The effect of Kurtosis on the accuracy of artificial neural network predictive model

This study aims to explore the effect of kurtosis level of the data in the output layer on the accuracy of artificial neural network predictive models. The artificial neural network predictive models are comprised of one node in the output layer and six nodes in the input layer. The number of hidden layer is automatically built by the program. Data are generated using simulation approach. The results show that the kurtosis level of the node in the output layer is significantly affect the accuracy of the artificial neural network predictive model. Platycurtic and leptocurtic data has significantly higher misclassification rates than mesocurtic data. However, the misclassification rates between platycurtic and leptocurtic is not significantly different. Thus, data distribution with kurtosis nearly to zero results in a better ANN predictive model.

Download Full-text

Pengujian Algoritma Artificial Neural Network (ANN) Untuk Prediksi Kecepatan Angin

Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) ◽

10.32672/jnkti.v2i1.1056 ◽

2019 ◽

Vol 2 (1) ◽

pp. 43

Author(s):

Syukri Syukri ◽

Samsuddin Samsuddin

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Output Layer ◽

Input Layer ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

Hidden Layer

Angin memiliki peran yang penting dalam kehidupan manusia, antara lain pada pembangkit listrik, pelayaran dan penerbangan. Ketiga sektor tersebut erat kaitannya dengan kondisi angin. Angin dapat muncul setiap saat dan setiap waktu serta perubahan geografis pada suatu wilayah. Hal ini mengakibatkan sulitnya menentukan kecepatan angin, maka untuk mengatasi masalah tersebut diperlukan prediksi kecepatan angin. Saat ini berbagai metode prediksi telah banyak dikembangkan, salah satu metode yang dapat digunakan untuk melakukan prediksi dengan akurasi yang tinggi yaitu algoritma Artificial Neural Network (ANN) Backpropagation. Arsitektur ANN yang digunakan adalah 4 parameter input layer, hidden layer (5, 10, 15, 20, 25 dan 30) dan output layer (1 parameter). Data pembelajaran dan pengujian didapatkan dari stasiun BMKG Blang Bintang Aceh Besar, berupa data kecepatan angin jam per harian periode Januari 2011 sampai dengan Desember 2015 yang terdiri dari arah angin, suhu, tekanan, kelembaban dan suhu. Hasil pengujian menunjukkan bahwa metode ANN Backpropagation cukup baik diterapkan untuk proses prediksi, kemampuan ANN dalam melakukan prediksi memiliki tingkat akurasi rata – rata yang lebih baik yaitu 96 %. Sedangkan nilai rata – rata kerapatan daya angin jam per harian yaitu 45.030 W/m2

Download Full-text

PEMODELAN JARINGAN SYARAF TIRUAN DENGAN CASCADE FORWARD BACKPROPAGATION PADA KURS RUPIAH TERHADAP DOLAR AMERIKA SERIKAT

Jurnal Gaussian ◽

10.14710/j.gauss.v7i1.26636 ◽

2018 ◽

Vol 7 (1) ◽

pp. 64-72

Author(s):

Ekky Rosita Singgih Wigati ◽

Budi Warsito ◽

Rita Rahmawati

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Processing System ◽

Training Data ◽

Neural Network Modeling ◽

Feed Forward Neural Network ◽

Output Layer ◽

Input Layer ◽

Artificial Neural ◽

Hidden Layer

Neural Network Modeling (NN) is an information-processing system that has characteristics in common with human brain. Cascade Forward Neural Network (CFNN) is an artificial neural network that its architecture similar to Feed Forward Neural Network (FFNN), but there is also a direct connection from input layer and output layer. In this study, we apply CFNN in time series field. The data used isexchange rate of rupiah against US dollar period of January 1st, 2015 until December 31st, 2017. The best model was built from 1 unit input layer with input Zt-1, 4 neurons in the hidden layer, and 1 unit output layer. The activation function used are the binary sigmoid in the hidden layer and linear in the output layer. The model produces MAPE of training data equal to 0.2995% and MAPE of testing data equal to 0.1504%. After obtaining the best model, the data is foreseen for January 2018 and produce MAPE equal to0.9801%. Keywords: artificial neural network, cascade forward, exchange rate, MAPE

