Epoch Value Research Articles

Comparison of Mars rotation angle models

AbstractWe compare published solutions for the rotation angle W(t) which describes the location of the prime meridian of Mars with respect to the ICRF equator in IAU recommendations. If the model for W includes a very long period term, we transform it into a quadratic polynomial with updated epoch value and rate, resulting in a difference in the mean epoch value up to 200 km. The mean and true epoch rotation angles are about 800 mas (13 m) apart in J2000 and should not be confused with each other in order to accurately locate the prime meridian. We identify two groups of radio-science solutions for W, which can be distinguished by the prime meridian location they used as a priori that differ from each other by about 100 m at J2000.

Automatic Door Access Model Based on Face Recognition using Convolutional Neural Network

Automatic door access technology by utilizing biometrics such as fingerprints, retinas and facial structures is constantly evolving. The use of masks during the Covid-19 Pandemic and post-pandemic has become an obligation wherever humans are active. The study aimed to create an automated door access model using Convolutional Neural Network (CNN) algorithms and Amazon Rekognition as cloud-based software. The CNN algorithm is applied to classify faces wearing masks or not wearing masks. The CNN architecture model uses sequential, convolution2D, max polling 2D, flatten dan dense. The hardware includes the Raspberry Pi, USB Webcam, Relay, and Magnetic Doorlock. The test results were obtained from the results of the accuracy plot on the Convolutional Neural Network model with an accuracy rate of 99% at an epoch value of 8 with a learning time of 67 seconds.

PERBANDINGAN METODE ANN BACKPROPAGATION DAN ARMA UNTUK PERAMALAN INFLASI DI INDONESIA

A country's development progress can be measured by good economic growth. If economic growth experiences rapid growth, it will usually trigger price increases. The occurrence of an uncontrolled increase in the price of goods or services for the needs of the community can cause inflation. inflation rate for a country is an inflation rate that has a low and stable value. One alternative is to provide an overview of the inflation in Indonesia by using forecasting analysis techniques. In this study, inflation forecasting analysis in Indonesia was carried out using the ANN Backpropagation and ARMA methods. The purpose of this research is to compare the performance results of the two methods and look at the best method for forecasting results. Based on the results of the analysis with the ANN Backpropagation method, the best network architecture model was ANN(7-4-1) using an epoch value of 400 and a learning rate of 0,1 with a value of MSE = 0,0112 and RMSE = 0,1065. While the results of the analysis using the ARMA method, the best model was obtained, namely ARMA(2,0,1) with the value MSE = 0,0648 and RMSE = 0,2545. So that the most optimal method used to predict inflation for the next period is the ANN Backpropagation method because it has a smaller error value. From this model, the results of forecasting inflation rates for the months of May to December 2022 are also obtained with a range of 0,01% to 0,5%.

Application Deep Learning to Predict Crypto Currency Prices and their Relationship to Market Adequacy (Applied Research Bitcoin as an Example)

redicting currency rates is important, for everyone who is trading and trying to build an investment portfolio from a range of crypto currencies. It is not subject to the same restrictions as fiat currencies. In this study, we seek to predict the exchange rate of BIT-COIN against the US dollar. The short-term data (365 observations) is processed using the LSTM model as one of the neural network models. Modeling is conducted by training a sample size of 67%, taking into account sharp fluctuations in the price of trade and a certain level of market efficiency. The GARCH model is used to select appropriate historical periods for how the LSTM model works and to test proficiency at the weak, semi-strong, and strong levels. The data series obtained from the website (Investing.com) have been processed. The researchers have found that the performance of the neural network improves as the EPOCH value increases with a training (research) period of 50 days before, which is consistent with the results of the proficiency test at the weak level. It agrees with the results of the sufficiency test at the weak level, which indicates that in the case under study (the Bitcoin market is effective at the weak level). It is advised that crypto-currency investors rely more on the historical trend of the price of the currency than on its current price, taking advantage of the artificial neural network model (LSTM) in dealing with little data of high volatility.

Radicalism Speech Detection in Indonesia on Twitter Using Backpropagation Neural Network Method

In this modern era, many people use social media easily and freely. One of the social media used is Twitter. The reason people use Twitter is that they can express their opinion freely. However, this freedom does not always have a positive impact on other Twitter users. One of the negative impacts for users is that they can spread radical content. Therefore, this research aims to detect whether a tweet contains radical elements or not using the backpropagation neural network method. The process is carried out by taking data on Twitter, after which the preprocessing process is carried out. Then the data is processed using imbalanced handling, where the data is divided into oversampling and undersampling data. After the data is divided, the next process is to do stopword and then look for accuracy by comparing different epoch values, namely 100, 150, 200, and 250. The best epoch value obtained is 200, with a final accuracy result of 86%.

