miRTRS: A Recommendation Algorithm for Predicting miRNA Targets
作者：
Jiang, Hui;Wang, Jianxin* ;Li, Min;Lan, Wei;Wu, Fang-Xiang;...
期刊：
IEEE/ACM Transactions on Computational Biology and Bioinformatics ,2020年17(3):1032-1041 ISSN：1545-5963
通讯作者：
Wang, Jianxin
作者机构：
[Li, Min; Jiang, Hui; Lan, Wei; Wang, Jianxin] Cent South Univ, Sch Informat Sci & Engn, Changsha 410083, Peoples R China.;[Jiang, Hui] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Peoples R China.;[Wu, Fang-Xiang] Univ Saskatchewan, Div Biomed Engn, Saskatoon, SK S7N 5A9, Canada.;[Pan, Yi] Georgia State Univ, Dept Comp Sci, Atlanta, GA 30302 USA.
通讯机构：
[Wang, Jianxin] C;Cent South Univ, Sch Informat Sci & Engn, Changsha 410083, Peoples R China.
关键词：
Prediction algorithms;Bipartite graph;Feature extraction;Prediction methods;Gene expression;Software algorithms;miRNA target;recommendation algorithm;bipartite graph
摘要：
microRNAs (miRNAs) are small and important non-coding RNAs that regulate gene expression in transcriptional and post-transcriptional level by combining with their targets (genes). Predicting miRNA targets is an important problem in biological research. It is expensive and time-consuming to identify miRNA targets by using biological experiments. Many computational methods have been proposed to predict miRNA targets. In this study, we develop a novel method, named miRTRS, for predicting miRNA targets based on a recommendation algorithm. miRTRS can predict targets for an isolated (new) miRNA with miRNA sequence similarity, as well as isolated (new) targets for a miRNA with gene sequence similarity. Furthermore, when compared to supervised machine learning methods, miRTRS does not need to select negative samples. We use 10-fold cross validation and independent datasets to evaluate the performance of our method. We compared miRTRS with two most recently published methods for miRNA target prediction. The experimental results have shown that our method miRTRS outperforms competing prediction methods in terms of AUC and other evaluation metrics. © 2004-2012 IEEE.
语种：
英文
展开
Automatic ICD code assignment of Chinese clinical notes based on multilayer attention BiRNN
作者：
Yu, Ying;Li, Min;Liu, Liangliang;Fei, Zhihui;Wu, Fang-Xiang;...
期刊：
Journal of Biomedical Informatics ,2019年91:103114 ISSN：1532-0464
通讯作者：
Wang, Jianxin
作者机构：
[Fei, Zhihui; Li, Min; Yu, Ying; Liu, Liangliang; Wang, Jianxin] Cent South Univ, Sch Comp Sci & Engn, Changsha 410083, Peoples R China.;[Yu, Ying] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Peoples R China.;[Wu, Fang-Xiang] Univ Saskatchewan, Div Biomed Engn, Saskatoon, SK S7N 5A9, Canada.;[Wu, Fang-Xiang] Univ Saskatchewan, Dept Mech Engn, Saskatoon, SK S7N 5A9, Canada.
通讯机构：
[Wang, Jianxin] C;Cent South Univ, Sch Comp Sci & Engn, Changsha 410083, Peoples R China.
关键词：
Codes (symbols);Embeddings;Multilayers;Semantics;Bidirectional recurrent neural networks;Character-enhanced;Clinical notes;Electronic health record;Hierarchical approach;ICD code;International classification of disease;Neural network model;Recurrent neural networks;Article;artificial neural network;attention;Chinese (language);hospital admission;human;International Classification of Diseases;linguistics;machine learning;medical record;multilayer attention bidirectional recurrent neural network;performance;prediction;priority journal;problem solving;short term memory;automation;China;electronic health record;information processing;machine learning;Automation;China;Datasets as Topic;Electronic Health Records;International Classification of Diseases;Machine Learning
摘要：
International Classification of Diseases (ICD) code is an important label of electronic health record. The automatic ICD code assignment based on the narrative of clinical documents is an essential task which has drawn much attention recently. When Chinese clinical notes are the input corpus, the nature of Chinese brings some issues that need to be considered, such as the accuracy of word segmentation and the representation of single Chinese characters which contain semantics. Taking the lengthy text of patient notes and the representation of Chinese words into account, we present a multilayer attention bidirectional recurrent neural network (MA-BiRNN) model to implement the assignment of disease codes. A hierarchical approach is used to represent the feature of discharge summaries without manual feature engineering. The combination of character level embedding and word level embedding can improve the representation of words. Attention mechanism is introduced into bidirectional long short term memory networks, which helps to solve the performance dropping problem when plain recurrent neural networks encounter long text sequences. The experiment is carried out on a real-world dataset containing 7732 admission records in Chinese and 1177 unique ICD-10 labels. The proposed model achieves 0.639 and 0.766 in F1-score on full-level code and block-level code, respectively. It outperforms the baseline neural network models and achieves the lowest Hamming loss value. Ablation analysis indicates that the multilevel attention mechanism plays a decisive role in the system for dealing with Chinese clinical notes.
