Claim Missing Document
Check
Articles

Found 33 Documents
Search

Implementasi Algoritma Random Forest Untuk Menentukan Penerima Bantuan Raskin Kurniawan, Ilham; Buani, Duwi Cahya Putri; Abdussomad, Abdussomad; Apriliah, Widya; Saputra, Rizal Amegia
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 10 No 2: April 2023
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.20236225

Abstract

Kemiskinan adalah salah satu perhatian mendasar dari setiap pemerintah. Program Beras Keluarga Miskin (Raskin) merupakan  salah satu program pemerintah. Skema raskin mempunyai tujuan meminimalisir beban rumah tangga tidak mampu sebagai bentuk bantuan untuk menaikkan ketahanan pangan melalui perlindungan sosial. Tujuan penelitian ini adalah menemukan akurasi tertinggi di antara algoritma klasifikasi prediktif yang diusulkan penerima bantuan raskin menggunakan tools python machine learning dan di implementasikan melalui suatu website. Klasifikasi adalah metode penambangan data yang menentukan kategori pada kelompok data untuk mendukung prediksi dan analisa yang semakin akurat. Beberapa algoritma klasifikasi pembelajaran mesin seperti, SVM, NB dan RF, digunakan pada penelitian ini demi menentukan penerima bantuan raskin. Eksperimen dilakukan menggunakan dataset Raskin Kelurahan Gunungparang, Kota Sukabumi yang bersumber dari Kelurahan Gunungparang. Kinerja algoritma klasifikasi dievaluasi dengan beragam metrik seperti Precision, Accuracy, F-Measure, dan Recall. Akurasi diukur melalui contoh yang dikelompokan dengan benar atau salah. Hasil yang diperoleh menunjukkan algoritma klasifikasi RF memiliki nilai precision, recall, f-measure dengan nilai 97%, nilai accuracy sebesar  97,26% dan nilai ROC 0,970, lebih baik dari algoritma klasifikasi lainnya yaitu perbedaan sebesar 5,11% dengan algoritma klasifikasi support vector machine dan 8,87% dengan algoritma klasifikasi naive bayes. Akurasi sangat baik digunakan sebagai acuan kinerja algoritma apabila jumlah False Negative dan False Positive jumlah nya mendekati. Hasil penelitian ini dibuktikan secara akurat dan sistematis menggunakan Receiver Operating Characteristic (ROC). Abstract The problem of poverty is one of the fundamental concerns of every government. The Raskin  program is one of the government's programs. The Raskin scheme has the aim of minimizing the burden on poor households in the form of assistance to improve food security by providing social protection. The purpose of this study is to find the highest accuracy among the predictive classification algorithms proposed by Raskin beneficiaries using python machine learning tools and implemented through a website. Classification is a data mining method that determines categories in data groups to support more accurate predictions and analysis. Therefore, three machine learning classification algorithms such as, support vector machine, naive bayes and random forest, were used in this experiment. to determine recipients of Raskin assistance. The experiment was carried out using the Raskin dataset, Gunungparang Village, Sukabumi City, which was sourced from Gunungparang Village. The performance of the classification algorithm is evaluated by various metrics such as Precision, Accuracy, F-Measure, and Recall. Accuracy is measured by correctly and incorrectly grouped samples. The results obtained show that the random forest classification algorithm has precision, recall, f-measure values with a value of 97%, an accuracy value of 97.26% and an ROC value of 0.970, better than other classification algorithms, namely the difference of 5.11% with the support vector classification algorithm. machine and 8.87% with naive bayes classification algorithm. Very good accuracy is used as a reference for algorithm performance if the number of False Negatives and False Positives is close. These results were proven accurately and systematically using Receiver Operating Characteristics (ROC).
Investigating the Readiness of EFL Pre-Service Teachers in Implementing Technology-Based Teaching: A Phenomenological Study Alaka, Anta; Nurhayati, Lusi; Widayanti, Eka; Habiburrahman, Habiburrahman; Kurniawan, Ilham; Amin, Muhammad Safiul
Journal of Languages and Language Teaching Vol. 13 No. 3 (2025): July
Publisher : Universitas Pendidikan Mandalika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33394/jollt.v13i3.14326