The Study of Render Farm Image Classification Using Deep Neural Network

Rendering on the making of movie animation is a process of combining the imagination of animators and artistic creativity by turning the graphic display into millions of moving images. To perform the rendering process, the render farm is used, which is a combination of a group of high-performance computers (super-computers) commonly referred to as Computer Generated Imager. Throughout this time, the render artist spends a considerable plenty of time on doing image analysis from render farms manually. Reflecting on that, the study presented in this paper propose a deep learning method can separate images of the results of render farms more quickly and accurately. The technique proposed in this study is the classification of approved or revised images as the results of the render farm machine by using Deep Neural Network (DNN) technique. To verify the DNN that best fits the dataset, experiments were carried out on several layer depths and adjustment of epoch. In terms of treatment of the dataset, the experiment scenario selected was percentage and cross validation. The best performance in the experiment results is provided by layer depth configuration of 10, epoch value 100. The configuration provides the value of accuracy, precision and recall of 90%, 96% and 92% respectively.

Recognition of Regional Traditional House in Indonesia Using Convolutional Neural Network (CNN) Method

Indonesia is a country that has a lot of cultural diversity. This cultural diversity needs to be preserved. If this is not done, the culture that is owned by Indonesia can slowly disappear. The reduction in cultural values can also reduce the sense of belonging to the culture. This lack of sense of ownership makes it easy for other nations to make claims on the culture that is owned by Indonesia. Indonesia will lose its characteristics as a country that has a lot of cultural diversity. One of the efforts to preserve culture is to recognize the characteristics of each culture and be able to recognize the differences between one culture and another. For example, recognizing traditional houses from various ethnic groups based on their image. In this research, the image classification of the characteristics of traditional houses from several ethnic groups in Indonesia was carried out. The classification used to identify an image. In this study, deep learning techniques are used with the Convolutional Neural Network (CNN) algorithm and Keras framework. This CNN use several layers namely convolutional, pooling, flatten, and dense layer. The development of deep learning models uses the Knowledge Discovery in Database (KDD) method. This method consists of nine stages. The built model is evaluated using k-fold cross validation with a k value of 5 and produces an average accuracy of 80%. This shows that the model built is capable of classifying well. The built model is evaluated with 3 different epoch values, namely 50, 75, and 100. The larger the epoch value used, the greater the accuracy value. The model built is also able to make predictions with an accuracy of 80%.

Seismic Data Quality Analysis Based on Image Recognition Using Convolutional Neural Network

Seismometer monitoring and evaluation activities at the Indonesia Tsunami Early Warning System (InaTEWS) station can be carried out through a seismometer sensor calibration system with the use of the software of Seismic Data Quality Analysis. The software output is in the form of a spectrum image that represents the conditions of the seismometer following the spectrum results. The identification of the seismometer condition can be made by pattern recognition in the spectrum image. This study employed a neural network, specifically the Convolutional Neural Network (CNN), to analyse the pattern condition. The test results show that the performance of the system will be excellent if 1024 hidden layers are used. In addition, the epoch test shows that the system works well when given a maximum epoch value of 50. The test of image size gives the result that the system performance will result in good using input with a size of 30x20 pixels. The final results of the classification of spectrum images using CNN will exhibit the identification of seismometer. For the validation, the confusion matrix test shows that the corresponding findings are 80%, while the conflicting results are 20%.

Implementasi Jaringan Saraf Tiruan Dalam Prediksi Penjualan Kue pada UD. Mak Kembar Pematang Siantar Dengan Backpropagation

UD.Mak Kembar is a shop engaged in the sale of cakes and bread, located in Rambung Merah. Until now, UD. Mak Kembar only uses a simple system in marketing information and recording, causing delays in marketing information and in recording sales calculations. Based on the problems above, the authors design and create a system at UD.Mak Kembar. This system applies predictions in its sales, and is built using an artificial neural network with the Backprogation algorithm. The results obtained with the best architecture 4-5-1 with an iterative process (epoch) during training with an epoch value = 75% and SSE achievement at the time of testing with SSE = 0.23950.