Download Full-text

Rapid Method for Prediction of Escherichia coli Numbers Using an Electronic Sensor Array and an Artificial Neural Network

Journal of Food Protection ◽

10.4315/0362-028x-67.8.1604 ◽

2004 ◽

Vol 67 (8) ◽

pp. 1604-1609 ◽

Cited By ~ 10

Author(s):

UBONRATANA SIRIPATRAWAN ◽

JOHN E. LINZ ◽

BRUCE R. HARTE

Keyword(s):

Neural Network ◽

Escherichia Coli ◽

Artificial Neural Network ◽

Transfer Function ◽

Sensor Array ◽

E Coli ◽

Output Layer ◽

Electronic Sensor ◽

Artificial Neural ◽

Hidden Layer

An electronic sensor array with 12 nonspecific metal oxide sensors was evaluated for its ability to monitor volatile compounds in super broth alone and in super broth inoculated with Escherichia coli (ATCC 25922) at 37°C for 2 to 12 h. Using discriminant function analysis, it was possible to differentiate super broth alone from that containing E. coli when cell numbers were 105 CFU or more. There was a good agreement between the volatile profiles from the electronic sensor array and a gas chromatography–mass spectrometer method. The potential to predict the number of E. coli and the concentration of specific metabolic compounds was investigated using an artificial neural network (ANN). The artificial neural network was composed of an input layer, one hidden layer, and an output layer, with a hyperbolic tangent sigmoidal transfer function in the hidden layer and a linear transfer function in the output layer. Good prediction was found as measured by a regression coefficient (R2 = 0.999) between actual and predicted data.

Download Full-text

Artificial Neural Network (ANN) Analysis of Co-pyrolysis of Waste Coconut Husk and Laminated Plastic Packaging

ASEAN Journal of Chemical Engineering ◽

10.22146/ajche.69521 ◽

2021 ◽

Vol 21 (2) ◽

pp. 241

Author(s):

Joselito Abierta Olalo

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Optimization Techniques ◽

Fuel Oil ◽

Oil Yield ◽

Coconut Husk ◽

Input Layer ◽

Artificial Neural ◽

Predicted Values ◽

Hidden Layer

Co-pyrolysis of plastic with biomass was used in the possible mitigation of environmental health problems associated with plastic waste. The pyrolysis method possessed the highest solution in the reduction of waste problems. Fuel oil can be produced through the pyrolysis of plastic and biomass waste. Many researchers used pyrolysis technology to produce a suitable amount of pyrolytic oil through different optimization techniques. This study will predict the percentage mass oil yield using an artificial neural network. It uses an input layer, hidden layer and an output layer. Three input factors for the input layer were (i) temperature, (ii) particle size, and (iii) percentage coconut husk. The structure has one hidden layer with two neurons. The artificial neural network was designed to predict the percentage oil yield after 15 pyrolysis runs set by the Box-Behnken design of the experiment. Percentage oil yields after pyrolysis were calculated. Results showed that temperature and percentage of coconut husk significantly influenced the percentage oil yield. Predicted values from simulation in the artificial neural network showed a good agreement through a correlation coefficient of 99.5%. The actual percentage oil yield overlaps the predicted values, which ANN demonstrates as a viable solution.