Abstract

This study aims to investigate EFL pre-service teachers' readiness to use technology in English Language Teaching (ELT) classrooms and identify the factors that influence their readiness. A phenomenological research design was employed, involving 30 final-semester EFL pre-service teachers enrolled in a teacher education program, selected through purposive sampling. Data were collected through open-ended surveys and interviews and analyzed thematically to extract key themes related to readiness, technological competence, and influencing factors. Findings demonstrated a high level of readiness among participants, supported by strong technological competence and confidence. Participants showed proficiency in using Learning Management Systems (LMS), Canva, and game-based applications like Kahoot to create interactive and engaging learning environments. Internal factors (such as self-confidence and technological skills) and external factors (such as institutional support, courses, and workshops) influenced their readiness. The findings provide a framework for enhancing teacher training curricula and suggest ways to improve student engagement and learning outcomes through effective technology integration. This study contributes to the limited literature on technology integration readiness among EFL pre-service teachers in Indonesia.
Implementation of the Decission Tree Algorithm to Determine Credit Worthiness Abdussomad, Abdussomad; Kurniawan, Ilham; Wibowo, Agung
Compiler Vol 12, No 2 (2023): November
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/compiler.v12i2.1911

Abstract

Credit is a loan from a bank that needs to be repaid with interest. In practice, problematic credit or bad credit often occurs due to less thorough credit analysis in the credit granting process, or from bad customers. This research aims to predict creditworthiness using the Decision Tree Classification Algorithm and find a solution for determining it. This research uses the CRISP-DM (Cross-Industry Standard Process for Data Mining) method. This research method tests the effects of using the decision tree, Support Vector Machine, and Naïve Bayes model with the Decision Tree Classification Algorithm. The decision tree classification algorithm accurately analyzed problem loans and non-problem debtors at 93.49%. The decision tree algorithm test results are better than the support vector machine by 3.45%, and naïve bayes by 13.03%. The results of our study were also 4.16% better than the previous study. This research has also implemented the selected model in the form of website application deployment.
Penggunaan Platform E-Commerce untuk Promosi dan Penjualan Produk Kerajinan di Kecamatan Sijunjung dengan OpenCart Kurniawan, Ilham; Annas, Firdaus; Tigana, Adra
JOVISHE : Journal of Visionary Sharia Economy Vol. 3 No. 2 (2024): Edition December 2024
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/jovishe.v3i2.468

Abstract

The purpose of this writing is to design a promotional system for handicraft products using the OpenCart CMS, aimed at facilitating promotions. The main issue faced by handicraft products is the uncertainty regarding orders and sales. Even though the products produced meet consumer expectations, there are often situations where items already manufactured remain unsold or are not collected by the buyers who ordered them. Some of the most sought-after products, such as phone cases, Islamic gowns, men's shirts, and songket fabrics, face various challenges, including different payment methods and production issues such as broken threads or patterns that do not align with customer preferences. Payments are usually made in cash or via bank transfer, and products are typically collected directly by buyers. For out-of-town buyers, delivery is sometimes arranged using intercity buses. Currently, there are many technologies available to enhance product sales and notify customers that their orders are ready. This study adopts the Research and Development (R&D) method with a development model comprising planning, production, and evaluation stages. The result of this research is a web-based promotional media platform utilizing the OpenCart application, which has been validated as both valid and practical. The findings demonstrate that OpenCart can serve as an effective supporting medium to enhance the competitiveness of handicraft products in the Sijunjung district..
Novel Compounds Design of Acertannin, Hamamelitannin, and Petunidin-3-Glucoside Typical Compounds of African Leaves (Vernonia amygdalina Del) as Antibacterial Based on QSAR and Molecular Docking Kurniawan, Ilham; Ambarsari, Laksmi; Kurniatin, Popi Asri; Wahyudi, Setyanto Tri
Jurnal Jamu Indonesia Vol. 8 No. 2 (2023): Jurnal Jamu Indonesia
Publisher : Tropical Biopharmaca Research Center, IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jji.v8i2.326

