检索结果-内蒙古大学图书馆

Genome-wide sequence-based prediction of peripheral proteins using a novel semi-supervised learning technique

BMC BIOINFORMATICS 2010年第Sup1期11卷 S6-S6页

作者： Bhardwaj, Nitin Gerstein, Mark Lu, Hui Univ Illinois Bioinformat Program Dept Bioengn Chicago IL 60607 USA Yale Univ Program Computat Biol & Bioinformat New Haven CT 06520 USA Yale Univ Dept Mol Biophys & Biochem New Haven CT 06520 USA Yale Univ Dept Comp Sci New Haven CT 06520 USA

Background: In supervised learning, traditional approaches to building a classifier use two sets of examples with pre-defined classes along with a learning algorithm. The main limitation of this approach is that examples from both classes are required which might be infeasible in certain cases, especially those dealing with biological data. Such is the case for membrane-binding peripheral domains that play important roles in many biological processes, including cell signaling and membrane trafficking by reversibly binding to membranes. For these domains, a well-defined positive set is available with domains known to bind membrane along with a large unlabeled set of domains whose membrane binding affinities have not been measured. The aforementioned limitation can be addressed by a special class of semi-supervised machine learning called positive-unlabeled (PU) learning that uses a positive set with a large unlabeled set. Methods: In this study, we implement the first application of PU-learning to a protein function prediction problem: identification of peripheral domains. PU-learning starts by identifying reliable negative (RN) examples iteratively from the unlabeled set until convergence and builds a classifier using the positive and the final RN set. A data set of 232 positive cases and similar to 3750 unlabeled ones were used to construct and validate the protocol. Results: Holdout evaluation of the protocol on a left-out positive set showed that the accuracy of prediction reached up to 95% during two independent implementations. Conclusion: These results suggest that our protocol can be used for predicting membrane-binding properties of a wide variety of modular domains. Protocols like the one presented here become particularly useful in the case of availability of information from one class only.

关键词： decision tree algorithm Peripheral Protein Modular Domain Bioinformatics Problem Peripheral Domain

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a decision support system for college student management based on the 5G communication system

引用

SOFT COMPUTING 2023年

作者： Liu, Zhe Zhang, Xuejuan Hao, Xingchang Qiqihar Univ Dept Student Affairs Management Qiqihar 161006 Heilongjiang Peoples R China Heilongjiang Univ Inst Educ Sci Harbin 150080 Heilongjiang Peoples R China Harbin Normal Univ Sch Educ Sci Harbin 150025 Heilongjiang Peoples R China

With the rapid development of science and technology, people have entered the information intelligence society. Multimedia technologies such as mobile terminal equipment are getting smarter and faster, and the upgrade speed is getting faster and faster. Previously, college students' management decision-making was mostly manual, which made management decision-making inconvenient. Therefore, a health management decision support system based on the 5G communication system is proposed. This paper intends to investigate the development of a 5G communication-based decision-support system for college student management. This study suggests a decision tree algorithm based on data mining and an edge decision algorithm based on the 5G communication infrastructure. According to the experimental findings of this study, 35.6% of colleges and universities in the nation have finished building intra-campus LANs in 2015, with a 38% work efficiency and a 65% convenience rate. Nearly all schools and universities will have entered the information age by 2019, when 89.3% of colleges and universities countrywide will have finished building intra-campus LANs. Additionally, this makes it much simpler to oversee and decide on students, and it is frequently convenient. It can be seen that the arrival of the 5G communication system has also had a huge impact on major universities. It makes it much easier for students to manage decision-making tasks. Therefore, it is necessary to design a decision support system for college student management based on the 5G communication system.

关键词： 5G communication system decision support systems Data mining decision tree algorithm

来源：评论

学校读者我要写书评

暂无评论

Modeling and Analysis of Psychological Change and Adaptability of College Students Based on Machine Learning as an Infrastructure to a Smart City

引用

JOURNAL OF TESTING AND EVALUATION 2023年第3期51卷 1650-1660页

作者： Wang, Jing Zhejiang Int Maritime Coll Acad Work Dept 268 Haitian Rd Zhoushan 316021 Peoples R China Zhejiang Int Maritime Coll Students Affairs Div 268 Haitian Rd Zhoushan 316021 Peoples R China

