检索结果-内蒙古大学图书馆

DRLM: A Robust Drug Representation Learning Method and its Applications

ieee-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2023年第6期20卷 3451-3460页

作者： Fu, Haitao Zhao, Cecheng Niu, Xiaohui Zhang, Wen Huazhong Agr Univ Coll Informat Wuhan 430070 Peoples R China Huazhong Agr Univ Hubei Engn Technol Res Ctr Agr Big Data Agr Bioinformat Key Lab Hubei Prov Key Lab Smart Anim Farming Technol Wuhan 430070 Peoples R China

Learning representations from data is a fundamental step for machine learning. High-quality and robust drug representations can broaden the understanding of pharmacology, and improve the modeling of multiple drug-related prediction tasks, which further facilitates drug development. Although there are a number of models developed for drug representation learning from various data sources, few researches extract drug representations from gene expression profiles. Since gene expression profiles of drug-treated cells are widely used in clinical diagnosis and therapy, it is believed that leveraging them to eliminate cell specificity can promote drug representation learning. In this paper, we propose a three-stage deep learning method for drug representation learning, named DRLM, which integrates gene expression profiles of drug-related cells and the therapeutic use information of drugs. Firstly, we construct a stacked autoencoder to learn low-dimensional compact drug representations. Secondly, we utilize an iterative clustering module to reduce the negative effects of cell specificity and noise in gene expression profiles on the low-dimensional drug representations. Thirdly, a therapeutic use discriminator is designed to incorporate therapeutic use information into the drug representations. The visualization analysis of drug representations demonstrates DRLM can reduce cell specificity and integrate therapeutic use information effectively. Extensive experiments on three types of prediction tasks are conducted based on different drug representations, and they show that the drug representations learned by DRLM outperform other representations in terms of most metrics. The ablation analysis also demonstrates DRLM's effectiveness of merging the gene expression profiles with the therapeutic use information.

关键词： Drugs Gene expression Task analysis Representation learning Iterative methods Integrated circuits Training Drug representation learning gene expression profile therapeutic use

来源：评论

学校读者我要写书评

暂无评论

MTGDC: A Multi-Scale Tensor Graph Diffusion Clustering for Single-Cell RNA Sequencing data

引用

ieee-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2023年第5期20卷 3056-3067页

作者： Liu, Qiaoming Wang, Dong Zhou, Li Li, Jie Wang, Guohua Harbin Inst Technol Zhengzhou Res Inst Sch Med & Hlth Harbin 150001 Heilongjiang Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin 150001 Heilongjiang Peoples R China

Single-cell RNA sequencing (scRNA-seq) is a new technology that focuses on the expression levels for each cell to study cell heterogeneity. Thus, new computational methods matching scRNA-seq are designed to detect cell types among various cell groups. Herein, we propose a Multi-scale Tensor Graph Diffusion Clustering (MTGDC) for single-cell RNA sequencing data. It has the following mechanisms: 1) To mine potential similarity distributions among cells, we design a multi-scale affinity learning method to construct a fully connected graph between cells;2) For each affinity matrix, we propose an efficient tensor graph diffusion learning framework to learn high-order information among multi-scale affinity matrices. First, the tensor graph is explicitly introduced to measure cell-cell edges with local high-order relationship information. To further preserve more global topology structure information in the tensor graph, MTGDC implicitly considers the propagation of information via a data diffusion process by designing a simple and efficient tensor graph diffusion update algorithm. 3) Finally, we mix together the multi-scale tensor graphs to obtain the fusion high-order affinity matrix and apply it to spectral clustering. Experiments and case studies showed that MTGDC had obvious advantages over the state-of-art algorithms in robustness, accuracy, visualization, and speed.

关键词： Tensors Clustering algorithms Sequential analysis RNA Diffusion processes Topology Kernel Clustering single-cell RNA-seq tensor graph diffusion mapping cell heterogeneity

来源：评论

学校读者我要写书评

暂无评论

When, Where and How Does it Fail? A Spatial-Temporal Visual Analytics Approach for Interpretable Object Detection in Autonomous Driving

引用

ieee TRANSACTIONS ON visualization AND COMPUTER GRAPHICS 2023年第12期29卷 5033-5049页

作者： Wang, Junhong Li, Yun Zhou, Zhaoyu Wang, Chengshun Hou, Yijie Zhang, Li Xue, Xiangyang Kamp, Michael Zhang, Xiaolong (Luke) Chen, Siming Fudan Univ Sch Data Sci Shanghai 200437 Peoples R China Ruhr Univ Bochum Inst Med IKIM UK Essen D-44801 Bochum Germany Monash Univ Fac IT Dept Data Sci & AI Clayton Vic 3800 Australia Penn State Univ State Coll PA 16801 USA

