Artificial neural network related to biological neuron network: a review

Volatile Organic Compounds ◽

Organic Compounds ◽

Food Waste ◽

Back Propagation ◽

Ann Model ◽

Neuron Network ◽

Volatile Organic ◽

This study examines the potential of artificial neural network (ANN) to predict Total Volatile Organic Compounds (TVOCs) released via decomposition of local food wastes. To mimic the decomposition process, a bioreactor was designed to stimulate the food waste storage condition. The food waste was modeled based on the waste composition from a residential area. A feed forward multilayer back propagation (Levenberg – Marquardt training algorithm) was then developed to predict the TVOCs. The findings indicate that a two-layer artificial neuron network (ANN) with six input variables and these include (outside and inside temperature, pH, moisture content, oxygen level, relative humidity) with a total of eighty eight (88) data are used for the modeling purpose. The network with the highest regression coefficient (R) is 0.9967 and the lowest Mean Square Error (MSE) is 0.00012 (nearest to the value of zero) has been selected as the Optimum ANN model. The findings of this study suggest the most suitable ANN model that befits the research objective is ANN model with one (1) hidden layer with fifteen (15) hidden neurons. Additionally, it is critical to note that the results from the experiment and predicted model are in good agreement.

A Novel Solid Neuron-Network Chip Based on Both Biological and Artificial Neural Network Theories

Advances in Neural Networks — ISNN 2005 - Lecture Notes in Computer Science ◽

10.1007/11427391_76 ◽

2005 ◽

pp. 479-484 ◽

Cited By ~ 2

Author(s):

Zihong Liu ◽

Zhihua Wang ◽

Guolin Li ◽

Zhiping Yu

Keyword(s):

Neural Network ◽

Neuron Network ◽

Application of artificial neural network in neutron/gamma pulse shape discrimination for EJ301 scintillation detector

Science & Technology Development Journal - Engineering and Technology ◽

10.32508/stdjet.v4i2.803 ◽

2021 ◽

Vol 4 (2) ◽

pp. first

Author(s):

Chuân Văn Phan ◽

Hải Xuân Nguyễn ◽

Anh Ngọc Nguyễn ◽

Hải Xuân Phạm ◽

Phong Xuân Mai ◽

...

Keyword(s):

Neural Network ◽

Energy Region ◽

Pulse Shape ◽

Gamma Ray ◽

Pulse Shape Discrimination ◽

Shape Discrimination ◽

Neuron Network ◽

Neutron Measurement ◽

The scintilator detectors are sensitive to both neutron and gamma radiation. Therefore, right identification of the pulses which generated by neutrons or gamma ray from these detectors plays an important role in neutron measurement by using scintilator detector. In order to improve the ability to pulse shape discrimination (PSD), many PSD techniques have been studied, developed and applied. In this work, we use a basic configuration of a Fully connected Neural network (Fc- Net) where the number of elements of the network is minimum, and each element corresponds to identified specification of neutron or gamma pulses measured by using EJ-301 scintilator detector. The minimum of error principle has been applied for neuron network design; therefore, the accuracy of recognitions did not affect by this reduced network. The obtained results show that the identify accuracy of FcNet is higher than those of digital charge integration (DCI) method. Being tested using 60Co radioactive source, it is shown that, with the application of the FcNet, the accuracy of the gamma pulses discrimination acquires 98.60% in the energy region from 50 to 2000 keV electron equivalent energy (keVee), and 95.59% in the energy region from 50 to 150 keVee. In general, the obtained results indicate that the artificial neural network method can be applied to build neutron/gamma spectrometers with limited hardware.

Neuron Network Modeling of Intensification of Isogumulone Extraction in a Rotary Pulse Generator

Food Processing Techniques and Technology ◽

10.21603/2074-9414-2021-3-593-603 ◽

2021 ◽

pp. 593-603

Author(s):

Anton Shafrai ◽

Elena Safonova ◽

Dmitry Borodulin ◽

Yana Golovacheva ◽

Sergey Ratnikov ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Artificial Neural Networks ◽