In order to improve the mental health education of college students, reduce the intermediate links, and improve work efficiency, this paper analyzes the psychological change characteristics and adaptability of college students based on machine learning. We should introduce speech recognition technology, carry out natural language processing, vectorize the speech text, construct the semantic perception model of college students' mental health states, and track the sensitive words similar to the evaluation standard of college students' mental health states;we should introduce multifeature fusion technology through measuring the description ability of different features, learn the complementary state of different sensitive words of different features, and perceive the psychological change characteristics of college students and serialize them;we should, based on the decision tree algorithm in machine learning, construct the analysis model of psychological adaptability of college students, analyze the sensitive words and the frequency and level of sensitive words in the process of college students' mental health conversations, determine their adaptability, and complete the modeling and analysis of psychological change characteristics and adaptability of college students based on machine learning. The experimental results show that the method has no change to the original dependency relation, the time cost of feature acquisition is still small, and the sensing effect of sensitive words is close to the ideal value.

关键词： machine learning decision tree algorithm mental health of college students adaptability

来源：评论

学校读者我要写书评

暂无评论

Application of gradient boosting regression model for the evaluation of feature selection techniques in improving reservoir characterisation predictions

引用

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING 2022年第PartE期208卷 109244-109244页

作者： Otchere, Daniel Asante Ganat, Tarek Omar Arbi Ojero, Jude Oghenerurie Tackie-Otoo, Bennet Nii Taki, Mohamed Yassir Univ Teknol PETRONAS Dept Petr Engn Seri Iskandar 32610 Perak Darul Rid Malaysia Univ Teknol PETRONAS Ctr Res Enhanced Oil Recovery Seri Iskandar 32610 Perak Darul Rid Malaysia Univ Manchester Sch Earth & Environm Sci Oxford Rd Manchester M13 9PL Lancs England Natl Off Hydrocarbons & Mines Dept Explorat 5 Ave Moulay Rachid Rabat Morocco

Feature Selection, a critical data preprocessing step in machine learning, is an effective way in removing irrelevant variables, thus reducing the dimensionality of input features. Removing uninformative or, even worse, misinformative input columns helps train a machine learning model on a more generalised data with better performances on new and unseen data. In this paper, eight feature selection techniques paired with the gradient boosting regressor model were evaluated based on the statistical comparison of their prediction errors and computational efficiency in characterising a shallow marine reservoir. Analysis of the results shows that the best technique in selecting relevant logs for permeability, porosity and water saturation prediction was the Random Forest, SelectKBest and Lasso regularisation methods, respectively. These techniques did not only reduce the features of the high dimensional dataset but also achieved low prediction errors based on MAE and RMSE and improved computational efficiency. This indicates that the Random Forest, SelectKBest, and Lasso regularisation can identify the best input features for permeability, porosity and water saturation predictions, respectively.

关键词： Feature selection techniques Dimensionality reduction techniques Reservoir characterisation Ensemble machine learning decision tree algorithm

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Assisted Prediction for Free-Space Continuous Variable Quantum Teleportation

IEEE PHOTONICS JOURNAL

引用

IEEE PHOTONICS JOURNAL 2022年第4期14卷 1页

作者： Xu, Jiaye Mao, Yun Chen, Yuxin Xu, Xiaowen Guo, Ying Cent South Univ Sch Phys & Elect Changsha 410083 Peoples R China Cent South Univ Sch Automat Changsha 410083 Peoples R China

Satellite-based quantum communication is critical in establishing a global quantum network for its ability to achieve thousand-kilometer-level tasks without the requirement of quantum relay. The free-space channel, however, is affected by diffraction, regular refraction, and atmospheric turbulence, which induce random wandering and broadening of the transmitted beam, resulting in the transmittance of fluctuation. In such a scenario, the ability to predict the unknown situation has become a problem worth considering. In this paper, we suggest a machine learning (ML) assisted prediction of continuous-variable quantum teleportation (CVQT) over satellite-ground channel. We apply the prediction algorithm, which involves k-nearest neighbor (KNN) algorithm and decision tree (DT) algorithm, to the squeezing parameter and the satellite altitude. Numerical analysis shows that the predicted parameter can reflect the actual derivation and calculation under certain circumstances within the allowable range of error. Moreover, we apply the prediction algorithm to the case affected by the fluctuating parameter transmittance. The results show that the ML-assisted prediction results are consistent with the actual data when zenith angles, turbulence strengths, and wavelengths are taken into account. It demonstrates the high identifying accuracy without increasing the complexity of the system.

