Syaiful Anam

Syaiful Anam

Auto-generated profile, based on publicly available information

Syaiful Anam

Brawijaya University

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2017 in International Journal of Mathematics and Mathematical Sciences
Verified
Journal Article
Open access
PDF file
ASAgus Suryanto
Agus Suryanto
IDIsnani Darti
Isnani Darti
SASyaiful Anam
Syaiful Anam
We analyze the dynamics of a fractional order modified Leslie-Gower model with Beddington-DeAngelis functional response and additive Allee effect by means of local stability. In this respect, all possible equilibria and their existence conditions are determined and their stability properties are established. We also construct nonstandard numerical schemes based on Grünwald-Letnikov approximation. The constructed scheme is explicit and maintains the positivity of solutions. Using this scheme, we perform some numerical simulations to illustrate the dynamical behavior of the model. It is noticed that the nonstandard Grünwald-Letnikov scheme preserves the dynamical properties of the continuous model, while the classical scheme may fail to maintain those dynamical properties.

21 December 2020 in Journal of Agricultural Engineering
Verified
Journal Article
Open access
PDF file
KPKestrilia Rega Prilianti
Kestrilia Rega Prilianti
SASyaiful Anam
Syaiful Anam
TBTatas H.P. Brotosudarmo
Tatas H.P. Brotosudarmo
ASAgus Suryanto
Agus Suryanto
The assessment of the photosynthetic pigment contents in plants is a common procedure in agricultural studies and can describe plant conditions, such as their nutritional status, response to environmental changes, senescence, disease status and so forth. In this report, we show how the photosynthetic pigment contents in plant leaves can be predicted non-destructively and in real-time with an artificial intelligence approach. Using a convolutional neural network (CNN) model that was embedded in an Androidbased mobile application, a digital image of a leaf was processed to predict the three main photosynthetic pigment contents: chlorophyll, carotenoid and anthocyanin. The data representation, low sample size handling and developmental strategies of the best CNN model are discussed in this report. Our CNN model, photosynthetic pigment prediction network (P3Net), could accurately predict the chlorophyll, carotenoid and anthocyanin contents simultaneously. The prediction error for anthocyanin was ±2.93 mg/g (in the range of 0-345.45 mg/g), that for carotenoid was ±2.14 mg/g (in the range of 0-211.30 mg/g) and that for chlorophyll was ±5.75 mg/g (in the range of 0-892.25 mg/g). This is a promising result as a baseline for the future development of IoT smart devices in precision agriculture.

28 October 2017 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
SAS Anam
S Anam
Optimization has become one of the important fields in Mathematics. Many problems in engineering and science can be formulated into optimization problems. They maybe have many local optima. The optimization problem with many local optima, known as multimodal optimization problem, is how to find the global solution. Several metaheuristic methods have been proposed to solve multimodal optimization problems such as Particle Swarm Optimization (PSO), Genetics Algorithm (GA), Artificial Bee Colony (ABC) algorithm, etc. The performance of the ABC algorithm is better than or similar to those of other population-based algorithms with the advantage of employing a fewer control parameters. The ABC algorithm also has the advantages of strong robustness, fast convergence and high flexibility. However, it has the disadvantages premature convergence in the later search period. The accuracy of the optimal value cannot meet the requirements sometimes. Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm is a good iterative method for finding a local optimum. Compared with other local optimization methods, the BFGS algorithm is better. Based on the advantages of the ABC algorithm and the BFGS algorithm, this paper proposes a hybrid of the artificial bee colony algorithm and the BFGS algorithm to solve the multimodal optimization problem. The first step is that the ABC algorithm is run to find a point. In the second step is that the point obtained by the first step is used as an initial point of BFGS algorithm. The results show that the hybrid method can overcome from the basic ABC algorithm problems for almost all test function. However, if the shape of function is flat, the proposed method cannot work well.

