Garuda - Garba Rujukan Digital

Analisis Accelerated Learning Pada Algoritma Backpropagation Menggunakan Adaptive Learning Rate Ermawati, Ermawati; Nababan, Erna Budhiarti; Mawengkang, Herman
SAMUDERA Vol 8, No 1 (2014)
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar

Jaringan syaraf tiruan backpropagation merupakan algoritma pembelajaran yang terawasi dimana output dari jaringan dibandingkan dengan target yang diharapkan sehingga diperoleh error output. Banyak model pembelajaran yang menggunakan algoritma backpropagation. Namun algoritma backpropagation mempunyai keterbatasan yaitu laju konvergensi yang cukup lambat. Pada penelitian ini penulis menambahkan parameter learning rate secara adaptif pada setiap iterasi dan koefisien momentum untuk menghitung proses perubahan bobot. Dari hasil simulasi komputer maka diperoleh perbandingan antara algoritma backpropagation standar dengan backpropagation adaptive learning. Untuk algoritma backpropagation standar kecepatan konvergensi mencapai 1000 epoch dengan nilai Mean Square Error (MSE) yang dihasilkan adalah 0,00044 sedangkan untuk algoritma backpropagation adaptive learning hanya 72 epoch dengan nilai Mean Square Error (MSE) yang dihasilkan 0.0000036. Hal ini menunjukkan bahwa algoritma backpropagation adaptive learning lebih cepat mencapai konvergensi daripada algoritma backpropagation standar.

Uncertainty Ontology for Module Rules Formation Waterwheel Control Azmi, Zulfian -; Nasution, Mahyuddin K. M.; Mawengkang, Herman; Zarlis, M
Scientific Journal of Informatics Vol 5, No 1 (2018): May 2018
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v5i1.14188

Implementation of Uncertainty model has not given maximum result in forming rule on an inference of a case. For testing to determine whether water quality is high, medium and low. The input variables used are temperature, pH, salinity and Disolved Oxygen. Testing is done by looking at the water turbidity change in the shrimp pond, to determine the water quality. Its water quality determines in the control module of the waterwheel rotation.Rolling the waterwheel moves quickly if pond water quality is low, moving slowly if water quality is medium and immobile if water quality is good. And the establishment of the rule with the approach of knowledge of Ontology to determine the relation between several variables (temperature, Ph, Disolved Oxygen and salinity). Each variable is set to its certainty value in the form of fuzzy value. Next is determined the relation of the four variables for the formation of rule.

Uncertainty Ontology for Module Rules Formation Waterwheel Control Azmi, Zulfian -; Nasution, Mahyuddin K. M.; Mawengkang, Herman; Zarlis, M
Scientific Journal of Informatics Vol 5, No 1 (2018): May 2018
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v5i1.14188

Implementation of Uncertainty model has not given maximum result in forming rule on an inference of a case. For testing to determine whether water quality is high, medium and low. The input variables used are temperature, pH, salinity and Disolved Oxygen. Testing is done by looking at the water turbidity change in the shrimp pond, to determine the water quality. Its water quality determines in the control module of the waterwheel rotation.Rolling the waterwheel moves quickly if pond water quality is low, moving slowly if water quality is medium and immobile if water quality is good. And the establishment of the rule with the approach of knowledge of Ontology to determine the relation between several variables (temperature, Ph, Disolved Oxygen and salinity). Each variable is set to its certainty value in the form of fuzzy value. Next is determined the relation of the four variables for the formation of rule.

Perbandingan Algoritma Stochastic Gradient Descent dan Naïve Bayes Pada Klasifikasi Diabetic Retinopathy Hadistio, Ryan Rinaldi; Mawengkang, Herman; Zarlis, Muhammad
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 6, No 1 (2022): Januari 2022
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v6i1.3426

The purpose of this research is to compare the performance of the Stochastic Gradient Descent and Naïve Bayes algorithms in classifying Diabetic Retinopathy. Diabetic retinopathy is a complication of diabetes that causes damage to the retina of the eye. These disturbances can be detected by early detection through data extracted from eye images. This research uses source data from the UCI Machine Learning Repository, namely Diabetic Retinopathy Debrecen, totaling 1,151 data records with 19 attributes consisting of 18 attributes and 1 target attribute. The validation test uses the Cross Validation method with a total of 10 k. From the comparison of the two proposed methods, the Stochastic Gradient Descent algorithm produces an average test accuracy of 70.16%, while Naïve Bayes produces an average accuracy of 56.74%. From the comparison of the two algorithms, the Stochastic Gradient Descent algorithm is known to be superior in classifying the Diabetic Retinopathy Debrecen Dataset.

