Claim Missing Document
Check
Articles

Found 5 Documents
Search

Analisis Metode Certainty Factor Pada Sistem Pakar Diagnosa Kerusakan Sepeda Motor Zalukhu, Anzas Ibezato; Irwan Syahputra; Suhardiansyah; Iqbal, Muhammad; Wijaya, Rian Farta
Bulletin of Information Technology (BIT) Vol 4 No 4: Desember 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i4.1083

Abstract

Motorcycles are a predominant mode of transportation in Indonesian society, comprising 84.5% of the total transportation vehicles in 2021 according to national BPS data. Despite providing convenience in mobility, motorcycles are susceptible to disturbances or damages that can hinder normal usage and potentially lead to accidents. Many motorcycle riders lack knowledge or awareness regarding potential issues with their motorcycles. This research aims to analyze the implementation of the certainty factor method in an expert system for identifying motorcycle malfunctions, with a focus on Giska Servis workshop. The certainty factor method serves as a reasoning tool to determine identification outcomes based on identified symptoms. The results of this study are expected to contribute to facilitating motorcycle riders in diagnosing symptoms of malfunctions in their vehicles. The certainty factor method offers a systematic and structured approach to identifying motorcycle issues. Through the implementation of this method, the research attempts to measure the success rate of the expert system in diagnosing malfunctions. Data from the identification results at Giska Servis workshop will be comprehensively analyzed to evaluate the accuracy and effectiveness of the certainty factor method in this context.By highlighting the success of this method, this research is expected to provide valuable insights for the development of expert systems for motorcycle issue identification. The findings of this study can serve as a guide for workshops and motorcycle users to enhance understanding and management of vehicle issues, thereby minimizing the potential for accidents and extending the lifespan of motorcycles.
Penerapan Metode Certainty Factor Pada Sistem Pakar Diagnosa Penyakit Gigi Dan Mulut Zalukhu, Anzas Ibezato; Irwan Syahputra; Suhardiansyah; Sitorus, Zulham; Khairul
Bulletin of Information Technology (BIT) Vol 4 No 4: Desember 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v4i4.1102

Abstract

Gigi dan mulut merupakan organ vital yang memainkan peran penting dalam menjaga kesehatan manusia. Kelainan pada gigi dan mulut dapat menjadi pemicu penyakit lain dalam tubuh. Pentingnya menjaga kesehatan gigi dan mulut ditekankan, terutama mengingat fungsinya yang esensial dalam berbicara, menjaga bentuk wajah, dan mengunyah makanan. Sayangnya, dengan perkembangan zaman, pola makan yang tidak sehat, seperti konsumsi makanan siap saji tinggi gula, garam, dan lemak, dapat menyebabkan masalah kesehatan gigi dan mulut. Penyakit gigi dan mulut sering disebabkan oleh mikroorganisme, dan pengetahuan terbatas tentang gejala-gejala penyakit ini dapat menjadi hambatan untuk diagnosis dini. Sebagai solusi, penelitian ini mengusulkan penerapan metode certainty factor dalam sistem pakar untuk mendiagnosis penyakit gigi dan mulut. Metode ini memungkinkan evaluasi tingkat keyakinan pakar terhadap data yang dianalisis, memberikan solusi atau rekomendasi dalam situasi kompleks. Penelitian ini mengacu pada pandangan pakar dokter gigi dan mulut, yang dianggap memiliki pengetahuan dan pengalaman yang mencukupi. Sistem pakar yang diusulkan bertujuan untuk meniru proses penalaran seorang pakar dalam memecahkan masalah spesifik dalam bidang gigi dan mulut. Dengan memanfaatkan certainty factor, sistem ini dapat menyediakan solusi yang lebih dapat diandalkan dan memberikan kontribusi pada upaya pencegahan serta penanganan dini penyakit gigi dan mulut.
ANALISIS DATA MINING DALAM PENGELOLAAN PERSEDIAAN STOK DENGAN ALGORITMA RANDOM FOREST DAN APRIORI (STUDI KASUS: TOKO CERIA BABYSHOP) Zalukhu, Anzas Ibezato; Iqbal, Muhammad; Nasution, Darmeli
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 3 (2025): August 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i3.3544

