請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/49187完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 周承復(Cheng-Fu Chou) | |
| dc.contributor.author | Chia-Yu Hu | en |
| dc.contributor.author | 胡嘉祐 | zh_TW |
| dc.date.accessioned | 2021-06-15T11:18:41Z | - |
| dc.date.available | 2020-08-21 | |
| dc.date.copyright | 2020-08-21 | |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-08-14 | |
| dc.identifier.citation | A. Y. N. Andrew L., Awni Y. Rectifier nonlinearities improve neural network acoustic models. In ICML, 2013. S. Cook. CUDA Programming: A Developer’s Guide to Parallel Computing with GPUs. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1st edition, 2012. J.-A. B. D. Taylor and J. Buckleton. Validating trueallele® dna mixture interpretation. In Journal of the Royal Statistical Society: Series C (Applied Statistics), vol. 64, no. 1, pp. 1-48, Jan 2015. J.-A. B. D. Taylor and J. Buckleton. The interpretation of single source and mixed dna profiles. In Forensic Science International: Genetics, vol. 7, no. 5, pp. 516 528, Sep,2013. J. B. Diederik P. Kingma. Adam: A method for stochastic optimization. In ICLR, 2015. L. v. d. M. K. Q. W. Gao Huang, Zhuang Liu. Densely connected convolutional networks. In CVPR, 2017. W.-C. C. T.-M. K. C.-P. L. H.-I. Y. T.-T. L. . J. C.-I. L. Hsiao-Lin Hwa, Ming-Yih Wu. Massively parallel sequencing analysis of nondegraded and degraded dna mixtures using the forenseq™ system in combination with euroformix software. 2018. G. D. G. H. Ilya Sutskever, James Martens. On the importance of initialization and momentum in deep learning. In ICML, 2013. S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML, 2015. K. L. K. T. Jacob Devlin, Ming-Wei Chang. Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL, 2019. Y. S. John Duchi, Elad Hazan. Adaptive subgradient methods for online learning and stochastic optimization. In Journal of Machine Learning Research 12, 2011. S. R. J. S. Kaiming He, Xiangyu Zhang. Deep residual learning for image recognition. In CVPR, 2016. C. E. S. J. L. S. W. P. A. J. L. B. M. W. Perlin, M. M. Legler and B. W. Duceman. The interpretation of single source and mixed dna profiles. In Forensic Science International: Genetics, vol. 7, no. 5, pp. 516-528, Nov 2011. T. B. Olaf Ronneberger, Philipp Fischer. U-net: Convolutional networks for biomedical image segmentation. In MICCAI, 2015. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala. Pytorch: An imperative style, high-performance deep learning library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors, 50 Advances in Neural Information Processing Systems 32, pages 8024–8035. Curran Associates, Inc., 2019. T. Z. A. A. E. Phillip Isola, Jun-Yan Zhu. Image-to-image translation with conditional adversarial networks. In CVPR, 2017. G. Van Rossum and F. L. Drake. Python 3 Reference Manual. CreateSpace, Scotts Valley, CA, 2009. S. S. L. T. B. O. R. Özgün Çiçek, Ahmed Abdulkadir. 3d u-net: Learning dense volumetric segmentation from sparse annotation. In MICCAI, 2016. G. S. Ø. Bleka and P. Gill. Euroformix: An open source software based on a continuous model to evaluate str dna profiles from a mixture of contributors with artefacts. In Forensic Science International: Genetics, vol. 21, pp. 35-44, March 2016. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/49187 | - |
| dc.description.abstract | 短縱列重複序列 (short tandem repeat; STR) 被廣泛用於法醫學應用。EuroforMix仍然被廣泛使用來判定DNA混合物中判定其單人檢體，但在混和物中有親緣關係和裂解的混和物中，EuroforMix表現較差。 本論文的目的是探索深度神經網路 (deep neural networks) 可以幫助解決判定此類問題。為此，我們提出了基於深度神經網路的模型。如結果所示，深度神經網路在裂解及親屬混和物上可以比EuroforMix提升約29\%的準確度，整體提升約5\%的準確度。儘管裂解的檢體以及具血緣關係個體的DNA混合物在解譯上仍然具有挑戰性，但神經網路具有更高的DNA混合物解譯準確度。基於該結果，我們得出結論：有了深度神經網路，DNA混合物不必僅使用現有的軟體進行判定。 | zh_TW |
| dc.description.abstract | Short tandem repeat (STR) is widely used in forensic applications. EuroforMix is still widely used to determine the single DNA in the DNA mixture,However, in mixtures with related and degraded, EuroforMix performs poorly. The purpose of this paper is to explore how deep neural networks can help resolve such problems. To this end, we have proposed a model based on deep neural networks. As shown by the results, the deep neural network can provide about 29\% more accuracy than EuroforMix in degraded related mixtures, and about 5\% more accuracy overall. Although the degraded samples and DNA mixtures of related individuals are still challenging to interpret, neural networks have higher accuracy of DNA mixture interpretation. Based on this result, we conclude that with deep neural networks, DNA mixtures do not have to be judged using only existing software. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T11:18:41Z (GMT). No. of bitstreams: 1 U0001-1208202018435500.pdf: 5121701 bytes, checksum: bc3f9f4e82c4e317e2c029d266506d5f (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | Verification Letter from the Oral Examination Committee i Acknowledgements iii 摘要 v Abstract vii Contents ix List of Figures xi List of Tables xiii Chapter 1 Introduction 1 Chapter 2 Related Work 3 Chapter 3 Problem clarification and data 5 3.1 problem description 5 3.2 STR Data 7 3.3 Datasets 8 Chapter 4 Method 15 4.1 Data Preprocess 15 4.2 Method 1 19 4.3 Method 2 20 Chapter 5 Results and Evaluation 39 5.1 Results of method 1 39 5.2 Results of base model of method 2 and data augmentation 40 5.3 Result of EuroforMix 42 5.4 Compare of each method and detail 43 Chapter 6 Future Work 45 Chapter 7 Conclusion 47 References 49 | |
| dc.language.iso | en | |
| dc.subject | DNA混合物 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 神經網路 | zh_TW |
| dc.subject | 短縱列重複序列 | zh_TW |
| dc.subject | DNA mixture | en |
| dc.subject | Short tandem repeat(STR) | en |
| dc.subject | neural network | en |
| dc.subject | machine learning | en |
| dc.title | 應用深度神經網路進行基於短縱列重複序列的DNA混合物解譯 | zh_TW |
| dc.title | Applying Deep Neural Network for STR-based DNA Mixture Interpretation | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 108-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 華筱玲(Hsiao-Lin Hwa),廖婉君(Wan-Jiun Liao),吳曉光(Hsiao-Kuang Wu),蔡子傑(Tzu-Chieh Tsai) | |
| dc.subject.keyword | 機器學習,神經網路,短縱列重複序列,DNA混合物, | zh_TW |
| dc.subject.keyword | machine learning,neural network,Short tandem repeat(STR),DNA mixture, | en |
| dc.relation.page | 51 | |
| dc.identifier.doi | 10.6342/NTU202003142 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2020-08-15 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1208202018435500.pdf 未授權公開取用 | 5 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。