检索结果-内蒙古大学图书馆

Chinese Control Conference (CCC)

作者： Yang Jixuan Zhang Qin Yang Peng Sun Junqing Tianjin Key Laboratory of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin China

The Laser Induced Breakdown Spectroscopy (LIBS) technology can be used to detect the elements in the alloy steel in real time. Quantitative analysis method of the traditional LIBS technology mainly has the calibration method and calibration free method, but there are two shortcomings: low prediction accuracy and over fitting. Random Forest Regression (RFR) algorithm can be used for classification and regression, can effectively avoid “overfitting” phenomenon. Therefore, in this paper, we combine the random forest regression algorithm with laser induced breakdown spectroscopy applied to the detection of the concentration of alloy steel elements in the metallurgy industry. At the same time, compared with partial least squares method based on the LIBS, the results show that the random forest algorithm combined with the LIBS technology has the higher prediction accuracy, lower root mean square error and better robustness.

关键词： Forestry Steel Regression tree analysis Predictive models Prediction algorithms Vegetation

来源：评论

学校读者我要写书评

暂无评论

ECG Based Identification by Deep Learning 12th

ECG Based Identification by Deep Learning

引用

12th Chinese Conference on Biometric Recognition, CCBR 2017

作者： Zheng, Gang Ji, Shengzhen Dai, Min Sun, Ying Tianjin Key Laboratory of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9783319699226

Strategies were proposed for Electrocardiogram (ECG) based identification. Firstly, a selecting mechanism based on information entropy was used to obtain whole heart beat signal;Secondly, a Depth Neural Network (DNN) based on Denoising AutoEncoder (DAE) was adopted in feature selection unsupervised, by which, the robustness of the recognition system could be improved in recognizing. Finally, 98.10% and 95.67% recognition rate were obtained on self-collected calm and high pressure data sets respectively, and 94.39% rate on combined data sets of MIT arrhythmia database (mitdb) and self-collected data averagely. © 2017, Springer International Publishing AG.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Research and Construction of Word Vector Extension Structure Based on Context

引用

Journal of Physics: Conference Series 2019年第1期1325卷

作者： Yiying Wang Hongyun Ning Tianjin Key Laboratory of Intelligence Computing & New Software Technology Tianjin University of Technology Tianjin 300384 China

The CBOW (Continuous Bag-of-Words) model is a three-layer forward neural network that predicts the central word vector by the fixed-size window information. In fact, context has a very important role in understanding the meaning of words. However, the context information of the fixed window size is partial and it is not enough to represent the whole context. Due to the polysemy of Chinese words, the same word may have different semantics in different contexts, while the traditional CBOW method ignores the polysemy of words. Therefore, this paper proposes a context-based word vector extension structure for the above problems. The main contents are as follows: (1) Introducing the concept of context vector. The entire sentence in which the target word is located is represented by a vector. (2) Constructing the polysemy storage method of words, adding a contextual list to each word vector, so that the multiple semantics of the words can be effectively distinguished. (3) Based on the word vector extension structure of this paper, a new character vector generation model is proposed, and the effect of the new model and the traditional CBOW model in the news headline similarity sorting task is compared. The experimental results show that the new character vector generation model based on the extension structure of the word vector obtains better result.

关键词：

来源：评论

学校读者我要写书评

暂无评论

new Big Data Collecting Method Based on Compressive Sensing in WSN

New Big Data Collecting Method Based on Compressive Sensing ...

引用

International Conference on Computer Communications and Networks (ICCCN)

作者： De-gan Zhang Xiao-hua Liu Yu-ya Cui Hong-tao Peng School of Computer Science &Engineering Tianjin University of Technology Tianjin China Computing & Novel software Technology Tianjin Key Lab of Intelligent Tianjin China Ministry of Education Key Laboratory of Computer Vision and System(TJUT) Tianjin China National Petroleum Corporation (CNPC) Managers Training Institute Beijing China

Considered the wireless sensor network clustering structure, a new big data collecting method based on compressive sensing is proposed. The collection process is as follows: in the cluster, the sink node sets the corresponding seed vector based on the distribution of network, and then sends it to each cluster head. Cluster head can generate corresponding own random spacing sparse matrix based on its received seed vector, and collect data through compressive sensing technology; Among clusters, clusters forward measurement values to sink node along multi-hop routing tree which we built before. Performance analyzing and comparison of results show that this method is superior to other methods regardless of in a cluster or inter-cluster.

