检索结果-内蒙古大学图书馆

20th International symposium on Medical Information Processing and analysis

作者： Diaz-Celis, Oscar Torres-Santamaria, Juan Caviedes, Mauricio Iregui, Marcela Gutierrez-Carvajal, R. E. Romero, Eduardo Cruz-Roa, Angel Univ Los Llanos GITECX Villavicencio Colombia Univ Los Llanos AdaLab Villavicencio Colombia Univ Mil Nueva Granada ACCEDER Bogota Colombia Univ Nacl Colombia CIM LAB Bogota Colombia Tecnol Monterrey Ind 5 0 Mexico City DF Mexico

ISBN: (纸本)9798331528669;9798331528652

Effective management and continuous monitoring of patients with cardiovascular risk are essential to reducing adverse events. Diagnostic tools, particularly evidence-based ones, have significantly improved healthcare and enabled advances in personalized medicine. Recommender systems (RS) commonly used to offer personalized recommendations based on historical clinical data and patterns in large health databases. This work presents a RS based on case evidence for monitoring and diagnosing cardiovascular health. Using a similarity approach through the clustering algorithm and multivariate analysis of non-negative matrix factorization (NMF), using the Framingham heart disease dataset to identify patient groups and their clinical profiles. This enables the evaluation of new patient cases, identification of similar cases, and inference of possible conditions or risks from a semi-supervised approach. The experimental results during train-validation show the best performances of NMF with lower average RMSE and lower variance of 0.2526 +/- 0.0022 for 13 groups and test performance of RMSE of 0.2550 and Accuracy of 0.7386, suggesting the potential use to retrieve similar cases and their associated prevalence diagnosis as a complementary diagnostic support tool.

关键词： Cardiovascular Risk Recommender Systems Similarity Non-negative Matrix Factorization Semi-supervise

来源：评论

学校读者我要写书评

暂无评论

Operation and maintenance analysis platform at IHEP

Operation and maintenance analysis platform at IHEP

引用

Annual Virtual International symposium on Grids and Clouds (ISGC)

作者： Hu, Qingbao Wang, Lu Jiang, Xiangwei Zheng, Wei Chinese Acad Sci Inst High Energy Phys Beijing Peoples R China

As the scale of computing facilities continues to grow and the computing environment becomes more and more complex, the difficulty of operation and maintenance of large-scale computing clusters is also increasing. Operation and maintenance methods based solely on configuration management automation technology cannot quickly and effectively solve various service failures in computing clusters. It is urgent to adopt emerging technologies to obtain comprehensive cluster operation and maintenance information, integrate monitoring data from multiple heterogeneous sources, and comprehensively analyze anomalous patterns in monitoring data. Based on the results of data analysis, it becomes possible to locate the root cause of service failures and help computing clusters quickly restore services. To provide a more stable cluster operating environment, IHEPCC combined big data technology and data analysis index tools to design and implement the operation and maintenance analysis toolkit (OMAT) as an open framework, which includes data collection, correlation analysis, anomaly detection, and alerting and other functions. This report introduces the architecture, processing capabilities, and some key functions of OMAT. Combined with the processing flow of monitoring data, it introduces the specific implementation of the system in data collection, data processing, data storage, and data visualization. The current OMAT platform has been applied to multiple cross-regional computing clusters including IHEP, covering about 5000 nodes. The collected information includes node status, storage performance, network traffic, user operations, account security, power environment, and other operation and maintenance indicators to ensure the computing cluster's performance and stable operation.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

A Forest-fire Damage Estimation and visualization Method for Time-series Multi-location 25

A Forest-fire Damage Estimation and Visualization Method for...

