scholarly journals PREDIKSI JUMLAH PENDERITA PENYAKIT TUBERKULOSIS DI KOTA BANDAR LAMPUNG MENGGUNAKAN METODE SVM (SUPPORT VECTOR MACHINE)

2020 ◽  
Vol 7 (3) ◽  
pp. 320
Author(s):  
Favorisen R. Lumbanraja ◽  
Ira Hariati Br Sitepu ◽  
Didik Kurniawan ◽  
Aristoteles Aristoteles
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Mycobacterium Tuberculosis ◽  
Gaussian Kernel ◽  
Weather Data ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Learning Support ◽  
Tuberculosis Patients ◽  
Long Time

<p><em>Tuberkulosis (TB atau TBC) merupakan salah satu penyakit infeksi yang disebabkan oleh Bakteri Mycobacterium tuberculosis. Bakteri tersebut merupakan bakteri yang sangat kuat sehingga dalam pengobatannya memerlukan waktu yang cukup lama. Pengobatan penyakit tuberkulosis dilakukan selama 6-9 bulan secara rutin dengan sedikitnya 3 macam jenis obat. Saat ini kebanyakan masyarakat menganggap batuk dalam jangka waktu berbulan-bulan merupakan batuk biasa, jika dicermati salah satu gejala yang ditimbulkan penyakit tuberkulosis, yaitu batuk dalam jangka waktu yang panjang. Pada penelitian ini digunakan data penderita tuberkulosis di Kota Bandar Lampung, data cuaca dan matrix jarak antara kejadian penderita tuberkulosis yang satu dengan kejadian yang lainnya dalam lingkup kecamatan. Jumlah dari keseluruhan data sebanyak 600 data dengan 44 variabel. Penelitian ini juga menggunakan 3 kernel yaitu, Linear, Gaussian, dan Polynomial dengan menggunakan Metode SVM dengan kernel Linear mendapatkan nilai rata-rata R<sup>2</sup> sebesar 51.43 %, pada percobaan dengan metode SVM dengan kernel Gaussian mendapatkan nilai rata-rata R<sup>2</sup> sebesar 58.53 % dan pada percobaan dengan metode SVM dengan kernel Polynomial mendapatkan nilai rata-rata R<sup>2</sup> sebesar 36.03 %.</em></p><p><strong><em>Kata Kunci</em></strong><em> : Prediksi penderita tuberculosis, tuberculosis, Machine Learning, Support Vector Machine.</em></p><p class="Abstrak"><em>Tuberculosis (TB / TBC) is one of infectious disease caused by Mycobacterium tuberculosis bacteria. These bacteria are very strong bacteria so for the treatment takes a long time. Tuberculosis treatment is carried out for 6-9 months regularly with at least 3 types of drugs. Currently, most of people consider a cough for months is a common cough, if looked by one of the symptoms caused by tuberculosis, which is a cough for a long time. In this research, data on tuberculosis patients in the city of Bandar Lampung were used, weather data and the distance matrix between the case of tuberculosis patients with other case within the district. The total number of data is 600 data with 44 variables. This research also uses 3 kernels</em><em> </em><em>namely, Linear, Gaussian, and Polynomial by using the SVM method with the Linear kernel getting an average R<sup>2</sup> value of 51.43%, in the experiment with the SVM method with a gaussian kernel getting an average R<sup>2</sup> value of 58.53% and at Experiments with the SVM method with the Polynomial kernel obtained an average value of R<sup>2</sup> of 36.03%</em><em> .</em></p><p class="Abstrak"><strong><em>Keywords</em></strong><em> : Prediction of tuberculosis sufferers, tuberculosis, Machine Learning, Support Vector Machine.</em></p>

scholarly journals Pancreatic Cancer Early Detection Using Twin Support Vector Machine Based on Kernel

Symmetry ◽  
2020 ◽  
Vol 12 (4) ◽  
pp. 667
Author(s):  
Wismaji Sadewo ◽  
Zuherman Rustam ◽  
Hamidah Hamidah ◽  
Alifah Roudhoh Chusmarsyah
Keyword(s):  
Machine Learning ◽  
Pancreatic Cancer ◽  
Support Vector Machine ◽  
Early Detection ◽  
Feature Space ◽  
Kernel Functions ◽  
Twin Support Vector Machine ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Rbf Kernel