PENINGKATAN AKURASI PREDIKSI PENGADAAN BAHAN BAKU PRODUKSI DENGAN MENGGUNAKAN METODE NEURAL NETWORK

Forecasting or prediction in production activities is an activity that aims to predict everything related to production, supply, demand, and use of technology in an industry. In the end, this prediction is often used by companies and operational management to make plans related to their business activities in certain periods. As a tool for measuring the level of predictions that are close to good accuracy which can be used as a reference for calculating a business process in the future, companies also need an accurate and tested measuring tool based on the type of estimate itself. The NEURAL NETWORK method with backpropagation calculates a pattern based on the history of several periods that have occurred. This method is often used to obtain prediction accuracy in forecasting activities. Inaccurate packaging stock inventory forecasting to support production needs causes the inventory space to exceed capacity and the production process is disrupted, so the selection of an appropriate forecasting method is needed. The use of the NEURAL NETWORK method with backpropagation to increase the accuracy of the prediction of the procurement of packaged goods in this study is very suitable. Results of Data Training with input data for begin stock, consumption, incoming, and safety stock and target data is the stock order yields the best MSE value of 0.03603642 on the number of neurons 11 with an epoch value of 1000 and a maximum error limit of 6, so that the test data resulted in the accuracy of the MAPE value of 0.52%.

Penerapan Jaringan Syaraf Tiruan Backpropagation Dalam Memprediksi Jumlah Pertumbuhan Kendaraan Di Provinsi Sumatera Utara

Motorized vehicles are part of the need for transportation of vehicles that are derivatives due to economic, social, and other activities. The growth of vehicles is not proportional to the population in the province of North Sumatra. This causes various negative impacts, one of which is an increase in traffic congestion, air pollution from motorized vehicles which causes an increase in greenhouse gas emissions. Based on this problem, it is necessary to predict the number of vehicles in North Sumatra Province using the backpropagation algorithm artificial neural network. The results of trials carried out with MATLAB R2011b software, the best architectural model is the 2-2-1 model with an accuracy rate of 94% with MSE number 0.000208514, epoch value 789. It can be concluded that the Backpropagation method can be used as one of the predictive methods that make it easier to find predictions. Whatever.

Modeling of copper removal from aqueous solutions by using carbon-based adsorbents derived from hazelnut and walnut shells by artificial neural network

The aim of this study is to model the removal of copper from an aqueous solution using Artificial Neural Network (ANN). Two different carbon-based materials (biochar) obtained by pyrolysis of hazelnut and walnut shells were used as adsorbents in a batch adsorption system. The surface area of biochars with a porous structure obtained from hazelnut and walnut shells were 124.347 m2/g and 256.931 m2/g, respectively. In adsorption experiments, initial copper concentration, adsorbent amount, temperature, pH, contact time and mixing speed were the adsorption parameters considered for the system and defined as inputs in the modeling studies. Experimental results for removing copper ions were found by changing pH 2.5-5, initial heavy metal concentration 15-45 ppm, adsorbent amount 1-3 g/L, mixing speed 200-600 rpm and temperature between 25-45oC. The % copper removal, which is tried to be maximized during the modeling phase, was selected as the model estimation parameter and defined as output to the system. ANN training was done with the Levenberg–Marquardt (LM) feed-forward algorithm and the data was categorised into 50% training, 25% validation and 25% testing. The maximum epoch value was determined as 8 iterations. Correlation coefficient (R2) values of the system were determined as 99% for education, validation and testing for the two different carbon-based adsorbents.

Portable Cough Classification System Based on Sound Feature Extraction Using Tiny Machine Learning

Cough is one of the most common markers that can provide information in diagnosing a disease. More specifically, cough is a common symptom of many respiratory infections. There are several types of cough, including: dry cough, wet cough (cough with phlegm), croup cough and whooping cough. This study aims to create a system that can classify the sounds of coughing up phlegm, dry cough, whooping cough and croup cough. The system development uses the concept of tiny machine learning. In the system built, Arduino Nano 33 BLE Sense is used as a control device and LED is used as an output device. In this study, the classification of dry cough, wet cough, croup cough and whooping cough was performed using the MFCC voice feature extraction. In the process of classifying coughing sounds using the Neural Network Classifier, the system has a percentage of dataset training accuracy from a total of 5 classes (croup, dry, noise, wet, whooping) of 97.1% by applying an epoch value of 500, window size 3000ms and a window increase of 500ms.