Heuristic algorithm for portfolio selection with minimum transaction lots . Afnaria; Herman Mawengkang
Proceedings of The Annual International Conference, Syiah Kuala University - Life Sciences & Engineering Chapter Vol 3, No 2 (2013): Engineering
Publisher : Syiah Kuala University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (171.531 KB)

Portfolio selection problem was first formulated in a paper written by Markowitz, where investment diversification can be translated into computing. Mean-variance model he introduced has been used and developed because of it’s limitations in the larger constraints found in the real world, as well as it’scomputational complexity which found when it used in large-scale portfolio. Quadratic programming model complexity given by Markowitz has been overcome with the development of the algorithm research. Theyintroduce a linear risk function which solve the portfolio selection problem with real constraints, i.e. minimum transaction lots. With the Mixed Integer Linear models, proposed a new heuristic algorithm that starts from the solution of the relaxation problems which allow finding close-to-optimal solutions. This algorithm is built on Mixed Integer Linear Programming (MILP) which formulated using nearest integer search method.

Application of The MOORA Method and Rank Order Centroid for Admission Recommendation System Power Programmer Ryan Rinaldi Hadistio; Herman Mawengkang; Muhammad Zarlis
CESS (Journal of Computer Engineering, System and Science) Vol 7, No 1 (2022): January 2022
Publisher : Universitas Negeri Medan

Riset ini bertujuan untuk menerapkan sistem pendukung keputusan menggunakan kombinasi metode MOORA dengan pembobotan Rank Order Centroid pada penentuan rekomendasi dalam penerimaan tenaga programmer. Kriteria yang dijadikan sebagai parameter dan tolak ukur dalam penilaian penerimaan tenaga programmer pada penelitian ini sebanyak 7 kriteria yang terdiri atas HTML dan CSS (C1), Jquery dan Javascript (C2), PHP (C3), Java (C4), Android (C5), .NET (C6), dan MySQL (C7). Sampel data yang diujikan pada penelitian ini berjumlah 5 alternatif dari data pelamar yang mengajukan diri sebagai tenaga programmer. Pengujian perhitungan yang dilakukan dengan menerapkan metode yang diusulkan memperoleh hasil yaitu dapat memberikan keputusan rekomendasi pelamar yang layak untuk diterima pada posisi tenaga programmer.

REVIEW MODEL EOQ UNTUK INVENTORI FARMASI RUMAH SAKIT DENGAN ADANYA PERMINTAAN BERVARIASI TERHADAP WAKTU Afnaria Afnaria; Tulus Tulus; Herman Mawengkang; Wiryanto Wiryanto
JISTech (Journal of Islamic Science and Technology) Vol 3, No 1 (2018)
Publisher : UIN Sumatera Utara Medan

Permintaan merupakan faktor penting guna menentukan jumlah persediaan inventori farmasi di rumah sakit. Sistem inventori farmasi dimana ukuran permintaannya diketahui merupakan sistem deterministik, dan sebaliknya disebut sistem dinamis, dimana permintaan dapat berubah dari waktu ke waktu. Model EOQ merupakan model inventori yang paling sering digunakan sampai saat ini. Model ini mengasumsikan permintaan stasioner sepanjang waktu tak berhingga, dimana inventori dimonitor secara kontinu dan re-order dapat dilakukan kapan saja. Parameter biaya order dan biaya penyimpanan diasumsikan konstan. Namun model ini tidak mengijinkan adanya stockout. Studi ini bertujuan me-review model EOQ dimana permintaannya merupakan fungsi linier terhadap waktu, dengan mengijinkan terjadinya stockout. Ketika terjadi stockout akan dilakukan backorder. Dimana model ini diselesaikan dengan meminimalkan biaya total inventori untuk setiap siklus

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search