关键词： Wireless sensor networks Compressed sensing Sparse matrices Big Data Routing Energy consumption Training

来源：评论

学校读者我要写书评

暂无评论

Study of Continuous Blood Pressure Measurement Based on Single lead Pulse Wave

Study of Continuous Blood Pressure Measurement Based on Sing...

引用

2017 2nd International Conference on Materials Science,Machinery and Energy Engineering(MSMEE 2017)

作者： Gang Zheng Lin-Lin Fan Jia Qi Tianjin Key Laboratory of Intelligent Computing and Software New Technology Tianjin University of technology School of computer science and engineering Tianjin University of technology

In order to achieve a non-invasive continuous measurement of blood pressure, a method of establishing a nonlinear blood pressure estimation model by BPNN(Back Propagation Neural Network)was proposed. By acquiring pulse wave, systolic and diastolic blood pressure value of every heart beat cycle were calculated based on the model, and continuous blood pressure was gotten as consequence. Experiments were done on 25 healthy young students and 33 patients in the ICU ward that introduced from MIMIC public database. Experiment result show that 95% systolic values and 96% diastolic values of health group were in confidence interval respectively, and that of patient group were 96.7% in systolic value and 95% in diastolic value respectively. And the blood pressure values measured by the proposed model met AAMI standard.

关键词： Pulse Wave Continuous Blood Pressure Measurement BPNN MIMIC

来源：评论

学校读者我要写书评

暂无评论

Block linked list index structure for large data full text retrieval

Block linked list index structure for large data full text r...

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Yang Yang Hongyun Ning Tianjin Key Laboratory of Intelligence Computing & New Software Technology Tianjin University of Technology Tianjin China

In order to solve the problems of the existing Chinese full-text retrieval algorithms in terms of large data, for example, data structure is difficult to expand, not suitable for incremental index, and the retrieval efficiency is low. Based on the traditional inverted index structure, this paper proposes an index structure, which can support large data storage with extension ability and update in real time: block linked-list index structure. Firstly, the new algorithm introduces the management concept of the block unit, the block unit is responsible for the management of the document set, and it creates an index for each term in the master index, then the index linked-list maps the term index and the block unit. This block linked-list index structure can greatly improve the ability of index expansion. Secondly, the main index and document index are both using the fixed-length storage with the same length, the positions of the terms' index information are both stationary in the master index file and the document index file of the block unit. According to the method, it can effectively solve the problems of the incremental index update and improve the update efficiency of the index. Finally, in the experiments, 350000 documents (about 1.46TB data) are randomly selected from the internet corpus (SogouT), which is used for comparing two index algorithms in three aspects, including the capability of initial datasets index creation, multitudinous files update and the retrieval of massive data sets. The results show that the new index algorithm has higher processing performance, especially in the efficiency of updating, with nearly 10% improvement.

关键词： Data structures Indexing Memory Periodic structures Computational efficiency Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Research on Hepatitis Auxiliary Diagnosis Model Based on Fuzzy Integral and GA-BP Neural Network

Research on Hepatitis Auxiliary Diagnosis Model Based on Fuz...

引用

2017 IEEE 8th International Conference on software Engineering and Service Science

作者： Chunyan Yang JinJie Song Tianjin Key Laboratory of Intelligent Computing & Novel Software Technology Tianjin University of Technology Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology

In this pa per, in order to impro ve the accuracy of hepatitis diagnosis in computer-aided diagnosis system, the medical data from the network public database were optimized by GA-BP neural network algorithm, and then we obtained the important index of judging the hepatitis and the weight of the index through thi s algorithm, we regarded the weight as the single point measure of non-additive, and then using the fuzzy integral calculated the proba bility of a person being diagnosed with hepatitis. From the results of calculation, using fuzzy integral can greatly improve the accuracy of hepatitis auxiliary diagnosis.