Arguably the most representative application of artificial intelligence, autonomous driving systems usually rely on computer vision techniques to detect the situations of the external environment. Object detection underpins the ability of scene understanding in such systems. However, existing object detection algorithms often behave as a black box, so when a model fails, no information is available on When, Where and How the failure happened. In this paper, we propose a visual analytics approach to help model developers interpret the model failures. The system includes the micro- and macro-interpreting modules to address the interpretability problem of object detection in autonomous driving. The micro-interpreting module extracts and visualizes the features of a convolutional neural network (CNN) algorithm with density maps, while the macro-interpreting module provides spatial-temporal information of an autonomous driving vehicle and its environment. With the situation awareness of the spatial, temporal and neural network information, our system facilitates the understanding of the results of object detection algorithms, and helps the model developers better understand, tune and develop the models. We use real-world autonomous driving data to perform case studies by involving domain experts in computer vision and autonomous driving to evaluate our system. The results from our interviews with them show the effectiveness of our approach.

关键词： Autonomous driving spatial-temporal visual analytics interpretability

来源：评论

学校读者我要写书评

暂无评论

Summarizing task-based applications behavior over many nodes through progression clustering 31

Summarizing task-based applications behavior over many nodes...

引用

31st Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2023

作者： Nesi, Lucas Leandro Pinto, Vinicius Garcia Schnorr, Lucas Mello Legrand, Arnaud Institute of Informatics PPGC/UFRGS Porto Alegre Brazil Univ. Grenoble Alpes Grenoble France Computer Science Center Federal Univ. of Rio Grande Rio Grande Brazil Univ. Grenoble Alpes Cnrs Inria Grenoble Inp Lig GrenobleF-38000 France

ISBN: (纸本)9798350337631

visualization strategies are a valuable tool in the performance evaluation of HPC applications. Although the traditional Gantt charts are a widespread and enlightening strategy, it presents scalability problems and may misguide the analysis by focusing on resource utilization alone. This paper proposes an overview strategy to indicate nodes of interest for further investigation with classical visualizations like Gantt charts. For this, it uses a progression metric that captures work done per node inferred from the task-based structure, a time-step clustering of those metrics to decrease redundant information, and a more scalable visualization technique. We demonstrate with six scenarios and two applications that such a strategy can indicate problematic nodes more straightforwardly while using the same visualization space. Also, we provide examples where it correctly captures application work progression, showing application problems earlier and as an easy way to compare nodes. At the same time that traditional methods are misleading. © 2023 ieee.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

IoT Platform for Facility Management Practices Using BIM and Blockchain Concept Integration 2

IoT Platform for Facility Management Practices Using BIM and...

引用

2nd International Conference on Smart Cities 4.0, Smart Cities 4.0 2023

作者： Elmansy, Nada Baraka, Moustafa German University In Cairo Faculty Of Engineering And Materials Science Cairo Egypt Civil Engineering Program Faculty Of Engineering And Materials Science German University In Cairo Geomatics & Geoinformatics Cairo Egypt

ISBN: (纸本)9781665474306

Facility Management (FM) practices requires an efficient representations and reliable tools. Building information Modelling (BIM) held great potential for FM maintenance practices providing necessary facility information. Slow adoption of new technologies in the built environment is still a burden due to several factors like the lack of information sharing and collaborations, and the poor level of trust of information. In the built environment public sector, data security remains one of the maj or system deficiencies. With the blockchain technology (BC) evolving in recent times, security of data could be leveraged. This research establishes a framework utilizing managed BC in the built environment FM. The scope of this system is to integrate the benefits of BIM and BC to manage data from an loT platform gathering ambient conditions information. The flow of information is regarded in the established framework through the integration of four modules, namely, 1) data collection module, 2) data processing module, 3) data storage module, and 4) data visualization module. Furthermore, the developed framework is tested and applied for the validation of the approach. Results of the system are shown and are established by the system to be continuously updated and stored. The developed system serves as a trusted-fully secure tool for FM practitioners to assess and visualize indoor ambient comfort. Thus, the developed tool is proposing a state-of art-concept in the quest of the industry to reach a common data platform for the whole facility life-cycle. © 2023 ieee.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Role of Educational data Mining and Learning Analytics Techniques Used for Predictive Modeling 3

Role of Educational Data Mining and Learning Analytics Techn...

