Claim Missing Document
Check
Articles

Found 3 Documents
Search

Klasifikasi Kualitas Air Minum menggunakan Penerapan Algoritma Machine Learning dengan Pendekatan Supervised Learning Savitri, Lidya; Nursalim, Rahmat
Diophantine Journal of Mathematics and Its Applications Vol. 2 No. 1 (2023)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/diophantine.v2i01.28260

Abstract

The need for the provision and service of clean water from time to time is increasing which is sometimes not matched by the ability and knowledge of clean water. The majority of people still do not know whether water is suitable for consumption or not. The quality of drinking water can be distinguished based on the mineral parameters contained in the water. This article will explain the classification of water sample data by applying a Machine Learning Algorithm, which includes modeling with Logistic Regression, Support Vector Machine (SVM), Random Forest Classifier, K- Nearest Neighbor(KNN), XGBoost Classifier. Classification models produce varying degrees of accuracy. The highest accuracy is obtained in the Random Forest Classifier model with an accuracy rate of 78%. Analysis of drinking water quality with machine learning algorithms is very easy to understand, because the results of this study produce very simple results so that they are easy to understand
Hypothetical learning trajectory (HLT) for proof logic topics on algebra course: What’re the experts think about? Agustiani, Riza; Nursalim, Rahmat
Al-Jabar: Jurnal Pendidikan Matematika Vol 11 No 1 (2020): Al-Jabar: Jurnal Pendidikan Matematika
Publisher : Universitas Islam Raden Intan Lampung, INDONESIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ajpm.v11i1.6204

Abstract

Proof has a role in the formation and development of mathematics in the history of mathematics. The ability to construct proof is one indicator of mathematical reasoning which is an important component of mathematics learning outcomes, especially in Algebra. This qualitative research aims to describe the design process of the Hypothetical Learning Trajectory for Proof Logic Topics. This research is based on design research. This research consists of three stages: preparing for the experiment, the design experiment, and the retrospective analysis. Data collection techniques in this research are walkthrough and interview. The walkthrough and interview were conducted in the first stage of design research (preparing the experiment) with two activities: expert review and reader proof to collect materials to revise the HLT. Four experts participated in the expert review. The experts are chosen based on the experience, both research experience, and teaching experience. The result of this research is the design of HLT for proof logic topics consist of four activities: reading proof, completing proof, examining proof, and Constructing proof. The four activities were well-done on the design experiment stage. 
Completion of the Diffusion Wave Flood Tracking Model Using the Method of Lines (MOL) Istikomah, Istikomah; Fauzi, Yulian; Nursalim, Rahmat
Diophantine Journal of Mathematics and Its Applications Vol. 3 No. 2 (2024)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/diophantine.v3i2.39007

Abstract

The flood tracking model is a method that can be used to predict when a flood will occur. The flood wave model is developed using a diffusion equation consisting of mass conservation equations and momentum conservation equations. This research was conducted to determine the application of the Method of Lines (MOL) in solving flood tracking models using the diffusion equation. The steps involved are discretizing the flood wave diffusion tracking equation by replacing the spatial derivative using the central difference method, resulting in a system of ordinary differential equations. Then, solving the system of ordinary differential equations using the fourth-order Runge Kutta method. The approach used in this research is quantitative. Simulations are performed by inputting a sample case and entering the data into the MATLAB program. The flow discharge produced increases as the flow velocity increases, and the resulting graph becomes more concave as the velocity increases. Thus, by knowing the changes in flow velocity, flow width, and flow depth in the upstream area of the river, it can be predicted how much the water discharge will change at each observation point downstream of the river.