Early detection of pancreatic cancer is difficult, and thus many cases of pancreatic cancer are diagnosed late. When pancreatic cancer is detected, the cancer is usually well developed. Machine learning is an approach that is part of artificial intelligence and can detect pancreatic cancer early. This paper proposes a machine learning approach with the twin support vector machine (TWSVM) method as a new approach to detecting pancreatic cancer early. TWSVM aims to find two symmetry planes such that each plane has a distance close to one data class and as far as possible from another data class. TWSVM is fast in building a model and has good generalizations. However, TWSVM requires kernel functions to operate in the feature space. The kernel functions commonly used are the linear kernel, polynomial kernel, and radial basis function (RBF) kernel. This paper uses the TWSVM method with these kernels and compares the best kernel for use by TWSVM to detect pancreatic cancer early. In this paper, the TWSVM model with each kernel is evaluated using a 10-fold cross validation. The results obtained are that TWSVM based on the kernel is able to detect pancreatic cancer with good performance. However, the best kernel obtained is the RBF kernel, which produces an accuracy of 98%, a sensitivity of 97%, a specificity of 100%, and a running time of around 1.3408 s.

scholarly journals ANALISIS KESEHATAN TERUMBU KARANG BERDASARKAN KARAKTERISTIK SUNGAI, LAUT, DAN POPULASI AREA PEMUKIMAN MENGGUNAKAN MACHINE LEARNING

2020 ◽  
Vol 5 (2) ◽  
Author(s):  
Adinda miftahul Ilmi Habiba ◽  
Agi Prasetiadi ◽  
Cepi Ramdani
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Nearest Neighbor ◽  
Ensemble Classifier ◽  
Support Vector ◽  
Learning Support ◽  
K Nearest Neighbor

Penelitian ini untuk mengetahui kualitas kesehatan terumbu karang disuatu wilayah di Indonesia dengan mengambil beberapa faktor seperti wisatawan yang datang, latitude, longtitude, suhu, tahun, populasi warga, jumlah pemuda, dan jumlah industri, dan metode yang digunakan adalah machine learning dengan algoritma K-Nearest Neighbor, Support Vector Machine, dan Ensemble Classifier, untuk ensemble menggunkan randomforest untuk mengambil cabang-cabang pohon atau fitur keputusan yang paling relevan dengan output, penelitian ini diharapkan bisa menjadi acuan bagi wilayah yang kondisi terumbu karangnya masih kurang baik dapat mencontoh wilayah yang kondisi terumbu karangnya sudah baik dengan melihat faktor apa saja yang mempengaruhi terumbu karang disuatu wilayah itu masuk kategori baik. Hasil akhir dari penelitian ini pada algoritma K-Nearest Neighbor faktor yang berpengaruh bagi kesehatan terumbu karang yaitu wisatawan yang datang, latitude, longtitude, suhu, tahum dan pupulasi warga, sementara pada algoritma Support Vector Machine faktor yang berpengaruh wisatawan yang datang, Latitude, suhu dan tahun untuk algoritma Ensemble Classifier faktor yang berpengaruh wisatawan yang datang, latitude, longtitude, suhu dan jumlah industry, Pada kasus ini algoritma Support Vector Machine memiliki kinerja lebih baik dibandingkan K-Nearest Neighbor dan Ensemble Classifier.Kata Kunci: Ekosistem, Ensemble Classifier, K-Nearest Neighbor, Machine Learning, Support Vector Machine 

scholarly journals Analisis Data Pada Jaringan Sensor Nirkabel Menggunakan Metode Support Vector Machine

2018 ◽  
Vol 1 (1) ◽  
pp. 8-15
Author(s):  
Caroline Layadi ◽  
Mohammad Fajar ◽  
Hasniati Hasniati ◽  
Izmy Alwiah Musdar
Keyword(s):  
Support Vector Machine ◽  
Wind Speed ◽  
Gaussian Kernel ◽  
Weather Data ◽  
Support Vector ◽  
Polynomial Evaluation ◽  
Evaluation Result ◽  
Average Accuracy ◽  
Result Show ◽  
Data Validity

The aims of this research are to implement Support Vector Machine for analyze abnormal data on sensor network and evaluate the implementation result. The data collection in the research were done through the searching of related libraries and software evaluate/testing. In this research, temperature, wind speed, and humidity tested using three kernels (linear, Gaussian, and polynomial). Evaluation result show that the implementation of Support Vector Machine can perform the best data validity analysis using Gaussian Kernel with the percentage of average accuracy, temperature 97.83%, humidity 94.5325%, and wind speed 96.93% for weather data 20-28 May and July 28-August 10, 2015. Meanwhile, for weather data June 5-6, 2017 obtained the percentage of average accuracy of temperature 92.855% and humidity 92.43%.