引用

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Kaur, Kanksha Dahiya, Omdev School of Computer Science and Engineering Lovely Professional University Punjab India

ISBN: (纸本)9798350336238

The use of data mining techniques to answer important educational questions is done with educational data mining that may be related to predicting students' performance or assessment. The purpose of these remains to address the goal of meeting and fulfilling the learning objectives. Learning analytics is a new approach for teachers to think about education and involves the visualization of data about students to improve learning. It is related to management strategies that prioritize quantitative measurements, which can sometimes be at odds with a teaching-focused approach to education. The purpose of this study is to perform a systematic literature review of the various techniques used in both educational data mining and learning analytics. The area of educational data mining utilizes data mining techniques to examine educational data. Meanwhile, learning analytics centers on utilizing data to gain knowledge about learning processes and student performance. The review will consider various techniques, including statistical methods, machine learning algorithms, and data visualization techniques, which are commonly used. The goal is to identify the most effective techniques for analyzing educational data and improving student learning outcomes. By performing a systematic literature review, this study will provide an overview of the current state of research in educational data mining and learning analytics. It will also identify gaps in the literature and suggest areas for future research. Ultimately, the findings of this study will be of great value to researchers, educators, and policymakers who are interested in using data to enhance the learning experience. For performing this, a few research questions have been designed to select relevant studies. In this study, the research articles from a decade, 2012 to 2022, are taken into consideration. From the overall search results, 41 studies have been taken into consideration that has addressed the scope and significan

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Emotional Attention: From Eye Tracking to Computational Modeling

引用

ieee TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第2期45卷 1682-1699页

作者： Fan, Shaojing Shen, Zhiqi Jiang, Ming Koenig, Bryan L. L. Kankanhalli, Mohan S. S. Zhao, Qi Natl Univ Singapore Sch Comp Singapore 119613 Singapore Univ Minnesota Dept Comp Sci & Engn Minneapolis MN 55455 USA Natl Univ Singapore Dept Elect & Comp Engn Singapore 117583 Singapore Southern Utah Univ Dept Psychol Cedar City UT 84720 USA

Attending selectively to emotion-eliciting stimuli is intrinsic to human vision. In this research, we investigate how emotion-elicitation features of images relate to human selective attention. We create the EMOtional attention dataset (EMOd). It is a set of diverse emotion-eliciting images, each with (1) eye-tracking data from 16 subjects, (2) image context labels at both object- and scene-level. Based on analyses of human perceptions of EMOd, we report an emotion prioritization effect: emotion-eliciting content draws stronger and earlier human attention than neutral content, but this advantage diminishes dramatically after initial fixation. We find that human attention is more focused on awe eliciting and aesthetic vehicle and animal scenes in EMOd. Aiming to model the above human attention behavior computationally, we design a deep neural network (CASNet II), which includes a channel weighting subnetwork that prioritizes emotion-eliciting objects, and an Atrous Spatial Pyramid Pooling (ASPP) structure that learns the relative importance of image regions at multiple scales. visualizations and quantitative analyses demonstrate the model's ability to simulate human attention behavior, especially on emotion-eliciting content.

关键词： Computational modeling visualization Observers Benchmark testing Analytical models Deep learning data models Human attention image sentiment human psychophysics convolutional neural network visual saliency

来源：评论

学校读者我要写书评

暂无评论

Design of Digital Twin-driven Integrated Control and Monitoring System for Transmission System

Design of Digital Twin-driven Integrated Control and Monitor...

引用

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Fan, Hongwei Chen, Buran Li, Qingshan Du, Yuyang Zhang, Xuhui Cao, Xiangang Xi'An University of Science and Technology School of Mechanical Engineering Xi'an China

ISBN: (纸本)9798350337754

Aiming at the problems of high cost, low efficiency, lack of real-time performance and visualization in existing control and monitoring methods of mechanical transmission system, an integrated control and monitoring scheme of mechanical transmission system based on digital twin is proposed. First, the detailed design of mechanical and electronic control system of physical platform was carried out. And the digital twin model was developed by Solidworks, 3ds MAX and Unity3D. Second, the hardware of monitoring and diagnosis system was built by piezoelectric accelerator, data acquisition instrument and upper computer. Meantime, the software was developed by LabVIEW. Finally, the transmission system fault test platform was used to carry out nine kinds of rotor imbalance test with different speeds and imbalances. The database was created by MySQL. Through experimental verification, the speed of digital twin model can be controlled and the historical or real-time data can also be invoked to drive the digital twin model. When the model was driven by experimental data, the user interface displayed the current state as rotor imbalance, and the turnplate was highlighted, which proves this work feasible and effective. © 2023 ieee.

