检索结果-内蒙古大学图书馆

International Conference on Semantic Computing

作者： Kazuma Hasegawa Akihiro Fujii Department of Applied Informatics Faculty of Science and Engineering Hosei University Japan Hosei University Japan

In the Knowledge Graph Reasoning Challenge, the plot of a mystery novel is converted into a knowledge graph. Building the graph requires the work of choosing the parts to put into the knowledge graph. This research aims to automate this task. Specifically, BERT, a Natural Language Processing model, is used to classify with either summary or non-summary, with the results proposed as the parts to put into the knowledge graph. We established a binary classification model and verified its accuracy. Its was found to have an F-value of 0.59. Given the likelihood of improving the accuracy, it is thought that organizing the dataset could have a significant impact. This is to be pursued as a next step.

关键词： Casting Computational modeling Bit error rate Semantics data visualization Knowledge graphs Natural language processing

来源：评论

学校读者我要写书评

暂无评论

EEG based BCI for Autonomous Control: A Review

EEG based BCI for Autonomous Control: A Review

引用

ieee Southeastcon

作者： Sanad Biswas W David Hairston Jason S. Metcalfe Sylvia Bhattacharya Dept. of Analytics and Data Science Kennesaw State University Marietta GA U.S US DEVCOM Army Research Laboratory Aberdeen Proving Ground MD U.S MD U.S Dept. of Engineering Technology Kennesaw State University Marietta GA U.S

Brain-computer interface (BCI) has had exciting improvements in the last decade due to the developments in brain science and computer technology, making BCI a top research area in applied science. With the advancement of technologies, researchers are now experimenting using BCI for operating vehicles, robots, and aircraft. However, choosing the suitable brain signal acquisition technique among the available ones is a big concern. In this paper, we will survey the studies that used the BCI framework for controlling vehicles and quadcopters, its limitations, its prospect, and the reason electroencephalogram (EEG) best suits the BCI framework.

关键词： Surveys visualization Prototypes Gaze tracking Electroencephalography Brain-computer interfaces Reliability

来源：评论

学校读者我要写书评

暂无评论

Visual Analytics and Exploration of Calcium Transient Imaging data using Event-Based Clustering

Visual Analytics and Exploration of Calcium Transient Imagin...

引用

ieee International Conference on Big data

作者： Shiaofen Fang Michal Lange Haoying Fu Yingying Chen Yaoying Ma Luddy School of Informatics Computing and Engineering Indiana University Indianapolis IN USA Department of Computer & Information Science Purdue University Indianapolis Department of Pharmacology and Toxicology School of Medicine Indiana University Indianapolis IN USA Department of Pharmacology and Toxicology Stark Neuroscience Institute School of Medicine Indiana University Indianapolis IN USA

Advances in imaging technology and fluorescent calcium indicators have increased the popularity of the application of miniature microscopes (miniscope) in freely-moving rodents when they are performing sophisticated behaviors. The recently established analysis tools, such as Minian, allow for the efficient extraction of neuronal calcium transients from raw videos. However, there is still a gap in front of neuroscientists to draw any conclusions based on the neuronal calcium signals detected during behavioral tests. The poor signal-to-noise ratio and unreliable neuron registration in miniscope images bring significant challenges to the data analysis tasks. This paper describes a visual analytics approach to the exploration of potential neuronal clustering based on the calcium signals and the behavioral tasks. This new interactive solution can be applied for the analysis and exploration of the correlations between calcium imaging data and addiction behavioral data using a combination of visualization, user interaction, visual clustering, and event-related feature selection techniques. The associated interactive software tool is designed to help neuroscientists develop neurobiological hypotheses underlying both physiological and pathological behaviors, which could be a milestone in the field of neuroscience to understanding behavioral coding in the brain at the neuronal level.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Informatics Workforce to Support the data Modernization Initiative: Assessment and Capacity Building at a State Public Health Agency

Informatics Workforce to Support the Data Modernization Init...

引用

ieee International Conference on Healthcare Informatics (ICHI)

作者： Sripriya Rajamani Sarah Solarz Amber Koskey Taylor Dawson Ann Kayser Hannah Woods Chris Brueske Aasa Dahlberg Schmit Informatics Program School of Nursing University of Minnesota Minneapolis MN USA Minnesota Dept of Health Surveillance Division Infectious Disease St. Paul MN USA Minnesota Dept of Health Office of Data Strategy and Interoperability St. Paul MN USA