Download Full-text

Konstruksi Model Matematika Pola Curah Hujan Menggunakan Artificial Neural Network (ANN) dengan Metode Backpropagation

Justek : Jurnal Sains dan Teknologi ◽

10.31764/justek.v1i1.400 ◽

2018 ◽

Vol 1 (1) ◽

pp. 10

Author(s):

Habibi Ratu Perwira Negara ◽

Irzani Irzani ◽

Ripai Ripai

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Rainfall Pattern ◽

Output Layer ◽

South Central ◽

Southern Central ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

Hidden Layer ◽

The Mathematical Model

Abstrak: Penelitian ini bertujuan untuk menentukan model pola curah hujan menggunakan Artificial Neural Network (ANN) dengan metode Backpropagatiaon. Sampel dalam penelitian ini adalah 5 pos pencataan hujan di daerah Lombok Tengah bagian Selatan dan 2 pos pencatatan hujan di daerah Lombok Timur bagian Selatan. Data penelitian berupa data setengah bulanan yang dicatat dari tahun 1973 sampai tahun 2010 untuk daerah Lombok Tengah bagian Selatan dan data dari tahun 1974 sampai tahun 2010 untuk daerah Lombok Timur bagian Selatan. Metode penilitian dilakukan dengan melakukan pembelajaran data curah hujan menggunakan 5 arsitektur yang berbeda. Pembelajaran dilakukan untuk menemukan arsitektur terbaik. Arsitektur untuk daerah Lombok Tengah bagian Selatan adalah 120 layer inputan, 240 layer hidden 1, 12 layer hidden 2, dan 1 layer output. Sedangkan arsitektur untuk daerah Lombok Timur bagian Selatan adalah 363 layer inputan, 54 layer hidden 1, 24 layer hidden 2, dan 1 layer output. Model matematika pola curah hujan yang diperoleh adalah .Abstract: This study aims to determine the model of rainfall pattern using Artificial Neural Network (ANN) with Backpropagatiaon method. The sample in this research is 5 rainfall checkpoint in South Central Lombok and 2 post recording of rain in South East of Lombok. The research data are semi-monthly data recorded from 1973 to 2010 for the southern part of Central Lombok and data from 1974 to 2010 for the southern part of Lombok Timur. Methods of research conducted by conducting rainfall data learning using 5 different architectures. Learning is done to find the best architecture. The architecture for the Southern Central Lombok area is 120 layers of input, 240 hidden layers 1, 12 hidden layers 2, and 1 output layer. While the architecture for the southern part of East Lombok is 363 layers inputan, 54 hidden layer 1, 24 hidden layer 2, and 1 output layer. The mathematical model of the obtained rainfall pattern is .

Download Full-text

Live to learn: learning rules-based artificial neural network

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v21.i1.pp558-565 ◽

2021 ◽

Vol 21 (1) ◽

pp. 558

Author(s):

Aseel Shakir I. Hilaiwah ◽

Hanan Abed Alwally Abed Allah ◽

Basim Akhudir Abbas ◽

Tole Sutikno

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Ann Model ◽

Output Layer ◽

Ann Models ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

Hidden Layer ◽

Intelligent Model ◽

Human Nervous System

An extensive review of the artificial neural network (ANN) is presented in this paper. Previous studies review the artificial neural network (ANN) based on the approaches (algorithms) used or based on the types of the artificial neural network (ANN). The presented paper reviews the ANN based on the goal of the ANN (methods, and layers), which become the main objective of this paper. As a famous artificial intelligent model, ANN mimics the human nervous system in handling the information transmited by different nodes (also known as neurons) in this model. These nodes are stacked in layers and work collectively to bring about solution to complex problems. Numerous structures exist for ANN and each of these structures is designed to addressa a specific task. Basically, the ANN architecture is comprised of 3 different layers wherein the first layer rpresents the input layer that consist of several input nodes that represent the input parameterfor the model. The hidden layer is te second layer and consists of a hidden layer of neurons. The neurons in this layer are directly connected to the neurons in the output layer. The third layer is the output layer which is the models’ response layer. The output layer neurons have the activation functions for the calculation of the ANN final output. The connection between the nodes in the ANN model is mediated by synaptic weights. This paper is a comprehensive study of ANN models and their layers.