1 September 2025 in BAREKENG: Jurnal Ilmu Matematika dan Terapan
Verified
Journal Article
Open access
PDF file
HFHaidar Ahmad Fajri
Haidar Ahmad Fajri
SASafrizal Ardana Ardiyansa
Safrizal Ardana Ardiyansa
SASyaiful Anam
Syaiful Anam
NMNatasha Clarrisa Maharani
Natasha Clarrisa Maharani
EJEric Julianto
Eric Julianto
Diabetes mellitus is a chronic condition with high blood sugar that can cause severe organ damage, affecting all ages globally. Early diagnosis is crucial for improving patients' quality of life, and machine learning offers a promising approach. The Support Vector Machine (SVM) is effective for classification, but feature selection is essential to enhance the relevance of features. The Whale Optimization Algorithm (WOA) is an optimal method for global feature selection, but it has a drawback-premature convergence, which can lead to suboptimal results. This issue should be addressed by modifying mutation operations, convergence factors, and population initialization, resulting in Binary Gaussian IWOA (BGIWOA). This research focuses on feature selection using BGIWOA, comparing it with Variance Inflation Factor (VIF) using SVM. The result show that BGIWOA is better than VIF and the best configuration BGIWOA’s parameter is with linear kernel. This configuration produces the best accuracy of 95.00%. BGIWOA-SVM demonstrates better accuracy with stable consistency compared to VIF-SVM. The best SVM model achieves average accuracy of 95.62% for training data and 95.58% for validation data, with an accuracy of 93.85% for the test data. This model also yields an average precision of 94.00%, a recall of 91.00%, and an -score of 92.00%. The model was also better than SVM without optimization, which only achieved a training accuracy of 84.25% and a testing accuracy of 81.30%. This model can assist in diagnosing diabetes with accurate and consistent predictions for new data. The results are specific to the diabetes dataset used in this research, so further testing on other binary datasets is necessary to confirm the model's effectiveness and generalizability across different domains and types of data.

11 June 2023 in BAREKENG: Jurnal Ilmu Matematika dan Terapan
Verified
Journal Article
Open access
PDF file
SASyaiful Anam
Syaiful Anam
MPM. Rafael Andika Putra
M. Rafael Andika Putra
ZFZuraidah Fitriah
Zuraidah Fitriah
IYIndah Yanti
Indah Yanti
NHNoor Hidayat
Noor Hidayat
DMDwi Mifta Mahanani
Dwi Mifta Mahanani
The number of claims plays an important role the profit achievement of health insurance companies. Prediction of the number of claims could give the significant implications in the profit margins generated by the health insurance company. Therefore, the prediction of claim submission by insurance users in that year needs to be done by insurance companies. Machine learning methods promise the great solution for claim prediction of the health insurance users. There are several machine learning methods that can be used for claim prediction, such as the Naïve Bayes method, Decision Tree (DT), Artificial Neural Networks (ANN) and Support Vector Machine (SVM). The previous studies show that the SVM has some advantages over the other methods. However, the performance of the SVM is determined by some parameters. Parameter selection of SVM is normally done by trial and error so that the performance is less than optimal. Some optimization algorithms based heuristic optimization can be used to determine the best parameter values of SVM, for example Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). They are able to search the global optimum, easy to be implemented. The derivatives aren’t needed in its computation. Several researches show that PSO give the better solutions if it is compared with GA. All particles in the PSO are able to find the solution near global optimal. For these reasons, this article proposes the health claim insurance prediction using SVM with PSO. The experimental results show that the SVM with PSO gives the great performance in the health claim insurance prediction and it has been proven that the SVM with PSO give better performance than the SVM standard.

24 May 2025 in Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Verified
Journal Article
Open access
PDF file
SASyaiful Anam
Syaiful Anam
IPImam Nurhadi Purwanto
Imam Nurhadi Purwanto
DMDwi Mifta Mahanani
Dwi Mifta Mahanani
FYFeby Indriana Yusuf
Feby Indriana Yusuf
HRHady Rasikhun
Hady Rasikhun
Health risk classification is important. However, health risk classification is challenging to address using conventional analytical techniques. The XGBoost algorithm offers many advantages over the traditional methods for risk classification. Hyperparameter Optimization (HO) of XGBoost is critical for maximizing the performance of the XGBoost algorithm. The manual selection of hyperparameters requires a large amount of time and computational resources. Automatic HO is needed to avoid this problem. Several studies have shown that Bayesian Optimization (BO) works better than Grid Search (GS) or Random Search (RS). Based on these problems, this study proposes health risk classification using XGBoost with Bayesian Hyperparameters Optimization. The goal of this study is to reduce the time required to select the best XGBoost hyperparameters and improve the accuracy and generalization of XGBoost performance in health risk classification. The variables used were patient demographics and medical information, including age, blood pressure, cholesterol, and lifestyle variables. The experimental results show that the proposed approach outperforms other well-known ML techniques and the XGBoost method without HO. The average accuracy, precision, recall and f1-score produced by the proposed method are 0.926, 0.920, 0.928, and 0.923, respectively. However, improvements are needed to obtain a faster and more accurate method in the future.