关键词： Continuous variable quantum teleportation machine learning K-nearest neighbor algorithm decision tree algorithm

来源：评论

学校读者我要写书评

暂无评论

A neuro-fuzzy network modeling method for uncovering the dynamic properties of time-varying systems

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2023年第1期191卷

作者： Liu, Zuolin Fang, Hongbin Xu, Jian Fudan Univ Inst AI & Robot Shanghai 200433 Peoples R China Tongji Univ Sch Aerosp Engn & Appl Mech Shanghai 200092 Peoples R China Fudan Univ MOE Engn Res Ctr AI & Robot Shanghai 200433 Peoples R China Fudan Univ Shanghai Engn Res Ctr AI & Robot Shanghai 200433 Peoples R China

Nonstationary signals are commonly encountered in various fields and applications. Modeling nonstationary signals with time-varying systems is of vital importance in understanding the un-derlying information and revealing the dynamic properties. In this paper, a neuro-fuzzy network -based method is proposed for the time-varying autoregressive (TVAR) system with multiple de-grees of freedom. By expressing the time-varying parameters as a set of local linear models and validity functions, the TVAR system is transformed into an equivalent neural fuzzy network. The model structure and the time-varying parameters of the TVAR system correspond to the archi-tecture and the weights of the equivalent neural network, respectively, and can be determined by training the equivalent neural network. Fundamentally, the new architecture is generated via growing and pruning the tree branches/neurons in a decision tree algorithm. Followed by a weights training process with Least Square optimization, the neural networks are finally evalu-ated with the target nonstationary signals. The optimal architecture and weights lie in the one with the least disparity. Several nonstationary signals, including the electroencephalogram and the radar wave that are qualitatively different in the time-frequency characteristics, are utilized to verify the effectiveness of the proposed method. Furthermore, we show that the proposed method is applicable not only to time-varying systems with complete measurements but also to incomplete measurable cases. Applying this method to the vibration signals output from a time -varying origami-tube structure under external excitations, the high time-frequency resolution of the proposed method is demonstrated via the time-frequency spectrum, from which the inherent mechanical properties and the underlying dynamic characteristics of the time-varying origami -tube structure are revealed.

关键词： Time -varying system identification decision tree algorithm Time frequency analysis Nonstationary signals Origami structure

来源：评论

学校读者我要写书评

暂无评论

Investigation of Mass Transfer with Different Models in a Solar Energy Food-Drying System

引用

ENERGIES 2019年第18期12卷 3447-3447页

作者： Demirpolat, Ahmet Beyzade Support Serv Dept TR-23200 Elazig Turkey

In drying systems, the examination of the drying rate values of the food product in advance gives important information about the raw material to be dried. In this study, thin-layer drying behavior of apple slices in a convective solar dryer was investigated. The experiments were carried out at a drying air temperature of 46-63 degrees C and a drying air speed of 0.7-1.8 m/s. In order to determine the drying kinetics, the mass change of apple slices was recorded under all drying air conditions. The effects of drying air temperature and speed, drying speed of apple slices, dimensionless moisture content, were investigated. In a solar drying system, thermal efficiency, solar radiation and air velocity values were measured. The drying kinetics of 15-mm thick apple slices were examined for three days in the solar drying system. Using the decision tree algorithm, which is a machine learning algorithm, a predictive model was created for moisture rate in drying experiments and four linear equations were obtained. According to obtained equations, the collector in the drying system depends on the inlet-outlet temperature values, the drying room inlet-outlet temperature values, the drying room humidity values and air velocity values. Moisture rate data were applied to twelve different models and their performance was determined by root mean square error (RMSE) analysis. The mathematical model with the least error rate was (RMSE: 0.09) Midilli model. A comparison was made between these drying models in the literature and the model generated by the decision tree algorithm. According to the results of RMSE error analysis, it was shown that the model created with the decision tree algorithm predicted the moisture rate values with less error values RMSE: 0.03) than the Midilli model.

