Using Data Mining Approaches for Force Prediction of a Dynamically Loaded Flexible Structure

2014 ◽  
Author(s):  
Meik Schlechtingen ◽  
Sofiane Achiche ◽  
Tiago Lourenco Costa ◽  
Maxime Raison ◽  
Ilmar Santos
Keyword(s):  
Data Mining ◽  
Research Work ◽  
Model Performance ◽  
Random Excitation ◽  
Force Transducer ◽  
Flexible Structure ◽  
Adaptive Models ◽  
Dynamically Loaded ◽  
Using Data ◽  
Selection Of

This paper presents the results obtained from a research work investigating the performance of different Adaptive models developed to predict excitation forces on a dynamically loaded flexible structure. For this purpose, a flexible structure is equipped with acceleration transducers at each degree of freedom and a force transducer for validation and training. The models are trained using data obtained from applying a random excitation force on the flexible structure. The performance of the developed models is evaluated by analyzing the prediction capabilities based on a normalized prediction error. The frequency domain is considered to analyze the similarity of the frequencies in the predicted and the original force signal. For a selection of the best models, a more advanced performance analysis is carried out. This includes application of the trained models to deterministic and non-deterministic excitation forces with different excitation frequencies and amplitudes. Additionally, the influence of the sampling frequency and sensor location on the model performance is investigated. The results obtained in this paper show that most data mining approaches can be used, when a certain degree of inaccuracy is accepted. Furthermore, the comparison study points out that the transducer location is crucial for the model performance. However, there exists no general solution for the final selection of models.

K-MEANS CLUSTERING ALGORITHM FOR SERVICE DATA ANALYSIS BASED ON CUSTOMERS COMBINATION

2018 ◽  
Vol 3 (1) ◽  
pp. 001
Author(s):  
Zulhendra Zulhendra ◽  
Gunadi Widi Nurcahyo ◽  
Julius Santony
Keyword(s):  
Data Mining ◽  
Data Analysis ◽  
Clustering Algorithm ◽  
Customer Complaints ◽  
Using Data ◽  
Clustering Data ◽  
Service Data ◽  
Selection Of

In this study using Data Mining, namely K-Means Clustering. Data Mining can be used in searching for a large enough data analysis that aims to enable Indocomputer to know and classify service data based on customer complaints using Weka Software. In this study using the algorithm K-Means Clustering to predict or classify complaints about hardware damage on Payakumbuh Indocomputer. And can find out the data of Laptop brands most do service on Indocomputer Payakumbuh as one of the recommendations to consumers for the selection of Laptops.

scholarly journals Using Data Mining with C4.5 Algorithm for Student Department Selection at MTs N Kaliangkrik

2021 ◽  
Vol 1 (1) ◽  
pp. 22-36
Author(s):  
Ardhin Primadewi
Keyword(s):  
Data Mining ◽  
Test Score ◽  
General Knowledge ◽  
General Intelligence ◽  
Test Results ◽  
Language Knowledge ◽  
C4.5 Algorithm ◽  
System Input ◽  
Using Data ◽  
Selection Of

Psychological tests can determine the characteristics of behavior, personality, attitudes, interests, motivation, attention, perceptions, thinking power, intelligence, fantasies of students. MTs N Kaliangkrik routinely conducts tests for the selection of majors on its students assisted by Pelita Harapan Bangsa Magelang. In the implementation of the test for students at MTs N Kaliangkrik, processing and calculating the score still used Ms. Excel which requires extra time to recap and know the test results and the school needs to recap the existing results. The system developed applies data mining using the C4.5 Algorithm to predict the selection of majors. The test that is used as system input is the grade IX test score of MTs N Kaliangkrik which includes verbal, non-verbal, general intelligence, language knowledge, definite knowledge, general knowledge, and qualitative power tests. The accuracy of the similarity in the system reaches 80% (good) so that the system is suitable for use as a prediction tool for selecting majors in other schools.

scholarly journals Analysis of acupoint selection and combinations in acupuncture treatment of asthma based on data mining

2021 ◽  
Author(s):  
Pan-Pan Shang ◽  
Cai-Tao Chen ◽  
Mi Cheng ◽  
Yang-Lin Shi ◽  
Yong-Qing Yang ◽  
...  
Keyword(s):  
Data Mining ◽  
Association Rule ◽  
Association Rule Mining ◽  
Acupuncture Treatment ◽  
Interconnection Network ◽  
Rule Mining ◽  
Bladder Meridian ◽  
Using Data ◽  
Conception Vessel ◽  
Selection Of