Detection of Breast Cancer Using Machine Learning Support Vector Machine Algorithm

2019 ◽  
Vol 16 (2) ◽  
pp. 441-444
Author(s):  
D. V. Soundari ◽  
R. Padmapriya ◽  
C. Thirumariselvi ◽  
N. Nanthini ◽  
K. Priyadharsini
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Support Vector ◽  
Learning Support ◽  
Support Vector Machine Algorithm ◽  
Breast Cancer Data ◽  
Data Set ◽  
Cancer Data ◽  
Hormone Imbalance

A woman majorly suffers due to breast cancer which is due to hormone imbalance. It leads to huge death in recent years. Early detection of the breast cancer is more important to prevent human lives. Image Processing plays an important to classify and detect the same. So this paper proposes machine learning based cancer classification using support vector machine with Wisconsin breast cancer data set.

scholarly journals Structure-sequence features based prediction of phosphosites of Serine/Threonine Protein Kinases of Mycobacterium tuberculosis

2021 ◽  
Author(s):  
Vipul Nilkanth ◽  
Shekhar Mande
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Mycobacterium Tuberculosis ◽  
Protein Kinases ◽  
Translational Regulation ◽  
Sequence Data ◽  
3D Structure ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Testing Dataset

Elucidation of signalling events in a pathogen is potentially important to tackle the infection caused by it. Such events mediated by protein phosphorylation play important roles in infection and therefore to predict the phosphosites and substrates of the serine/threonine protein kinases, we have developed a Machine learning based approach and predicted the phosphosites for Mycobacterium tuberculosis serine/threonine protein kinases using kinase-peptide structure-sequence data. This approach utilizes features derived from kinase 3D-structure environment and known phosphosite sequences to generate Support Vector Machine based kinase specific predictions of phosphosites making it suitable for prediction of phosphosites of STPKs with no or scarce data of their phosphosites. Support vector machine outperformed the four machine learning algorithms we tried (random forest, logistic regression, support vector machine and k-nearest neighbours) with aucROC value of 0.88 on the independent testing dataset and a ten-fold cross validation accuracy of ~81.6% for the final model. Our predicted phosphosites of M. tuberculosis STPKs form an useful resource for experimental biologists enabling elucidation of STPK mediated post-translational regulation of important cellular processes. The training features file and model files, together with usage instructions file, are available at: https://github.com/vipulbiocoder/Mtb-KSPP

scholarly journals Application of Machine Learning to a Medium Gaussian Support Vector Machine in the Diagnosis of Motor Bearing Faults

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2266
Author(s):  
Shih-Lin Lin
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Learning Algorithms ◽  
Kernel Functions ◽  
Fault Detection And Diagnosis ◽  
Machine Learning Algorithms ◽  
Gaussian Kernel ◽  
Support Vector ◽  
Data Set ◽  
Motor Bearing

In recent years, artificial intelligence technology has been widely used in fault prediction and health management (PHM). The machine learning algorithm is widely used in the condition monitoring of rotating machines, and normal and fault data can be obtained through the data acquisition and monitoring system. After analyzing the data and establishing a model, the system can automatically learn the features from the input data to predict the failure of the maintenance and diagnosis equipment, which is important for motor maintenance. This research proposes a medium Gaussian support vector machine (SVM) method for the application of machine learning and constructs a feature space by extracting the characteristics of the vibration signal collected on the spot based on experience. Different methods were used to cluster and classify features to classify motor health. The influence of different Gaussian kernel functions, such as fine, medium, and coarse, on the performance of the SVM algorithm was analyzed. The experimental data verify the performance of various models through the data set released by the Case Western Reserve University Motor Bearing Data Center. As the motor often has noise interference in the actual application environment, a simulated Gaussian white noise was added to the original vibration data in order to verify the performance of the research method in a noisy environment. The results summarize the classification results of related motor data sets derived recently from the use of motor fault detection and diagnosis using different machine learning algorithms. The results show that the medium Gaussian SVM method improves the reliability and accuracy of motor bearing fault estimation, detection, and identification under variable crack-size and load conditions. This paper also provides a detailed discussion of the predictive analytical capabilities of machine learning algorithms, which can be used as a reference for the future motor predictive maintenance analysis of electric vehicles.

scholarly journals Comparison Algorithm Kernels on Support Vector Machine (SVM) To Compare The Trend Curves with Curves Online Forex Trading

