scholarly journals Penerapan Jaringan Syaraf Tiruan dalam Memprediksi Tingkat Kriminal di Kabupaten Simalungun Menggunakan Algoritma Backpropagation

2019 ◽  
Vol 1 (1) ◽  
pp. 64-73
Author(s):  
Muhammad Julham ◽  
S Sumarno ◽  
Fitri Anggraini ◽  
Anjar Wanto ◽  
S Solikhun
Keyword(s):  
Architectural Model ◽  
Architectural Models

The number of criminal rates that occur in the area of Simalungun Regency each year experiences an increase and decrease in crime cases each year. For example in the types of gambling crimes, in 2012 there were 89 cases, in 2013 there were 102 cases, in 2014 there were 92 cases, in 2015 there were 102 cases, in 2016 there were 94 cases, and in 2017 there were 86 cases. Then this problem is used as a basis in this study, which aims to provide information in the form of prediction data to the police in an effort to anticipate the rise in cases of types of crime in the following year. Efforts are being made to predict the level of crime in Simalungun Regency by applying the Bacpropagation algorithm ANN method. This research uses MATLAB R2011b and uses 5 architectural models to test the data that will be used for etimation / prediction, namely models 4-20-1, 4-30-1, 4-40-1, 4-50-1, 4- 70-1. Then the best architectural model results obtained are architectural models 4-20-1 with an accuracy of 93%, with the number of epochs 4575 in 51 seconds and MSE of 0,0009995011. This model will be used to predict Criminal Levels in Simalungun District from 2018 to 2022 with an accuracy of 93%.

Architectural Models for Reliable Multi-User Interfaces

2012 ◽  
pp. 76-91
Author(s):  
Mario Ciampi ◽  
Antonio Coronato ◽  
Giuseppe De Pietro ◽  
Luigi Gallo
Keyword(s):  
Complex Systems ◽  
Formal Methods ◽  
User Interfaces ◽  
Interactive Systems ◽  
Input Devices ◽  
Agent Based ◽  
Architectural Model ◽  
Architectural Models ◽  
Interface Standardization

Virtual Environments are complex systems in that they involve the crucial concept of sharing. Users can share knowledge of each other’s current activities, environments, and actions. In this chapter, the authors discuss about interaction interoperability, intended to mean the ability of two or more users to cooperate despite the heterogeneity of their interfaces. To allow such interoperability, formal methods to formalize the knowledge and middleware solutions for sharing that knowledge are required. After introducing the state-of-the-art solutions and the open issues in the field, the authors describe a system for providing interaction interoperability among multi-user interfaces. Rather than focusing on the de-coupling of input devices from interaction techniques and from interaction tasks, this chapter suggests integrating interactive systems at higher level through an interface standardization. To achieve this aim, the authors propose: i) an architectural model able to handle differences in input devices and interaction tasks; ii) an agent-based middleware that provides basic components to integrate heterogeneous user interfaces. The chapter also presents a case study in which an agent-based middleware is used to support developers in the interconnection of monolithic applications.

A MODEL-DRIVEN APPROACH TO WEAVE ARCHITECTURAL STYLES INTO SERVICE-ORIENTED ARCHITECTURES

2011 ◽  
Vol 20 (02) ◽  
pp. 201-220 ◽  
Author(s):  
MARCOS LÓPEZ-SANZ ◽  
JUAN MANUEL VARA ◽  
ESPERANZA MARCOS ◽  
CARLOS E. CUESTA
Keyword(s):  
Software Engineering ◽  
Architectural Style ◽  
Service Oriented Architectures ◽  
Model Driven Development ◽  
Model Driven ◽  
Architectural Styles ◽  
Architectural Model ◽  
Service Oriented ◽  
Architectural Models ◽  
Model Driven Approach

