13 research outputs found
Model Jaringan Saraf Tiruan untuk Variabel Tidak Pasti
No full textThe Implementation of Artificial Neural Network (ANN) model does not provide
optimal results in learning with the large quantity with inputs of many variable
and real time. The variable stated in matrix with plenty of quantity makes the
process in pattern recognition getting slow. A model is required to minimize input
for training and to recognize patterns faster. Variable recognition is required to
know the special characteristics of inputs which may represent all inputs using a
model. Artificial Neural Network also has weaknesses for arithmatic and data
processing the inputs not binary, with determining the degree of membership of
each variable. And, for each selection of variables with probability techniques
and linear programming. And data is expressed as row vectors and selected by
calculating the euclidean distance between each row vector. Furthermore, the
selected data can represent input for training. With the model algorithm which is
called as Artificial Neural Network Model for Uncertain Variabels, it helps solve
problems in the system. And validation is performed on an actuator, one of which
is the moving water wheel or not, by using variable dissolved oxygen, pH, salinity,
temperature, brightness, alkalinity, ammonia, water hardness to determine water
quality with Matrix Laboratory software.Penerapan Model Jaringan Saraf Tiruan (JST) belum memberikan hasil yang
optimal pada pembelajaran dengan input dari variabel yang banyak dan tidak pasti.
Jumlah variabel yang besar yang dinyatakan dalam bentuk matriks membuat
proses menjadi lambat dalam pengenalan pola. Dibutuhkan sebuah model yang
dapat meminimalkan variabel sebelum di lakukan pelatihan agar dapat mengenal
pola lebih cepat. Dibutuhkan pengenalan variabel yang hanya mengenali ciri khas
variabel yang dapat mewakili dari seluruh variabel dengan menggunakan sebuah
model. Jaringan Saraf Tiruan memiliki kelemahan untuk aritmatika dan pengolahan
data dalam input yang tidak bernilai biner, dengan menentukan derajat keanggotaan
masing-masing variabel. Dan untuk seleksi masing-masing variabel dengan teknik
probabilitas dan programing linear. Dan data dinyatakan sebagai vektor baris dan
diseleksi dengan menghitung jarak euclidean antara masing-masing vektor baris.
Selanjutnya data yang terseleksi tersebut dapat mewakili data untuk dilakukan
pelatihan. Dengan menggunakan model Jaringan Saraf Tiruan untuk Variabel
Tidak Pasti (VTP) membantu menyelesaikan permasalahan pada sistem. Dan validasi
dilakukan pada suatu aktuator salah satunya kincir air bergerak atau tidak, dengan
menggunakan variable dissolved oxygen, pH, salinitas, suhu, kecerahan, alkalinitas,
amonia, kesadahan air untuk menentukan kualitas air dengan software Matrix
Laboratory.118 HalamanDisertasi Dokto
Pengantar Sistem Pakar dan Metode (Introduction of Expert System and Methods)
No full textviii, 156 hlm.; Ind.: 26 c
Model Jaringan Syaraf Tiruan untuk Variabel tidak Pasti pada Kontrol Putaran Kincir Angin
Get PDFPemanfaatan sumber energi angin memberikan keuntungan dalam hal ramah lingkungan, menjadi sumber energi yang bisa diandalkan. Pemanfaatan kincir angin di dalam penggunaannya dibutuhkan kontrol agar penggunaannya dapat efisien. untuk putaran kincir angin. Dalam penelitian ini diimplementasikan pada model Jaringan Saraf Tiruan untuk Variabel Tidak Pasti yang diharapkan dapat memberikan solusi dalam menyelesaikan permasalahan terkait kincir angin. Pemanfatan kincir angain ini sebagai solusi dari pemanfaatan energi baru terbarukan, dari dampak emisi gas berbahaya dari sumber bahan bakar fosil. Serta Penggunaan minyak bumi, batu bara dan sumber energi fosil lainnya yang semakin lama semakin berkurang. Selanjuitnya model Jaringan Saraf Tiruan untuk Variabel Tidak Pasti ini menggunakan teknik probabilitas, derajat keanggotaan, fungsi logika OR, linear programing dan jarak euclidean untuk mengurangi proses pembelajaran. Pada penelitian terkait kontrol kincir angin ini menggunakan variabel tekanan udara, penyinaran matahari dan suhu untuk menentukan apakah kincir angin bergerak atau tidak. Akhirnya penelitian ini dengan model Jaringan Saraf Tiruan untuk Variabel Tidak Pasti ini diharapkan kedepan dapat menghasilkan sistem kontrol putaran kincir angin cerdas yang dapat digunakan untuk memprediksi terkait kontrol putaran kincir angin dengan data input yang bebeda
Bandwidth Limitation Based on Content Classification Using Queue Trees and Hierarchical Token Buckets
No full textInternet services become a mandatory to society in a daily basis. The key issue of this service is the crucial bandwidth that is caused by traffic congestion which leads to poor network performance. Therefore, bandwidth management is required as an effort to reduce traffic congestion on hotspot services by using the Queue Tree and Hierarchical Token Bucket methods. This study conducted a comparison of Queue Type analysis on the Queue Tree method, namely First In First Out (FIFO) and Random Early Detect (RED) to determine the process of sending data packets that can reduce congestion when building hotspot services. Test results on 10 FIFO and RED clients show that Queue Type FIFO is superior to Queue Type RED, with a FIFO QoS index of 87.5% and RED 75% with a difference of 15%, based on Quality of Service (QoS) with standard TIPHON
Pengantar sistem pakar (introduction of expert system and methods) / Zulfian Azmi, Verdi Yasin
No full text
COMPARATIVE ANALYSIS OF HYPERPARAMETER OPTIMIZATION TECHNIQUES ON LIGHTGBM FOR ASTHMA PREDICTION
Get PDFThis study presents a comparative study of hyperparameter optimization methods applied to the Light Gradient Boosting Machine (LightGBM) algorithm for asthma prediction. Traditional machine learning models often face limitations in accuracy and generalization capabilities due to suboptimal hyperparameter configurations. To address these challenges, this study evaluates and compares four approaches: Default LightGBM, RandomizedSearchCV, Optuna Optimization, and Bayesian Optimization. Experimental results show that Bayesian Optimization provides the best performance with an accuracy of 78%, a precision of 0.7778, a recall of 0.7778, an F1-score of 0.7778, and an ROC-AUC of 0.975. These findings emphasize the importance of selecting an appropriate optimization strategy to improve model performance in clinical prediction tasks. Overall, this study confirms the effectiveness of Bayesian Optimization in improving the predictive capabilities of LightGBM and provides an important contribution to the development of decision support systems in healthcare, particularly in the diagnosis and management of asthm
Uncertainty Ontology for Module Rules Formation Waterwheel Control
Get PDFImplementation 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