Application of the NARX neural network for predicting a one-dimensional time series

Time series data analysis and forecasting tool for studying the data on the use of network traffic is very important to provide acceptable and good quality network services, including network monitoring, resource management, and threat detection. More and more, the behavior of network traffic is described by the theory of deterministic chaos. The traffic of a modern network has a complex structure, an uneven rate of packet arrival for service by network devices. Predicting network traffic is still an important task, as forecast data provide the necessary information to solve the problem of managing network flows. Numerous studies of actually measured data confirm that they are nonstationary and their structure is multicomponent. This paper presents modeling using Nonlinear Autoregression Exogenous (NARX) algorithm for predicting network traffic datasets. NARX is one of the models that can be used to demonstrate non-linear systems, especially in modeling time series datasets. In other words, they called the categories of dynamic feedback networks covering several layers of the network. An artificial neural network (ANN) was developed, trained and tested using the LM learning algorithm (Levenberg-Macwardt). The initial data for the prediction is the actual measured network traffic of the packet rate. As a result of the study of the initial data, the best value of the smallest mean-square error MSE (Mean Squared Error) was obtained with the epoch value equal to 18. As for the regression R, its output ANN values in relation to the target for training, validation and testing were 0.97743. 0.9638 and 0.94907, respectively, with an overall regression value of 0.97134, which ensures that all datasets match exactly. Experimental results (MSE, R) have proven the method's ability to accurately estimate and predict network traffic

Algoritma Fungsi Perlatihan pada Machine Learning berbasis ANN untuk Peramalan Fenomena Bencana

Research has been carried out with several training functions using standard backpropagation methods, One-Step Secant (OSS), and Bayesian regulation. The purpose of this study was to (i) analyze the Performance accuracy (Performance) of the standard backpropagation method and (ii) optimize the training function with the One-Step Secant (OSS) and Bayesian regulation methods to obtain comparison results of the three methods in the search for the best results implementation of disaster phenomenon forecasting data. The research method is based on quantitative methods with times-series data on disaster phenomena in Indonesia over the last ten years (2011-2020) which were analyzed using two network architecture models, namely 4-8-1 and 4-10-1. The results showed that the 4-8-1 architectural model with the Bayesian regulation training function method was able to optimize quite well through accelerating training time and resulted in a low MSE measurement, although not the lowest with an epoch value of 197 iterations and a Performance of 0.0148480766. The lowest epoch value is generated by the OSS method, but it Performs poorly. The best Performance is produced by the standard backpropagation method with the traingd training function, but the training process for achieving convergence is also too long. In general, it can be concluded that the 4-8-1 architectural model with Bayesian regulation can be used to predict (predict) the phenomenon of natural disasters in Indonesia because the training time to achieve convergence is not too long and Performs exceptionally well.

Facial Emotion Detection Using Haar-Cascade Classifier and Convolutional Neural Networks

Computer vision has the challenge to detect the facial emotions of humans. Recently, in computer vision and machine learning, it’s possible to detect emotion from video or image accurate. In our research will propose to classify facial emotion using Haar-Cascade Classifier and Convolutional Neural Networks. The experiment uses the FER2013 dataset which was collected for the facial expression recognition dataset, and we proposed seven classified facial expression. The CNN model gain MSE and accuracy value based on epoch variety. The results showed that with the increase in the epoch value, the smaller MSE value would be obtained, likewise, the accuracy value would be increased. Thus, the proposed algorithm of CNN is proven to be effective for facial emotion detection.

Comparison of Type-2 Fuzzy Inference Method and Deep Neural Networks for Mass Detection from Breast Ultrasonography Images

In this study, mass detection from breast ultrasonography images was realized using deep neural networks. Dataset is a collection of publicly available ultrasonography images which were classified by their biopsy results. A total of 153 breast ultrasonography images that contain 89 malign and 64 benign tumours were used. Image augmentation and deep neural network software was developed using Python 3,5 environment on Visual Studio Community 2017 IDE. A hybrid method including Keras ImageDataGenerator Class and image preprocessing techniques was introduced. Twenty images from both classes were randomly split from the dataset for testing after the network was designed. The network had a success rate of 100% at an epoch value of 70. The result of this study was compared with the result of another study that implemented type-2 fuzzy inference system with a success rate of 99,34%. 
 As a conclusion, it can be expressed that the deep neural networks are more successful than fuzzy inference systems in tumour detection from breast ultrasonography images. Therefore, it can be more convenient to use deep neural network technology in computer aided detection systems for mass detection from breast ultrasonography images.

