No abstract

No abstract

Application that able to predict plant growth patterns as function of nutrients obtained from fertilization pattern is very useful in agriculture, especially for research .It can be realized with support of biological sciences, mathematics, and computer technology, which popularly called by bioinformatics.The purpose of this research was to design and build a simulation system of fertilization effect on plants growth patterns with Backpropagation Neural Network. As the object of research is green mustard (Brassica Rapa). The parameters of growth modeling arethe number of seedling leaves and the length of leaves as function of changes in fertilizing elements (micro and macro) which are applied. First, green mustard are planted in the test field and then some fertilizing variations are applied for each plant. Fertilizing variations marked by variations of micro and macro nutrients in the applied fertilizer. The growth of each plant is monitored and recorded, from germination until the plant is ready for harvest. Observational data of plant growth then processed by Backpropagation Neural Network into a model of green mustard growth. From the model, software system of green mustard growth simulation as the function of fertilizing variations is built. The system testing is done using data obtained from direct observations at the plant field. Fertilization effects on green mustard growth patterns is evident in the increasing number of seedling leaves and length of leaves which indicates a reproductive improvement of the plant. Using Backpropagation Neural Network with five neuron in its hidden layer, the minimal error of the system achieved when the minimal epoch is 1000. Through experiment on several data variation of green mustard growth, the average obtained precision for NL (number of leaves) and LL (length of leaves) are 83% and 85%, respectively, which indicate that this system has achieved the expected target.

No abstract

PMS Employee Cooperative is a savings and loan cooperative which aims to provide storage and loan services to employees who work at PT. Pro Manunggal Solusi and does not yet have a Decision Support System (SPK). A decision support system is needed in determining the eligibility of cooperative loans to employees. This study aims to help simplify and accelerate and minimize errors that occur in the cooperative borrower feasibility assessment process. The method used for this decision is to use the Simple Additive Weighting (SAW) method. Six criteria are used for the loan eligibility assessment process, namely criteria 1 (Loan size), criterion 2 (Loan Purpose), criterion 3 (Salary), criterion 4 (Position), criterion 5 (Age), criterion 6 (Period of service). Based on the results of the calculation, it can be concluded that each loan employee will be approved according to the ranking and is limited by the balance. If the balance is sufficient, the loan will be approved, but if the balance is less, the loan will be rejected. Of the total value of the ranking results, loans approved with a sufficient balance were Susanto (0.82) with a 12.13% chance, Sentot Sudiyantono (0.80) with a probability of 11.83%, and Siswandi (0.73) with big chance 10.80%.

No abstract

Obstacles that occur today in the PT. Era ray Box still use manual calculation for the stock of rawmaterials, so the impact on the delay in the department information and management company itself. In additionthe company also often lose money because the number of ordering goods is increasing and are still usingmanual calculation so that the risk of causing an invalid calculation and not achieving the target onproduction.Genetic algorithms are search techniques in computer science to find a settlement forecasts foroptimization and search problems. The results of the optimization experiments that have been carried out, theresults obtained are different by comparing the 10 iterations, 100 iterations and 1000 iterations. From theexperiments performed by the user with a genetic algorithm system in the output of raw materials Dregs S.awal2438333333 kg, Dregs Exit 3002885622 kg, 342 kg S.awal spindles, spindles Exit 1069444444 kg, 988 kgS.awal Carton, Cardboard Exit 9358 kg, obtained the best fitness value is 28679.2.

No abstract