Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) TIN: TERAPAN INFORMATIKA NUSANTARA Jurnal Pendidikan dan Teknologi Indonesia
Sumihar, Yo'el Pieter
Unknown Affiliation
Aerospace Engineering Arts Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Social Sciences Veterinary Other

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
AUTOMATED ANAEMIA DETECTION FROM CONJUNCTIVA IMAGES : A MACHINE LEARNING APPROACH FOR ANDROID APPLICATION Henry, Valentino Sas; Sumihar, Yo'el Pieter; Maedjaja, Febe
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 2 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i2.5218

Abstract

Anaemia is a common global disorder condition in which the red blood cell count is lower than normal. Traditional diagnostic methods often prove costly, invasive, and inaccessible, leading to delays in treatment and severe consequences. This study explores non-invasive techniques leveraging smartphone technology for efficient anaemia detection. Some researcher investigated that eye’s conjunctiva analysis can a viable alternative, considering its rich blood vessel network and sensitivity to anaemia indicators, independent of skin color. Utilizing smartphone cameras, the study establishes a robust correlation between the color of the conjunctiva and anaemia status, offering a promising avenue for non-invasive diagnosis. Employing a hybrid methodology, the study integrates You Only Look Once (YOLO) version 8 for efficient object detection, achieving a mean average precision of 96% in extracting Regions of Interest (ROI) from conjunctiva images. Subsequently, K-Nearest Neighbors (KNN) classification of features extracted from these ROI’s attained an 83% accuracy rate in determining anaemia status. Furthermore, the study aims to extend its impact by developing an Android application using the Flutter framework. This application integrates the established YOLO and KNN approaches, enabling real-time anaemia detection through smartphone cameras. Such a tool holds the potential to facilitate early evaluations in resource-constrained regions, enabling timely diagnosis and intervention, thus mitigating the adverse effects of untreated anaemia.
Implementasi Metode ViSQOL Dalam Mengidentifikasi Noise pada Kualitas Suara Streaming Spotify Setiawan Matangkin, Jimmi; Rudatyo Himamunanto, Agustinus; Budiati, Haeni; Sumihar, Yo'el Pieter
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 7 (2025): JPTI - Juli 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.848

Abstract

Kualitas suara pada layanan streaming Spotify seringkali tidak konsisten akibat gangguan noise dan variasi parameter jaringan, yang berdampak pada kualitas pengalaman pengguna (QoE). Penelitian ini bertujuan mengevaluasi kualitas audio Spotify menggunakan algoritma ViSQOL dengan menganalisis pengaruh jenis noise seperti pink noise, background noise, compression noise, dan impulse noise. Network noise juga diuji berdasarkan parameter jaringan yaitu throughput, delay, packet loss, dan jitter. Sebanyak 800 sampel audio direkam menggunakan Audacity dan dianalisis di MATLAB untuk memperoleh nilai Mean Opinion Score (MOS), Signal-to-Noise Ratio (SNR), dan Spectral Distortion. Hasil menunjukkan bahwa pink noise 50% menurunkan MOS menjadi 61–65%, sementara impulse noise memberikan dampak paling signifikan dengan MOS 15–17%. Background noise masih dapat ditoleransi. Pada parameter jaringan, MOS tertinggi diangka 4.31 terjadi pada delay 132.16 ms dan packet loss 0.49%, sedangkan MOS terendah diangka 4.26 tercatat saat delay 62.15 ms dan packet loss 1.9%. Temuan ini menegaskan pentingnya pengendalian terhadap noise dan stabilitas jaringan untuk menjaga kualitas layanan audio.
The Design and Evaluation of a Decentralized E-Voting System Using Ethereum Smart Contracts Hurit, Ludgerdus Pati; Sumihar, Yo'el Pieter; Budiati, Haeni
TIN: Terapan Informatika Nusantara Vol 6 No 8 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v6i8.8997

Abstract

The widespread implementation of electronic voting systems poses ongoing challenges related to data integrity, transparency, and centralized control, which can increase the risk of vote manipulation and reduce traceability. To address these issues, this study designs and evaluates a decentralized electronic voting system implemented using Ethereum smart contracts. The objective of this research is to test the ability of blockchain technology to support a secure, transparent, and tamper-resistant voting process in a decentralized environment. The research methodology includes requirements analysis, system design, system implementation, and functional testing. Black-box testing was conducted to verify the system's functionality throughout the voting process. The proposed system permanently records voting transactions on the blockchain, preventing unauthorized modifications while allowing transaction verification by network participants. Voter privacy is maintained by separating voter identity data from voting records and implementing blockchain address abstraction, ensuring that individual votes cannot be directly linked to voter identities. System evaluation focuses on transaction costs and confirmation times. Performance testing was conducted using six test transactions on the Sepolia blockchain network. The total transaction cost recorded was 0.006076 ETH, with an average cost of 0.001013 ETH per transaction. The minimum transaction cost of 0.000091 ETH occurred during voting operations, while the maximum cost of 0.005596 ETH was associated with smart contract deployment and higher network base fees. The average transaction confirmation time was approximately 12 seconds. Although the evaluation was based on a limited number of transactions, the results indicate that the proposed system demonstrates reliable transaction execution, acceptable gas usage, and high transparency. Further large-scale testing is recommended for future work.
Co-Authors Febe Maedjaja Haeni Budiati Henry, Valentino Sas Hurit, Ludgerdus Pati Rudatyo Himamunanto, Agustinus Setiawan Matangkin, Jimmi