Model-driven development is recognized as one of the most promising approaches in software engineering. Recent research in the area highlights the importance of using an explicit architectural model in this context. Since service-oriented architectures have also demonstrated to be adequate to overcome current software needs, the idea of using the model-driven approach to generate service-oriented architectural models has successfully flourished in the last years. However, the emphasis on the Service-Oriented Computing (SOC) paradigm has led to the design of architectures lacking some desirable features. Knowing the benefits provided by architectural styles, we have found that their use can help us to overcome those needs. Our goal is to obtain a service-oriented model which satisfies the requirements of the concrete architecture and complies with the constraints and vocabulary defined for a specific architectural style. To achieve this, here, we propose to use a weaving model which merges the concrete architectural model with a model of the architectural style of choice.

scholarly journals Desarrollo arquitectónico de tres especies de Acacia

2017 ◽  
pp. 7
Author(s):  
Amparo Echeverry-Gómez ◽  
Henricus F.M. Vester
Keyword(s):  
Related Species ◽  
Development Pattern ◽  
Vegetative Development ◽  
Development Patterns ◽  
Legume Trees ◽  
Branching Patterns ◽  
Architectural Model ◽  
Architectural Models ◽  
Do So

Studies about the vegetative development of Legume trees are relatively rare. In order to infer about the evolution of different development patterns a study of taxonomically related species is requiered. We analyzed three species of Acacia (A . collinsii, A. cedilloi and A. dolichoslachya) which according to preliminary observations show branching patterns as defined in the architectural model of Troll or Champagnat in order to answer the question which is the evolutionary relation between these models. We describe the development pattern of these species and found that a combination of architectural models is needed to do so. We found that mixed plagiotropic axes in A. collinsii are relayed by orthotropic axes during development and open a discussion to the evolutionary origen of the mixed axis.

scholarly journals MODEL ARSITEKTUR NEURAL NETWORK DENGAN BACKPROPOGATION PADA PREDIKSI TOTAL LABA RUGI KOMPREHENSIF BANK UMUM KONVENSIONAL

2018 ◽  
Vol 5 (2) ◽  
pp. 147 ◽  
Author(s):  
Agus Perdana Windarto ◽  
Muhammad Ridwan Lubis ◽  
Solikhun Solikhun
Keyword(s):  
Neural Network ◽  
Mean Square Error ◽  
Financial Services ◽  
Back Propagation ◽  
Mean Square ◽  
Comprehensive Income ◽  
Income Statement ◽  
Architectural Model ◽  
Testing Accuracy ◽  
Architectural Models

<p><em>determine the marketing strategy in increasing the total comprehensive income. This study aims to create the best architectural model using Backpropogation where this model can later be made to make predictions of total comprehensive income. The variable used in this study is the total comprehensive income statement data of PT. Bank Mandiri, Tbk (January - November 2016). Data sourced from the Financial Services Authority (www.ojk.go.id). From a series of trials conducted with 4 architectural models tested, namely 4-25-1; 4-50-1; 4-100-1 and 4-50-75-1, obtained the best architectural model 4-50-1 with Epoch training = 1977, Mean Square Error (MSE) of 0,000997867 with the correctness of testing accuracy reaching 80%.</em></p><p><strong><em>Keywords</em></strong><em>: Artificial Neural Network, Back-propagation, Comprehensive Income, Prediction, Economy, Architecture</em><em> </em></p><p><em>Prediksi total laba rugi komprehensif sangatlah penting untuk memprediksi dimana posisi angka total laba rugi komprehensif pada suatu bank.  Informasi tersebut berguna bagi masayarkat dalam menentukan arah investasi masyarakat ke depan, begitu juga bagi pihak bank berguna untuk menentukan kebijakan strategi pemasaran dalam meninggkatkan total laba komprehensif tersebut. Penelitian ini bertujuan untuk membuat model arsitektur terbaik dengan menggunakan Backpropogation dimana model ini nantinya dapat dilakukan untuk membuat prediksi terhadap total laba rugi komprehensif. Variabel yang digunakan pada penelitian ini adalah data total laba rugi komprehensif PT. Bank Mandiri,Tbk (Januari – November 2016). Data bersumber dari Otoritas Jasa Keuangan (<a href="http://www.ojk.go.id/">www.ojk.go.id</a>). Dari serangkaian uji coba yang dilakukan dengan 4 model arsitektur yang diuji yakni 4-25-1; 4-50-1; 4-100-1 dan 4-50-75-1, diperoleh model arsitektur terbaik 4-50-1 dengan </em><em>Epoch training = 1977</em><em>, </em><em>Mean Square Error (MSE) sebesar </em><em>0,000997867 dengan </em><em>tingkat akurasi pengujian mencapai kebenaran 80%.</em><em> </em></p><p><strong><em>Kata kunci</em></strong><em>: Jaringan saraf tiruan, Back-propagation, Laba Rugi Komprehensif, Prediksi, Ekonomi, Arsitektur</em></p>