语种：
英文
展开
Corrigendum to “Optimal design methods for a digital human-computer interface based on human reliability in a nuclear power plant: Part 2: The optimization design method for component quantity” [Ann. Nucl. Energy 106 (2017) 247–255]
作者：
Jiang, Jianjun* ;Zhang, Li;Wang, Yiqun;Xie, Tian;Wu, Daqing;...
期刊：
Annals of Nuclear Energy ,2018年111:715 ISSN：0306-4549
通讯作者：
Jiang, Jianjun
作者机构：
[Jiang, Jianjun; Wang, Yiqun; Zhang, Mengjia; Zhang, Li; Xie, Tian] Univ South China, Human Factors Inst, Sch Management, Hengyang 421001, Hunan, Peoples R China.;[Jiang, Jianjun; Zhang, Li] Hunan Inst Technol, Sch Safety & Environm Engn, Hengyang 421002, Hunan, Peoples R China.;[Li, Min; Wu, Daqing] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Hunan, Peoples R China.;[Peng, Yuyuan] South China Univ Technol, Sch Comp Engn, Guangzhou Coll, Guangzhou 510830, Guangdong, Peoples R China.;[Peng, Jie] GuangDong Univ Finance & Econ, Informat Sci Coll, Guangzhou 510320, Guangdong, Peoples R China.
通讯机构：
[Jiang, Jianjun] U;Univ South China, Human Factors Inst, Sch Management, Hengyang 421001, Hunan, Peoples R China.
摘要：
The author regrets that the order of author list and affiliations of the above paper were incorrectly produced in the printed issue. The correct order of author list and affiliations appears above. The authors would like to apologise for any inconvenience caused. © 2017
语种：
英文
展开
核电厂数字化人-机界面二类任务信息导航调度算法研究
作者：
蒋建军;张力;王以群;谢天;李敏;...
期刊：
核动力工程 ,2018年39(1):140-145 ISSN：0258-0926
作者机构：
[张力; 蒋建军; 王以群; 戴立操; 谢天] Human Factors Institute, School of Management, University of South China, Hengyang, Hunan, 421001, China;[彭玉元] School of Economic and Management, Guangzhou College of South China University of Technology, Guangzhou, 510830, China;[李敏] College of computer science and technique, University of South China, Hengyang, Hunan, 421001, China;[蒋建军; 张力] School of Safety and Environment Engineering, Hunan Institute of Technology, Hengyang, Hunan, 421002, China
关键词：
二类任务;信息导航;数学模型;调度算法
摘要：
为减轻核电厂数字化人-机界面二类任务信息导航画面配置给操纵员带来的工作负荷,本文提出二类任务信息导航的调度算法以解决导航信息画面的配置。通过建立调度算法的执行流程、数学模型、信息导航特征提取子算法、相同关键字统计子算法,获得了导航信息画面配置的调度算法。仿真实验结果表明,该算法在平均周转时间、算法的正确性方面具有较好的性能,能应用于导航信息画面的智能配置,以减少操纵员人工方式画面配置所产生的开销。
语种：
中文
展开
A cognitive reliability model research for complex digital human-computer interface of industrial system
作者：
Jiang, Jianjun* ;Wang, Yiqun;Zhang, Li;Wu, Daqing;Li, Min;...
期刊：
Safety Science ,2018年108:196-202 ISSN：0925-7535
通讯作者：
Jiang, Jianjun
作者机构：
[Jiang, Jianjun; Wang, Yiqun; Zhang, Li; Li, Pengcheng; Xie, Tian; Dai, Licao] Univ South China, Human Factors Inst, Sch Management, Hengyang 421001, Hunan, Peoples R China.;[Jiang, Jianjun; Zhang, Li] Hunan Inst Technol, Sch Safety & Environm Engn, Hengyang 421002, Hunan, Peoples R China.;[Li, Min; Wu, Daqing] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Hunan, Peoples R China.;[Zhang, Anna; Wang, Shiwei; Shi, Xianyun; Li, Peiyao] Univ South China, Sch Econ & Management, Dept Informat Management & Informat Syst, Grade E Commerce 15, Hengyang 421001, Hunan, Peoples R China.