Abstract

Antibacterial secondary metabolites such as tannins and their derivatives are found in the Vernonia amygdalina Del. Antibiotic resistance can develop due to overuse, reducing the efficacy of drugs to prevent and treat infections. This research aims to use the Quantitative Structure-Activity Relationship (QSAR) and the semi-empirical method Austin Model 1 (AM1) to design a modified novel compound from African leaves that has improved antibacterial activity. This research includes a descriptor calculation of QSAR using AM1 MOE on typical compounds from African leaves, and calculation results are chosen based on a multilinear regression statistical analysis. The model equation represents the three primary parameters of QSAR, which are electronic, hydrophobic, and steric parameters, which will be used to measure modified compounds. Molecular docking using Autodock Tools (The Scripps Research Institute, USA), and analysis of results of docking Autodock Tools using Discovery Studio 3.5 Client. The best QSAR model obtained is LogEC50 = (0.829 x LogP) - (1,302 x AM1_HOMO) - (0.339 x AM1_dipole) - (5,128 x mr) + (0.145 x vol) - (11,355). The results showed that EC50 prediction of modified hamamelitannin has the best activity with the lowest ΔGbind -9.0 kcal/mol and inhibition constant of 0.249 μM. In summary, the novel compound's design calculation has better antibacterial activity, as indicated by a lower EC50, than fosfomycin or compounds without modification. The modified hamamelitannin compound was found to have better antibacterial activity (prediction EC50 = 0.1933 μM) than the original (experimental EC50 = 145.50 μM).
Analysis of Tube Expansion Percentage on Microstructure and Hardness of 316L Stainless Steel Tube-to-Tubesheet Connections with GTAW Process Syaiful Amri, Moh.; Bachtiar, Bachtiar; Miftachul Munir, Moh.; Mukhlis, Mukhlis; Ari, Muhammad; Kurniawan, Ilham
Journal of Mechanical Engineering, Science, and Innovation Vol 5, No 2 (2025): (October)
Publisher : Mechanical Engineering Department - Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.jmesi.2025.v5i2.8161

Abstract

This study analyzes the effect of varying tube expansion percentages on the mechanical properties, microstructure, and hardness of SA-213 TP316L tubes joined to SA-240 TP316L tubesheets in a shell-and-tube type heat exchanger. The tube expansion process was carried out using a roller expander with three expansion levels: 4%, 8%, and 12%, followed by Gas Tungsten Arc Welding (GTAW) at 150 A. Microstructural observations revealed that all joint zones were dominated by austenite with small amounts of delta ferrite, where increasing expansion percentages induced significant changes in the expand area: slight deformation at 4%, grain elongation at 8%, and pronounced grain distortion at 12%. Macrostructural observations showed perfect fusion between the tube and tubesheet for all variations, with no macro defects such as lack of fusion or porosity. Vickers hardness testing indicated the highest values in the expand area for all variations, with a maximum of 377 Kgf/mm², exceeding the standard limit of 250 Kgf/mm² for stainless steel. The hardness of the base metal was around 180 Kgf/mm², while the weld metal ranged from 220–230 Kgf/mm² due to delta ferrite formation. The increase in hardness in the expand area was attributed to cold working effects, indicating that post-tube expansion heat treatment is necessary to reduce residual stresses and restore the optimal mechanical properties of the material.
Rancang Bangun Sistem Pembelajaran Pengenalan Komponen Elektronika Berbasis Pengolahan Citra Kurniawan, Ilham; Aulia, Suci; Hartaman, Aris
eProceedings of Applied Science Vol. 9 No. 1 (2023): Februari 2023
Publisher : eProceedings of Applied Science

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

Abstract

Abstract—Perkembangan teknologi seiring dengan berjalannya waktu saat ini banyak inovasi dan perkembangan, salah satunya sistem pendeteksi objek untuk membantu manusia dalam mengenal dan memahami mengenai komponen elektronika. Komponen elektronika memiliki dua klasifikasi utama yaitu komponen aktif dan komponen pasif, jenis komponen elektronika aktif seperti Dioda, LED, IC dan jenis komponen elektronika pasif seperti Resistor, Kapasitor dan Induktor. Hal tersebut menyebabkan beberapa manusia kesulitan untuk mengenali klasifikasi dari jenis komponen tersebut. Pada Proyek Akhir ini telah dirancang suatu sistem untuk mendeteksi dan mengenali komponen elektronika berbasis pengolahan citra. Dengan adanya sistem ini nantinya diharapkan dapat membantu para pengguna untuk mengenali komponen sesuai dengan jenis dan fungsinya. Sistem perancangan ini akan dilakukan menggunakan sebuah platform executable document Google Colab. Pengujian proyek akhir ini menggunakan indikator bounding box. Hasil dari perencanaan ini menunjukkan bahwa sistem dapat melakukan pendeteksi komponen elektronika berbasis pengolahan citra dengan metoda bounding box. Dari hasil pengujian pada 11 skenario, diperoleh tingkat akurasi 100% dan rata-rata waktu proses 6,83 detik setiap citra pada skenario 1-6, dan tingkat akurasi 89% dengan rata-rata waktu proses 37 detik pada skenario 7-11.Kata Kunci— Komponen Elektronika, Pengolahan Citra, Komponen Aktif, Komponen Pasif, Bounding Box.
Implementasi Model Rapid Application Development untuk Aplikasi Pelayanan Jasa Maintenance Pada PT. Dwi Tirtamas Tekhnik Karawang Apriliah, Widya; Agrelia, Priska; Kurniawan, Ilham; Abdussomad, Abdussomad; Priska Agrelia
PROFITABILITAS Vol 2 No 1 (2022): JURNAL PROFITABILITAS
Publisher : Sistem Informasi Akuntansi Kampu Kabupaten Karawang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/profitabilitas.v2i1.1290

