DSpace collection: 博碩士論文
http://ir.lib.ncu.edu.tw/handle/987654321/118
The collection's search engineSearch the Channels
http://ir.lib.ncu.edu.tw/simple-search
AI法官之研究:深度學習於刑事訴訟裁判的應用;Research on AI Judges: Application of Deep Learning in Criminal Trial Adjudication
http://ir.lib.ncu.edu.tw/handle/987654321/93559
title: AI法官之研究:深度學習於刑事訴訟裁判的應用;Research on AI Judges: Application of Deep Learning in Criminal Trial Adjudication abstract: 此近幾年運用機器學習(Machine learning )與深度學習(Deep learning)方式對於繁體中文、簡體中文、英文等法律文本進行法律專業術語的標記、法律罪章名稱的分類以及法律量刑範圍的預測逐漸為人們所關注,由此國內因國民法官的議題而也有了AI法官議題的延伸,希冀透過更理性、客觀與一制性的邏輯處理能力準確一致的進行案件的裁量。其中據OpenAI實驗室的測試Generative Pre-trained Transformer (GPT)模型如果參加美國紐約州(State of New York)所舉辦的律師司法考試,成績將可落在平均值前10%的高水準,具有相當優秀的法律知識成果,見其Transformer模型於司法文書的應用上的成果。將中文法律領域於機器學習與深度學習的應用,最先碰到的是法律資料結構化的問題,中華民國法律在資料結構化方面處理不易。由於法律資料的數量龐大且法條種類繁多,資料之間的關係和層次復雜,因此需要進行有效的資料結構化和組織化處理。本次AI法官模型研究中的模型架構分為資料前處理、AI法官系統裁量特徵選取、模型訓練與預測三個階段,資料前處理階段會自司法院資料開放平臺下載全國各級法院1996年1月份至2022年8月份裁判書資料JSON開放資料格式檔案。以Bidirectional Encoder Representati-ons from Transformers進行裁判書文本的處理,可通過對法律裁判書的文本來進行訓練,學習到裁判書中的語意信息和詞彙的關係,並將裁判書內容轉換為向量表示,取出資料集中酒後駕車案件類型的特徵。最後以多任務學習multi-task learning結合自動調整loss weight的方式進行模型的訓練與預測,以同時得到罪責及刑期兩種預測結果,準確率可達到0.95。;In recent years, the use of machine learning and deep learning methods for tagging legal terminology, classifying legal chapter names, and predicting legal sentencing ranges in legal texts written in Traditional Chinese, Simplified Chinese, and Englis- h has gradually become a topic of interest. This has led to the extension of the AI judge issue in domestic circles due to the issue of citizen judges. The hope is to us- e more rational, objective, and standardized logic processing capabilities to make a- ccurate and consistent judgments in legal cases.According to tests conducted by O- penAI Laboratory, the Generative Pre-trained Transformer (GPT) model can achie- ve high-level scores, placing it in the top 10% on the New York State Bar Exam. This indicates that the model has achieved excellent legal knowledge results, dem- onstrating its effectiveness in the application of transformer models in legal doc- uments.In the application of machine learning and deep learning in the Chinese le- gal field, the first challenge encountered is the problem of legal data structuring. The legal system in the Republic of China (Taiwan) is not easy to handle in terms of data structuring. Due to the vast amount of legal data and the complexity of the relationships and hierarchies between different types of legal provisions, effective data structuring and organization is necessary. In this study of the AI judge model, the model architecture is divided into three stages: data preprocessing, feature sele- ction for the AI judge system′s discretion, and model training and prediction. In the data preprocessing stage, the national court′s judgment data in JSON open data format from January 1996 to August 2022 is downloaded from the Judicial Depart- met Open Data Platform. The Bidirectional Encoder Representations from Trans- formers (BERT) is used to process the text of the judgments. By training on the text of legal judgments, the model learns the semantic information and vocabulary relationships within the judgments and converts the judgment contents into vector representations. Relevant features are extracted from the dataset for cases involve- ng drunk driving. Finally, the model is trained and predicted using multi-task lear- ning and automatic loss weight adjustment to obtain both the prediction results for the criminal liability and the sentence length, with an accuracy rate of 0.95.