scholarly journals Wandering Among Models: Stendhal, Proust, Sebald

1970 ◽  
Vol 26 ◽  
pp. 165-182
Author(s):  
Mari Lending
Keyword(s):  
Art Criticism ◽  
Marcel Proust ◽  
Plaster Cast ◽  
East Anglia ◽  
Detailed Model ◽  
Architectural Model ◽  
Architectural Models ◽  
The Temple ◽  
Real Places

This paper draws on twofold fictional landscapes; the imaginary landscapes emerging in the writings of Stendhal, Marcel Proust and W.G. Sebald as well as the invented landscapes evoked by the architectural model. Stendhal’s extensive travels are reflected in his novels, several memoirs, art criticism and guidebooks. Similarly, the topic of travelling saturates Sebald’s fiction and essays: the restless flight and the contemplative promenade in various ways frame his outstanding and existential configurations of architecture. Despite the fact that the protagonist of A la recherche is a reluctant and anxious traveler, the longing for experiencing new places are of profound importance in Proust’s oeuvre. One after another, the architectural models in Stendhal’s Mémoires d’un touriste (1838), Proust’s A l’Ombre des jeunes Filles en fleurs (1918) and Sebald’s The Rings of Saturn (1995) destabilize the rapports between descriptions and geographies, fantasies and landscapes. In Stendhal, Proust and Sebald (almost) real places and real models are inscribed in imaginary journeys, presenting landscapes in which we, the readers, can wander among models, guided by the protagonist-narrator. The collection of cork models of Roman monuments Stendhal encounter at Nîmes, the plaster cast of the doorway of the ‘Persian’ Balbec Church ad the Trocadéro Museum in Paris, and the hyper-detailed model of the temple of Jerusalem that ‘Sebald’ comes across walking through East Anglia on foot, in complex ways unfolds the powerful autonomy of the architectural model.

scholarly journals Artificial Neural Network Pada Industri Non Migas Sebagai Langkah Menuju Revolusi Industri 4.0

2019 ◽  
Vol 4 (1) ◽  
pp. 155-160
Author(s):  
Iin Parlina ◽  
Anjar Wanto ◽  
Agus Perdana Windarto
Keyword(s):  
Sensitivity Analysis ◽  
Oil And Gas ◽  
Oil Industry ◽  
Oil Processing ◽  
Software Model ◽  
Beverage Industry ◽  
Architectural Model ◽  
Architectural Models ◽  
Artificial Neural ◽  
The Republic