关键词： Condition monitoring

来源：评论

学校读者我要写书评

暂无评论

DisAVR: Disentangled Adaptive Visual Reasoning Network for Diagram Question Answering

引用

ieee TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 4812-4827页

作者： Wang, Yaxian Wei, Bifan Liu, Jun Zhang, Lingling Wang, Jiaxin Wang, Qianying Xi An Jiao Tong Univ Sch Comp Sci & Technol Natl Engn Lab Big Data Analyt Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ Key Lab Intelligent Networks & Network Secur Minist Educ Xian 710049 Shaanxi Peoples R China Lenovo Res Beijing 100094 Peoples R China

Diagram Question Answering (DQA) aims to correctly answer questions about given diagrams, which demands an interplay of good diagram understanding and effective reasoning. However, the same appearance of objects in diagrams can express different semantics. This kind of visual semantic ambiguity problem makes it challenging to represent diagrams sufficiently for better understanding. Moreover, since there are questions about diagrams from different perspectives, it is also crucial to perform flexible and adaptive reasoning on content-rich diagrams. In this paper, we propose a Disentangled Adaptive Visual Reasoning Network for DQA, named DisAVR, to jointly optimize the dual-process of representation and reasoning. DisAVR mainly comprises three modules: improved region feature learning, question parsing, and disentangled adaptive reasoning. Specifically, the improved region feature learning module is designed to first learn robust diagram representation by integrating detail-aware patch features and semantically-explicit text features with region features. Subsequently, the question parsing module decomposes the question into three types of question guidance including region, spatial relation and semantic relation guidance to dynamically guide subsequent reasoning. Next, the disentangled adaptive reasoning module decomposes the whole reasoning process by employing three visual reasoning cells to construct a soft fully-connected multi-layer stacked routing space. These three cells in each layer reason over object regions, semantic and spatial relations in the diagram under the corresponding question guidance. Moreover, an adaptive routing mechanism is designed to flexibly explore more optimal reasoning paths for specific diagram-question pairs. Extensive experiments on three DQA datasets demonstrate the superiority of our DisAVR.

关键词： Cognition visualization Task analysis Question answering (information retrieval) Semantics Geometry Routing Diagram understanding visual reasoning diagram question answering

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent management and control software for gas drainage in the whole mine based on cross platform architecture 7

Design of intelligent management and control software for ga...

引用

7th ieee Information Technology and Mechatronics Engineering Conference, ITOEC 2023

作者： Wu, Kejie Chongqing Research Institute of China Coal Science and Industry Group Chongqing China State Key Laboratory of Gas Disaster Monitoring and Emergency Technology Chongqing China

ISBN: (纸本)9798350334197

The existing coal mine gas drainage anomaly recognition needs to use manual assistance to view relevant data analysis, lacking of independent and intelligent analysis means;The ability of timely disposal of abnormal drainage is weak, and the multi system linkage control function is lacking when gas disasters occur;The software deployment environment is single, and cross platform and cross end application access cannot be realized. Aiming at the above problems, an intelligent management and control software for gas drainage in the whole mine based on cross platform architecture is designed. The software consists of two parts which contains company side and mine side. Those technologies such as extraction multi-source data collection, extraction borehole auxiliary design, extraction data analysis, operation and maintenance management of extraction equipment, extraction GIS display, and extraction integration control are used to realize the global visualization of the extraction system. The multi-level data traceability access mechanism is established by constructing characteristic map of thematic data, which realizes the comprehensive analysis of the mathematical and physical characteristics, extraction evaluation characteristics, equipment fault characteristics, extraction anomaly characteristics, and borehole trajectory characteristics of the extraction data. In case of abnormal drainage, the software can automatically link the broadcasting system to inform the evacuation personnel in the dangerous area of gas emission, and link the ventilation monitoring system to strengthen the ventilation in the abnormal area, and automatically push the abnormal alarm message to the relevant person in charge through the message push strategy, so as to quickly and timely solve the drainage problem. We use Docker technology to realize that SQL Server database and Web terminal applications are deployed in the Docker environment. The native HTML technology combined with the responsiv

关键词： Coal mines

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：