Claim Missing Document
Check
Articles

Found 7 Documents
Search

Image enhancement in palmprint recognition: a novel approach for improved biometric authentication Kusban, Muhammad; Budiman, Aris; Hari Purwoto, Bambang
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 2: April 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i2.pp1299-1307

Abstract

Several researchers have used image enhancement methods to reduce detection errors and increase verification accuracy in palmprint identification. Divergent opinions exist among experts regarding the best method of image filtering to improve image palmprint recognition. Because of the unique characteristics of palmprints and the difficulties in preventing counterfeiting, image-filtering techniques are the subject of this current research. Researchers hope to create the best biometric system possible by utilizing various techniques. These techniques include image enhancement, Gabor orientation scales, dimension reduction techniques, and appropriate matching strategies. This study investigates how different filtering approaches might be combined to improve images. The palmprint identification system uses a 3W filter, which combines wavelet, Wiener, and weighted filters. Optimizing results entails coordinating the 3W filter with Gabor orientation scales, matching processes, and dimension reduction methods. The research shows that accuracy may be considerably increased using a 3W filter with a Gabor orientation scale of [8×7], the kernel principal component analysis (KPCA) dimension reduction methodology, and a cosine matching method. Specifically, a value of 99.722% can be achieved. These results highlight the importance of selecting appropriate settings and techniques for palmprint recognition systems.
Design and Development of Object Detection Radar with IoT-Based Matlab Software Visualization Ihsan, Dias Khairul Ihsan; Fadlilah, Umi; Kusban, Muhammad
Emitor: Jurnal Teknik Elektro Vol 24, No 2: July 2024
Publisher : Universitas Muhammadiyah Surakarta

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

Abstract

Radar is an abbreviation for Radio Detection and Ranging, which means an electromagnetic wave system that functions to detect, measure and map objects in the surroundings. So far, the development of radar technology has tended to focus on object detection without considering effective integration and connectivity. Therefore, this research aims to develop a radar that can detect, measure and differentiate between moving and stationary objects. This research does not only pay attention to the detection aspect, but also integrates Matlab R2022a for visualization, Internet of Things (IoT) for centralized connectivity and the Blynk mobile application to increase the efficiency of object monitoring. This research uses ultrasonic sensors and Passive Infra-Red (PIR) sensors, ultrasonic sensors to read distance parameters and PIR sensors to detect moving or stationary objects. The ultrasonic and PIR sensors will be controlled by the ESP32 and serve as a centralized connectivity system that will connect to a Web server and mobile devices, while the Matlab R2022a software will visualize the environment around the radar at a 180o angle and connect with Thingspeak and the PushBullet mobile application. The results of the test are compared with a standard measuring instrument, namely a meter. In this research analysis, error calculations are used to see the uncertainty value of the sensor readings used. Based on research, the ultrasonic sensor reading accuracy results were 98.99% and for the PIR sensor the sensor could read every test angle starting from 30, 60, 90 120 and 150 degree, however at angles 30 and 150 degree it had quite a long delay.
The Impact of Extreme Data Imbalance on Evaluation Metrics of Deep Learning Models for Loan Default Prediction Budiyanto, Irffan; Budiyanto, Arief; Avianto, Donny; Kusban, Muhammad
Emitor: Jurnal Teknik Elektro Vol 25, No 2: July 2025
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/emitor.v25i2.10719

