Data mining
Tobias Wagner; Alexander Gepperth; Elmar Engels
Abstract
This study proposes a framework for the automated hyperparameter optimization of a bearing fault detection pipeline for Permanent Magnet Synchronous Motors (PMSMs) without the need for external sensors. An Automated Machine Learning (AutoML) pipeline search is performed through genetic optimization to ...
Read More
This study proposes a framework for the automated hyperparameter optimization of a bearing fault detection pipeline for Permanent Magnet Synchronous Motors (PMSMs) without the need for external sensors. An Automated Machine Learning (AutoML) pipeline search is performed through genetic optimization to reduce human-induced bias due to inappropriate parameterizations. A search space is defined, which includes general methods of signal processing and manipulation as well as methods tailored to the respective task and domain. The proposed framework is evaluated on the bearing fault detection use case under real-world conditions. Considerations on the generalization of the deployed fault detection pipelines are also considered. Likewise, attention was paid to experimental studies for evaluations of the robustness of the fault detection pipeline to variations of the motors working condition parameters between the training and test domain.
Data mining
Amir Daneshvar; Fariba Salahi; Maryam Ebrahimi; Bijan Nahavandi
Abstract
The aim of analyzing passengers' behavioral patterns is providing support for transportation management. In other words, to improve services like scheduling, evacuation policies, and marketing, it is essential to understand spatial and temporal patterns of passengers' trips. Smart Card Automated Fare ...
Read More
The aim of analyzing passengers' behavioral patterns is providing support for transportation management. In other words, to improve services like scheduling, evacuation policies, and marketing, it is essential to understand spatial and temporal patterns of passengers' trips. Smart Card Automated Fare Collection System (SCAFCS) makes it possible to utilize data mining tools for the purpose of passengers' behavioral pattern analysis. The specific goal of this research is to obtain functional information for passenger's behavioral pattern analysis in city express bus which is called BRT, and classification of passengers to improve performance of bus fast transportation system. Additionally, it is attempted to predict usage and traffic status in a line through predicting passenger's behavior in a bus line. In this paper, smart card data is applied to provide combinational algorithms for clustering and analysis based on data mining. To this end, we have used a combination of data mining methods and particle swarm optimisation algorithm and leveraged multivariate time series prediction to estimate behavioral patterns. Results show that price and compression ratio features are the most influencing features in the separability of transportation smart card data. According to obtained Pareto front, four features include a card identification number, bus identification number, bus line number, and charge times are influencing clustering criteria.
Data mining
Ramez Kian; Hadeel S Obaid
Abstract
Human life today is intertwined with abundant trade and economic exchanges, and life would not be possible without trade and commerce. One of the main pillars of financial exchanges are banks and financial and credit institutions, which, as the vital arteries of the economy, are responsible for transferring ...
Read More
Human life today is intertwined with abundant trade and economic exchanges, and life would not be possible without trade and commerce. One of the main pillars of financial exchanges are banks and financial and credit institutions, which, as the vital arteries of the economy, are responsible for transferring funds and keeping the economy alive. In the world of economic competition between organizations, profitability and proper performance for stakeholders are the basic principles of the organization's survival. To increase profitability, banks must take measures that, in addition to reducing costs, increase the level of service and customer satisfaction. The best way to do this is to use new technologies and orient the bank's policies to provide services in person and independent of time and place. The use of new technologies in the banking system sometimes leads to customers' distrust and distrust of the bank. Therefore, solutions to detect fraud in banking transactions should be provided. This article aims to discover a model for face-to-face transactions and to establish a system to block fraudulently issued transactions. Therefore, a big data clustering method is designed to timely identify bribery in banking transactions. The results show that using the big data clustering method in the fastest time can detect and stop possible fraud in customers' banking transactions.
Data mining
Mohammad Amin Rahbar
Abstract
One of the most important issues in financial, economic, and accounting matters is the phenomenon of bankruptcy and its prediction. There is presented a hybrid method of Genetic Algorithm (GA) and Adaptive Neural-Fuzzy Network (ANFIS) model to evaluate predicting the bankruptcy of companies listed on ...