<br>資料庫一體機導入之個案研究;Implementation of Database Appliance - A Case Study
http://ir.lib.ncu.edu.tw/handle/987654321/92786
title: 資料庫一體機導入之個案研究;Implementation of Database Appliance - A Case Study abstract: 本研究探討個案公司導入資料庫軟硬體整合設備Oracle Exadata對業務營運和效能的影響。研究採用個案研究法,透過研究者親身參與和蒐集、參考Oracle官方網站以及技術文件與個案公司Oracle Exadata導入專案文件,記錄整理與分析個案資料,提供未來有相同需求IT人員,評估資料庫環境設計和導入資料庫一體機需求時的參考資訊。
本研究說明個案因何種原因規劃導入資料庫一體機、導入的規劃與過程以及遇到的挑戰,至最終資料庫一體機導入後的改變與結果效益。研究的結果顯示,資料庫一體機的導入與整合,提升A公司資料存取效能與儲存資源、提供更穩定的資料庫服務環境並透過雲端佈署及監控降低IT人員的維護人力,建議未來研究可以進一步探索如何將企業資料庫導入雲端。;This study investigates the impact of implementing Oracle Exadata, a database hardware and software integrated solution, on the business operations and performance of a case company. The research adopts a case study approach, involving the researcher′s active involvement in data collection and analysis through personal engagement, reference to Oracle′s official website and technical documentation, and examination of the case company′s Oracle Exadata implementation project documents. The findings aim to provide valuable insights and recommendations for IT personnel within organizations who are evaluating database environment design or considering the adoption of integrated database appliances.
The case study starts by elucidating the reasons behind the case company′s decision to implement Oracle Exadata. Next, the planning and challenges during the implementation process is explained. Finally, the resulting changes and benefits on the case company after the successful implementation of Oracle Exadata is summarized.
The results demonstrate that the integration of the database appliance significantly enhance data access performance, optimize storage resources, provide a more stable database service environment, and reduce IT personnel maintenance efforts through cloud-based deployment and monitoring. Future research could explore the possibilities of migrating enterprise databases to the cloud.
<br>台灣中小企業e化現況之個案研究;A Case Study of Small and Medium Enterprises Digitization in Taiwan
http://ir.lib.ncu.edu.tw/handle/987654321/92782
title: 台灣中小企業e化現況之個案研究;A Case Study of Small and Medium Enterprises Digitization in Taiwan abstract: 自 1970 年代以來,企業開始引進大型主機系統來實現電腦化,但在1990年代中期之前,企業電腦化的概念和範圍並無顯著改變。隨著網際網路和通訊技術的快速發展以及商業模式的變革,大幅改變企業電腦化時代的許多觀念與執行方式,而近期企業數位轉型開始盛行,透過大數據、人工智慧等技術改變企業營運模式,促使企業必須將企業流程數據化,適時導入數位工具迅速轉型以強化競爭力。而中小企業對經濟體的重要性凸顯中小企業e化與數位轉型的關鍵,中小企業能否強化現有e化基礎並善用數位科技進行變革,不只關乎其個別企業自身的生存與競爭,亦關乎其所屬產業升級及國家的競爭力。
有鑑於此,本研究聚焦在傳統中小企業,以個案公司e化現況與現行經營模式下面臨的問題與挑戰為例,探討中小企業特性、企業e化、數位轉型、企業資源規劃與跨境境電子商務等相關研究文獻,透過個案公司現行ERP系統改善與導入跨境電子商務營運成效等分析,提出方法與建議,為其他中小企業在此方面提供借鑒和參考。
經個案研究結果,ERP系統須將CRM與SCM進行整合,提升ERP系統整合營運綜效,方能在現有企業e化基礎,達成企業數位轉型目標。未來導入跨境電子商務應以第三階段營運模式產出為基準並成立專職營運部門與人員,才能提升跨境電子商務營運成效。;Since the 1970s, businesses have been introducing large-scale mainframe systems for computerization. However, the concept and scope of enterprise computerization did not undergo significant changes until the mid-1990s. With the rapid development of the internet, communication technologies, and transformative business models, many concepts and execution methods of enterprise computerization have been drastically altered. In recent years, digital transformation has become prevalent among businesses, driving the need for enterprises to digitize their processes and swiftly adopt digital tools such as big data and artificial intelligence to enhance competitiveness. The importance of small and medium-sized enterprises (SMEs) to the economy highlights the key role of e-commerce and digital transformation in SMEs. Whether SMEs can strengthen their existing e-commerce foundation and effectively utilize digital technologies for transformation not only affects their own survival and competitiveness but also impacts industry upgrades and national competitiveness.