通讯机构：
[Jiang, Jianjun] U;[Jiang, Jianjun] H;Univ South China, Human Factors Inst, Sch Management, Hengyang 421001, Hunan, Peoples R China.;Hunan Inst Technol, Sch Safety & Environm Engn, Hengyang 421002, Hunan, Peoples R China.
关键词：
Digital human-computer interface;Cognitive reliability model;Bayesian network
摘要：
Nowadays, traditional human–machine interface has been converted into digital human–computer interface in most industrial control rooms, then, cognitive process and reliability are also bound to be different from traditional human–machine interface. Aiming at the situation, the authors in this paper propose a cognitive reliability model with influencing factors based on Bayesian network. Taking a nuclear power plant (Npp) as research background, taking simulative experiment as study way, parameter values in cognitive reliability mathematical model are obtained by analyzing much experimental data. The proposed model is reasonable, accurate, sensitive and convergent by analyzing experiment data. Cognitive error probabilities of some tasks regarding a hot transmission system (HTS) leak accident in a Npp are obtained according to the proposed model and simulative experiments. The model provides a simple and feasible approach to analyze cognitive reliability of operating process in digital human–computer interface. © 2017 Elsevier Ltd
语种：
英文
展开
Numerical simulation to quantify the leakage risk in a multi-layer aquifer system of pure brine recovery and CO2 -enhanced brine recovery: a case study of potassium-rich brine recovery in Jianghan Basin of China
作者：
Fang, Qi;Lv, Junwen;Peng, Guojian* ;Luo, Caiwu;Li, Mi;...
期刊：
Environmental Earth Sciences ,2017年76(13):1-11 ISSN：1866-6280
通讯作者：
Peng, Guojian
作者机构：
[Li, Mi; Fang, Qi; Lv, Junwen; Tan, Wenfa; Luo, Caiwu; Luo, Yingfeng] Univ South China, Sch Environm & Safety Engn, Hengyang 421001, Peoples R China.;[Peng, Guojian] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Peoples R China.
通讯机构：
[Peng, Guojian] U;Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Peoples R China.
关键词：
Pure brine recovery (PBR);CO2-enhanced brine recovery (CO2-EBR);A multi-layer aquifer;Leakage risk;Pressure control
摘要：
Deep brine recovery enhanced by supercritical CO2 injection is proposed to be a win–win method for the enhancement of brine production and CO2 storage capacity and security. However, the cross-flow through interlayers under different permeability conditions is not well investigated for a multi-layer aquifer system. In this work, a multi-layer aquifer system with different permeability conditions was built up to quantify the brine production yield and the leakage risk under both schemes of pure brine recovery and enhanced by supercritical CO2. Numerical simulation results show that the permeability conditions of the interlayers have a significant effect on the brine production and the leakage risk as well as the regional pressure. Brine recovery enhanced by supercritical CO2 injection can improve the brine production yield by a factor of 2–3.5 compared to the pure brine recovery. For the pure brine recovery, strong cross-flow through interlayers occurs due to the drastic and extensive pressure drop, even for the relative low permeability (k=10−20m2) mudstone interlayers. Brine recovery enhanced by supercritical CO2 can successfully manage the regional pressure and decrease the leakage risk, even for the relative high permeability (k=10−17m2) mudstone interlayers. In addition, since the leakage of brine mainly occurs in the early stage of brine production, it is possible to minimize the leakage risk by gradually decreasing the brine production pressure at the early stage. Since the leakage of CO2 occurs in the whole production period and is significantly influenced by the buoyancy force, it may be more effective by adopting horizontal wells and optimizing well placement to reduce the CO2 leakage risk. © 2017, Springer-Verlag GmbH Germany.
语种：
英文
展开
Optimal design methods for a digital human-computer interface based on human reliability in a nuclear power plant: Part 2: The optimization design method for component quantity
作者：
Jiang, Jianjun* ;Zhang, Li;Xie, Tian;Wu, Daqing;Li, Min;...