A workforce that is skilled in informatics and data science is critical to achieving the objectives of the data Modernization Initiative (DMI) in public health. The Minnesota Department of Health conducted an informatics workforce assessment in December 2022. The survey captured information in 5 domain areas and across 6 proficiency levels (no knowledge to expert) with an estimated 15-20 minutes to complete. In all of the 5 domains (performing assessments and leading advancements of health information systems; data exchanges and systems interoperability; data and IT governance; data analytics, visualization and reporting; implementation, development and management of systems), the staff who identified themselves at expert proficiency was <3% and as advanced was approximately 10%. Staff with awareness/basic/intermediate proficiency were interested in trainings. University course work (51.8%) followed by online modules (33.4%) were common modes of prior trainings. The staff also identified desired trainings that spanned across various tools/skills (e.g., SQL, R, Tableau, HL7, Rhapsody, REDCap) along with informatics and interoperability overview. These findings will be utilized to offer trainings to interested staff and collaborations with university have been initiated.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Surface Material Classification Based on Unbalanced Visual and Haptic data: A Double-DQN Method

引用

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2023年 72卷 1页

作者： Liu, Guohong Lv, Shuai Wang, Cong Li, Xiaomeng Nai, Weizhi Jilin Univ Coll Commun Engn Changchun 130022 Peoples R China

The article focuses on surface material classification with unbalanced visual and haptic data, which is important in teleoperation and robotic recognition. For this problem, existent classification methods inevitably suffer from performance degradation, as they tend to emphasize the major classes and ignore the minor ones. To overcome such an issue, we address this classification problem by the double deep $Q$ -learning network (DDQN) method which not only offers strong representation ability but also avoids overestimation. Specifically, we first transform haptic accelerations to their spectrograms by short-time Fourier transform (STFT), and, respectively, feed visual images and haptic spectrograms to pretrained ResNet50 for extracting low-dimensional feature vectors. Then, the hybrid visual-haptic feature vectors are fed into DDQN as a sequence of states. With respect to each state, DDQN assigns it with an estimated class label. By comparing with the true label, DDQN earns a reward that is dependent on the imbalance ratio of the class. Through maximization of the cumulative rewards, DDQN enhances its classification performance. For the purposes of validation, numerical evaluations are carried out on the TUM69, LMT108, and HaTT datasets. The results show that DDQN outperforms the existent methods in both classification performance and computational complexity.

关键词： Haptic interfaces visualization Feature extraction Residual neural networks Spectrogram Deep learning Convolutional neural networks Double deep Q-learning network (DDQN) hybrid visual-haptic data residual network surface material classification unbalanced measurement

来源：评论

学校读者我要写书评

暂无评论

Efficient Generation of Approximate Region-based Geo-maps from Big Geotagged data

Efficient Generation of Approximate Region-based Geo-maps fr...

引用

ieee International Workshop on Computer-Aided Modeling, Analysis, and Design of Communication Links and Networks, CAMAD

作者： Isam Mashhour Al Jawarneh Luca Foschini Antonio Corradi Department of Computer Science University of Sharjah Sharjah United Arab Emirates Dipartimento di Informatica – Scienza e Ingegneria University of Bologna Viale Risorgimento 2 Bologna Italy

smart city applications scenarios, such as traffic monitoring, require regularly generating region-based geographical maps (geo-maps) such as choropleth, to uncover statistical patterns in the data, therefore helping municipalities to achieve better urban planning. However, with tremendous avalanches of big data arriving in fast streams, it is becoming cumbersome and inefficient to achieve the visualization task in a timely manner. Having said that, spatial approximate query processing presents itself as an indispensable and reliable solution in cases of data overloading. In this paper, we focus on presenting a novel system for generating efficiently region-based geo-maps from fast arriving big georeferenced data streams. We specifically present ApproxGeoViz. It is a system for generating approximate region-based maps from fast arriving data relying on a novel stratified-like spatial sampling method. We have built a standard-compliant prototype and tested its performance on real smart city data. Our results show that ApproxGeoViz is efficient in terms of time-based and accuracy-based QoS constraints such as running time and approximate map accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the Construction of a Multimodal Cognitive Graph of Textile and Clothing

Research on the Construction of a Multimodal Cognitive Graph...

引用

ieee International Conference on Software Quality, Reliability and Security Companion (QRS-C)

作者： Peng Ye Xinyi Lan Yufan Chen Zhipeng Wang Wei Ye School of Computer Science and Artificial Intelligence Wuhan Textile University China Engineering Research Center of Hubei Province for Clothing Information Wuhan Textile University China

With the development of the textile and clothing industry, understanding and grasping the characteristics and properties of textiles and clothing has become increasingly important. This article proposes a multimodal textile and clothing cognition graph(CG) construction method to comprehend textiles and clothing better. This method combines knowledge graph(KG) and multimodal data processing techniques to integrate various information about textiles and clothing into a unified CG. Firstly, critical information is extracted from textual and image data related to textiles and clothing using web crawling techniques. Then, utilizing modeling and representation methods of KG, the extracted information is organized into entities and relationships, thus constructing a CG for textiles and clothing. Finally, browsing and analysis of the textile and clothing CG are realized through graph visualization and interactive technologies. Experimental results demonstrate that this method can effectively construct a multimodal CG for textiles and clothing, supporting research and applications in the textile and clothing field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human-Spa: An Online Platform Based on Spatial Transcriptome data for Diseases of Human Systems

Human-Spa: An Online Platform Based on Spatial Transcriptome...

