检索结果-内蒙古大学图书馆

25th International Conference Information Visualisation (IV) - AI and Visual Analytics and Data Science

作者： Costa, Iuri Lima, Rodrigo Resque dos Santos, Carlos Gustavo Meiguins, Bianchi Serique Marques Soares, Anderson Gregorio da Silva Franco, Roberto Yuri Fed Univ Para Comp Sci Grad Program Belem Para Brazil Fed Rural Univ Amazonia Belem Para Brazil

ISBN: (纸本)9781665438278

This paper presents a proposal for text visualization with a focus on the representation of sentences and sentiments. It is noteworthy that traditional text visualization techniques, such as wordcloud, do not visually present relations between words, making it challenging to analyze textual data more deeply through visualization. EmojiText uses a directed graph, where the nodes represent the words and the edges represent the sequence in which the words appear in the sentences. Furthermore, the area of each node is related to the frequency of the represented word, and each node is associated with an emoji that represents the most frequent sentiment associated with the word. Finally, the edges also allow identifying the sentiment at the sentence level. The tool also includes zoom interactions, filters, details on demand, visual mapping configuration, and temporal analysis functionality through animations and multiple views for comparisons. The tool was developed in a javascript programming language using the *** framework and is available at http://***/.

关键词： Text visualization Sentiment visualization visualization technique

来源：评论

学校读者我要写书评

暂无评论

visualization technique for time-variant hydrogen concentration distribution in porous materials using hydrogen storage alloy thin film

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2018年第27期43卷 12377-12385页

作者： Watanabe, Konosuke Hamada, Koshi Araki, Takuto Yokohama Natl Univ Grad Sch Engn 79-5 Hodogaya Ku Yokohama Kanagawa 2408501 Japan Yokohama Natl Univ Fac Engn 79-5 Hodogaya Ku Yokohama Kanagawa 2408501 Japan

An understanding of the mechanism whereby hydrogen is transported in porous materials is a key factor when developing hydrogen-utilizing equipment. For instance, studying the start-up and degradation characteristics of Polymer Electrolyte Fuel Cell (PEFC) requires the distribution of the time-variant hydrogen concentration to be measured at times of the order of 10(-1) s. However, few studies on time-variant hydrogen transport in porous materials have been reported, and conventional measuring methods are insufficient in terms of their time resolution. This study led to the development of a visualization technique using the characteristics of a MgNi thin film, the reflection rate of which changes along with the hydrogen concentration. The new visualization technique makes it possible to investigate and understand the distribution of the time-variant hydrogen concentration. (C) 2018 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.

关键词： Porous material Time-variant hydrogen concentration visualization technique

来源：评论

学校读者我要写书评

暂无评论

VisMillion: A novel interactive visualization technique for real-time big data

VisMillion: A novel interactive visualization technique for ...

引用

International Conference on Graphics and Interaction (ICGI)

作者： Pires, Goncalo Mendes, Daniel Goncalves, Daniel Univ Lisbon Inst Super Tecn INESC ID Lisboa Lisbon Portugal

ISBN: (纸本)9781728163789

The rapid increase of connected devices causes more and more data to be generated and, in some cases, this data needs to be analyzed as it is received. As such, the challenge of presenting streaming data in such way that changes in the regular flow can be detected needs to be tackled, so that timely and informed decisions can be made. This requires users to be able to perceive the information being received in the moment in detail, while maintaining the context. In this paper, we propose VisMillion, a visualization technique for large amounts of streaming data, following the concept of graceful degradation. It is comprised of several different modules positioned side by side, corresponding to different contiguous time spans, from the last few seconds to a historical view of all data received in the stream so far. Data flows through each one from right to left and, the more recent the data, the more detailed it is presented. To this end, each module uses a different technique to aggregate and process information, with special care to ensure visual continuity between modules to facilitate the analysis. VisMillion was validated through a usability evaluation with 21 participants, as well as performance tests. Results show that it fulfills its objective, successfully aiding users to detect changes, patterns and anomalies in the information being received.

关键词： Streaming Big Data Real-Time visualization technique Aggregation

来源：评论

学校读者我要写书评

暂无评论

Analysis and Design of IPMSM Drive System Based on visualization technique in Discrete Time Domain 9

Analysis and Design of IPMSM Drive System Based on Visualiza...

引用

2017 9th Annual IEEE Energy Conversion Congress & Exposition (ECCE)

作者： Li, Haoyuan Zhang, Xing Yang, Shuying Li, Fei Yang, Jian Cao, Pengpeng Hefei Univ Technol Sch Elect Engn & Automat Hefei Anhui Peoples R China

ISBN: (纸本)9781509029983

The performance of interior permanent magnet synchronous motor (IPMSM) drive system is affected by parameters variation and digital control delay, which increases the difficulty and complexity of analyzing and designing, a visualization technique is proposed in discrete time domain. First of all, D-partition method is used to obtain stable region of IPMSM current loop, while the sampling & computation delay and pulse width modulation (PWM) delay are considered. Then the effects of speed, inductance, resistance, dc-link voltage and switching frequency on stability are analyzed, and stable region area (SRA) is put forward as an index of these effects. Furthermore, a gain-phase margin tester is used to get the gain margin and phase margin curves. A desired margin region is derived, and parameters optional region is obtained while taking parameters variation into consideration. Finally, according to the 3D graphic of bandwidth, an optimal set of PI parameters is chosen from the parameters optional region. Experimental results prove out the validity and feasibility of the proposed technique.