Abstract

Abstract: This research analyzes inventory management at Toko Ceria Babyshop by applying data mining techniques, specifically Random Forest and Apriori algorithms. Effective inventory management is crucial for aligning product availability with market demand, preventing overstocking or stockouts, and optimizing operational costs. Sales transaction data from June to December 2024, comprising 20,578 sales transactions, 3,593 purchase entries, 2,736 initial stock entries, and 1,331 final stock entries, were divided into 80:20 training and testing sets. The Random Forest implementation showed that weekly purchase quantity predictions were more effective than monthly predictions, evidenced by lower Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) values for weekly predictions (16.10, 1.76, 4.01) compared to monthly (39.68, 3.19, 6.30). Furthermore, the R-squared (R²) value was higher for the weekly model (0.21) than the monthly (0.04), indicating better weekly prediction accuracy. The Apriori algorithm successfully identified product association patterns for both 2-itemsets and 3-itemsets, with all rules exhibiting lift values above 1, signifying positive relationships between products. This purchasing pattern information is highly beneficial for developing marketing strategies such as bundling, shelf arrangement, cross-selling promotions, and improved inventory planning. Keywords: Data mining, Random Forest, Apriori, stok Inventory, Toko Ceria Babyshop Abstrak: Penelitian ini berfokus pada analisis pengelolaan persediaan stok di Toko Ceria Babyshop melalui penerapan teknik data mining menggunakan algoritma Random Forest dan Apriori. Efektivitas pengelolaan persediaan sangat krusial dalam bisnis untuk menyelaraskan ketersediaan produk dengan permintaan pasar, mencegah kelebihan atau kekurangan stok, dan mengoptimalkan biaya operasional. Data transaksi penjualan yang dikumpulkan dari Juni hingga Desember 2024 terdiri dari 20.578 transaksi penjualan, 3.593 entri pembelian, 2.736 entri stok awal, dan 1.331 entri stok akhir, yang kemudian dibagi menjadi set pelatihan dan pengujian dengan rasio 80:20. Hasil implementasi algoritma Random Forest menunjukkan prediksi kuantitas pembelian mingguan lebih efektif dibandingkan bulanan, ditunjukkan oleh nilai Mean Squared Error (MSE), Mean Absolute Error (MAE), dan Root Mean Squared Error (RMSE) yang lebih rendah pada prediksi mingguan (16.10, 1.76, 4.01) dibandingkan bulanan (39.68, 3.19, 6.30). Selain itu, nilai R-squared (R²) juga lebih tinggi untuk model mingguan (0.21) dibandingkan bulanan (0.04), mengindikasikan akurasi prediksi mingguan yang lebih baik. Algoritma Apriori berhasil mengidentifikasi pola asosiasi produk, baik untuk 2-itemset maupun 3-itemset, dengan semua aturan memiliki nilai lift di atas 1, yang menunjukkan hubungan positif antar produk. Informasi mengenai pola pembelian ini sangat bermanfaat untuk pengembangan strategi pemasaran seperti bundling, penataan rak, promosi cross-selling, serta perencanaan persediaan stok yang lebih baik. Kata kunci: Data mining, Random Forest, Apriori, Persediaan stok, Toko Ceria  Babyshop
Penerapan Algoritma Dijkstra Dan Metode Topsis Dalam Sistem Rekomendasi Barbershop Berbasis Android Hulu, Adil Priman Hati; Zalukhu, Anzas Ibezato
Jurnal Armada Informatika Vol 9 No 2 (2025)
Publisher : STMIK Methodist Binjai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36520/jai.v9i2.193

Abstract

The rapid growth of modern barbershops in Medan City has increased user difficulties in determining the nearest location while selecting the best barbershop based on multiple service criteria. The main problems involve finding optimal routes and selecting the best alternatives based on price, service quality, style, health protocols, and distance. This study develops an Android-based barbershop recommendation system by integrating the Dijkstra algorithm for shortest path search and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method for alternative ranking. Dijkstra calculates the shortest distance from the user's location, while TOPSIS determines the best recommendation using weighted criteria. The results show that the system effectively provides the fastest routes and optimal recommendations according to user preferences, improving search efficiency and decision-making accuracy.
Sistem Pendukung Keputusan Rekomendasi Calon Ketua BEM Pada Perguruan Tinggi Menggunakan Metode Weighted Product (WP) dan MOORA Syahputra, Irwan; Zalukhu, Anzas Ibezato; Hulu, Adil Priman Hati; Sartika, Dewi; Suhardiansyah, Suhardiansyah
Bulletin of Computer Science Research Vol. 6 No. 2 (2026): February 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i2.992

Abstract

The BEM Chairperson is the highest position in an intra-campus organization elected by students. The process of selecting the BEM chairperson begins with a selection and choice based on several specific criteria that have different assessment weights. To determine the decision-making process, a decision support system (DSS) is one of the tools in solving this problem. Weight Product (WP) and MOORA are methods in SPK that are widely used to resolve decision-making that has many criteria and ranking systems. This study compares the WP and MOORA methods in selecting BEM chairperson candidates. Based on the calculation results, it is found that both methods can produce a sequence of BEM chairperson candidates. The stages of completing the WP and MOORA methods are determining the decision criteria, determining the weight of each criterion, determining alternatives and their values ??for each criterion, creating a decision matrix, normalizing the decision matrix, calculating the preference value for each alternative, sorting the largest value as a decision recommendation. Based on the results of the calculations for both methods, we can compare that the MOORA method, based on the Recommendation Assessment for the Election of Student Executive Board Chairperson at Budidarma University, Medan, selected alternative A1, Muhammad Aldi, S.Kom, with an optimization value of 0.4572. However, using the WP method, the selection of alternative A1, Muhammad Aldi, with a preference value of 0.193116, was selected as BEM Chairperson.