The research conducted aims to make predictions with artificial neural metwork (backpopagation) and sensitivity analysis in the non-oil processing industry for the value of industrial exports. Data was obtained from the Badan Pusat Statistik (BPS) in collaboration with the Ministry of Industry of the Republic of Indonesia in the last 7 years (2011-2017). The process is carried out by dividing the data into 2 parts (training and testing) to obtain the best architectural model. The data processing uses the help of Matlab 6.0 software. Model selection is done by try and try to get the best architectural model. In this study using 7 architectural models (15-2-1; 15-5-1; 15-10-1; 15-15-1; 15-2-5-1; 15-5-10-1 and 15- 10-5-1) who have been trained and tested. By using the help of Matlab 6.0 software, the best architectural model is obtained 15-2-1 with an accuracy rate of 93%, epoch training = 189,881, MSE testing = 0.001167108 and MSE training = 0,000999622. The best architecture will be continued to predict the non-oil industry based on the most dominant export value using sensitivity analysis. From the architectural model a prediction of 5 out of 15 non-oil and gas industries contributes: Food & Beverage Industry, Textile & Apparel Industry, Basic Metal Industry, Rubber Industry, Rubber and Plastic Goods and Metal Goods Industry, Not Machines and Equipment , Computers, Electronics and Optics.

scholarly journals MODEL ALGORITMA RESILIENT BACKPROPAGATION DALAM MEMPREDIKSI EKSPOR BIJIH COKLAT MENURUT NEGARA TUJUAN UTAMA DALAM MENDORONG LAJU PERTUMBUHAN EKONOMI

2019 ◽  
Vol 2 (2) ◽  
pp. 67-75
Author(s):  
Sundari Retno Andani Neno ◽  
Rafiqa Dewi Rafiqa ◽  
Solikhun Lihun
Keyword(s):  
Economic Growth ◽  
Cocoa Beans ◽  
Architectural Model ◽  
The Future ◽  
Ann Models ◽  
Architectural Models ◽  
The Government

The purpose of this study predicts the export of brown ore according to the country the main objective in driving the pace of economic growth. Cocoa beans including plantation products are exported and are very profitable for Indonesia. However, the quality of cocoa beans exported by Indonesia is known to be low. The low quality of Indonesian cocoa is due to several reasons, including rare Indonesian cocoa beans which are fermented first. Indonesia is an exporter of cocoa beans. The government must be able to predict brown ore exports in the future so that the government can take steps or policies on how to make reliable strategies in an effort to increase the export of brown ore in the future. Backpropagation is one of the ANN models that has the ability to get a balance between the ability of the network to recognize patterns used during training and the ability of the network to respond correctly to input patterns that are similar (but not the same) to the patterns used during training. After a training experiment and testing of architectural models 12-4-1, 12-8-1, 8-12-1, and 8-16-1, the best architectural model was 12-12-1 with 100% accuracy.

scholarly journals Stemflow and throughfall on several tree architectural models

2021 ◽  
Vol 918 (1) ◽  
pp. 012002
Author(s):  
R Y K S Wibowo ◽  
R Hermawan ◽  
S B Rushayati
Keyword(s):  
Water Conservation ◽  
Urban Forest ◽  
Linear Regression Analysis ◽  
Multiple Linear Regression Analysis ◽  
Area Index ◽  
Architecture Model ◽  
Architectural Model ◽  
Architectural Models ◽  
The Difference ◽  
Hemispherical Photograph

Abstract The aim of developing urban forests for steep areas is to prevent erosion. Erosion can be caused by stemflow and throughfall. The difference in stemflow and throughfall is thought to be due to differences in the tree architecture model. The study investigates the effects of several tree architectural models on the amount of stemflow and throughfall. It is hoped that data and information of this research can be taken into consideration in selecting tree species for the benefit of soil and water conservation in urban forest areas that have the potential for erosion and sedimentation. The collection and processing of data comprised the rainfall data obtained from Meteorological Climatological and Geophysical Agency, measurement of leaf area index using a hemispherical photograph and Hemiview 2.1 software, measurement of stemflow and throughfall in five tree architectural models (Massart, Aubreville, Koriba, Rauh, and Troll). Afterward, the relationship between the dependent and independent variables is known through multiple linear regression analysis using Minitab 16 software. The result showed that the tree architectural model influences stemflow and throughfall. The tree architectural model with the highest stemflow and throughfall is Rauh, and the lowest belongs to the Massart architectural model. The tree architectural model that can be used for land and water conservation is Massart; the species is Diospyros discolor Willd.