AUTOMATICS NUMBER PLATE RECOGNITION USING CONVOLUTION NEURAL NETWORK

In the last few years, Automatic Number Plate Recognition (ANPR) systems have become widely used for security, safety, and also commercial aspects such as parking control access, and legal steps for the red light violation, highway speed detection, and stolen vehicle detection. The license plate of any vehicle contains a number of numeric characters recognized by the computer. Each country in the world has specific characteristics of the license plate. Due to rapid development in the information system field, the previous manual license plate number writing process in the database is replaced by special intelligent device in a real-time environment. Several approaches and techniques are exploited to achieve better systems accuracy and real-time execution. It is a process of recognizing number plates using Optical Character Recognition (OCR) on images. This paper proposes a deep learning-based approach to detect and identify the Indian number plate automatically. It is based on new computer vision algorithms of both number plate detection and character segmentation. The training needs several images to obtain greater accuracy. Initially, we have developed a training set database by training different segmented characters. Several tests were done by varying the Epoch value to observe the change of accuracy. The accuracy is more than 95% that presents an acceptable value compared to related works, which is quite satisfactory and recognizes the blurred number plate.

Detection and Diagnosis of Skin Diseases Using Residual Neural Networks (RESNET)

Skin diseases have become prevalent in the present times. It has been observed in a study that every year the percentage of global population suffering from skin diseases is 1.79%. These diseases have a potential to become extremely dangerous if they are not treated in the nascent stages. It is extremely important that skin diseases are detected and diagnosed at the starting stages so that serious risks to life are avoided. Often, exhaustive tests are required so as to arrive on a conclusion regarding skin condition, the patient may be affected with. Thus, an expert system is required that has the ability to identify diseases and propose the required diagnosis. Presently, only a few solutions are available for diagnosis of skin diseases using computerized system but this is an era which is under extensive research and can be developed further. As the existing system has certain loopholes, this system attempts to override the present problems by applying a different approach. As a result of comparison of results from numerous research papers, an expert system has been developed by choosing residual neural networks (ResNet) and this system can be used to aid skin specialists in identifying and diagnosing various major diseases of skin like (Eczema, Psoriasis & Lichen Planus, Benign Tumors, Fungal Infections and Viral Infections) in more effective and efficient manner. The causes for identified skin disease can be outlined through this system and treatment can be provided. We have used Python language for implementing the proposed expert system that uses a 50-layer ResNets for training a dataset that has been taken from DERMNET. We achieved an accuracy of 95% using ResNet for training of the model and prediction of results at an epoch value of 10.

Design Plant Disease Detection System Using Deep Learning Convolutional Neural Network

Indonesia is an agrarian country whose people mostly work in agriculture by contributing to the 3rd largest GDP. But on the other hand, the main problem in agriculture is the development of pests and diseases of crops. There are cases where there are crops that are attacked by diseases with less obvious symptoms for farmers. For example, in citrus plants that are attacked by CVPD. Initially, the citrus plant does not show too early symptoms of the disease, making it difficult to distinguish from healthy plants. Based on these problems early detection and identification of plant diseases are the main factors to prevent and reduce the spread of plant diseases. The study used deep learning methods with the Convolutional Neural Network (CNN) algorithm model. The dataset used comes from PlantVillage with a total of 20,639 leaf image files that have been classified based on their respective classes. The design of the model architecture is done by designing the CNN model following the DenseNet121 architecture, by changing the parameters to improve the accuracy results. Image size is 64, train shape (20639, 64, 64, 3), epoch value 50,100, and 150. The number of input layers used is 4 layers with shapes (64, 64, 3). Densenet121 shape (1024), global average pooling2D shape (1024), batch normalization 2 (1024), dropout (1024), dense (256), batch normalization 3 (256), root (Dense) (15). This research was conducted with 3 epoch iteration tests to find the best accuracy value. The training data for epoch 50,100, and 150 produces an average model accuracy of 99.38% and the average value of the model loss is 0.019% can also be seen from the testing data results for epoch 50,100, and 150 has an average model of 95.16% and can be seen also from the average value for the loss is 0.20%. Based on the algorithm that applied the resulting training accuracy of 99.58% and the accuracy of testing 96.41% then design this application is useful to accurately detect diseases in plants by using leaf imagery of the plant.