关键词： hepatitis auxiliary diagnosis GA-BP neural network fuzzy integral

来源：评论

学校读者我要写书评

暂无评论

Study on Short Text Classification with Integrated Algorithm 13

Study on Short Text Classification with Integrated Algorithm

引用

13th Web Information Systems and Applications Conference, WISA 2016

作者： Zhao, Dexin Du, Nana Qin, Liangliang Tianjin Key Laboratory of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9781509054374

With the rapid growth of the number of short text, how to effectively realize the automatic classification of short text is needed to be solved in the information domain. According to the characteristics of short text, this paper proposes Bagging-NB & Bagging-BSJ, which are two classification algorithms based on the improvement of current integrated classifiers. Traditional classifier NB, SVM, J48 are used as the basis classifiers to train the classification models. Compared with several individual classifiers, our methods have excellent results in a variety of classification evaluation indexes. © 2016 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Research on green vehicle scheduling problem of free picking up and delivering customers for airlines ticketing company 28

Research on green vehicle scheduling problem of free picking...

引用

28th Chinese Control and Decision Conference, CCDC 2016

作者： Gang, Hao Meiling, Feng Hainan, Zhao Junqing, Sun Tianjin Key Laboratory of Intelligent Computing and Novel Software Technique Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9781467397148

In this paper, the vehicle scheduling and routing problem of airline ticketing companies which provide free services of picking customers up and delivering them to airports is studied. Taking the time window constraints, customer satisfaction and time-dependent factors into consideration, this paper presents the mathematical model which take minimizing vehicle use cost and carbon emission as its objectives. According to the characteristics of the problem, a hybrid algorithm, which combines heuristic and tabu search algorithms, is designed to solve the model. Then, a simulated numerical case is employed to verify the validity of the mathematical model and the hybrid algorithm. The simulating experiments about the numerical case show that by the model and the hybrid algorithm a vehicle scheduling and routing plan can be found with significant reduction in carbon emission and without clear increase of the total vehicle operational cost compared to the plan by the traditional approach. This shows that the vehicle scheduling and routing plan found by the approach proposed in this paper is more environmentally friendly and does not significantly increase total vehicle operational cost of the company. © 2016 IEEE.

关键词： Airport Pickup Service Customer Satisfaction Green Routes Tabu Search Algorithm Vehicle Routing Problem

来源：评论

学校读者我要写书评

暂无评论

Research on Green Vehicle Scheduling Problem of Free Picking up and Delivering Customers for Airlines Ticketing Company

Research on Green Vehicle Scheduling Problem of Free Picking...

引用

第28届中国控制与决策会议

作者： Hao Gang Feng Meiling Zhao Hainan Sun Junqing Tianjin Key Laboratory of Intelligent Computing and Novel Software Technique Tianjin University of Technology

ISBN: (纸本)9781467397155

In this paper,the vehicle scheduling and routing problem of airline ticketing companies which provide free services of picking customers up and delivering them to airports is *** the time window constraints,customer satisfaction and time-dependent factors into consideration,this paper presents the mathematical model which take minimizing vehicle use cost and carbon emission as its *** to the characteristics of the problem,a hybrid algorithm,which combines heuristic and tabu search algorithms,is designed to solve the ***,a simulated numerical case is employed to verify the validity of the mathematical model and the hybrid *** simulating experiments about the numerical case show that by the model and the hybrid algorithm a vehicle scheduling and routing plan can be found with significant reduction in carbon emission and without clear increase of the total vehicle operational cost compared to the plan by the traditional *** shows that the vehicle scheduling and routing plan found by the approach proposed in this paper is more environmentally friendly and does not significantly increase total vehicle operational cost of the company.

关键词： Vehicle Routing Problem Airport Pickup Service Green Routes Tabu Search Algorithm Customer Satisfaction

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：