scholarly journals IDENTIFIKASI MODEL ARSITEKTUR JENIS POHON FAMILI LAURACEAE DI KAWASAN ARBORETUM SYLVA UNIVERSITAS TANUNGPURA PONTIANAK

2019 ◽  
Vol 7 (3) ◽  
Author(s):  
Evlin Sitanggang ◽  
Togar Fernando Manurung ◽  
Slamet Rifanjani
Keyword(s):  
Research Method ◽  
Tree Architecture ◽  
Physical Contact ◽  
Family Tree ◽  
Deep Roots ◽  
Dominant Form ◽  
Architecture Model ◽  
Architectural Model ◽  
Architectural Models ◽  
A Site

The tree architecture model is one of the important morphological features of the plants in characterizing each tree. Trees are plants with woody stems, deep roots, and have branches far from the ground and are more than 3 meters high (Hakim and Utomo 2003). trees are also one of the soft elements (softcape) that are very often used in the development of a site or landscape with a variety of unique characteristics. One of the unique characteristics of a tree is the dominant form of tree architecture formed by its canopy. This research was carried out at the Sylva Arboretum in Tanjungpura Pontianak for 3 weeks starting from July 4 2018 to July 24 2018 to observe and identify the architectural model of the lauraceae family tree. The research objective was to determine the architectural model of the Lauraceae family tree in Sylva Arboretum in Tanjungpura University Pontianak. The research method used is the exploration method, which is done by roaming, which means that observations can be made with visual and physical contact. Based on the results of the research and discussion, lauraceae family tree architecture models found in the Arboretum Sylva Area of Tanjungpura University Pontianak as many as four architectural models namely Rauh, Roux, Petit and Scarrone. The four architectural models were found in six species of trees, namely Ulin (Eusideroxylon zwageri), Medang sahung (Achiodaphne glabra), Medang pasir (Litsea eliptica), Medang bubur (Litsea resinosa), Medang sisik (Dehaasia firma), and Kayu manis (Cinnamomum iners).Keyword: Family of Lauraceae, Model of Tree Architecture, Sylva Arboretum

JARINGAN SYARAF TIRUAN DALAM MEMPREDIKSI JUMLAH PRODUKSI DAGING SAPI BERDASARKAN PROVINSI

2018 ◽  
Vol 2 (1) ◽  
Author(s):  
Ahmad Revi ◽  
Solikhun Solikhun ◽  
M Safii
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Meat Production ◽  
Beef Production ◽  
Architectural Model ◽  
Architectural Models ◽  
Artificial Neural ◽  
Input Variables ◽  
The Government ◽  
Target Data

Prediction is a process for estimating how many needs will be in the future. This study aims to predict the amount of beef production by province. Beef is one source of protein which is also a high value comodities. Meat production in Indonesia in general tends to increase by around 2.76% per year. But along with the increase in beef production in Indonesia, the level of meat consumption in Indonesia tends to fluctuate in recent years. Imports are the most common step taken by the government to meet domestic beef needs. By using the Artificial Neural Network and backpropagation algorithm, it will be predicted the amount of beef production based on the province in order to determine the steps to meet domestic beef demand based on the amount of beef consumption in the community. This study uses 11 input variables, namely data from 2005 to 2016 with 1 target, data of 2017. Using 5 architectural models to test the data to be used for prediction, the 11-4-1 model, 11-8-1 , 11-18-1, 11-20-1 and 11-28-1. Obtained the results of the best architectural model is the 11-28-1 architectural model with truth accuracy of 100%, the number of epochs 15 and MSE is 0.008623197. This model will be used in predicting the amount of beef production by province.Keywords : Beef production, prediction, backpropagatin, Artificial Neural Network

Sign in / Sign up

Export Citation Format

Share Document