Abstract

The growth of financial technology has made online loans more accessible, but it has also increased the risk of borrowers failing to repay. Developing a reliable system to predict loan defaults is therefore very important. A common problem in these predictions is an imbalance in the data – there are far fewer cases of loan defaults (the minority class) than loans that are paid back on time (the majority class). This imbalance can cause the prediction models to be biased. This research specifically investigates the effect of an extremely increased data imbalance ratio (from 1:170 to 1:33,612) on the evaluation metrics of a Deep Neural Network (DNN) model, particularly when using the Adaptive Synthetic Sampling (ADASYN) oversampling technique. The method used involves adopting a previous research approach that combines ADASYN to handle data imbalance and DNN for prediction, applied to an updated Lending Club dataset with a more severe level of imbalance. The results demonstrate a critical breakdown in key evaluation metrics. Compared to previous research, Accuracy remains high (0.9515) and Specificity is strong (0.9516). However, there is a catastrophic decrease in Precision to almost zero (0.0001), a very low Recall (0.1667), and a resulting F1-Score that is also nearly zero (0.0002). A visual analysis using Principal Component Analysis (PCA) reveals that this decline in Precision is caused by synthetic minority samples generated by ADASYN completely overlapping with the original majority cluster, leading to a massive number of false positives. In conclusion, ADASYN fails to maintain a usable performance level under extreme imbalance conditions, rendering the model ineffective for its intended purpose and highlighting the critical need for alternative strategies when dealing with severe minority class scarcity.
The Impact of the Warkac Method on Palmprint Recognition Robustness and Accuracy Kusban, Muhammad
Prosiding University Research Colloquium Proceeding of The 20th University Research Colloquium 2025: Bidang Teknik dan Rekayasa
Publisher : Konsorsium Lembaga Penelitian dan Pengabdian kepada Masyarakat Perguruan Tinggi Muhammadiyah 'Aisyiyah (PTMA) Koordinator Wilayah Jawa Tengah - DIY

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

Abstract

Palmprint recognition is a promising biometric method due to the stability and uniqueness of its texture patterns. This study proposes the Warkac method (Wavelet-Wiener-Gabor-KPCA-Cosine), a systematic integration of image processing and feature extraction techniques to improve the robustness and accuracy of palmprint recognition systems. The process starts with wavelet decomposition and Wiener filtering for noise reduction, followed by detail weighting to enhance dominant features. Feature extraction is carried out using a 7x5 Gabor filter, with dimensionality reduction by Kernel Principal Component Analysis (KPCA). Matching is performed using cosine similarity, which efficiently distinguishes low-dimensional biometric features. Evaluations conducted on three public databases (PolyU, IITD, CASIA) with various matching and dimensionality reduction methods show that KPCA–Cosine delivers the best performance, achieving a verification rate of 99.455% and EER of 0.00546, followed closely by LDA–Cosine. Hausdorff and Ndistance methods perform poorly, with verification rates below 55%. This study demonstrates that the proper integration of filtering and non-linear transformation techniques can significantly enhance palmprint recognition performance under diverse input conditions.
Analisa Tingkat Potensi Sinar Matahari untuk Pembangkit Listrik Tenaga Surya di Daerah Pantai Asyari, Hasyim; Firmansyah, Roby Achmad; Kusban, Muhammad
Prosiding Simposium Nasional Rekayasa Aplikasi Perancangan dan Industri 2020: Prosiding Simposium Nasional Rekayasa Aplikasi Perancangan dan Industri
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (545.478 KB)

Abstract

Indonesia merupakan negara kepulauan yang sampai saat ini nilai elektrifikasinya masih dibawah 100%. Hal ini dapat ditemui masih banyaknya pulau kecil-kecil yang belum mendapat aliran listrik dari PT. Perusahaan Listrik Negara. Kepulauan yang belum teraliri listrik di Jawa Tengah adalah Pulau Panjang yang masuk wilayah Kabupaten Jepara. Pengelola tempat wisata pulau panjang saat ini menyediakan pembangkit listrik tenaga diesel sebagai sarana penyedia energi listrik pada malam hari di pulau tersebut. Namun pembangkit tersebut dinyalakan hanya kurang lebih 8 jam yaitu dimulai jam 17.00 - 23.00 dan jam 04.00 – 06.00. listrik yang diproduksi pembangkit tersebut untuk penerangan, sumber daya peralatan elektronik. Manajemen sistem pengoperasian pembangkit tersebut memberikan perasaan kurang nyaman bagi wisatawan atau masyarakat yang berkunjung ke pulau panjang, karena adanya keterbatasan waktu sumber energi listrik. Penelitian ini bertujuan untuk mengetahui tingkat potensi sinar matahari untuk menghasilkan energi listrik sebagai upaya untuk menyediakan energi listrik pada siang hari, agar masyarakat yang berkunjung merasa lebih nyaman. Metode penelitian ini adalah dengan melakukan pengukuran secara langsung potensi energi listrik yang dapat dihasilkan oleh panel kapasitas 100 Wp dengan jenis mono kristral. Adapun peralatan lain yang digunakan adalah batere kapasitas 50 Ah, Inverter kapasitas 1000 Watt, Battery charge controller 12/24 Volt dan 10 A. Penelitian dilakukan tanggal 9 – 15 maret 2019. Hasil dari pengujian pada tanggal 15 maret 2019, daya maksimal mencapai 99,9 Watt, terjadi pada jam 13,30 dengan intensitas cahaya matahari 95,500 Lux. Namun pada tanggal 11 maret 2019 jam 17.00 nilai intensitas cahaya matahari hanya 850 Lux sehingga daya keluaran 0,1 Watt.
Sistem Pengontrol Suhu CNC Laser Cutting 40W dengan Modul TEC1-12706 Rohmatulloh, Abidin; Kusban, Muhammad
Emitor: Jurnal Teknik Elektro Vol 24, No 1: Maret 2024
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/emitor.v24i1.4365

