scholarly journals JARINGAN SYARAF TIRUAN ALGORITMA BACKPROPAGATION DALAM MEMPREDIKSI KETERSEDIAAN KOMODITI PANGAN PROVINSI RIAU

2017 ◽  
Vol 2 (2) ◽  
pp. 196-209
Author(s):  
Eka Pandu Cynthia, Edi Ismanto
Keyword(s):  
Processed Food ◽  
Training Process ◽  
Backpropagation Algorithm ◽  
Sweet Potatoes ◽  
Green Beans ◽  
Productivity Level ◽  
Actual Output ◽  
Input Variables ◽  
Food Commodities ◽  
Food Commodity

A system for predicting the availability of food commodities can help in making decisions. Artificial Neural Network is a method that is able to carry out mathematical processes for predicting the availability of food commodities. With the Backpropagation algorithm, the previous data processing is used as input to predict the availability of food commodities. Data processed as input variables are Area of ​​Harvest, Productivity Level, Number of Production and Number of Consumption Needs. While the processed food commodities are types of Rice, Corn, Soybeans, Peanuts, Green Beans, Cassava and Sweet Potatoes. The data was taken from 2006 to 2013. The years 2006 to 2012 were used as input data, while for 2013 they were targeted data. Some stages of Backpropagation are initializing weights, activating, calculating input weights and output biases and changing weights and biases. This stage will obtain the output to be achieved with the smallest error approach so that the predicted results of the availability of food commodities are obtained. The training process uses Matlab software tools 6.1. The result is a prediction of the amount of food commodity availability by the training and testing process producing actual output as the target achieved.

scholarly journals MENGKAJI PERILAKU HARGA KOMODITI PANGAN DI KOTA PALU MENGGUNAKAN METODE BACKPROPAGATION

2018 ◽  
Vol 15 (1) ◽  
pp. 58-68
Author(s):  
I N Peole ◽  
R Ratianingsih ◽  
D Lusiyanti
Keyword(s):  
Sweet Potato ◽  
Commodity Prices ◽  
Red Pepper ◽  
Green Beans ◽  
Yellow Corn ◽  
Backpropagation Method ◽  
Food Commodities ◽  
Hidden Layer ◽  
The Brain ◽  
Food Commodity

Artificial neural network is an information processing paradigm that is inspired by biological neural cell systems, like the brain, that processes information. The purpose of this research is to develop neural networks to predict the price of food commodities using backpropagation method. The research was conducted by using the rate of monthly price of food commodities in Palu from January 2011 - December 2015. The data is used to predict food commodity prices forduring 2016. The backpropagation networks consists of three layers. The first layer of input is constructedin the form of monthly prices of IR 64, ciherang, membramo, cimandi, superwin, sintanur, cisantana, sticky black, sticky white, yellow corn dry, white corn, soybeans, peanuts, green beans, cassava, sweet potato, onion, garlic, red pepper large, red pepper curls, cayenne pepper, cabbage round, potatoes, tomatoes, carrots, cauliflower, beans, onion, avocado, red apples, green apples, oranges, jackfruit, mango, pineapple, papaya, banana, banana horns, rambutan, bark, olive, durian, watermelon, and mangosteen from January – December that consist of 12 variables. One hidden layer consistof five neurons and the other one is the output, that is  the food commodity prices. The training process shows that on a maximum iterations on 500, constant learning rate 0,3 and 0,6 momentum, the predictions have 97.92% of level accuracy. The identification resultof food commodity prices behavior in Palu is predicted as follow: IR 64 Rp7.387, ciherang Rp8.182, membramo Rp8.150, cimandi Rp8.131, superwin Rp8.228, sintanur Rp8.660, cisantana Rp8.122, black sticky rice Rp21.383, white sticky rice Rp16.558, dry yellow corn Rp5.983, white corn Rp9.283, soybeans Rp14.600, peanuts Rp20.008, green beans Rp16.375, cassava Rp8.225, sweet potato Rp8. 542, red onion Rp28.550, garlic Rp21.208, red chili Rp27.308, curly red chili Rp23.650, cayenne Rp36.450, round cabbage Rp6.833, Rp12.067 potatoes, tomatoes Rp6.108, carrots 11.000, cauliflower Rp8.625, beans Rp10.333, scallion Rp25.242, avocado 11.000, red apple Rp29.023, green apple Rp31.067, orange Rp6.083, jackfruit Rp23.483, mango Rp11.187, pineapple Rp8.183, papaya Rp10.600, bananas Rp8.481, horn banana Rp2.683, rambutan Rp8.450, barking Rp5.625, tan Rp8.366, durian Rp19.208, watermelon Rp14.528 and mangosteen Rp18.067. It is predicted that the food commodity prices increased monthly.

