Please use this identifier to cite or link to this item:
http://repository.ipb.ac.id/handle/123456789/161359Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Puspita, R. Tony Ibnu Sumaryada Wijaya | - |
| dc.contributor.advisor | Yani, Sitti | - |
| dc.contributor.author | Sajidi, Halim | - |
| dc.date.accessioned | 2025-03-07T01:17:48Z | - |
| dc.date.available | 2025-03-07T01:17:48Z | - |
| dc.date.issued | 2025 | - |
| dc.identifier.uri | http://repository.ipb.ac.id/handle/123456789/161359 | - |
| dc.description.abstract | Higgs boson adalah partikel fundamental yang memberikan massa kepada partikel elementer sesuai Model Standar (SM) fisika partikel. Validasi keberadaannya penting untuk memastikan konsistensi SM. Penelitian ini bertujuan menganalisis peluruhan Higgs boson menjadi pasangan tau-lepton ( ?????? ) menggunakan kombinasi Neural Network klasik dan Variational Quantum Classifier (VQC). Data yang digunakan berasal dari ATLAS full-detector simulation, meliputi peristiwa signal yaitu peluruhan Higgs ke tautau serta tiga background utama: peluruhan ?? ? ????? ¯, ?? + ??????, dan ????? ¯. Data preprocessing mencakup pembersihan, transformasi, penanganan data tak seimbang (teknik SMOTE), dan pembagian data menjadi data latih dan uji. Neural Network klasik dirancang dengan fungsi aktivasi sigmoid dan optimizer Adam, sedangkan VQC memanfaatkan ZZFeatureMap dan quantum circuits untuk klasifikasi. Neural Network (NN) memberikan kinerja yang baik, dengan akurasi lebih dari 80%. Variational Quantum Classifier (VQC) menghasilkan akurasi kurang dari 70%. Penggunaan teknik SMOTE pada data latih meningkatkan akurasi model VQC. Neural Network klasik lebih unggul dalam hal akurasi, efisiensi, dan kemampuan generalisasi pada dataset ini dibandingkan dengan VQC. | - |
| dc.description.abstract | The Higgs boson is a fundamental particle that gives mass to elementary particles according to the Standard Model (SM) of particle physics. Validation of its existence is important to ensure the consistency of the SM. This study aims to analyze the decay of the Higgs boson into tau-lepton pairs ( ????? ¯ ) using a combination of classical Neural Network and Variational Quantum Classifier (VQC). The data used comes from the ATLAS full-detector simulation, including the signal event, the Higgs decay to tautau, and three main backgrounds: the decay of ?? ? ????? ¯ , ?? + ?????? , dan ????? ¯. Data preprocessing includes cleaning, transformation, handling of unbalanced data (SMOTE technique), and division of data into training and test data. The classical Neural Network is designed with sigmoid activation function and Adam optimizer, while VQC utilizes ZZFeatureMap and quantum circuits for classification. The Neural Network (NN) provided good performance, with an accuracy of over 80%. The Variational Quantum Classifier (VQC) yielded less than 70% accuracy. The use of SMOTE techniques on the training data improved the accuracy of the VQC model. The classical Neural Network is superior in terms of accuracy, efficiency, and generalization ability on this dataset compared to VQC. | - |
| dc.description.sponsorship | null | - |
| dc.language.iso | id | - |
| dc.publisher | IPB University | id |
| dc.title | Variational Quantum Classifier (VQC) untuk Klasifikasi Sinyal Higgs Boson | id |
| dc.title.alternative | Variational Quantum Classifier (VQC) for Higgs Boson Signal Classification | - |
| dc.type | Skripsi | - |
| dc.subject.keyword | Higgs boson | id |
| dc.subject.keyword | Neural Network | id |
| dc.subject.keyword | Variational Quantum Classifier | id |
| Appears in Collections: | UT - Physics | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| cover_G7401201087_fb9aa19459e44a248a416dbe519fabc9.pdf | Cover | 1.25 MB | Adobe PDF | View/Open |
| fulltext_G7401201087_6ed951cd2d31458db83a40c46f698c78.pdf Restricted Access | Fulltext | 1.86 MB | Adobe PDF | View/Open |
| lampiran_G7401201087_3df8af26a815408ca878cb2706019d6e.pdf Restricted Access | Lampiran | 650.48 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.