Download Full-text

Optimasi Model Artificial Neural Network untuk Klasifikasi Paket Jaringan

SIMETRIS ◽

10.51901/simetris.v14i2.135 ◽

2020 ◽

Vol 14 (2) ◽

pp. 1-5

Author(s):

Indra Gunawan

Keyword(s):

Neural Network ◽

Machine Learning ◽

Artificial Neural Network ◽

Packet Size ◽

Input Layer ◽

Packet Length ◽

Artificial Neural ◽

Hidden Layer ◽

Game Browsing

Klasifikasi jaringan internet dibutuhkan secara luas oleh berbagai pihak untuk penghematan, pengalokasian, pembatasan sumber daya internet. Berbagai teknik digunakan untuk hal tersebut, salah satunya adalah dengan pendekatan machine learning khususnya algoritma jaringan syaraf tiruan (artificial neural network) yang selanjutnya disingkat ANN. ANN bekerja dengan cara meniru cara kerja syaraf otak manusia. AAN pada penelitian ini digunakan untuk mengklasifikasikan paket jaringan. Dataset yang digunakan adalah terdiri dari 990.558 baris data, 4 kolom input(X) meliputi protocol, port, timestamp, packet length. Kolom output(Y) terdiri satu kolom 5 label (App, Sosmed, Game, Browsing, Streaming). Selanjutnya dataset ini dibagi menjadi 3 yaitu training, test, dan validation. Tujuan dari penelitian ini adalah, pertama, untuk mengetahui kemampuan algoritma ANN untuk pengklasifikasian paket berdasarkan per satu paket. Kedua, menemukan model ANN yang paling optimal untuk permasalahan diatas. Kesimpulan yang didapatkan adalah Algoritma neural network dapat digunakan pada klasifikasi paket jaringan, tetapi jika dataset yang digunakan memiliki karakteristik-karakteristik seperti jumlah variabel X kecil, data pada variabel X sangat lebar jaraknya seperti (port, packet size, time to previous packet, protocol) maka akurasi tinggi sulit untuk didapatkan. Kedua, jika permasalahan yang diselesaikan memiliki kemiripan dengan penelitian ini, maka arsitektur model ANN yang paling optimal adalah: jumlah neuron input layer adalah 7 kali jumlah variabel X, jumlah neuron hidden layer adalah 1/2,8 kali jumlah neuron input, jumlah hidden layer satu, nilai dropout 0,33, metode aktivasi tanh-tanh-softmax, metode optimasi adamax. Nilai accuracy stabil didapatkan pada iterasi (epoch) ke-600, nilai loss stabil didapatkan pada epoch ke-1000. Nilai accuracy yang didapatkan sebesar 0,8 dan nilai loss 0,32 pada iterasi ke seribu.

Download Full-text

Comprehensive Method of Botnet Detection Using Machine Learning

International Journal of Open Source Software and Processes ◽

10.4018/ijossp.287613 ◽

2021 ◽

Vol 12 (4) ◽

pp. 0-0

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Malicious Code ◽

Large Network ◽

Botnet Detection ◽

Comprehensive Method ◽

Input Layer ◽

Optimal Accuracy ◽

Artificial Neural ◽

Hidden Layer

The botnet interrupts network devices and keeps control of the connections with the command, which controls the programmer, and the programmer controls the malicious code injected in the machine for obtaining information about the machines. The attacker uses a botnet to commence dangerous attacks as DDoS, phishing, despoil of information, and spamming. The botnet establishes with a large network and several hosts belong to it. In the paper, the authors proposed the framework of botnet detection by using an Artificial Neural Network. The author research upgrading the extant system by comprising of cache memory to fast the process. Finally, for detection, the author used an analytical approach, which is known as an artificial neural network that contains three layers: the input layer, hidden layer, output layer, and all layers are connected to correlate and approximate the results. The experiment result determines that the classifier with 25 epochs gives optimal accuracy is 99.78 percent and shows the detection rate is 99.7 percent.