COLOR CHANGES IN PIGMENT-FREE RESIDUES FROM GAMMA-IRRADIATED GREEN BEANS, BROCCOLI, SWEET POTATOES AND CARROTS

1960 ◽  
Vol 25 (6) ◽  
pp. 739-749 ◽  
Author(s):  
F. J. FRANCIS ◽  
G. E. LIVINGSTON ◽  
R. FRANCESCHINI ◽  
T. WISHNETSKY
Keyword(s):  
Sweet Potatoes ◽  
Green Beans ◽  
Color Changes ◽  
Gamma Irradiated

scholarly journals Total Arsenic Determination and Speciation in Infant Food Products by Ion Chromatography-Inductively Coupled Plasma-Mass Spectrometry

2004 ◽  
Vol 87 (1) ◽  
pp. 244-252 ◽  
Author(s):  
Nohora P Vela ◽  
Douglas T Heitkemper
Keyword(s):  
Inductively Coupled Plasma ◽  
Inorganic Arsenic ◽  
Dry Weight ◽  
Food Products ◽  
Arsenic Species ◽  
Arsenic Content ◽  
Infant Food ◽  
Sweet Potatoes ◽  
Green Beans ◽  
Inductively Coupled

Abstract Health risk associated with dietary arsenic intake may be different for infants and adults. Seafood is the main contributor to arsenic intake for adults while terrestrial-based food is the primary source for infants. Processed infant food products such as rice-based cereals, mixed rice/formula cereals, milk-based infant formula, applesauce and purée of peaches, pears, carrots, sweet potatoes, green beans, and squash were evaluated for total and speciated arsenic content. Arsenic concentrations found in rice-based cereals (63–320 ng/g dry weight) were similar to those reported for raw rice. Results for the analysis of powdered infant formula by inductively coupled plasma-mass spectrometry (ICP-MS) indicated a narrow and low arsenic concentration range (12 to 17 ng/g). Arsenic content in purée infant food products, including rice cereals, fruits, and vegetables, varies from <1 to 24 ng/g wet weight. Sample treatment with trifluoroacetic acid at 100°C were an efficient and mild method for extraction of arsenic species present in different food matrixes as compared to alternative methods that included sonication and accelerated solvent extraction. Extraction recoveries from 94 to 128% were obtained when the summation of species was compared to total arsenic. The ion chromatography (IC)-ICP-MS method selected for arsenic speciation allowed for the quantitative determination of inorganic arsenic [As(III) + As(V)], dimethylarsinic acid (DMA), and methylarsonic acid (MMA). Inorganic arsenic and DMA are the main species found in rice-based and mixed rice/formula cereals, although traces of MMA were also detected. Inorganic arsenic was present in freeze-dried sweet potatoes, carrots, green beans, and peaches. MMA and DMA were not detected in these samples. Arsenic species in squash, pears, and applesauce were not detected above the method detection limit [5 ng/g dry weight for As(III), MMA, and DMA and 10 ng/g dry weight for As(V)].

Determination of Lead and Cadmium in Foods by Anodic Stripping Voltammetry: II. Collaborative Study

1982 ◽  
Vol 65 (4) ◽  
pp. 978-986
Author(s):  
Stephen G Capar ◽  
Raymond J Gajan ◽  
Elizabeth Madzsar ◽  
Richard H Albert ◽  
Marion Sanders ◽  
...  
Keyword(s):  
Anodic Stripping Voltammetry ◽  
Collaborative Study ◽  
Stripping Voltammetry ◽  
Green Beans ◽  
Formula Milk ◽  
Lead And Cadmium ◽  
Anodic Stripping ◽  
Food Commodities ◽  
Cadmium And Lead ◽  
High Level

Abstract A dry ash anodic stripping voltammetric method for determining lead and cadmium in foods was collaboratively studied by 20 laboratories. The food commodities studied were strained green beans, beef (baby food), fish (mackerel), infant formula (milk base), apple juice, and cereal (wheat farina). Each collaborator analyzed 3 commodities, each consisting of 2 duplicate lead and cadmium fortification levels, for a total of 4 samples for each commodity. The low fortification levels ranged from 0.03 to 0.08 ppm for cadmium and from 0.05 to 0.15 ppm for lead. The high fortification levels ranged from 0.12 to 0.28 ppm for cadmium and from 0.24 to 0.45 ppm for lead. Each commodity was analyzed by 10 collaborators. The average overall reproducibilities of the low level fortifications were 247c for lead and 21% for cadmium; for the high level fortifications, average overall reproducibilities were 18% for lead and 16% for cadmium. The average accuracies of the collaborative results as measured by comparison to reference values were 96 and 97% for cadmium and lead, respectively. This method has been adopted official first action.