引用

25th International Electronics symposium, IES 2023

作者： Hamano, Amane Sasaki, Shiori Musashino University Faculty of Data Science Tokyo Japan

ISBN: (纸本)9798350314731

This paper presents a method for estimating and visualizing the extent and severity of forest-fire damage using time-series geographic information and satellite image data, and its application to multi-location analysis for the purpose of evaluating the impact of forest loss on the global environment. First, the Normalized Burn Ratio (NBR) of forests is calculated using multispectral satellite images before and after the forest fire. Second, using the NBRs before and after the fire, the difference (dNBR) is calculated to estimate the severity of the fire and its extent. Third, the size of fire-Affected area is estimated from these results to compare among multiple locations using GIS. The accuracy of this method is verified by comparing the estimated affected area with the actual affected area. With serious forest fires occurring around the world in recent years, there is a growing demand for a method to accurately assess the impact of forest fires and the importance of forests in the urban and global environment. This study demonstrates the feasibility of our method and its potential contribution to 'SDG15 monitoring' as a realization of time-series multi-location analysis and prediction of disaster-Affected areas through case experiments on forest fires occurred in Australia, Indonesia, and Japan. © 2023 ieee.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Follow My Eye: Using Gaze to Supervise Computer-Aided Diagnosis

引用

ieee TRANSACTIONS ON MEDICAL IMAGING 2022年第7期41卷 1688-1698页

作者： Wang, Sheng Ouyang, Xi Liu, Tianming Wang, Qian Shen, Dinggang Shanghai Jiao Tong Univ Sch Biomed Engn Shanghai 200240 Peoples R China Univ Georgia Dept Comp Sci Athens GA 30606 USA ShanghaiTech Univ Sch Biomed Engn Shanghai 201210 Peoples R China Shanghai United Imaging Intelligence Co Ltd Dept Res & Dev Shanghai 201807 Peoples R China

When deep neural network (DNN) was first introduced to the medical image analysis community, researchers were impressed by its performance. However, it is evident now that a large number of manually labeled data is often a must to train a properly functioning DNN. This demand for supervision data and labels is a major bottleneck in current medical image analysis, since collecting a large number of annotations from experienced experts can be time-consuming and expensive. In this paper, we demonstrate that the eye movement of radiologists reading medical images can be a new form of supervision to train the DNN-based computer-aided diagnosis (CAD) system. Particularly, we record the tracks of the radiologists' gaze when they are reading images. The gaze information is processed and then used to supervise the DNN's attention via an Attention Consistency module. To the best of our knowledge, the above pipeline is among the earliest efforts to leverage expert eye movement for deep-learning-based CAD. We have conducted extensive experiments on knee X-ray images for osteoarthritis assessment. The results show that our method can achieve considerable improvement in diagnosis performance, with the help of gaze supervision.

关键词： visualization Biomedical imaging X-ray imaging Solid modeling Deep learning Annotations Medical diagnostic imaging Visual attention eye-tracking machine attention model computer-aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Predictive analysis of IoT Systems Performance

Predictive Analysis of IoT Systems Performance

引用

2024 Photonics and Electromagnetics Research symposium, PIERS 2024

作者： Tasic, Igor Chen, Tianhua Grabs, Elans Ipatovs, Aleksandrs Cano, Maria-Dolores Universidad Politécnica de Cartagena Cartagena30202 Spain Riga Technical University Institute of Telecommunications RigaLV-1048 Latvia

ISBN: (纸本)9798350375909

Internet of Things (IoT) deployments are becoming a de facto solution for monitoring all types of devices, systems, and infrastructures in various fields. Furthermore, IoT is considered as a key element for implementing digital twins. The architecture of IoT deployments is usually composed of three entities: end nodes with embedded sensors able for data capturing, an intermediate element (gateway) that receives data from end nodes and forwards it to a cloud, and the cloud, which can be a (virtual) server responsible for processing the received data, creating information and knowledge, offering a proper visualization, and in some cases, taking actions as a response. Two essential tasks in IoT systems are to measure the level of quality of the offered service and to predict quality drops during the service operation. Here we present a tool called QUITO (QUality of IoT Operation) that measures the level of quality of the offered IoT service in four different dimensions, called Quality of data, Quality of Information, Quality of user Experience, and Quality Cost. Then the performance of the service is predicted using Deep Learning, which enables taking countermeasures to avoid quality drops before it can happen. We implemented the tool and tested it in simulated scenarios, assuming the use of LoRa and LoRaWAN as one of the most common protocols within the Low Power Wide Area Network technology. Results show that QUITO can monitor and forecast the performance of IoT systems with a granularity level not currently present in other proposals. © 2024 ieee.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Vibration analysis and Suppression of Megawatt Permanent Magnet Generator 6

Vibration Analysis and Suppression of Megawatt Permanent Mag...