Regression Model ◽

Test Data ◽

Pulse Generator ◽

Processing Temperature ◽

Neuron Network ◽

Introduction. Artificial neural networks are a popular tool of contemporary research and technology, including food science, where they can be used to model various technological processes. The present research objective was to develop an artificial neural network capable of predicting the content of isogumulone in a hop extract at given technological parameters of the rotary pulse generator. Study objects and methods. The mathematical modeling was based on experimental data. The isogumulone content in the hop extract I (mg/dm3) served as an output parameter. The input variables included: processing temperature t (°C), rotor speed n (rpm), processing time  (min), and the gap between the rotor teeth and stator s (mm). Results and discussion. The resulting model had the following parameters: two hidden layers, 30 neurons each; neuron activation function – GELU; loss function – MSELoss; learning step – 0.001; optimizer – Adam; L2 regularization at 0.00001; training set of four batches, 16 records each; 9,801 epochs. The accuracy of the artificial neural network (1.67%) was defined as the mean relative error. The error of the regression model was also low (2.85%). The neural network proved to be more accurate than the regression model and had a better ability to predict the value of the output variable. The accuracy of the artificial neural network was higher because it used test data not included in the training. The regression model when tested on test data showed much worse results. Conclusion. Artificial neural networks proved extremely useful as a means of technological modeling and require further research and application.

Reactivity margin evaluation software for WWR-c reactor

Nuclear Energy and Technology ◽

10.3897/nucet.4.31862 ◽

2018 ◽

Vol 4 (3) ◽

pp. 197-201

Author(s):

Ivan Belyavtsev ◽

Sergey Starkov

Keyword(s):

Neural Network ◽

Network Architecture ◽

Software Package ◽

Web Application ◽

Approximation Error ◽

Computational Experiments ◽

Neuron Network ◽

Artificial Neural ◽

Reactivity Margin

The WWR-c reactor reactivity margin can be calculated using a precision reactor model. The precision model based on the Monte Carlo method (Kolesov et al. 2011) is not well suited for operational calculations. The article describes the work on creating a software package for preliminary evaluations of the WWR-c reactor reactivity margin. The research has confirmed the possibility of using an artificial neural network to approximate the reactivity margin based on the reactor core condition. Computational experiments were conducted on training the artificial neural network using the precision model data and real reactor measured data. According to the results of the computational experiments, the maximum relative approximation error ∆k/k for fuel burnup was 3.13 and 3.56%, respectively. The mean computation time was 100 ms. The computational experiments showed it possible to construct the artificial neural network architecture. This architecture became the basis for building a software package for evaluating the WWR-c reactor reactivity margin – REST API based web-application – which has a convenient user interface for entering the core configuration. It is also possible to replenish the training sample with new measurements and train the artificial neuron network once again. The reactivity margin evaluation software is ready to be tested by the WWR-c reactor personnel and to be used as a component of the automated reactor refueling system. With minor modifications, the software package can be used for reactors of other types.

Modeling the neurodynamics of a biological neuron using a feedforward artificial neural network

[Proceedings 1992] IJCNN International Joint Conference on Neural Networks ◽

10.1109/ijcnn.1992.227141 ◽

2003 ◽

Author(s):

J.E. Steck ◽

J.S. Dalton

Keyword(s):

Neural Network ◽

Biological Neuron ◽

Artificial neural network in prediction of pelvic organ prolapse

Aspirantskiy Vestnik Povolzhiya ◽

10.17816/2072-2354.2020.20.3.132-137 ◽

2020 ◽

Vol 20 (5-6) ◽

pp. 132-137

Author(s):

Alexey V. Galkin ◽

Natalya G. Galkina ◽

Oleg I. Kaganov ◽

Nadezhda S. Karamysheva ◽

Ekaterina A. Kalinina ◽

...

Keyword(s):

Neural Network ◽

Pelvic Organ Prolapse ◽

Heart Valves ◽

Pelvic Organ ◽

Chronic Obstructive ◽

Neuron Network ◽

Obstructive Pulmonary Disease ◽

Artificial Neural ◽

Artificial Neural Network Ann

The aim of this study was to assess the possibility of using an artificial neural network in predicting pelvic organ prolapse. 180 patients were selected from the urological database, of which 62 had pelvic organ prolapse, in 118 cases prolapse was not detected. Data analysis was carried out with the use of the artificial neural network (ANN). As a result, the most important risk factors or predictors for the development of pelvic organ prolapse include the number of births, the number of pregnancies, chronic obstructive pulmonary disease, prolapse of the heart valves, as well as accessory chords, urinary incontinence before/after childbirth, BMI. Artificial neuron network can potentially be useful in decision-making on the development of preventive measures aimed at the prophylaxis of pelvic organ prolapse.

