RETRACTED ARTICLE: Design and implementation of bank CRM system based on decision tree algorithm

Chen, Caixia; Geng, Lei; Zhou, Sheng

doi:10.1007/s00521-020-04959-8

Cited by 23 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The decision tree establishment process mainly includes the generation of initial decision trees and the pruning of decision trees. Because there are many kinds of attributes in data samples, it is necessary to use decision tree algorithm to analyze and calculate which attribute is selected as the initial root node and determine the topological structure between attributes 13 . Based on the improved decision tree algorithm, this paper studies the fault location of power system.…”

Section: Fault Diagnosis and Locationmentioning

confidence: 99%

Design of power system fault location and diagnosis system based on improved decision tree algorithm

2023

Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023)

View full text Add to dashboard Cite

The 10 kV distribution line in the power system has the characteristics of complex network structure and scattered load distribution. The frequency of faults in the line is relatively high, especially the single-phase ground fault, which accounts for more than 80% of the distribution network faults and has strong concealment. The most common and destructive fault in the power grid is the short-circuit fault of the transmission line. During the short-circuit, the instantaneous heat released by the arc and the enormous electric power generated by the short-circuit current can cause serious damage to the electrical equipment. In this regard, this article based on an improved decision tree algorithm to locate power system faults and designed a diagnostic system. The research results indicate that as the number of tested circuit boards increases, the prior probability of faults becomes closer to the actual distribution of faults, and the average diagnostic cost of faults is the lowest among the three algorithms. The average search length of the algorithm in this paper gradually decreases, and the downward jump of the curve indicates that the decision tree structure generated by the corresponding algorithm here has been adjusted. The power system fully and reasonably applies the temporal attributes of alarm information, effectively improving the problem of difficulty in re modeling when topology changes.

show abstract

Section: Fault Diagnosis and Locationmentioning

confidence: 99%

Design of power system fault location and diagnosis system based on improved decision tree algorithm

2023

Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023)

View full text Add to dashboard Cite

show abstract

“…Assuming that there are A 𝑝 is the probability of any record belonging to c i , which can be estimated by s i / s. The total entropy of the data set S is the weighted average of the information of different categories when dividing the data type [7]. Here, the data set S can be divided into a total of V subsets {S 1 , S 2 , ..., S v } using the A attribute, and the total entropy of the data set S is the weighted average of the entropy values of the V subsets.…”

Section: Figure 1 Commonly Used Data Mining Classification Algorithmsmentioning

confidence: 99%

Resource Integration Efficiency Analysis of Precision Instrument under Data Mining

Xia¹

2022

FBEM

View full text Add to dashboard Cite

This study aims to explore the factors that affect the integration efficiency of resources in the use of various precision instruments by enterprises. A strategy to improve the resource integration efficiency of enterprises is proposed. Firstly, the theory and integration technology of precision instruments are described. Decision tree technology in the field of data mining technology is introduced as a basis. The effectiveness of computers for resource integration work is explored. The influence of resource integration efficiency is discussed from five factors: government subsidy, fiscal taxation, commodity preference, enterprise market financing, and enterprise financial department planning. The financial department has the most significant impact, and most of the other four factors emphasize the capital utilization of enterprises and the motivation of employees. Therefore, it is proposed that the financial department of enterprises should be improved. Regarding the ability of market financing, it is emphasized that employee incentive strategies should be submitted to achieve the ultimate goal of improving the efficiency of resource integration, which provides a particular theoretical reference for the customization of enterprise resource data acquisition strategies.

show abstract

“…There are four levels of autism (mild, moderate, severe, and very severe). Although autism among children has rapidly spread in recent years, there is not enough research addressing the causes and effects of this disease [3]. In this paper, we studied and analyzed autism data among children affected in the Dohuk governorate using Machine Learning (ML) methods.…”

Section: Introductionmentioning

confidence: 99%

Analysis and Classification of Autism Data Using Machine Learning Algorithms

Hassan

Taher

2022

SJUOZ

View full text Add to dashboard Cite

Autism is a neurodevelopmental disorder that affects children worldwide between the ages of 2 and 8 years. Children with autism have communication and social difficulties, and the current standardized clinical diagnosis of autism still relies on behaviour-based tests. The rapidly growing number of autistic patients in the Kurdistan Region of Iraq necessitates. However, such data are scarce, making extensive evaluations of autism screening procedures more difficult. For this purpose, the use of machine learning algorithms for this disease to assist health practitioners if formal clinical diagnosis should be pursued was investigated. Data from 515 patients were collected in Dohuk city related to autism screening for young children. Three classification algorithms, namely (DT, KNN, and ANN) were applied to diagnose and predict autism using various rating scales. Before applying the above classifiers, the newly obtained data set was in different ways undergo data reprocessing. Since our data is unbalanced with high dimensionality, we suggest combining SMOTE (Synthetic Minority Hyper sampling Technique) and PCA (Primary Component Analysis) to improve the performance of classification models. Experimental results showed that the combination of PCA and SMOTE methods improved classification performance. Moreover, ANN exceeded the other models in terms of accuracy and F1 score, suggesting that these classification methods could be used to diagnose autism in the future.

show abstract

RETRACTED ARTICLE: Design and implementation of bank CRM system based on decision tree algorithm

Cited by 23 publications

References 13 publications

Design of power system fault location and diagnosis system based on improved decision tree algorithm

Design of power system fault location and diagnosis system based on improved decision tree algorithm

Resource Integration Efficiency Analysis of Precision Instrument under Data Mining

Analysis and Classification of Autism Data Using Machine Learning Algorithms

Contact Info

Product

Resources

About