Abstract

Pengontrolan suhu pada tabung laser CO2 sangat penting untuk menjaga kinerja tabung laser. Tabung laser sendiri menghasilkan energi berupa cahaya dan panas. Energi panas ini jika tidak dikendalikan akan berpotensi merusak tabung laser. Adanya sistem pengontrol suhu menggunakan modul TEC1-12706 sangat bermanfaat untuk menjaga kinerja laser. Modul ini termasuk dalam thermoelectric yang mampu merubah energi listrik menjadi energi panas atau dingin dan juga sebaliknya. Penggunaan modul TECI-12706 termasuk ramah lingkungan karena tidak memakai Freon sebagai bahan utamanya. Proses yang dilakukan yaitu mensirkulasikan air dari tabung menuju peltier untuk didinginkan dan dibawa lagi menuju tabung. Proses ini menggunakan dua sensor yaitu sensor suhu dan sensor waterflow. Kriteria yang harus dipenuhi yaitu suhu tidak boleh kurang dari 25 derajat celcius atau melebihi 35 derajat celcius. Selain itu, volume air yang mengalir juga tidak boleh kurang dari 20 liter per menit. Hasil percobaan sistem pengontrol suhu menggunakan peltier TEC1-12706 mampu menurunkan suhu saat laser sedang running dengan cara mendinginkan air sirkulasi pada tabung laser.
Perancangan dan Implementasi Sistem Pencuci dan Sterilisasi Tangan Berbasis Arduino Uno untuk Pencegahan Penularan COVID-19 Raihan, Muhammad Akbar; Kusban, Muhammad
Emitor: Jurnal Teknik Elektro Vol 24, No 1: Maret 2024
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/emitor.v24i1.4783

Abstract

Penyebaran COVID-19 dapat dicegah melalui tindakan pencegahan seperti mencuci tangan dan sterilisasi yang efektif. Maka penelitian ini memiliki tujuan dalam merancang dan membangun sistem otomatis untuk mencuci serta mensterilkan tangan berbasis Arduino uno sebagai upaya untuk mengurangi resiko penyebaran COVID-19. Sistem ini menggunakan sensor inframerah untuk mendeteksi hadirnya tangan dan memulai proses pencucian tangan secara otomatis, dimulai dari pemberian air terhadap tangan, kemudian mencemprotkan cairan sabun pada tangan yang sudah terdeteksi sensor yang berada di tempat sabun, dilanjutkan kembali dengan pemberian air untuk membilas sabun dan diakhiri dengan pengeringan tangan dengan blower udara dan sinar UV yang terpisah dari keran air dan tempat sabun. Pengujian dilakukan dengan mengukur waktu yang dibutuhkan untuk mencuci dan mensterilkan tangan, serta tingkat keberhasilan keberhasilan dalam mencapai standar sanitasi yang diharapkan. Hasil penelitian menunjukkan bahwa sistem ini efektif dalam mencuci dan mensterilkan tangan secara otomatis dengan waktu yang relatif cepat, serta dapat membantu mengurangi resiko penyebaran COVID-19 pada tempat umum seperti sekolah, kantor, dan tempat lainnya. Sensor terbaca mulai dari jarak 7cm sampai dengan jarak 1cm, dan debit air mencapai 1120 mL dalam 5 detik. Sabun dapat keluar jika aktif lebih dari 2 detik, dan akurasi sensor suhu mencapai 0,05%.