scholarly journals Kombinasi Synthetic Minority Oversampling Technique (SMOTE) dan Neural Network Backpropagation untuk menangani data tidak seimbang pada prediksi pemakaian alat kontrasepsi implan

2019 ◽  
Vol 5 (2) ◽  
pp. 128
Author(s):  
Mustaqim Mustaqim ◽  
Budi Warsito ◽  
Bayu Surarso

Combination of Synthetic Minority Oversampling Technique (SMOTE) and Backpropagation Neural Network to handle imbalanced class in predicting the use of contraceptive implants  Kegagalan akibat pemakaian alat kontrasepsi implan merupakan terjadinya kehamilan pada wanita saat menggunakan alat kontrasepsi secara benar. Kegagalan pemakaian kontrasepsi implan tahun 2018 secara nasional sejumlah 1.852 pengguna atau 4% dari 41.947 pengguna. Rasio angka kegagalan dan keberhasilan pemakaian kontrasepsi implan yang cenderung tidak seimbang (imbalance class) membuatnya sulit diprediksi. Ketidakseimbangan data terjadi jika jumlah data suatu kelas lebih banyak dari data lain. Kelas mayor merupakan jumlah data yang lebih banyak, sedangkan kelas minor jumlahnya lebih sedikit. Algoritma klasifikasi akan mengalami penurunan performa jika menghadapi kelas yang tidak seimbang. Synthetic Minority Oversampling Technique (SMOTE) digunakan untuk menyeimbangkan data kegagalan pemakaian kontrasepsi implan. SMOTE menghasilkan akurasi yang baik dan efektif daripada metode oversampling lainnya dalam menangani imbalance class karena mengurangi overfitting. Data yang sudah seimbang kemudian diprediksi dengan Neural Network Backpropagation. Sistem prediksi ini digunakan untuk mendeteksi apakah seorang wanita mengalami kehamilan atau tidak jika menggunakan kontrasepsi implan. Penelitian ini menggunakan 300 data, terdiri dari 285 data mayor (tidak hamil) dan 15 data minor (hamil). Dari 300 data dibagi menjadi dua bagian, 270 data latih dan 30 data uji. Dari 270 data latih, terdapat 13 data latih minor dan 257 data latih mayor. Data latih minor pada data latih diduplikasi sebanyak data pada kelas mayor sehingga jumlah data latih menjadi 514, terdiri dari 257 data mayor, 13 data minor asli, dan 244 data minor buatan. Sistem prediksi menghasilkan nilai akurasi sebesar 96,1% pada epoch ke-500 dan 1.000. Implementasi kombinasi SMOTE dan Neural Network Backpropagation terbukti mampu memprediksi pada imbalance class dengan hasil prediksi yang baik.  The failed contraceptive implant is one of the sources of unintended pregnancy in women. The number of users experiencing contraceptive-implant failure in 2018 was 1,852 nationally or 4% out of 41,947 users. The ratio between failure and success rates of contraceptive implant, which tended to be unbalanced (imbalance class), made it difficult to predict. Imbalance class will occur if the amount of data in one class is bigger than that in other classes. Major classes represent a bigger amount of data, while minor classes are smaller ones. The imbalance class will decrease the performance of the classification algorithm. The Synthetic Minority Oversampling Technique (SMOTE) was used to balance the data of the contraceptive implant failures. SMOTE resulted in better and more effective accuracy than other oversampling methods in handling the imbalance class because it reduced overfitting. The balanced data were then predicted using backpropagation neural networks. The prediction system was used to detect if a woman using a contraceptive implant was pregnant or not. This study used 300 data, consisting of 285 major data (not pregnant) and 15 minor data (pregnant). Of 300 data, two groups of data were formed: 270 training data and 30 testing data. Of 270 training data, 13 were minor training data and 257 were major training data. The minor training data in the training data were duplicated as much as the number of data in major classes so that the total training data became 514, consisting of 257 major data, 13 original minor data, and 244 artificial minor data. The prediction system resulted in an accuracy of 96.1% on the 500th and 1,000th epochs. The combination of SMOTE and Backpropagation Neural Network was proven to be able to make a good prediction result in imbalance class.

2020 ◽  
Vol 13 (1) ◽  
pp. 36-46
Author(s):  
Mustaqim Mustaqim ◽  
Budi Warsito ◽  
Bayu Surarso

Data imbalance occurs when the amount of data in a class is more than other data. The majority class is more data, while the minority class is fewer. Imbalance class will decrease the performance of the classification algorithm. Data on IUD contraceptive use is imbalanced data. National IUD failure in 2018 was 959 or 3.5% from 27.400 users. Synthetic minority oversampling technique (SMOTE) is used to balance data on IUD failure. Balanced data is then predicted with neural networks. The system is for predicting someone when using IUD whether they have a pregnancy or not. This study uses 250 data with 235 major data (not pregnant) and 15 minor data (pregnant). From 250 data divided into two parts, 225 training and 25 testing data. Minority class on training data will be duplicated to 1524%, so that the amount of minority data become balanced with  the majority data. The results of predictive with an accuracy rate of  99.9% at 1000 epoch.