引用

6th Asia Energy and Electrical Engineering symposium (AEEES)

作者： Yu Honghao Sun Yutian Zou Jibin Jin Huiyong Harbin Elect Machinery Co Ltd Product Design Dept Harbin Peoples R China Harbin Elect Machinery Co Ltd Harbin Inst Large Elect Machinery Harbin Peoples R China Harbin Inst Technol Sch Elect Engn & Automat Harbin Peoples R China

ISBN: (数字)9798350373479

ISBN: (纸本)9798350373486;9798350373479

The megawatt permanent magnet generator has emerged as the fundamental power supply equipment for marine power generation systems. Effectively mitigating its vibration noise standed out as one of the most crucial challenges in motor design. Current research primarily focused on optimizing the electromagnetic structure and enhancing control strategies for permanent magnet generators. In this study, a novel connection structure with radial elasticity and axial rigidity is proposed to effectively alleviate the impact of stator core vibrations on the stator frame. A 2.7MW permanent magnet generator was taken as an example, electromagnetic forces and vibrations generated by it are initially calculated through analysis, and the reliability of this calculation method is verified by comparing it with experimental data. Subsequently, the prototype incorporates the special connection structure, and its effectiveness is confirmed through comparison with vibration analysis results.

关键词： Permanent magnet generator electromagnetic vibration vibration suppression optimal design

来源：评论

学校读者我要写书评

暂无评论

Exploiting Near-data Processing to Accelerate Time Series analysis

Exploiting Near-Data Processing to Accelerate Time Series An...

引用

ieee-Computer-Society Annual symposium on VLSI (ISVLSI)

作者： Fernandez, Ivan Quislant, Ricardo Giannoula, Christina Alser, Mohammed Gomez-Luna, Juan Gutierrez, Eladio Plata, Oscar Mutlu, Onur Univ Malaga Malaga Spain Natl Tech Univ Athens Zografos Greece Swiss Fed Inst Technol Zurich Switzerland

ISBN: (数字)9781665466059

ISBN: (纸本)9781665466059

A time series is a chronologically ordered set of samples of a real-valued variable that can contain millions of observations. Time series analysis is used to analyze information in a wide variety of domains [128]: epidemiology, genomics, neuroscience, medicine, environmental sciences, economics, and more. Time series analysis includes finding similarities (mo-tifs) and anomalies (discords) between every two subsequences (i.e., slices of consecutive data points) of the time series. There are two major approaches for motif and discord discovery: approximate and exact algorithms. Approximate algorithms are faster than exact algorithms, but they can provide inaccurate results or limited discord detection, which cannot be tolerated by many applications (e.g., vehicle safety systems). Unlike approximate algorithms, exact algorithms do not yield false positives or discordant dismissals, but can be very time-consuming on large time series data. Thus, anytime versions (aka interruptible algorithms) of exact algorithms are proposed to provide approximate solutions quickly and can return a valid result even if the user stops their execution early. The state-of-the-art exact anytime method for motif and discord discovery is matrix profile [142], which is based on Euclidean distances and floating-point arithmetic. We evaluate a recent CPU implementation of the matrix profile algorithm [149] on a real multi-core machine (Intel Xeon Phi KNL [76]) and observe that its performance is heavily bottlenecked by data movement. In other words, the amount of computation per data access is not enough to hide the memory latency and thus time series analysis is memory-bound. This overhead caused by data movement limits the potential benefits of acceleration efforts that do not alleviate the data movement bottleneck in current time series applications.

关键词： Economics Neuroscience Time series analysis Vehicle safety Memory management Genomics Very large scale integration

来源：评论

学校读者我要写书评

暂无评论

Hator: A High-Efficiency CGRA-Based 32/64-Bit Hashing Accelerator with Real-Time Performance analysis 17

Hator: A High-Efficiency CGRA-Based 32/64-Bit Hashing Accele...