scholarly journals ANALISIS KETIMPANGAN WILAYAH DAN ARAHAN PENGEMBANGAN WILAYAH DI KABUPATEN BURU PROVINSI MALUKU

2018 ◽  
Vol 20 (4) ◽  
pp. 472
Author(s):  
Rifyan Ruman ◽  
Setia Hadi ◽  
Baba Barus
Keyword(s):  
Data Analysis ◽  
Agricultural Development ◽  
Health Facilities ◽  
Analysis Method ◽  
Sweet Potatoes ◽  
Green Beans ◽  
Location Quotient ◽  
Land Capability ◽  
Education And Health ◽  
Data Analysis Method

The purpose of this study was to determine the class-leading commodity and land capability and potential of land that can be used for agricultural development in Buru. Data analysis method used was overlying maps, Location Quotient (LQ) and Shift Share Analysis (SSA) to determine the main commodity. The result is elaborated as follow inequality in Buru can be seen from inadequate infrastructure especially the condition of road, education and health facilities. Based on analysis of LQ and SSA in the Buru Regency, Commodities priorities in this region are sweet potatoes, peanuts, green beans, peppers, onion, tomato, spinach, kale, squash, eggplant, beans, avocado, mango, jackfruit, durian, orange, papaya, banana, cashew, and clove. The potential cultivate land for each sub-districts as Namlea (22390.73 ha), District Waeapo (68615.62 ha), District of Waplau (22173.26 ha), District Batabual (7920.27 ha) and District Air Buaya (10985.77 ha) that can be utilized for the development of agriculture-based according to the vision of Buru and in accordance with the commodity that exist in each district.

scholarly journals APLIKASI JARINGAN SARAF TIRUAN DAN PARTICLE SWARM OPTIMIZATION UNTUK PERAMALAN INDEKS HARGA SAHAM BURSA EFEK INDONESIA

2017 ◽  
Vol 6 (1) ◽  
pp. 22
Author(s):  
Desy Wartati ◽  
Nur Aini Masruroh
Keyword(s):  
Particle Swarm Optimization ◽  
Stock Price ◽  
Particle Swarm ◽  
Computation Time ◽  
Bp Algorithm ◽  
Stock Index ◽  
Ann Model ◽  
Training Process ◽  
Backpropagation Algorithm ◽  
Swarm Optimization

Jakarta Composite Index (JCI) is the main stock index in Indonesia Stock Exchange, which indicates the movement of the performance of all stocks listed. The data of stock price index often experience rapid fluctuations in a short time, so it is needed to carry out an analysis to help investor making the right investment decisions. Forecasting JCI is one of the activities that can be done because it helps to predict the value of the stock price in accordance with the past patterns, so it can be a consideration to make a decision. In this research, there are two forecasting models created to predict JCI, which are Artificial Neural Network (ANN) model with (1) Backpropagation algorithm (BP) and (2) Backpropagation algorithm model combined with Particle Swarm Optimization algorithm (PSO). The development of both models is done from the stage of the training process to obtain optimal weights on each network layer, followed by a stage of the testing process to determine whether the models are valid or not based on the tracking signals that are generated. ANN model is used because it is known to have the ability to process data that is nonlinear such as stock price indices and PSO is used to help ANN to gain weight with a fast computing time and tend to provide optimal results. Forecast results generated from both models are compared based on the error of computation time and forecast error. ANN model with BP algorithm generates computation time of training process for 4,9927 seconds with MSE of training and testing process is respectively 0,0031 and 0,0131, and MAPE of forecast results is 2,55%. ANN model with BP algorithm combined with PSO generates computation time of training process for 4,3867 seconds with MSE of training and testing process is respectively 0,0030 and 0,0062, and MAPE of forecast result is 1,88%. Based on these results, it can be concluded that ANN model with BP algorithm combined with PSO provides a more optimal result than ANN model with BP algorithm.

scholarly journals Sifat fisik makanan padat (foodbar) berbasis tepung komoditas lokal

2020 ◽  
Vol 4 (1) ◽  
pp. 32-38
Author(s):  
Anni Nuraisyah
Keyword(s):  
Sweet Potato ◽  
Fast Food ◽  
Raw Materials ◽  
Content Volume ◽  
Composite Flour ◽  
Potato Flour ◽  
Sweet Potatoes ◽  
Green Beans ◽  
Bean Flour ◽  
Sweet Potato Flour