Read More
One of the most important issues in financial, economic, and accounting matters is the phenomenon of bankruptcy and its prediction. There is presented a hybrid method of Genetic Algorithm (GA) and Adaptive Neural-Fuzzy Network (ANFIS) model to evaluate predicting the bankruptcy of companies listed on the Tehran Stock Exchange. The statistical population of this research is the successful and bankrupt manufacturing companies in Tehran Stock Exchange and in this research, there is a different way as opposed to previous and purposeful research and all companies can prevent their possible bankruptcy with accurate forecasting. In this way, the statistical population includes 136 companies consisting of bankrupt and non-bankrupt companies. In order to construct prediction models, four variables were first selected: 1) independent sample t-test, 2) Correlation Matrix (CM), 3) Step-by-step Diagnostic Analysis (SDA), and 4) Principal Component Analysis (PCA). The final financial ratios were selected from 19 financial ratios that using selected financial ratios and a hybrid model of ANFIS and GA and the results of the proposed model and its comparison with the hybrid model of GA and Group Method of Data Handling (GMDH) shows the high capability of the proposed GA-ANFIS model in bankruptcy prediction modeling and its superiority over Group Method of Data Handling with GA-GMDH method. The results also show that the CM-GA-ANFIS model is known as the best model for predicting bankruptcy of companies listed on the Tehran Stock Exchange. The main reason for choosing the model (GA-ANFIS) is that in addition to the fact that for the first time a combination of two methods ANFIS and GA is used to predict the bankruptcy of companies, and also in none of the studies conducted in both areas which further highlights the need for the present study.
Data mining
Aboosaleh Mohammad Sharifi; Kaveh Khalili Damghani; Farshid Abdi; Soheila Sardar
Abstract
Cryptocurrencies are considered as new financial and economic tools having special and innovative features, among which Bitcoin is the most popular. The contribution of the Bitcoin market continues to grow due to the special nature of Bitcoin. The investors' attention to Bitcoin has increased significantly ...
Read More
Cryptocurrencies are considered as new financial and economic tools having special and innovative features, among which Bitcoin is the most popular. The contribution of the Bitcoin market continues to grow due to the special nature of Bitcoin. The investors' attention to Bitcoin has increased significantly in recent years due to significant growth in its prices. It is important to create a prediction system which works well for investment management and business strategies due to the high chaos and volatility of Bitcoin prices. In this study, in order to improve predictive accuracy, Bitcoin price dataset is first divided into a time interval through time window, then propose a new model based on Long Short-Term Memory (LSTM) neural networks and Metaheuristic algorithms. Chaotic Dolphin Swarm Optimization algorithm is used to optimize the LSTM. Performance evaluation indicated that the proposed model can have more effective predictions and improve prediction accuracy. In addition, the performance of the optimized model is better and more reliable than other models.
Data mining
Fatemeh Mirsaeedi; Iman Sadeghi; Mohammad Ghodoosi
Abstract
This study aims to identify and employ qualified individuals and assign different organizational positions. Accordingly, a data mining approach is proposed. This paper presents an empirical study which has important practical application in modern human resource management. Therefore, effective features ...
Read More
This study aims to identify and employ qualified individuals and assign different organizational positions. Accordingly, a data mining approach is proposed. This paper presents an empirical study which has important practical application in modern human resource management. Therefore, effective features on staff selection are extracted from literature and entered into the database after expert approval respectively. Further, the impact of each feature on staff selection is determined and the ability of applied classification algorithms is compared. The results represent that the organizational position feature has a great impact on forecasting of selection or rejection. Data mining algorithms used in this study have acceptable performance based on accuracy rate, and J48 algorithm performs better comparing to other algorithms based on accuracy rate, recall, F-measure and area under Receiver Operating Characteristic (ROC) curve. Three features of background, level of education, and major are identified as effective features in association rules. Finally, an approach is presented for applying data mining algorithms in employees hiring and organizational positions assignment procedure