ANALISIS JARINGAN SARAF TIRUAN BACKPROPAGATION TERHADAP PERAMALAN NILAI TUKAR MATA UANG RUPIAH DAN DOLAR

BAREKENG JURNAL ILMU MATEMATIKA DAN TERAPAN ◽

10.30598/barekengvol8iss2pp27-32 ◽

2014 ◽

Vol 8 (2) ◽

pp. 27-32

Author(s):

Dorteus L. Rahakbauw

Keyword(s):

Neural Network ◽

Time Series ◽

Learning Rate ◽

Neuron Network ◽

Artificial Neural ◽

Artificial Neural Network Ann

Kurs atau nilai tukar mata uang. Jenis kurs ada tiga macam, yaitu kurs jual, kurs beli, dan kurs tengah. Kurs dibutuhkan untuk menentukan sesuatu yang perlu dilakukan yang berkaitan dengan kurs itu misalnya keputusan investasi jangka pendek, keputusan penganggaran modal, keputusan pembiayaan jangka panjang, dan penilaian laba. Oleh karena itu, perlu dilakukan upaya untuk memprediksi besarnya kurs untuk beberapa waktu ke depan. Permasalahan yang dihadapi adalah cara untuk memprediksi besarnya kurs yang menghasilkan nilai prediksi dengan tingkat kesalahan yang minimal. Peramalan merupakan suatu proses untuk memprediksi kejadian ataupun perubahan di masa yang akan datang. Dalam suatu proses kegiatan, proses peramalan ini merupakan awal dari suatu rangkaian kegiatan, dan sebagai titik tolak kegiatan berikutnya. Pemodelan time series seringkali dikaitkan dengan proses peramalan (forecasting) suatu nilai karakteristik tertentu pada periode kedepan, melakukan pengendalian suatu proses ataupun untuk mengenali pola perilaku sistem. Dengan mendeteksi pola dan kecenderungan data, kemudian memformulasikannya dalam suatu model, maka dapat digunakan untuk memprediksi data yang akan datang. Model dengan akurasi yang tinggi akan menyebabkan nilai prediksi cukup valid untuk digunakan sebagai pendukung dalam proses pengambilan keputusan.Salah satu metode peramalan yang berkembang saat ini adalah menggunakan Artificial Neural Network (ANN), dimana ANN telah menjadi objek penelitian yang menarik dan banyak digunakan untuk menyelesaikan masalah pada beberapa bidang kehidupan, salah satu diantaranya adalah untuk analisis data time series pada masalah Forecasting (Loh, 2003). Salah satu jaringan yang sering digunakan untuk prediksi data time series adalah Backpropagation neuron network. Dalam penelitan ini akan dibahas mengenai penggunaan jaringan saraf tiruan backpropagation untuk memprediksi kurs jual Rupiah (Rp) per 1 dolar amerika (USD). Dalam penelitian ini akan dibagi sebanyak 70% dari data yang ada sebagai pelatihan dan 30% dari data sebagai data pengujian. Dan dalam penelitian ini digunakan data kurs bulan Oktober 2013-Januari 2014, yang diambil dari situs Bank Indonesia. Dalam proses penelitian diperoleh Learning rate yang digunakan untuk data harian adalah 0.5, proses epoch berhenti pada iterasi ke-27088 untuk data harian, dengan pencapaian gradient sebesar 0,0081822 dan nilai R untuk pelatihan data sebesar 0,99494 yang berarti sangat baik. Selanjutnya data di uji dan memperoleh R sebesar 0,48638 yang berarti masih dikatakan baik untuk mempediksi data uji. Beberapa hal yang mempengaruhi hasil penelitian juga seperti data histories yang digunakan untuk variable masukkan JST kurang banyak, data yang digunakan untuk memprediksi kurs tidak bisa mewakili sebagai faktor utama yang mempengaruhi nilai kurs, dan batas nilai kesalahan yang kurang kecil serta kesesuaian bobot dalam arsitektur jaringan.