Article Per Year (5 Year)
p-Index From 2021 - 2026
3.117
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) Jurnal Teknologi International Journal of Artificial Intelligence Research JURNAL MEDIA INFORMATIKA BUDIDARMA Jurnal Abdimas Mahakam Progresif: Jurnal Ilmiah Komputer Techno Xplore : Jurnal Ilmu Komputer dan Teknologi Informasi Jurnal Asiimetrik: Jurnal Ilmiah Rekayasa Dan Inovasi Jurnal Tekinkom (Teknik Informasi dan Komputer) Jurnal Sistem Komputer dan Informatika (JSON) Scientific Student Journal for Information, Technology and Science Malcom: Indonesian Journal of Machine Learning and Computer Science Jurnal Pengabdian Masyarakat Nasional Jurnal Polimesin
Ahmad Fauzi
Universitas Buana Perjuangan Karawang
Humanities Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mechanical Engineering Public Health Social Sciences

Published : 23 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 23 Documents
Search

 1   2   3 
Optimization of S-EDM Process Parameters on Material Removal Rate using Copper Electrodes Khoirudin Khoirudin; Sukarman Sukarman; Nana Rahdiana; Ade Suhara; Ahmad Fauzi
Jurnal POLIMESIN Vol 21, No 1 (2023): February
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jpl.v21i1.3199

Abstract

This article demonstrates that the sinker electrical discharge machining (S-EDM) method can be enhanced using SPHC (JIS G 3131) materials with a hardened surface. During S-EDM, neither contact nor a cutting force exists between the electrode and the workpiece. S-EDM is advantageous because it eliminates mechanical stress, chatter, and vibration issues with traditional milling. S-EDM is widely employed, for example, in the manufacturing of molds for automotive and aviation components. Taguchi design and signal-to-noise ratio (S/N ratio) were selected to examine the impact of the input parameter model on the material removal rate (MRR). The Taguchi approach assessed three input parameters and three experimental levels. The parameters pulse current (I), spark time (Ton), and gap voltage (Vg) were chosen to evaluate the MRR performance of the S-EDM process with the SPHC-hardened workpiece material. Copper with a diameter of 10 mm is chosen as the electrode material. This study aims to determine the optimal MRR for the chosen input variables. Results indicate that a more effective pulse current value promotes debris removal from the machining zone and stabilizes following spark release, speeding the material removal rate (MRR). In the S-EDM machining process, the pulse current value significantly affects the MRR and is one of the most significant response variables
Performance Comparison of Support Vector Machine Algorithm and Logistic Regression Algorithm Hanny Hikmayanti; Anis Fitri Nurmasruriyah; Ahmad Fauzi; Nunung Nurjanah; Arphilia Nur Rani
International Journal of Artificial Intelligence Research Vol 7, No 1.1 (2023)
Publisher : STMIK Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v7i1.1.1114

Abstract

According to the World Health Organization (WHO), there are around 7 million breast cancer patients each year, with about 5 million of them dying. Based on Globocan 2018 data, the death rate from breast cancer averages 17 per 100,000 people with incidents of 2.1 per 100,000 people attacking women in Indonesia. Hence breast cancer causes spread genetic mutations in the DNA of breast epithelial cells that radiate to the ducts. The purpose of this study was to classify the type of cancer (benign or malignant) that was suffered. The difference between previous research and this research is in the algorithm testing method chosen. In this study the algorithm used is SVM and Logistic Regression by applying the SMOTE technique. The K-fold cross validation method is used in testing this research. The accuracy results obtained are 1.0, precision 1.0 and recall 1.0.While the highest evaluation results for the model without SMOTE were Accuracy 0.97, precision 1.0 and recall 0.90 with the LR method. So based on the results of the comparison, it shows that the evaluation of models using SMOTE tends to be higher than models without SMOTE
PENERAPAN ALGORITMA NAÏVE BAYES UNTUK PREDIKSI PENERIMAAN KARYAWAN Intan Murni Pratiwi; Ahmad Fauzi; Santi Arum Puspita Lestari; Yana Cahyana
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 1 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i1.1282

Abstract

The number of job seekers keeps growing, as does the quantity of companies that open job vacancies and offer opportunities to prospective employees. In terms of recruiting new employees, companies are very selective.. Companies are very selective in accepting prospective workers, where prospective workers must have qualifications that are in accordance with the positions needed in the company, because employees are an important asset in the growth and development of the company. because employees are an important factor in the growth and development of the company. Quality companies need good employees. This research uses employee recruitment data from PT Atma Darma Apta. The data has 372 rows and 8 attributes. The Naïve Bayes algorithm and the assessment techniques Mean Squared Error, Root Mean Squared Error, and R2 Score are used in this study. The results showed that the algorithm obtained good results by using a 90 to 10 data division resulting in a large accuracy value of 97.14%. In addition, the MSE, RMSE, and R2 Score values have quite good results, which are 2.86, 16.90, and 1.00. The 70 to 30 data division produces poor values with error values of 152.80 and 123.60, but the accuracy and R2 Score values are quite large at 96.15% and 0.95. With these results, this research can be continued into an application that can predict employee selection results.
Co-Authors Ade Suhara Adie Putra Agung Rahmat Ahmad Rahman Amelia Pratiwi Amri Abdulah Anis Fitri Nurmasruriyah Anwar Ilmar Ramadhan April Hananto Ardi Apriansyah Arphilia Nur Rani Aviv Yuniar Rahman Ayu Sri Rahayu Baihaqi, Kiki Ahmad Bambang Sukowo Candra Zonyfar Dodi Mulyadi Dwi Kusumaningrum Hanny Hikmayanti Handayani Indra, Jamaludin Intan Murni Pratiwi Irma Putri Rahayu Khoirudin Khoirudin Khoirudin Lestari, Santi Arum Puspita Mohamad Rizkiyanto Murtalim Nana Rahdiana Novalia, Elfina Nunung Nurjanah Rahmat Rahmat Randy Kurniadi Ricko Valderama Ridwan Maulana Saruni Dwiasnati Siregar, Amril Mutoi Sony Hartono Wijaya Sriyanto Sriyanto Sukarman Sukarman Sumanto Sutan Faisal Sutan Faisal Tjong Wan Sen Toif Muhayat Tukino Tukino Yana Cahyana Yudo Devianto Yusuf Khoiruddin