the lung parenchyma area;2) extracts local and global lung parenchyma features by a contrastive learning strategy;and 3) jointly performs feature learning and classifier learning to improve predictive performance. We evaluated our network on a large multi-center dataset (2316 patients), which outperforms (AUC=0.827) the previous state-of-the-art methods. Extensive experiments also demonstrated the effectiveness of the contrastive learning modules.

关键词： EGFR gene mutation targeted therapy lung cancer contrastive learning computed tomography

来源：评论

学校读者我要写书评

暂无评论

Modeling of Metaheuristics with Deep Transfer Learning Based Visual data Mining for the Healthcare Sector 6

Modeling of Metaheuristics with Deep Transfer Learning Based...

引用

6th Iraqi International Conference on Engineering Technology and its Applications, IICETA 2023

作者： Abed, Z. Shnawa, Ammar H. Hadi, M.R. Ibrahim, Karrar Adnan, Myasar Mundher Hameed, Waleed Ahl Al Bayt University Karbala Iraq National University of Science and Technology Dhi Qar Iraq Altoosi University College Najaf Iraq Al-Zahraa University for Women Karbala Iraq The Islamic University Najaf Iraq Medical Technical College Al-Farahidi University Baghdad Iraq

ISBN: (纸本)9798350303339

data mining is a process that interacts with a large dataset to determine complex interesting patterns from unknown structured data. Visual data mining (VDM) is considered a combination of two disciplines: data mining and visualization to explore useful and implicit knowledge from a huge dataset. Also, it is strongly associated with multimedia systems, high-performance computing, computer graphics, human-computer interaction, and pattern recognition. Recently, VDM approaches find useful in the healthcare sector to aid the decision-making process. In addition, the design of VDM approaches for healthcare applications needs special consideration to make sure security of data. Artificial intelligence (AI) methods play a vital role in achieving scalability and accurate analysis from real-time environments. Therefore, this study develops a blockchain-assisted quantum bacterial colonial optimization with deep learning (BAQBCO-DL) algorithm for VDM in the healthcare environment. The proposed BAQBCO-DL model exploits BC technology for secured data communication in the healthcare sector. In addition, the BAQBCO-DL model designs a U-Net-based segmentation with an optimal densely connected network (DenseNet) model for feature extraction, and the hyperparameter tuning process is performed using the QBCO algorithm. Finally, a probabilistic neural network (PNN) classifier is utilized to define appropriate class labels. An extensive experimental analysis is conducted to report the superior performance of the BAQBCO-DL technique and the outcomes are measured under several aspects. The simulation outcomes underlined the supremacy of the BAQBCO-DL algorithm over recent methodologies. © 2023 ieee.

关键词： data mining

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：