Abstract

Information is one of the important things that affect the development of business activities in the business sector, whether it's a service business or non-service, To realize this, currently in all aspects of the business field, there is no need to apply technology to produce information and support data processing in its business processes. In service, it also requires the support of an information system to facilitate data processing and effectiveness in providing services. At PT. Dwi Tirtamas The current technique requires an information system to be applied to maintenance service business activities to facilitate data processing, report presentation, information delivery and make it easier to provide maintenance services to customers. Therefore, in this research, an information system will be designed and built for maintenance services at PT. Dwi Tirtamas Karawang Technique. The software development model used in this study is the RAD (Rapid Application Development) model and the programming language for building an information system for maintenance services using the Java programming language.
Implementation of Maximum power control of Solar Panels using Modified Perturb and Observe Algorithm based on Adaptive Neuro Fuzzy Inference System Kurniawan, Ilham; Yuhendri, Muldi; Hendra, Ayu; Hidayat, Rahmat
Journal of Industrial Automation and Electrical Engineering Vol. 1 No. 1 (2024): Vol 1 No 1 (2024): June 2024
Publisher : Department of Electrical Engineering Universitas Negeri Padang

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

Abstract

In this modern era, the need for renewable energy is increasing, and solar panels are one of the main solutions. To maximize the efficiency of energy extraction from solar panels, a method is needed. Based on the characteristics of voltage and current, the output power of these solar panels changes following changes in irradiation and temperature. Changes in the output power value have a maximum point, where each voltage and current value has a different maximum power point at each change in temperature. For this reason, the Maximum Power Point Tracker (MPPT) method is used to solve this problem by adjusting the solar panel voltage at the maximum point using a power converter. In this study, the MPPT control system will be implemented using a boost converter. This study develops a Maximum Power Point Tracking (MPPT) control system based on the Adaptive Neuro-Fuzzy Inference System (ANFIS), which is developed from conventional perturbation and observation algorithms. The ANFIS-based MPPT control system is implemented using an Arduino microcontroller. The experimental results verify that the proposed ANFIS-based MPPT system has successfully controlled the output power of solar panels at the maximum point
BUDAYA NUSANTARA DALAM PERSPEKTIF PENGAJARAN DAN PENERAPAN HUKUM ISLAM Fauziah, Ai Samrotul; Taufiqurrohman, Essa Salman; Hanafi, Hilmi; Kurniawan, Ilham
FIKRAH Vol 8 No 2 (2024): DESEMBER
Publisher : Ibn Khaldun University, Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32832/fikrah.v8i2.20614

Abstract

The culture of Nusantara represents a wealth that reflects the diversity of ethnicities, traditions, and local values in Indonesia. From the perspective of Islamic law implementation, the interaction between local culture and Sharia norms is highly relevant. Islamic law, which is universal in nature, needs to be integrated with local cultures to ensure its acceptance and understanding by the community. This study employs a literature review method to analyze various primary and secondary sources, including Islamic legal texts, scholarly works, historical documents, and literature on Nusantara culture. It examines how the values of Nusantara culture, such as deliberation (musyawarah), mutual cooperation (gotong royong), and local wisdom, can strengthen the application of Islamic law within the social and cultural contexts of society. Through this approach, the study aims to highlight the importance of dialogue between Islamic law and local culture and its implications for fostering a harmonious and just society. The findings are expected to provide insights into the synergy between law and culture in creating a more effective and inclusive legal system in Indonesia.