期刊：
Annals of Nuclear Energy ,2017年106:247-255 ISSN：0306-4549
通讯作者：
Jiang, Jianjun
作者机构：
[Jiang, Jianjun; Zhang, Li] Hunan Inst Technol, Sch Safety & Environm Engn, Hengyang 421002, Hunan, Peoples R China.;[Jiang, Jianjun; Wang, Yiqun; Zhang, Mengjia; Xie, Tian] Univ South China, Sch Econ & Management, Human Factors Inst, Hengyang 421001, Hunan, Peoples R China.;[Li, Min; Wu, Daqing] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Hunan, Peoples R China.;[Peng, Yuyuan] South China Univ Technol, Guangzhou Coll, Sch Comp Engn, Guangzhou 510830, Guangdong, Peoples R China.;[Peng, Jie] GuangDong Univ Finance & Econ, Informat Sci Coll, Guangzhou 510320, Guangdong, Peoples R China.
通讯机构：
[Jiang, Jianjun] H;[Jiang, Jianjun] U;Hunan Inst Technol, Sch Safety & Environm Engn, Hengyang 421002, Hunan, Peoples R China.;Univ South China, Sch Econ & Management, Human Factors Inst, Hengyang 421001, Hunan, Peoples R China.
关键词：
Affinity error probability mapping function;Human reliability;Quantity of components;Quick convergence search method
摘要：
This is the second in a series of papers describing the optimal design method for a digital human-computer interface of nuclear power plant (Npp) from three different points based on human reliability. The purpose of this series is to explore different optimization methods from varying perspectives. This present paper mainly discusses the optimal design method for quantity of components of the same factor. In monitoring process, quantity of components has brought heavy burden to operators, thus, human errors are easily triggered. To solve the problem, the authors propose an optimization process, a quick convergence search method and an affinity error probability mapping function. Two balanceable parameter values of the affinity error probability function are obtained by experiments. The experimental results show that the affinity error probability mapping function about human-computer interface has very good sensitivity and stability, and that quick convergence search method for fuzzy segments divided by component quantity has better performance than general algorithm. © 2017 Elsevier Ltd
语种：
英文
展开
核电厂数字化规程在屏之间布局方法及评价
作者：
蒋建军;张力;王以群;彭玉元;李鹏程;...
期刊：
广东工业大学学报 ,2016年19(3):71-76 ISSN：1007-7162
作者机构：
南华大学经济管理学院人因研究所，湖南衡阳，421001;湖南工学院，湖南衡阳，421002;华南理工大学广州学院计算机工程学院，广东广州，510800;南华大学计算机科学与技术学院，湖南衡阳，421001;[李鹏程; 王以群; 李敏; 张力; 伍大清; 张晓玲; 蒋建军] 南华大学
关键词：
事故规程;人因可靠性;动态标识最短移动路径算法
摘要：
面对数字化系统带来的挑战,以减少同一操纵员在屏之间的移动距离为目标,以核电厂数字化人机界面事故规程为研究对象,以人因可靠性为基础,提出事故规程布局的动态标识最短移动路径算法,并利用神经网络人因可靠性评价方法分析执行过程的可靠性。提出的方法通过实例进行了分析,实验表明提出的方法具有较好的性能,能解决核电厂数字化事故规程在屏之间的自动布局。
语种：
中文
展开
Optimal design method for a digital human–computer interface based on human reliability in a nuclear power plant. Part 3: Optimization method for interface task layout
作者：
Jiang, Jianjun* ;Wang, Yiqun;Zhang, Li;Xie, Tian;Li, Min;...
期刊：
Annals of Nuclear Energy ,2016年94:750-758 ISSN：0306-4549
通讯作者：
Jiang, Jianjun
作者机构：
[Jiang, Jianjun; Zhang, Li; Wang, Yiqun; Xie, Tian] Univ South China, Sch Econ & Management, Human Factors Inst, Hengyang 421001, Hunan, Peoples R China.;[Zhang, Li] Hunan Inst Technol, Hengyang 421002, Hunan, Peoples R China.;[Li, Min; Wu, Daqing] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Hunan, Peoples R China.;[Peng, Yuyuan] S China Univ Technol, Guangzhou Coll, Sch Comp Engn, Guangzhou 510830, Guangdong, Peoples R China.;[Shen, Mengxu; Weng, Mengyun; Xie, Cen; Wang, Shiwei; Li, Peiyao] Univ South China, Sch Econ & Management, Dept Informat Management & Informat Syst, Grade Ecommerce 15, Hengyang 421001, Hunan, Peoples R China.
通讯机构：
[Jiang, Jianjun] U;Univ South China, Sch Econ & Management, Human Factors Inst, Hengyang 421001, Hunan, Peoples R China.