2017 ◽  
Vol 2 (2) ◽  
Author(s):  
Irfan Abbas
Keyword(s):  
Support Vector Machine ◽  
Data Exchange ◽  
Foreign Exchange Market ◽  
Gaussian Kernel ◽  
Risk Level ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Trading Systems ◽  
The Difference ◽  
The Right

At this time, the players Forex Trading generally still use the data exchange in the form of a Forex Trading figures from different sources. Thus they only receive or know the data rate of a Forex Trading prevailing at the time just so difficult to analyze or predict exchange rate movements future. Forex players usually use the indicators to enable them to analyze and memperdiksi future value. Indicator is a decision making tool. Trading forex is trading currency of a country, the other country's currency. Trading took place globally between the financial centers of the world with the involvement of the world's major banks as the major transaction. Trading Forex offers profitable investment type with a small capital and high profit, with relatively small capital can earn profits doubled. This is due to the forex trading systems exist leverage which the invested capital will be doubled if the predicted results of buy / sell is accurate, but Trading Forex having high risk level, but by knowing the right time to trade (buy or sell), the losses can be avoided. Traders who invest in the foreign exchange market is expected to have the ability to analyze the circumstances and situations in predicting the difference in currency exchange rates. Forex price movements that form the pattern (curve) up and down greatly assist traders in making decisions. The movement of the curve used as an indicator in the decision to purchase (buy) or sell (sell). This study compares (Comparation) type algorithm kernel on Support Vector Machine (SVM) to predict the movement of the curve in live time trading forex using the data GBPUSD, 1H. Results of research on the study of the results and discussion can be concluded that the Kernel Dot, Kernel Multiquaric, Kernel Neural inappropriately used for data is non-linear in the case of data forex to follow the pattern of trend curves, because curves generated curved linear (straight) and then to type of kernel is the closest curve similar to the curve trend of online forex trading is Anova kernel and kernel radial, a little closer Combination Gaussian kernel, kernel Epachnenikof and to kernel polynomial form a parabolic curve open. key words: Trading Forex, Support Vector Machine, Kernel Anova, Dot Kernel, Kernel Multiquaric, Kernel Neural, Prediction, radial Kernel, Kernel Gaussian Combination, Epachnenikof kernel, polynomial kernel, EURUSD H1

Using Kernel Fisher Criterion for Gaussian Kernel Optimization

2015 ◽  
Vol 734 ◽  
pp. 534-538
Author(s):  
Li Yun Zhong ◽  
Yu Ze Liu
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Evaluation Criterion ◽  
Gaussian Kernel ◽  
Support Vector ◽  
Optimization Approach ◽  
Fisher Criterion ◽  
Learning Methods ◽  
Gradient Based ◽  
Kernel Optimization

Empirical success of kernel-based learning methods is very much dependent on the kernel used. We propose an effective Gaussian kernel optimization approach for support vector machine (SVM). The key property of the proposed approach is that it adopts the kernel Fisher criterion (KFC) as the evaluation criterion to measure the goodness of the kernel used. After introducing a distance-based representation of KFC, we optimize the Gaussian kernel by using a gradient-based algorithm, which is based on the possibility of computing the gradient of KFC with respect to the width parameter of Gaussian kernel. The proposed approach is demonstrated with two popular UCI machine learning benchmark examples.

scholarly journals New Design Method of Solid Propellant Grain Using Machine Learning

Processes ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 910
Author(s):  
Seok-Hwan Oh ◽  
Hyoung Jin Lee ◽  
Tae-Seong Roh
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Solid Propellant ◽  
Support Vector Machine Model ◽  
Design Method ◽  
Burning Surface ◽  
Gaussian Kernel ◽  
Support Vector ◽  
Machine Model ◽  
Analysis Techniques

The correlation between solid propellant grain configuration and burning surface area profile is a complicated nonlinear problem. Nonlinear optimization has been adopted to design grain configurations that satisfied the objective area profiles. However, as conventional design methods are impractical, with limited performance, it is necessary to investigate alternatives. Useful information for grain design can be obtained by analyzing the aforementioned correlation. However, this aspect has not been studied owing to the requirement of large amounts of data and analysis techniques. In this study, machine learning was used to develop a new design method. The objective of machine learning was to train a model to classify classes of data. The database stores various sets of configuration variables and their classes. The proposed Gaussian kernel-based support vector machine model predicts the class of newly designed grains. The results verified that the model accurately predicted the class of the set of configuration variables and can be used to modify the set of configuration variables to satisfy the requirement. Thus, it was confirmed that machine learning is an appropriate approach to grain design; however, further research is needed to analyze its practicality.

Sign in / Sign up

Export Citation Format

Share Document