Therefore, this study focuses on traditional SMEs and takes a case company′s e-commerce status and challenges faced under the current operating model as an example. It explores relevant literature on SME characteristics, enterprise computerization, digital transformation, enterprise resource planning (ERP), and cross-border e-commerce. Through the analysis of the case company′s ERP system improvement and the implementation of cross-border e-commerce operational effectiveness, the study provides methods and recommendations for other SMEs in this area for reference and guidance.
Based on the findings of the case study, it is crucial to integrate customer relationship management (CRM) and supply chain management (SCM) into the ERP system to enhance its operational efficiency and achieve the digital transformation goals on the existing e-commerce foundation. In the future, the adoption of cross-border e-commerce should be based on a third-stage operational model output and establish dedicated operational departments and personnel to improve cross-border e-commerce operational effectiveness.
<br>深度學習唇語辨識之研究;A Study on Lip Reading Recognition using Deep Learning
http://ir.lib.ncu.edu.tw/handle/987654321/92778
title: 深度學習唇語辨識之研究;A Study on Lip Reading Recognition using Deep Learning abstract: 近年來,深度學習已成為人工智慧領域的一個熱門研究方向,深度學習利用多層神經網絡從大量數據中學習特徵和模式,並從中生成高度准確的預測和分類結果。它已被成功應用於語音辨識、圖像識別、自然語言處理等領域,成為當今人工智慧發展的重要推動力。
本論文將深度學習應用於唇語辨識中,利用深度學習的訓練技術來分析人們說話時嘴唇的型態及動作變化來識別語音,以MIRACL-VC1 Dataset為樣本,透過深度學習的技術使用卷積神經網絡(CNN)取唇部特徵值並分別於長短期記憶模型(LSTM)及雙向長短期記憶網絡(BiLSTM)進行訓練並比較其片語準確率,透過適當的數據前處理技術,如時間序列正規化,以及參數的調整,實驗結果皆以ResNet152模型呈現出較好的表現,其中ResNet152與BiLSTM結合後的準確率最高。
;In recent years, deep learning has emerged as a popular research direction in the field of artificial intelligence. Deep learning leverages multi-layer neural networks to learn features and patterns from vast amounts of data, generating highly accurate predictions and classifications. It has been successfully applied in various domains, including speech recognition, image recognition, natural language processing, and has become a significant driving force in the advancement of artificial intelligence.
This paper focuses on applying deep learning to lip reading, utilizing deep learning training techniques to analyze the shape and motion variations of the lips during speech in order to recognize spoken words. The MIRACL-VC1 Dataset is used as the sample dataset. Deep learning techniques, specifically Convolutional Neural Networks (CNN), are employed to extract lip features, followed by training with both Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (BiLSTM) models. The phrase accuracy of these models is compared. Through appropriate data preprocessing techniques such as time series normalization and parameter adjustment, experimental results demonstrate that the ResNet152 model consistently exhibits superior performance. Particularly, the highest accuracy is achieved when ResNet152 is combined with BiLSTM.
In summary, this paper explores the application of deep learning to lip reading, employing deep learning techniques to analyze lip shape and motion during speech for speech recognition. The MIRACL-VC1 Dataset is used, and lip features are extracted using a Convolutional Neural Network (CNN). Training is performed with LSTM and BiLSTM models. By employing suitable data preprocessing techniques and parameter adjustments, experimental results consistently highlight the superior performance of the ResNet152 model, particularly when combined with BiLSTM.
<br>