关键词：
Digital human–computer interface;Human reliability;Optimization method;Shortest moving path optimization algorithm
摘要：
This is the last in a series of papers describing the optimal design for a digital human–computer interface of a nuclear power plant (NPP) from three different points based on human reliability. The purpose of this series is to propose different optimization methods from varying perspectives to decrease human factor events that arise from the defects of a human–computer interface. The present paper mainly solves the optimization method as to how to effectively layout interface tasks into different screens. The purpose of this paper is to decrease human errors by reducing the distance that an operator moves among different screens in each operation. In order to resolve the problem, the authors propose an optimization process of interface task layout for digital human–computer interface of a NPP. As to how to automatically layout each interface task into one of screens in each operation, the paper presents a shortest moving path optimization algorithm with dynamic flag based on human reliability. To test the algorithm performance, the evaluation method uses neural network based on human reliability. The less the human error probabilities are, the better the interface task layouts among different screens are. Thus, by analyzing the performance of each interface task layout, the optimization result is obtained. Finally, the optimization layouts of spurious safety injection event interface tasks of the NPP are obtained by an experiment, the proposed methods has a good accuracy and stabilization. © 2016 Elsevier Ltd
语种：
英文
展开
基于人因可靠性的核电厂数字化人机界面功能单元数量优化方法
作者：
蒋建军;张力;王以群;彭玉元;李敏;...
期刊：
原子能科学技术 ,2015年49(10):1876-1881 ISSN：1000-6931
作者机构：
[张力; 青涛; 蒋建军; 李鹏程; 王以群] Human Factors Institute, School of Economic &, Management, University of South China, Hengyang, China;[张晓玲; 伍大清] School of Computer Science and Technique, University of South China, Hengyang, China;[李敏] Networks Center, University of South China, Hengyang, China;[彭玉元] School of Computer Engineering, Guangzhou College of South China University of Technology, Guangzhou, China;[张力] Hunan Institute of Technology, Hengyang, China
关键词：
核电厂数字化人机界面;构件数量;取中查找提取方法;失误亲和率函数
摘要：
核电厂数字化人机界面功能块中的构件数量给操纵员带来了极大负荷并影响人误事件的发生。本文对功能块中的参数数量建立了一完整的优化流程图,对流程图中的几个关键部分进行详细研究:对因子数量采用动态模糊分段法产生模糊数量段;在模糊数量段因子的搜索中,建立了模糊数量段的取中查找提取方法,大幅提高了搜索性能;对人机界面参数量设计了失误亲和率函数。试验结果表明:模糊数量段的取中查找提取方法明显优于顺序查找提取方法,失误亲和率函数具有较好的稳定性、收敛性及灵敏度。
语种：
中文
展开
基于SmartFoxServer的网络游戏服务器系统的研究与设计
作者：
栗芳凯;刘振宇;李敏
期刊：
数字社区&智能家居 ,2012年8(13):3075-3077 ISSN：1009-3044
作者机构：
南华大学计算机科学与技术学院,湖南衡阳,421001;[刘振宇; 李敏; 栗芳凯] 南华大学
关键词：
游戏服务器;大规模;高并发
摘要：
网络游戏服务器需要支持大规模用户同时在线,设计和开发上具有一定的复杂度。SmartFoxServer是一款成熟的游戏服务器软件,支持大规模高并发的用户访问。该文首先对SmartFoxServer进行了深入的研究,并介绍了如何基于SmartFoxServer开发具有可扩展性和可维护性的游戏服务器端系统。
语种：
中文
展开
基于SOA的模型驱动测试应用研究
作者：
李敏;刘振宇
期刊：
电脑知识与技术 ,2008年4(36):2784-2786 ISSN：1009-3044
作者机构：
南华大学,计算机科学与技术学院,湖南,衡阳,421001;南华大学,网络信息中心,湖南,衡阳,421001;[刘振宇; 李敏] 南华大学
关键词：
面向服务架构;模型驱动测试;模型驱动架构;统一建模测试设置
摘要：
随着应用系统规模增大,功能复杂性增强,对于用于保证软件质量的现有软件测试技术显得越来越力不从心。特别是近几年兴起的基于模型驱动架构的分布式并发系统对软件测试提出了更高的要求。模型驱动测试从系统层面上分析测试系统,根据系统需求说明书和测试任务,设计系统测试模型,生成测试代码,执行测试过程,大大提高了软件测试的效率。本论文基于模型驱动架构设计一个功能简单的货币交换Service,阐述模型驱动测试软件测试过程。
语种：
中文
展开