2011 ◽  
Vol 189-193 ◽  
pp. 2042-2045 ◽  
Author(s):  
Shang Jen Chuang ◽  
Chiung Hsing Chen ◽  
Chien Chih Kao ◽  
Fang Tsung Liu

English letters cannot be recognized by the Hopfield Neural Network if it contains noise over 50%. This paper proposes a new method to improve recognition rate of the Hopfield Neural Network. To advance it, we add the Gaussian distribution feature to the Hopfield Neural Network. The Gaussian filter was added to eliminate noise and improve Hopfield Neural Network’s recognition rate. We use English letters from ‘A’ to ‘Z’ as training data. The noises from 0% to 100% were generated randomly for testing data. Initially, we use the Gaussian filter to eliminate noise and then to recognize test pattern by Hopfield Neural Network. The results are we found that if letters contain noise between 50% and 53% will become reverse phenomenon or unable recognition [6]. In this paper, we propose to uses multiple filters to improve recognition rate when letters contain noise between 50% and 53%.


Author(s):  
Brian Bucci ◽  
Jeffrey Vipperman

In extension of previous methods to identify military impulse noise in the civilian environmental noise monitoring setting by means of a set of computed scalar metrics input to artificial neural network structures, Bayesian methods are investigated to classify the same dataset. Four interesting cases are identified and analyzed: A) Maximum accuracy achieve on training data, B) Maximum overall accuracy on blind testing data, C) Maximum accuracy on testing data with zero false positive detections, D) Maximum accuracy on testing data with zero false negative rejections. The first case is used to illustrative example and the later three represent actual monitoring modes. All of the cases are compared and contrasted to illuminate respective strengths and weaknesses. Overall accuracies of up to 99.8% are observed with no false negative rejections and accuracies of up to 98.4% are also achieved with no false positive detections.


2019 ◽  
Vol 4 (1) ◽  
pp. 1
Author(s):  
Candra Dewi ◽  
Suci Sundari ◽  
Mardji Mardji

Patchouli (Pogostemon Cablin Bent) has higher PA (Patchouli Alcohol) and oil production if grown in soil containing 75% organic matter. One way that can be used to detect the content of organic matter is to use soil images. The problem in the use of soil images is the color of the soil that is almost similar, namely the gradation between dark brown to black. Therefore, color features are not enough to be used as input in the recognition process. For this purposes, texture features are added in this study in addition to color features. The color features are extracted using color moment and the texture features are extracted using Gray Level Co-occurrence Matrix (GLCM). These feature was then chosen to get the best combination as input in the identification process using the Backpropagation Neural Network (BPNN). The system identifies the quantity of soil organic matter into five classes, namely very low, low, medium, high, and very high. The highest accuracy result obtained was 73% and MSE value 0.5122 by using five GLCM features (Angular Second Moment, contrast, correlation, Inverse Difference Moment, and entropy). This result was obtained by using the BPNN parameter, namely learning rate values 0.5, maximum iteration values of 1000, number training data 210, and total test data 12.


2021 ◽  
Vol 10 (1) ◽  
pp. 113-119
Author(s):  
Muhammad Ezar Al Rivan ◽  
Gabriela Repca Sung

Papaya is one of the fruits that grows in the tropics area, one of the kinds that people’s love the most is papaya California. The quality identification of papaya California fruit can be measured using color, defect, and size. Color, defect and size extracted from image of papaya. The dataset that used in this research are 150 images papaya California. The dataset consist of 3 quality there are good, fair and low.  Identification of papaya using the backpropagation neural network method with 17 training function in each training data with 3 different neurons in the hidden layer. The best result of the test is using training function trainrp with 10 neurons is 81,33% for accuracy, 73,37% for precision, and 72% for recall, with 20 neurons is 82,67% for accuracy, 75,24% for precision, and 74% for recall, and with 25 neurons is 80,89% for accuracy, 74,42% for precision, and 71,33% for recall.


2016 ◽  
Vol 3 (2) ◽  
pp. 86
Author(s):  
Delima Ayu S ◽  
Franky Arisgraha ◽  
Retna Apsari

Heart disease is one disease with high mortality rate in the world. Based on WHO records from 112 countries at 2004, the rate is 29% of all deaths each year. Medical devices are necessary to diagnose one's health as an indication of a disease. Nowadays, Indonesia still imports medical devices, for the diagnosis of heart failure, from abroad. This research aims to assist the monitoring of cardiac patients with bradycardia and tachycardia appearances of message condition patient’s heart rate at the same time. The results were displayed with the output of bradycardia condition of the heart rate (heart rate less than 60 beats per minute) or tachycardia (heart rate over 100 beats per minute). The system displayed the data read from the heart to the PC embedded system to monitor the condition of the patients under decisions based on backpropagation neural network. Classification system could be performed quite well, training data and by testing the 10 pieces, the optimal weight gain was 1727 iteration, the learning rate was 0.1122, and the error was below 0.001 (0.0009997).


