Article Per Year (5 Year)
p-Index From 2020 - 2025
0.751
P-Index
This Author published in this journals
All Journal Simtek : Jurnal Sistem Informasi dan Teknik Komputer Journal of System and Computer Engineering
inda, nur
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Analisis Perbandingan Kinerja Model Yolov7 dalam Deteksi Kuku Diabetes inda, nur
Journal of System and Computer Engineering Vol 5 No 2 (2024): JSCE: Juli 2024
Publisher : Universitas Pancasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61628/jsce.v5i2.1334

Abstract

Abstract Diabetes mellitus (DM) is a degenerative and non-communicable disease that can be seen from the color of the fingernails. In analyzing color the human eye has limitations in color recognition and texture analysis while computers are able to classify millions of colors and slight texture changes to recognize changes in individual nail color to prevent early symptoms of diabetes using the YOLOv7 method to represent a one-stage model for detecting objects using a Convolutional Neural Network ( CNN). This research was carried out at the Polewali Community Health Center. Sampling was carried out by taking medical records and conducting interviews with the relevant doctors. Sample data was taken from several diabetes mellitus patients and several workers at the Polewali Community Health Center for healthy nail sample data. The results of testing the YOLOv7 model with epoch 100 showed accuracy of 81%, precision of 82.4%, recall of 95.5% and F1-Score of 88.5%. Testing the YOLOv7 model with epoch 200 resulted in an accuracy of 90%, precision of 93.3%, recall of 93.3% and F1-Score of 93.3%. Testing the YOLOv7-x model with epoch 100 resulted in an accuracy of 71.4%, precision 72.3%, recall 82.9% and F1-Score 77.2%. Testing the YOLOv7-x model with epoch 200 resulted in an accuracy of 63.3%, precision 60.4%, recall 90.6% and F1-Score 72.5%. Testing the YOLOv7-tiny model with epoch 100 resulted in an accuracy of 91.4%, precision 95.6%, recall 93.5% and F1-Score 94.5%. Testing the YOLOv7-tiny model with epoch 200 resulted in an accuracy of 94.6%, precision 93%, recall 100% and F1-Score 96.4%. The results of comparative testing of the YOLOv7 model in detecting diabetic nails, concluded that the ideal model that can be used is the YOLOv7-tiny model with an epoch value of 200. Keywords: Confusion Matrix, CNN, Diabetes Mellitus, Nails, YOLOv7
Sistem Pengusiran Hama Burung Secara Otomatis Pada Lahan Pertanian Padi inda, nur; Tria, Rahmi
Journal of System and Computer Engineering Vol 6 No 1 (2025): JSCE: January 2025
Publisher : Universitas Pancasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61628/jsce.v6i1.1517

Abstract

The importance of advancing sustainable rice farming is because rice is a staple food whose production must be increased to meet the basic needs of the community. The problem that occurs to rice farmers is that thousands of bird pests look for food in fertile rice fields, causing great losses for farmers. The way farmers efficiently repel bird pests is by developing technology that can monitor bird activity around rice fields in real time remotely and is able to repel bird pests by using the Internet Of Things (IoT) development. which aims to design IoT or tools that can monitor bird activity in real time around agricultural areas remotely, by utilizing PIR sensors to detect bird pests, LDR resistors detect light, ESP32-CAM to monitor rice fields and utilizing solar panel power as a sound signal generator that will sound disturbing the bird's hearing system so that the birds fly away and move the DC motor to repel bird pests automatically and the data collected from the ESP32-CAM (1) sensor will be sent to the IoT platform with the Telegram application connected via an internet connection, allowing farmers to monitor remotely via smart devices such as smartphones or computers.
KLASIFIKASI KUALITAS BUNGA CENGKEH DENGAN METODE FASTER REGION CONVOLUTIONAL NEURAL NETWORK (FASTER R-CNN) Dayanti, Dayanti; Yuyun, Yuyun; Hasriani, Hasriani; Syarif, Irwan; Inda, Nur
Simtek : jurnal sistem informasi dan teknik komputer Vol. 10 No. 2 (2025): Oktober 2025
Publisher : STMIK Catur Sakti Kendari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51876/simtek.v10i2.1666

Abstract

Bunga cengkeh menjadi penting mengingat peran sentralnya dalam sektor pertanian dan industri. Cengkeh bukan hanya sebagai tanaman rempah-rempah yang memiliki nilai ekonomis tinggi, tetapi juga memiliki signifikansi kultural. Di samping kegunaannya sebagai bahan dalam industri makanan dan farmasi, bunga cengkeh telah lama digunakan dalam pengobatan tradisional dan aromaterapi. Namun, tantangan terkait perubahan iklim, teknik Petani cengkeh masih menggunakan indra penglihatan untuk mengetahui kualitas hasil pengeringan panen cengkeh yang kekurangannya masih bersifat subjektif. Penelitian ini bertujuan untuk memudahkan baik petani, produksi maupun konsumen dalam memilah kualitas dari bungah cengkeh menggunakan teknologi kecerdasan buatan. Metode yang digunakan dalam penelitian ini adalah machine learning menggunakan Faster R-CNN. Data sampel yang digunakan menggunakan dataset yang telah dikumpulkan dilokasi penelitian dan dibagi menjadi 3 kelas yaitu kualitas baik, kualitas sedang dan kualitas buruk. Hasil pengujian menggunakan parameter ukur tingkat kecerahan ruangan (lux), jarak pengambilan objek dan pengujian pada objek lain didapatkan hasil bahwa pengujian menggunakan dataset augmentasi dengan parameter ukur nilai lux 600 dan pengambilan jarak 17cm sebagai pengujian dengan tingkat keberhasilan yang tinggi sebesar 86% dan sistem dapat membedakan objek bunga cengkeh dengan objek lain. Hasil rata-rata pengujian yang didapatkan dengan proses augmentasi sebesar 51%.
MEDACT: FUNGSI AKTIVASI HIBRID BARU UNTUK MODEL RESNET PADA KLASIFIKASI CITRA MEDIS Baital, Muhammad Syarif; Jasman, Jasman; Inda, Nur
Simtek : jurnal sistem informasi dan teknik komputer Vol. 10 No. 2 (2025): Oktober 2025
Publisher : STMIK Catur Sakti Kendari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51876/simtek.v10i2.1685

Abstract

Penelitian ini menyoroti pentingnya pemilihan fungsi aktivasi pada model deep learning untuk klasifikasi tumor otak berbasis citra MRI. Sebanyak sebelas fungsi aktivasi, termasuk ReLU, Leaky ReLU, ELU, Swish, Mish, PReLU, GELU, SELU, HardSwish, MedAct Fixed, dan MedAct Learnable, dievaluasi pada arsitektur ResNet. Hasil menunjukkan hampir semua fungsi mencapai akurasi pengujian ≥ 99% dengan perbedaan relatif kecil. ReLU, Swish, Mish, dan MedAct Learnable menempati posisi terbaik dengan hanya dua kesalahan klasifikasi, sedangkan PReLU dan MedAct Fixed menunjukkan kelemahan dengan tujuh kesalahan. Temuan penting adalah bahwa fungsi aktivasi baru (MedAct Learnable), mampu menyamai performa fungsi aktivasi modern terbaik dan menunjukkan peningkatan signifikan dibandingkan MedAct Fixed. Hal ini menegaskan bahwa sifat adaptif parameter α memberikan kontribusi positif terhadap generalisasi model.
Co-Authors Baital, Muhammad Syarif Dayanti, Dayanti Hasriani Hasriani, Hasriani Jasman Jasman Syarif, Irwan Tria, Rahmi Yuyun, Yuyun