引用

17th ieee International symposium on Embedded Multicore/Many-core Systems-on-Chip, MCSoC 2024

作者： Nguyen, Hai Hau Luan, Pham Hoai Vu, Tuan Hai Tran, Van Duy Duong Le, Vu Trung Lam, Duc Khai Tran, Thi Diem Nakashima, Yasuhiko University of Information Technology - Vnuhcm Viet Nam Nara Institute of Science and Technology Nara Japan

ISBN: (纸本)9798331530471

Developing hashing hardware to support diverse 32-bit and 64-bit hash functions at high speed and with low power consumption is necessary to meet the varied security requirements in the rapid explosion of blockchain and IoT integration. Over the past decade, a coarse-grained reconfigurable array (CGRA) has emerged as the most efficient hardware architecture to facilitate high flexibility, high performance, and low power for cryptography. However, existing CGRA-based cryptographic accelerators currently support only 32-bit hash functions and lack real-time performance evaluation on actual hardware. To address these issues, this paper proposes a CGRA-based hashing accelerator named Hator to support a variety of 32-bit and 64-bit hash functions with high speed and energy efficiency on actual FPGA hardware. Three new ideas are proposed to achieve these goals, including the Processing Element Array eXtension (PEAX), which allows data processing with up to 64-bit granularity;a dual Arithmetic Logic Unit (ALU) to maximize hardware resources for both 32-bit and 64-bit operations;and a massive data processing mechanism with multiple pipelined working sessions for efficient calculating of large amounts of continuous data. Accordingly, the real-time performance analysis of Hator on various hash functions shows that the power-delay product (PDP) of the Hator is better than that of powerful CPUs by 8.08-42.49 times. Additionally, evaluations on ASICs with 45nm CMOS technology show that the Hator outperforms existing CGRAs by 1.77 to 3.49 times in throughput and 1.37 to 20.42 times in energy efficiency. © 2024 ieee.

关键词： Reconfigurable architectures

来源：评论

学校读者我要写书评

暂无评论

Exploration and analysis of Image-based Simulation Ensembles

Exploration and Analysis of Image-based Simulation Ensembles

引用

24th Eurographics Conference on visualization, EuroVis 2022

作者： Dahshan, M. Turton, T.L. Polys, N. University of North Florida United States Los Alamos National Laboratory United States Virgina Tech United States

ISBN: (纸本)9783038681854

Scientists run simulation ensembles to study the behavior of a phenomenon using varying initial conditions or input parameters. However, the I/O bottlenecks hinder performing large-scale multidimensional simulations. In situ visualization approaches address the variability of I/O performance by processing output data during simulation time and saving predetermined visualizations in image databases. This poster proposes a visual analytics approach to exploring and analyzing image-based simulation ensembles, taking advantage of semantic interaction, feature extraction, and deep learning techniques. Our approach uses deep learning and local feature techniques to learn image features and pass them along with the input parameters to the visualization pipeline for in-depth exploration and analysis of parameter and ensemble spaces simultaneously. © 2022 The Author(s) Eurographics Proceedings © 2022 The Eurographics Association.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Haptic Distinguishability of Surface Materials with Boosting Technique 27

Enhancing Haptic Distinguishability of Surface Materials wit...

引用

ieee Haptics symposium (HAPTICS)

作者： Priyadarshini, K. Chaudhuri, Subhasis Indian Inst Technol Dept Elect Engn Mumbai Maharashtra India Sony AI Tokyo Japan

ISBN: (纸本)9781665420297

Discriminative features are crucial for several learning applications, such as object detection and classification. Neural networks are extensively used for extracting discriminative features of images and speech signals. However, the lack of large datasets in the haptics domain often limits the applicability of such techniques. This paper presents a general framework for the analysis of the discriminative properties of haptic signals. We demonstrate the effectiveness of spectral features and a boosted embedding technique in enhancing the distinguishability of haptic signals. Experiments indicate our framework needs less training data, generalizes well for different predictors, and outperforms the related state-of-the-art.

关键词： Measurement Neural networks Training data Object detection Feature extraction Boosting Haptic interfaces

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：