Author(s):  
Wee-Beng Tay ◽  
Murali Damodaran ◽  
Zhi-Da Teh ◽  
Rahul Halder

Abstract Investigation of applying physics informed neural networks on the test case involving flow past Converging-Diverging (CD) Nozzle has been investigated. Both Artificial Neural Network (ANN) and Physics Informed Neural Network (PINN) are used to do the training and prediction. Results show that Artificial Neural Network (ANN) by itself is already able to give relatively good prediction. With the addition of PINN, the error reduces even more, although by only a relatively small amount. This is perhaps due to the already good prediction. The effects of batch size, training iteration and number of epochs on the prediction accuracy have already been tested. It is found that increasing batch size improves the prediction. On the other hand, increasing the training iteration may give poorer prediction due to overfitting. Lastly, in general, increasing epochs reduces the error. More investigations should be done in the future to further reduce the error while at the same time using less training data. More complicated cases with time varying results should also be included. Extrapolation of the results using PINN can also be tested.


2020 ◽  
Vol 9 (3) ◽  
pp. 273-282
Author(s):  
Isna Wulandari ◽  
Hasbi Yasin ◽  
Tatik Widiharih

The recognition of herbs and spices among young generation is still low. Based on research in SMK 9 Bandung, showed that there are 47% of students that did not recognize herbs and spices. The method that can be used to overcome this problem is automatic digital sorting of herbs and spices using Convolutional Neural Network (CNN) algorithm. In this study, there are 300 images of herbs and spices that will be classified into 3 categories. It’s ginseng, ginger and galangal. Data in each category is divided into two, training data and testing data with a ratio of 80%: 20%. CNN model used in classification of digital images of herbs and spices is a model with 2 convolutional layers, where the first convolutional layer has 10 filters and the second convolutional layer has 20 filters. Each filter has a kernel matrix with a size of 3x3. The filter size at the pooling layer is 3x3 and the number of neurons in the hidden layer is 10. The activation function at the convolutional layer and hidden layer is tanh, and the activation function at the output layer is softmax. In this model, the accuracy of training data is 0.9875 and the loss value is 0.0769. The accuracy of testing data is 0.85 and the loss value is 0.4773. Meanwhile, testing new data with 3 images for each category produces an accuracy of 88.89%. Keywords: image classification, herbs and spices, CNN. 


Kursor ◽  
2017 ◽  
Vol 8 (3) ◽  
pp. 135
Author(s):  
Mohammad Zoqi Sarwani

E-complaint is one of the technologies which is used to collect feedback from customers in the form of criticism and suggestions using electronic systems. For some companies or agencies, ecomplaint is used to provide better services to its customers. This study is aimed to perform sentiment analysis of an e-complaint service, with the case of Brawijaya University. There are three main stages for the proposed system, i.e. Text Preprocessing, Text Weighting, and PNN forthe classification. Tokenization, filtering, and stemming are done in the text preprocessing. Resulted text from the preprocessing stage is weighting using Term Inverse Document Frequent (TFIDF). To classify the negative or positive complaints, PNN are used in the last stage. For the experiments, 70 data are used as the training data, and 20 data are used as the testing data. The experimental results based on the combination of the number of training and testing dataset, showed that the accuracy achieved up to 90%.


Polymers ◽  
2021 ◽  
Vol 13 (22) ◽  
pp. 3874
Author(s):  
Yan-Mao Huang ◽  
Wen-Ren Jong ◽  
Shia-Chung Chen

This study addresses some issues regarding the problems of applying CAE to the injection molding production process where quite complex factors inhibit its effective utilization. In this study, an artificial neural network, namely a backpropagation neural network (BPNN), is utilized to render results predictions for the injection molding process. By inputting the plastic temperature, mold temperature, injection speed, holding pressure, and holding time in the molding parameters, these five results are more accurately predicted: EOF pressure, maximum cooling time, warpage along the Z-axis, shrinkage along the X-axis, and shrinkage along the Y-axis. This study first uses CAE analysis data as training data and reduces the error value to less than 5% through the Taguchi method and the random shuffle method, which we introduce herein, and then successfully transfers the network, which CAE data analysis has predicted to the actual machine for verification with the use of transfer learning. This study uses a backpropagation neural network (BPNN) to train a dedicated prediction network using different, large amounts of data for training the network, which has proved fast and can predict results accurately using our optimized model.


Sign in / Sign up

Export Citation Format

Share Document