Consumption of fast food continuously can be detrimental to human health. An effective solution is to make innovative food that is able to meet the adequacy of nutrition, one of which is foodbar. The raw materials used in the manufacture of foodbar come from local commodities which are flourished, including sweet potatoes, green beans and Moringa and added porang to unite the three ingredients. Yellow sweet potato flour contains 77.7% carbohydrates with high digestibility (98%), while Moringa leaf flour contains 27.1 grams / 100 grams protein. Mung bean flour is used as a flavoring agent, while porang flour which is rich in glucomannan acts as a binder agent to produce foodbar products that are not easily destroyed. The treatment in this study used two factors, namely the composition of the composite flour and the composition of the addition of porang. Observations made include physical properties including water content, volume expansion, kamba density and texture of the foodbar. The best treatment on the foodbar was the combination treatment of 100 grams of yellow sweet potato flour (40 grams) green bean flour (60 grams) moringa leaf flour and (4%) porang (P3T1).

scholarly journals Validation of A MS Based Proteomics Method for Milk and Egg Quantification in Cookies at The Lowest VITAL Levels: An Alternative to The Use of Precautionary Labeling

2020 ◽  
Author(s):  
Linda Monaci ◽  
Elisabetta De Angelis ◽  
Rocco Guagnano ◽  
Aristide P. Ganci ◽  
Iganzio Garaguso ◽  
...  
Keyword(s):  
Processed Food ◽  
Scenario Development ◽  
Food Industries ◽  
Promising Tool ◽  
Total Milk ◽  
Contamination Levels ◽  
Food Commodities ◽  
Reference Doses ◽  
Voluntary Basis ◽  
Labelling System

The prevalence of food allergy has increased over the last decades and consequently the food labeling policies have improved over the time in different countries to regulate allergen presence in foods. In particular, Reg 1169 in EU mandates the labelling of 14 allergens whenever intentionally added to foods, but the inadvertent contamination by allergens still remains uncovered topic. In order to warn consumers on the risk of cross-contamination occurring in certain categories of foods, a precautionary allergen labelling system has been put in place by food industries on voluntary basis. In order to reduce the overuse of PAL, reference doses and action limits have been proposed by the VITAL project representing a guide in this jeopardize scenario. Development of sensitive and reliable mass spectrometry methods are therefore of paramount importance in this regard to check the contamination levels in foods. In this paper we describe the development of a managed time MRM method based on a triple quadrupole platform for milk and egg quantification in processed food. The method was in house validated and allowed to achieve levels of proteins lower than 0.2mg of total milk and egg proteins respectively in cookies, challenging the doses recommended by VITAL. The method was finally applied to cookies labeled as milk and egg-free. This method could represent in perspective a promising tool to be implemented along the food chain to detect even tiny amounts of allergens contaminating food commodities.

scholarly journals MEASUREMENT OF COOPERATIVE PRODUCTIVITY LEVEL: IN ACEH: THE MALMQUIST INDEX APPROACH

2021 ◽  
Vol 23 (1) ◽  
pp. 48
Author(s):  
Azhari Azhari ◽  
Kamaruddin Kamaruddin
Keyword(s):  
Cooperative Education ◽  
Malmquist Index ◽  
Business Climate ◽  
Productivity Level ◽  
Index Approach ◽  
Input Variables ◽  
The Government ◽  
Third Line ◽  
Using Data ◽  
Index Value

Based on article 33 of the 1945 constitution, cooperatives are the backbone of Indonesia national economy. However, the hopes of cooperative to become the locomotive of the Indonesian economy are still far from expectation. the purpose of this research to measure the level of productivity and efficiency of cooperatives by using Data Envelopment Analysis and Malmquist Index analysis tools. Input variables used are own capital, external capital, labor, and members, while the output variable is turnover and the surplus (SHU) cooperatives from 23 districts/cities in Aceh from 2014 to 2016. Test results show that cooperatives that have an index value-efficient only in seven districts / cities, while in terms of productive cooperatives in Aceh as many as 14 districts/cities in Aceh. It is expected that policymakers in fostering and empowering cooperatives in Aceh, both from the government and cooperative management and other stakeholders, can improve cooperative performance through cooperative education and training for cooperative human resources, provide a conducive business climate and provide capital loans with easy schemes for cooperative. The limitation of this study is that the types of cooperatives used are cooperatives as a whole not classifying cooperative types. Testing the level of efficiency and productivity of cooperatives with various types of cooperatives that exist is a special attraction The objective is in the third line, the method is in the fourth line, the results and discussion are in the sixth line, the conclusions and suggestions are on the eighth line and so on.

Sign in / Sign up

Export Citation Format

Share Document