Download Full-text

PERAMALAN JUMLAH PERMINTAAN UDANG BEKU PND MENGGUNAKAN METODE JARINGAN SYARAF TIRUAN (JST) BACKPROPAGATION

JURNAL AGROTEKNOLOGI ◽

10.19184/j-agt.v11i1.5438 ◽

2017 ◽

Vol 11 (1) ◽

pp. 17 ◽

Cited By ~ 1

Author(s):

Iid Mufidah ◽

Sony Suwasono ◽

Yuli Wibowo ◽

Deddy Wirawan Soedibyo

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Network Architecture ◽

Series Data ◽

Architecture Design ◽

Neural Network Architecture ◽

Output Layer ◽

Artificial Neural Network Architecture ◽

Artificial Neural ◽

Hidden Layer

Forecasting is the art or science to estimate how many needs will come in order to meet the demand for goods or services, often based on historical time series data. The growing number of emerging companies in Indonesia today has created a very tight business competition in both services and products. Consumers choose the best service and high quality and low price. Consumer demand is always uncertain or varied in each subsequent period. The aim of this research was to determind the best backpropagation neural network architecture design and to predict the demand of frozen product of PND 26/30. This research used the method of Neural Network (ANN) and Processing ANN using MATLAB software. Implementation of ANN method in PT.XYZ using Backpropagation algorithm. Artificial neural network architecture used was 12 input layer, 1 output layer, and 12 hidden layer and activation function used tansig and purelin. Tansig for hidden layer and purelin for output layer. The best artificial neural network architecture design for product demand for PND 31/40 was a multi layer feedforward value of Mean Square Error (MSE) network training value of 0.01 with MAPE 3.35. The result of JST forecasting period 2017 were 960 MC, 637 MC, 572 MC, 993 MC, 1386 MC, 480 MC, 135 MC, 1209 MC, 1476 MC, 1029 MC, 290 MC, and 952 MC. Keywords: artificial neural network, PND 26/30, backpropagation, MSE, MAPE

Download Full-text

Application of a multilayer perceptron artificial neural network for identification of peach cultivars based on physical characteristics

PeerJ ◽

10.7717/peerj.11529 ◽

2021 ◽

Vol 9 ◽

pp. e11529

Author(s):

Adel M. Al-Saif ◽

Mahmoud Abdel-Sattar ◽

Abdulwahed M. Aboukarima ◽

Dalia H. Eshra

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Multilayer Perceptron ◽

Activation Function ◽

Cross Entropy ◽

Output Layer ◽

Entropy Error ◽

Artificial Neural ◽

The Cross ◽

Hidden Layer

In the fresh fruit industry, identification of fruit cultivars and fruit quality is of vital importance. In the current study, nine peach cultivars (Dixon, Early Grande, Flordaprince, Flordastar, Flordaglo, Florda 834, TropicSnow, Desertred, and Swelling) were evaluated for differences in skin color, firmness, and size. Additionally, a multilayer perceptron (MLP) artificial neural network was applied for identification of the cultivars according to these attributes. The MLP was trained with an input layer including six input nodes, a single hidden layer with six hidden nodes, and an output layer with nine output nodes. A hyperbolic tangent activation function was used in the hidden layer and the cross entropy error was given because the softmax activation function was functional to the output layer. Results showed that the cross entropy error was 0.165. The peach identification process was significantly affected by the following variables in order of contribution (normalized importance): polar diameter (100%), L∗ (89.0), b∗ (88.0%), a∗ (78.5%), firmness (71.3%), and cross diameter (37.5.3%). The MLP was found to be a viable method of peach cultivar identification and classification because few identifying attributes were required and an overall classification accuracy of 100% was achieved in the testing phase. Measurements and quantitative discrimination of peach properties are provided in this research; these data may help enhance the processing efficiency and quality of processed peaches.

Download Full-text