Penerapan Algoritma Quantum K-Nearest Neighbors Untuk Pengenalan Objek

Muntazhar, Ahmad Zaki Al (2023) Penerapan Algoritma Quantum K-Nearest Neighbors Untuk Pengenalan Objek. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06111940000012-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (5MB) | Request a copy

Abstract

Pengenalan objek adalah penelitian penting yang mensimulasikan kemampuan penglihatan manusia pada komputer atau robot. Seiring perkembangan zaman penelitian ini semakin mutakhir, hanya saja menemui tantangan berupa 3V: volume data yang besar; variasi data yang banyak; dan velocity atau kecepatan proses yang perlu semakin singkat. Hal ini membuat para ilmuan mulai mencari jalan keluar untuk menghadapi masalah tersebut. Di sisi lain, perkembangan komputasi kuantum telah membuka peluang baru dalam bidang Quantum Machine Learning (QML), yang menggabungkan kekuatan komputasi kuantum dengan teknik pembelajaran mesin. Salah satu algoritma menarik dalam QML adalah Quantum k-Nearest Neighbors (QKNN), yang dapat digunakan dalam pengenalan objek berbasis citra. Namun, penggunaan QKNN dalam pengenalan objek berbasis citra masih terbatas dan perlu dikembangkan lebih lanjut. Penelitian ini bertujuan untuk menerapkan dan menganalisis algoritma QKNN berbasis komputasi kuantum dalam pengenalan objek berbasis citra. Langkah-langkahnya meliputi merepresentasikan citra dalam bentuk keadaan kuantum, perhitungan jarak antara dua keadaan kuantum menggunakan metode fidelity, dan penentuan label menggunakan majority vote berdasarkan jarak terdekat. Pada penelitian ini, algoritma QKNN diuji dengan menggunakan 84 dataset citra sintetis dengan perbandingan 64:20. Hasil eksperimen pada ragam 2 kelas, QKNN berhasil rata-rata 0.80. menunjukkan bahwa algoritma QKNN mampu mengenali objek dengan tingkat akurasi sebesar 0.65 dengan k=3 pada dataset 4 kelas. Hal ini menunjukkan perlunya telaah lebih lanjut baik dari segi fidelity ataupun teknik preprocessing data guna meningkatkan kinerja QKNN.
===============================================================================================================================
Object recognition is an important research that simulates human vision capabilities in computers or robots. As time goes by, this research is getting more sophisticated, but it encounters challenges in the form of 3V: (volume) large volume of data; (variety) large variety of data; (velocity) and the need for fast data processing. This has led scientists to start looking for solutions to these problems. On the other hand, the development of quantum computing has opened up new opportunities in the field of Quantum Machine Learning (QML), which combines the power of quantum computing with machine learning techniques. One of the interesting algorithms in QML is Quantum k-Nearest Neighbors (QKNN), which can be used in image-based object recognition. However, the use of QKNN in image-based object recognition is still limited and needs to be developed further. This research aims to apply and analyze the quantum computing-based QKNN algorithm in image-based object recognition. The steps include representing the image in the form of quantum states, calculating the distance between two quantum states using the fidelity method, and determining the label using majority vote based on the closest distance. In this study, the QKNN algorithm was tested using 84 synthetic image datasets with a ratio of 64:20. The experimental results on the 2-class variety, QKNN succeeded on average 0.80. shows that the QKNN algorithm is able to recognize objects with an accuracy rate of 0.65 on the 4-class dataset. This shows the need for further study both in terms of data fidelity and data preprocessing techniques to improving QKNN's performance.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Quantum K-Nearest Neighbors, Quantum Computing, Object Recognition, Fidelity, Quantum K-Nearest Neighbors, Komputasi Kuantum, Pengenalan objek, Fidelity
Subjects:	Q Science > Q Science (General) Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics Q Science > QA Mathematics > QA336 Artificial Intelligence Q Science > QA Mathematics > QA76.6 Computer programming. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.546 Computer algorithms
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Ahmad Zaki Al Muntazhar
Date Deposited:	15 Aug 2023 04:34
Last Modified:	15 Aug 2023 04:34
URI:	http://repository.its.ac.id/id/eprint/102357

Actions (login required)

View Item