关键词： solar energy mass transfer moisture rate decision tree algorithm

来源：评论

学校读者我要写书评

暂无评论

Design and Optimization of Personalized Education System Based on Intelligent algorithms

引用

Procedia Computer Science 2024年 243卷 514-522页

作者： Jie Zhu Yahong Liao Danni Lu Wuhan Railway Vocational College of Technology Wuhan 430205 Hubei China Xiamen Jin Shang Middle School Xiamen 361000 Fujian China Hubei Vocational College of Railway Transportation Wuhan 430070 Hubei China

The education industry, as the top priority of social operation, is constantly emerging with education systems or online education platforms based on internet technology. However, most of them are facing problems of rigidity, stiff, or resource scarcity. Therefore, this article aimed to establish a personalized education system to solve this problem and optimize the system based on intelligent algorithms. At the end of this article, a comparison was made on the algorithm performance of the decision tree algorithm in the intelligent algorithm. Compared with the original algorithm of the system, the accuracy increased from 70.35% to 75.68%. The system based on the intelligent algorithm also helped the students in the experimental class improve their grades, and even cleared the score record below 40 points, helping to improve the overall performance of the entire class.

关键词： Intelligent algorithm decision tree algorithm Personalized Education System Particle Swarm Optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Psychological Counseling and Treatment Path of Painting based on Mobile Internet Technology

International Journal of Social Science and Education Resear...

引用

International Journal of Social Science and Education Research 2021年第3期4卷 116-126页

作者： Wan Min

Psychological counseling has been highly valued by all walks of life, and the way of psychological consultation has a significant impact on the effect of psychotherapy. The psychological consultation between the Internet and reality has become important in the face of psychological counseling with the deepening of the research on the Internet plus mental health. This study was performed with the following aims: (1) examine the development of psychological counseling under the Internet environment, especially based on the current situation of psychological counseling in colleges and universities; (2) explore the painting psychological test and analysis method, its implementation path, and the classification and evaluation method of painting image based on decision tree algorithm; (3) design the ＂painting heart sound＂ painting psychological software system based on mobile Internet and software engineering technology; and put the ＂painting heart＂ painting psychology software system into *** sound painting psychological software system was applied in four cases. The practice results showed that the Internet plus psychological counseling had a great advantage in painting therapy, which was an effective way to do psychological counseling in colleges and universities, implement the ＂10 major educating people＂ system, and maintain the mental health of college students. The findings might help enrich psychological counseling channels and improve psychological consultation results.

关键词： decision tree algorithm Drawing voice software system Mobile Internet Painting psychological test Psychological consultation

来源：评论

学校读者我要写书评

暂无评论

Fault Detection, Classification and Localization Along the Power Grid Line Using Optimized Machine Learning algorithms

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2024年第1期17卷 49-49页

作者： Najafzadeh, Masoud Pouladi, Jaber Daghigh, Ali Beiza, Jamal Abedinzade, Taher Islamic Azad Univ Dept Elect Engn Shabestar Branch Shabestar Iran

Distributed energy generation increases the need for smart grid monitoring, protection, and control. Localization, classification, and fault detection are essential for addressing any problems immediately and resuming the smart grid as soon as possible. Simultaneously, the capacity to swiftly identify smart grid issues utilizing sensor data and easily accessible frequency and voltage data from PMU devices is a prerequisite of this task. Therefore, this paper proposes new methods using fuzzy logic and adaptive fuzzy neural networks as well as machine learning and meta-heuristic algorithms. First, line voltage is used by a fuzzy thresholding method to estimate when a transmission line defect would develop in less than 1.2 clock cycles. Next, features taken from frequency signals in the real-time interval are utilized to classify the type of error using machine learning systems (decision tree algorithm and random forest algorithm) optimized with wild horse meta-heuristic algorithm. To locate the precise problem location, we finally use a neural fuzzy inference system that is capable of adapting to new data. We employ a simulated power transmission system in MATLAB to test our proposed solutions. Mean square error (MSE) and confusion matrix are used to assess the efficiency of a classifier or detector. For the decision tree algorithm method, the detector attained an acceptable MSE of 2.34e-4 and accuracy of 98.1%, and for the random forest algorithm method, an acceptable MSE of 3.54e-6 and accuracy of 100%. Furthermore, the placement error was less than 153.6 m in any direction along the line.

关键词： Fault detection and classification Smart network Fault localization Wild horse optimization algorithm Fuzzy neural inference system decision tree algorithm Random forest algorithm

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：