引用

ieee International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yunyun Su Feifei Cui Shiyu Yan Quan Zou Chen Cao Zilong Zhang School of Computer Science and Technology Hainan University Haikou China School of Life Sciences Hainan University Haikou China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China

Spatial transcriptomics has become a major method for high-throughput analysis of gene expression at the current level of cells, which can directly study gene expression changes in disease cells, reveal the occurrence and development mechanism of diseases, identify potential therapeutic targets related to diseases, and provide new clues for disease diagnosis and treatment. Although there have been major breakthroughs in the analysis and acquisition of transcriptome data, there are still many challenges in how to effectively manage, share and utilize these valuable data resources in the study of human systemic diseases. To solve this problem, we are committed to building a spatial transcriptome database website related to human systemic diseases, aiming to provide reliable datasets related to multiple diseases, and provide certain data information and analysis results to accelerate the progress of human systemic diseases research. This paper will introduce the construction process of the database website in detail, and discuss its application prospects in disease research, with the aim of promoting further development and innovation in the field of human health. Here, Human-spa mainly includes 12 Human systems, 38 disease types, 55 datasets, and Human-Spa provides a very friendly web interface for visualization and dataset parsing. In conclusion, the construction of Human-Spa will provide a powerful tool and resource platform for Human disease research. Human-Spa is available for free at http://***/

关键词：

来源：评论

学校读者我要写书评

暂无评论

visualization of potential differences in comprehension by distribution of notes and questions in online programming courses

Visualization of potential differences in comprehension by d...

引用

ieee International Conference on Teaching, Assessment and Learning for Engineering (TALE)

作者： Xiaonan Wang Hidenari Kiyomitsu Yancong Su Kazuhiro Ohtsuki Yi Sun Kento Shigyo Graduate School of Intercultural Studies Kobe University Kobe Japan School of Design and Art Xiamen University of Technology Xiamen China Graduate School of Information Technology Kobe Institute of Computing Kobe Japan Academy of Interdisciplinary Studies Hong Kong University of Science and Technology Hong Kong China

This study presents an innovative approach to understanding differences in student comprehension in online programming courses by analyzing note-taking and questioning patterns and the distribution of grades. It enables instructing educators to understand learners' learning behaviors better. We designed and developed a system to support online learning that enables students to take notes and ask questions while viewing online courses and allows instructors to grasp overall feedback. We used a visualization method based on the location of notes and questions as they appear in the learning videos to enable instructors to capture their learners' learning better. Visualizing the distribution of notes and questions shows differences among students' note-taking patterns and learning strategies. The underlying comprehension patterns involved lead to differences in the patterns of notes and questions. We compared data from learners in different score bands to verify the correlation between note types and scores. By visualizing and comparing notes with the same type of correlation, the results show the correlation between note types and grades and the potential of the visualization method to analyze students' learning strategies and learning personalities. It provides valuable insights into student engagement, comprehension, and learning strategies, which can inform the development of more effective teaching methods. This study is relevant in the contemporary educational landscape, particularly as many institutions transition to online formats. Detecting student engagement and comprehension levels in these contexts is crucial.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SpriteHyper2vec: A SCSPRITE data Completion Method Based on Hypergraph Random Walk

SpriteHyper2vec: A SCSPRITE Data Completion Method Based on ...

引用

ieee International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Yamin Liu Yusen Ye Lin Gao School of computer science and technology Xidian University 2 South Taibai Road Xi’an Shaanxi PR China

scSPRITE is an emerging method to capture multi-way chromatin interaction and generate high-resolution, genome-wide three dimensional (3D) genome organization in single cells. However, the data obtained from scSPRITE often contain missing values and exhibit sparsity, making it difficult to directly observe local structures of the 3D genome at the level of single cells or even small cell populations. Additionally, comprehending the chromatin conformation composition entails a large number of cell populations by scSPRITE with huge cost. Therefore, it is valuable to impute these missing values and extract higher-order structures using computational methods. Here, we propose SpriteHyper2vec, a single-cell imputation algorithm based on hypergraph, specifically designed for scSPRITE datasets, which effectively capture local and global topological structures by generalizing Node2vec method. When compared with original method, SpriteHyper2vec significantly improves the similarity between small cell populations and the benchmark data. Furthermore, the completion capability of SpriteHyper2vec enables the identification of A/B compartment-like structures even in small cell populations. In summary, SpriteHyper2vec effectively enhances the visualization and comparison of 3D organization in small cell populations based on scSPRITE data.

关键词：

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：