关键词： IPMSM D-partition method delay visualization technique P1 parameters

来源：评论

学校读者我要写书评

暂无评论

An Efficient Algorithm Embedded in an Ultrasonic visualization technique for Damage Inspection Using the AE Sensor Excitation Method

引用

SENSORS 2014年第11期14卷 20439-20450页

作者： Liu, Yaolu Goda, Riu Samata, Kiyoshi Kanda, Atsushi Hu, Ning Zhang, Jianyu Ning, Huiming Wu, Liangke Chongqing Univ Coll Aerosp Engn Chongqing 400044 Peoples R China Chiba Univ Dept Mech Engn Chiba 2638522 Japan JAL Engn Co Ltd Tokyo 1440041 Japan Japan Aerosp Explorat Agcy Tokyo 1810015 Japan

To improve the reliability of a Lamb wave visualization technique and to obtain more information about structural damages (e.g., size and shape), we put forward a new signal processing algorithm to identify damage more clearly in an inspection region. Since the kinetic energy of material particles in a damaged area would suddenly change when ultrasonic waves encounter the damage, the new algorithm embedded in the wave visualization technique is aimed at monitoring the kinetic energy variations of all points in an inspection region to construct a damage diagnostic image. To validate the new algorithm, three kinds of surface damages on the center of aluminum plates, including two non-penetrative slits with different depths and a circular dent, were experimentally inspected. From the experimental results, it can be found that the new algorithm can remarkably enhance the quality of the diagnostic image, especially for some minor defects.

关键词： visualization technique Lamb waves kinetic energy diagnostic image

来源：评论

学校读者我要写书评

暂无评论

Effect of Process and Material Parameters on the Permeabilities of Reinforcement Mats: Experimentations and Machine Learning techniques

引用

FIBERS AND POLYMERS 2024年第6期25卷 2285-2302页

作者： Zade, Anita Neogi, Swati Kuppusamy, Raghu Raja Pandiyan Natl Inst Technol Dept Chem Engn Warangal 506004 Telangana India Indian Inst Technol Dept Chem Engn Composite Applicat Lab Kharagpur 721302 W Bengal India

The main objective of this work was to evaluate the effect of processing and material parameters on the reinforcement mat permeability through mould-filling experiments and to model the reinforcement mat permeability as a function of porosity, mat layers, test-fluid viscosity and injection pressure using machine learning (ML) techniques. Two experimental methods based on electrical sensors and visualization techniques were employed to measure the permeability through temporal flow front tracking. The fibre wetting analysis was performed using contact angle measurements to analyse the test fluid saturation at the reinforcement mats and its effect on mat permeability. Artificial neural network (ANN) and the adaptive neuro-fuzzy inference system (ANFIS) ML models were adopted to model effective permeability as a function of four input parameters using the experimental data. From the results, the order of permeability was obtained between 8 x 10-10 to 8 x 10-9 m2 for chopped strand glass-fibre mat, 8.8 x 10-10 to 8 x 10-9 m2 for jute fibre mat, 8.9 x 10-10 to 8.5 x 10-9 m2 for woven roving glass-fibre mat, and 8.9 x 10-10 to 1 x 10-8 m2 for hemp fibre mat. From the fibre wetting analysis, it was found that the mat permeability decreases with the increase in the test fluid-fibre surface wetting time. From the modelling analysis, it was found that the adopted ANN and ANFIS techniques predicted permeability values qualitatively and quantitatively with R2 values of 0.967 and 0.975, respectively. From the statistical analysis, ANFIS has shown an efficient correlation with the experimental permeability as a function of input key parameters than the ANN approach.

关键词： Flow sensors visualization technique Mat permeability ANFIS ANN

来源：评论

学校读者我要写书评

暂无评论

Experimental investigation of air concentration profiles in a dam bottom outlet by using gray scale images with high resolution

引用

JOURNAL OF visualization 2022年第6期25卷 1189-1207页

作者： Pozos-Estrada, Oscar Eugenio Rojas-Flores, Marcos Valentin Avalos-Saucedo, Francisco Rene Avila-Lopez, Simon Univ Nacl Autonoma Mexico Inst Ingn Dept Hydraul Engn Mexico City 04510 DF Mexico