Objective: Using data mining, the present study aimed to discover the most effective acupoints and combinations in the acupuncture treatment of asthma. Methods: The main acupoints prescribed in these clinical trials was collected and quantified. A network analysis was performed to uncover the interconnections. Additionally, hierarchical clustering analysis and association rule mining were conducted to discover the potential acupoint combinations. Results: Feishu (BL13), Dingchuan (EX-B1), Dazhui (GV14), Shengshu (BL23), Pishu (BL20), and Fengmen (BL12) appeared to be the most frequently used acupoints for asthma. While the Bladder Meridian of Foot Taiyang, the Governor Vessel, and the Conception Vessel, compared to other meridians, were found to be the more commonly selected meridians. In the acupoint interconnection network, Feishu (BL13), Fengmen (BL12), Dingchuan (EX-B1), and Dazhui (GV14) were defined as key node acupoints. Association rule mining analysis demonstrated that the combination of Pishu, Shenshu, Feishu, and Dingchuan, as well as that of Feishu, Dazhui, and Fengmen were potential acupoint combinations that should be selected with priority in asthma treatment. Conclusion: This study provides valuable information regarding the selection of the most effective acupoints and combinations for clinical acupuncture practice and experimental study aimed at the prevention and treatment of asthma.

scholarly journals Employee Performance Prediction Using EPP Framework

2020 ◽  
pp. 297-302
Author(s):  
M. Karthika ◽  
T. Meyyappan
Keyword(s):  
Data Mining ◽  
Performance Prediction ◽  
Employee Performance ◽  
Research Work ◽  
Prediction Methods ◽  
Internal Factors ◽  
Using Data ◽  
Proper Solutions

In the today's industrial world, every company’s growth is depends on their employees. The company achievements are completely based on the employees in the organization. The employees’ performances are measured by the targets and achievements. But some external and internal factors affect the employees’ goals and achievements. Hence, the company has to find the performance of every employee and make proper solutions to improve the performance. This research work proposes a fully automated framework which can perform deep analysis of employees’ performance and job fitness using data mining and prediction methods.

scholarly journals Penerapan Teknik Clustering Data Mining untuk Memprediksi Kesesuaian Jurusan Siswa (Studi Kasus SMA PGRI 1 Subang)

Faktor Exacta ◽  
2020 ◽  
Vol 13 (2) ◽  
pp. 125
Author(s):  
Tubagus Riko Rivanthio ◽  
Mardhiya Ramdhani
Keyword(s):  
Data Mining ◽  
Data Processing ◽  
Private School ◽  
Similar Data ◽  
Clustering Techniques ◽  
Academic Achievements ◽  
Processing Data ◽  
Using Data ◽  
Clustering Data ◽  
Selection Of

<p>SMA PGRI 1 Subang is a private school that has several missions, one of which is the establishment of academic and non-academic achievements. In an effort to achieve the mission must supervise student achievement. The effort he did was to provide understanding in the selection of majors in accordance with the interests and talents of students. But in the activity of providing understanding, the school does not yet have a model that can evaluate the interests and talents of students to choose majors. The model can be obtained using student data processing. Data processing can be done using data mining, namely data mining clustering techniques. The technique will produce a model in the selection of majors. This clustering process is the process of grouping similar data based on the similarity of data held by students. The research method used is the CRISP-DM method which has 6 stages consisting of: Business Understanding, Data Understanding, Data Processing, Modeling, Evaluation, and Dissemination. The data that is processed is 620 data consisting of class of students in 2014, 2015, 2016. The results of processing using clustering obtained 6 clusters that have different models for each cluster. The results of this study can be used by schools in recommending courses chosen by students according to students' interests and talents, so students can learn optimally.</p><strong><em>Key words</em></strong>: clustering, dataMining, suitability, majors, students

scholarly journals Disease Prediction and Drug Recommendation Android Application using Data Mining (Virtual Doctor)

2019 ◽  
Vol 8 (3) ◽  
pp. 6996-7001
Keyword(s):  
Data Mining ◽  
Research Work ◽  
Application Programming Interface ◽  
Machine Learning Algorithms ◽  
Useful Knowledge ◽  
Medical Databases ◽  
Application Programming ◽  
Mining Procedure ◽  
Using Data ◽  
Programming Interface

Data Mining is a method that requires analyzing and exploring large blocks of data to glean meaningful trends and patterns. In today’s period, every person on earth relies on allopathic treatments and medicines. Data mining techniques can be applied to medical databases that have a vast scope of opportunity for textual as well as visual data. In medical services, there are myriad obscure data that needs to be scrutinized and data mining is the key to gain useful knowledge from these data. This paper provides an application programming interface to recommend drugs to users suffering from a particular disease which would also be diagnosed by the framework through analyzing the user's symptoms by the means of machine learning algorithms. We utilize some insightful information here related to mining procedure to figure out most precise sickness that can be related with symptoms. The patient can without much of a stretch recognize the diseases. The patients can undoubtedly recognize the disease by simply ascribing their issues and the application interface produces what malady the user might be tainted with. The framework will demonstrate complaisant in critical situations where the patient can't achieve a doctor's facility or when there are situations, when professional are accessible in the territory. Predictive analysis would be performed on the disease that would result in recommending drugs to the user by taking into account various features in the database. The experimental results can also be used in further research work and for Healthcare tools.

Sign in / Sign up

Export Citation Format

Share Document