Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal EPSILON: Journal of Electrical Engineering and Information Technology
Maria Bestarina Laili
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
RANCANG BANGUN BATTERY PACK LITHIUM 144V/220AH UNTUK MOBIL LISTRIK Sunardi, Egi; Maria Bestarina Laili; Jelita Permatasari; Hanopa Abdul Hidayah; Diky Zakaria
EPSILON: Journal of Electrical Engineering and Information Technology Vol 23 No 1 (2025): EPSILON - Journal of Electrical Engineering and Information Technology
Publisher : Department of Electrical Engineering, UNJANI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55893/epsilon.v23i1.127

Abstract

The development of electric vehicle (EV) technology is advancing rapidly in various aspects, driven by the need for environmentally friendly and efficient transportation solutions. Electric vehicles are powered by electric motors, which require an energy source in the form of a battery arranged into a battery pack. A battery pack consists of battery cells arranged in series and parallel to meet the energy specifications required by the electric vehicle. Currently, lithium batteries are considered the best choice for electric vehicles due to their advantages in energy density and cost per cycle compared to other types of batteries. In the design of this battery pack, the vehicle's specifications require a voltage of 144V to power the electric motor, with a target usage time of 5 hours, leading to a designed capacity of 220Ah. The battery used is a Lithium Ferro Phosphate (LFP) type with specifications of 3.2V and 22Ah. Based on mathematical calculations, the battery pack design utilizes 10 batteries in parallel and 48 in series to achieve the required specifications. The design also takes into account the maximum storage space inside the vehicle, with the battery pack divided into two banks placed in the front and rear of the vehicle to maintain a balanced center of gravity. After assembly, voltage measurements showed that the maximum voltage achieved was 153.6V. Testing was conducted after the batteries were installed in the vehicle, which showed that the vehicle could be operated for 19 hours with an average current of 11.5A. From the test results, the battery capacity was calculated to be approximately 218.5Ah. The test results indicate that the battery performance does not fully match the theoretical calculations, due to factors such as battery characteristics and energy losses in the vehicle system.
Implementasi Sistem Pendeteksi Buku dengan YOLOv8 Maria Bestarina Laili; Raihan Alfariji; James Tri Septiono; Muhammad Farid Idlal; Egi Sunardi
EPSILON: Journal of Electrical Engineering and Information Technology Vol 23 No 1 (2025): EPSILON - Journal of Electrical Engineering and Information Technology
Publisher : Department of Electrical Engineering, UNJANI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55893/epsilon.v23i1.130

Abstract

Pendeteksian objek secara otomatis merupakan salah satu teknologi yang berkembang pesat dalam bidang visi komputer, khususnya dalam konteks pengelolaan data visual berbasis citra digital. Buku sebagai objek fisik yang umum dijumpai di perpustakaan, toko, dan lingkungan pendidikan memiliki potensi untuk diidentifikasi secara otomatis guna mendukung proses inventarisasi dan digitalisasi. Tujuan jurnal ini ialah untuk mengimplementasikan dan mengevaluasi kinerja algoritma deteksi objek YOLOv8 dalam mengenali dan melokalisasi objek buku pada gambar statis. Model YOLOv8 dipilih karena memiliki arsitektur yang efisien dan telah terbukti unggul dalam kecepatan serta akurasi deteksi. Dataset yang digunakan terdiri dari citra-citra beranotasi yang menggambarkan berbagai kondisi penempatan dan orientasi buku. Setelah melalui proses pelatihan dan pengujian, model dievaluasi menggunakan metrik precision, recall, F1-score, dan mean Average Precision (mAP). Model deteksi ini memiliki nilai box loss sebesar 0.4325 dan class loss sebesar 0.3096. Semakin kecil nilai loss, semakin akurat prediksi yang dihasilkan oleh model. Model juga mencapai mAP 50 sebesar 0.80 dalam metrik, dan mAP50-0.97 sebesar 0.811 dalam metrik. Hasil penelitian ini berhasil mengimplementasikan model YOLOv8 untuk mendeteksi buku dengan tingkat presisi sebesar 88% dan recall sebesar 94% dengan tingkat akurasi sebesar 90% dan 92%.
Co-Authors Diky Zakaria Egi Sunardi Hanopa Abdul Hidayah James Tri Septiono Jelita Permatasari Muhammad Farid Idlal Raihan Alfariji Sunardi, Egi