Most dams include bottom outlets consisting of tunnels or pipes to control water discharge by using valves or slide gates to regulate water level in reservoirs for service operation or during an emergency. When the gates are partially open, subatmospheric pressure can develop on the downstream side of the gates, leading to possible damage by cavitation and vibration. In order to avoid the latter, an aeration system is usually installed downstream of the gates to keep the local pressure above the vapor pressure for preventing cavitation. The present study aims to estimate the air concentration profiles for a series of hydraulic jumps that occur on the downstream side of a partially open gate of a bottom outlet using a flow visualization technique, known as Image Processing Procedure (IPP), which consists of the Image Editing and the Pixel Intensity Matrix algorithms. This technique uses a high-speed camera and is based on the hypothesis that air concentration profiles can be estimated from the pixel intensity of each photograph, and also offers the possibility to obtain such profiles in any point along the hydraulic jump without disturbing the flow. The results obtained after applying the IPP to the photographs of the experimental study have very good agreement with the profiles obtained with a conductivity probe, indicating that the IPP can be a powerful tool to complement intrusive probe measurements. In addition, to evaluate the capability of the proposed IPP the experimental data were compared with a two-dimensional diffusion equation. Comparisons between predicted and measured results show good correlation demonstrating the potential of the proposed methodology.

关键词： Bottom outlet Hydraulic jump visualization technique Air concentration Pixel intensity

来源：评论

学校读者我要写书评

暂无评论

Parallel Assemblies Plot, a visualization tool to explore categorical and quantitative data: application to digital mobility outcomes 16

Parallel Assemblies Plot, a visualization tool to explore ca...

引用

IEEE 16th Pacific visualization Symposium (IEEE PacificVis)

作者： Cantu, Alma Mico-Amigo, Maria Encarna Del Din, Silvia Fernstad, Sara Johansson Newcastle Univ Sch Comp Newcastle Upon Tyne Tyne & Wear England Newcastle Univ Translat & Clin Res Inst Newcastle Upon Tyne Tyne & Wear England

ISBN: (纸本)9798350321241

This paper presents a tool enabling the visual analysis of multivariate heterogeneous data. Large amounts of measured and contextual data are being gathered for a large number of applications, increasing connectivity across different data types. While measured data are often quantitative, contextual data tend to be categorical. This results in datasets containing multivariate data with heterogeneous properties. Difference in the natures of these properties raises challenges when combining them for analysis. This paper presents the design of a tool that enables the exploration of multivariate heterogeneous data by combining the strengths of Parallel Coordinates and Parallel Sets. The design relied on the application domain of real-life mobility monitoring that is particularly affected by the challenge mentioned above. To validate the suggested approach this paper presents the result of a usability evaluation, which confirms that the presented design is as efficient as other exiting tools while providing more features for correlation analysis.

关键词： Heterogeneous data Multivariate data visualization technique Scientific visualization

来源：评论

学校读者我要写书评

暂无评论

Image-Based Malware Classification Using Multi-layer Perceptron 4th

Image-Based Malware Classification Using Multi-layer Percept...

引用

4th International Conference on Networks, Intelligent Systems and Security (NISS)

作者： Ouahab, Ikram Ben Abdel Elaachak, Lotfi Bouhorma, Mohammed Abdelmalek Essaadi Univ Fac Sci & Techn Comp Sci Syst & Telecommunicat Lab LIST Tangier Morocco

ISBN: (纸本)9789811636370;9789811636363

Classification of malware variants is the most challenging task in the cybersecurity landscape. Malware developers keep one step ahead of defenders for the sake of using advanced artificial intelligence techniques. That is why we are in extreme need of an efficient malware classifier. In this paper, we proposed and experiment a malware classifier able to affect each inputted malware into its corresponding family. To do so, we use the multi-layer perceptron algorithm with malware visualization technique. It refers to converting a malware binary into grayscale images. Besides, to reach a great accuracy, we experiment different architectures by varying hidden layers, neurons and activation functions. Then, we obtained an accuracy of 97.6%. At the end, we compare the obtained results with literature, and we conclude that the multi-layer perceptron algorithm is a good malware classifier with specified hyperparameters that were used.

关键词： Machine learning Malware classification MLP visualization technique

来源：评论

学校读者我要写书评

暂无评论

The Application of visualization technique to Tidal Current Forecasting in China Offshore Area

引用

2nd International Conference on Energy, Environment and Sustainable Development (EESD 2012)

作者： Li, Jiarui Li, Ruijie Zhang, Yifeng Shan, Haitao Minist Educ Key Lab Coastal Disaster & Def Nanjing 210098 Jiangsu Peoples R China Tianjin Res Inst Water Transport Engn Tianjin 300000 Peoples R China

ISBN: (纸本)9783037855508

Based on C# language, using MSchart control and Matlab toolbox, a tidal current forecasting visual system for china offshore area was built. The forecasting results were shown by static curves and animation. Through the visual system, the operation process of calculation is simplified. The discrete data are shown by pictures and animation which is more intuitively and lively.

关键词： china offshore area tidal current forecasting visualization technique

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：