關鍵字查詢 | 類別:會議論文 | | 關鍵字:Machine learning

[第一頁][上頁]12[次頁][最末頁]目前在第 1 頁 / 共有 43 筆查詢結果
序號 學年期 教師動態
1 108/1 統計系 謝璦如 助理教授 會議論文 發佈 Exploring the feasibility of data augmentation while using smaller biobank data sets , [108-1] :Exploring the feasibility of data augmentation while using smaller biobank data sets會議論文Exploring the feasibility of data augmentation while using smaller biobank data setsChia Jung Lee; Ai Ru Hsieh(謝璦如); Pui Yan Kwok; Cathy SJ FannComputational tools;Bioinformatics;Genetic epidemiology;Genotype-phenotype correlations;Phenome-wide associationEmpowered by new computing technology and low genotyping cost, large biobank projects like UK Biobank (UKB) have had fruitful results in the advancement of biomedical sciences. However, there are several smaller biobanks sampling from different ethnic groups and the statistical power to detect any association from these datasets is lower. Data augmentation by synthesizing unobserved samples show promising results in the application of machine learning algorithms. Here, we hypothesized that augmentation of small biobank data can increase statistical power and detect reliable association signals. A two-step strategy was adopted. First, control
2 108/2 資創系 張峯誠 副教授 會議論文 發佈 Image recognition approach for expediting chinese cafeteria checkout process , [108-2] :Image recognition approach for expediting chinese cafeteria checkout process會議論文Image recognition approach for expediting chinese cafeteria checkout processB.-T. Wu; Y.-W. Tsou; E. Tan; F.-C. Changfood recognition;automatic price calculation;nutrition facts calculation;object detection;YOLOv3;image recognition;machine learning;transfer learningOne of the common running themes in modern-day Chinese cafeterias is the hold up in foot traffic in queueing due to checkout. We find out that this bottleneck is caused by the staff requiring extra time to look up the prices of those miscellaneous entrees and calculating the total due amount during checkout. In this paper, this issue is addressed by introducing real-time image recognition techniques into this process. By using a webcam taking live video feed at the checkout desk with the image recognition model outputs the total due amount simultaneously, we are able to eliminate the need to perform manual price calculations. Additionally, the nu
3 108/1 資創系 陳惇凱 助理教授 會議論文 發佈 Exploring the Use of Machine Learning Techniques for Content-Based Fake News Detection , [108-1] :Exploring the Use of Machine Learning Techniques for Content-Based Fake News Detection會議論文Exploring the Use of Machine Learning Techniques for Content-Based Fake News DetectionDuenkai Chen;SuXin Chong; Kazushige Sato;Kenas Christano Umbu Zogara;Hannah M. Fakatouen_US國內無20191114~20191115是TWN2019中華民國科技管理學會年會暨論文研討會新北市, 台灣
4 107/2 電機系 劉智誠 助理教授 會議論文 發佈 Single-precision floating-point neural network with FPGA , [107-2] :Single-precision floating-point neural network with FPGA會議論文Single-precision floating-point neural network with FPGAS.A. Li; C.C. Liu; L.H. Chou; H.Y. Chen; H.S. Wei; Y.C. Wand; Y.C.; Liu, H.C. Yuen國際無20190707~20190710是CHNInternational Conference on Machine Learning and Cybernetics (ICMLC)Kobe, Japan
5 107/2 機械系 李宜勳 副教授 會議論文 發佈 Development of A Gait Training System Using Pneumatic Actuators: Control And Validation , [107-2] :Development of A Gait Training System Using Pneumatic Actuators: Control And Validation會議論文Development of A Gait Training System Using Pneumatic Actuators: Control And ValidationYing-Hui Yang;Ting-Wei Liang;Lian-Wang Lee;I-Hsum Lien國際無20190707~20190710是JPN2019 International Conference On Machine Learning And CyberneticsKobe, Japan
6 108/1 電機系 莊博任 教授 會議論文 發佈 Network Intrusion Detection using Hybrid Machine Learning , [108-1] :Network Intrusion Detection using Hybrid Machine Learning會議論文Network Intrusion Detection using Hybrid Machine LearningPo-Jen Chuang; Si-Han Lien國際淡水校園20191107~20191110是TWN2019 International Conference on Fuzzy Theory and Its ApplicationsTamsui, New Taipei City, Taiwan
7 107/2 電機系 許駿飛 教授 會議論文 發佈 Stabilization of inertia wheel inverted pendulum using fuzzy-based hybrid control , [107-2] :Stabilization of inertia wheel inverted pendulum using fuzzy-based hybrid control會議論文Stabilization of inertia wheel inverted pendulum using fuzzy-based hybrid controlChun-Fei Hsu; Bo-Rui Chen; Tsu-Tian Leeen國際無20190707~20190710是JPN2019 International Conference on Machine Learning and CyberneticsKobe, Japan
8 107/2 電機系 許駿飛 教授 會議論文 發佈 Motion control design for dynamic spherical mobile robot via fuzzy control approach , [107-2] :Motion control design for dynamic spherical mobile robot via fuzzy control approach會議論文Motion control design for dynamic spherical mobile robot via fuzzy control approachWei-Fu Kao; Chun-Fei Hsuen國際無20190707~20190710是JPN2019 International Conference on Machine Learning and CyberneticsKobe, Japan
9 107/2 電機系 李祖添 約聘專任一般講座教授 會議論文 發佈 Stabilization of Inertia Wheel Inverted Pendulum Using Fuzzy-Based Hybrid Control , [107-2] :Stabilization of Inertia Wheel Inverted Pendulum Using Fuzzy-Based Hybrid Control會議論文Stabilization of Inertia Wheel Inverted Pendulum Using Fuzzy-Based Hybrid ControlBo-Rui Chen; Chun-Fei Hsu; Tsu-Tian Leeen國際無20190707~20190710是JPN2019 International Conference on Machine Learning and CyberneticsKobe, Japan
10 107/2 電機系 李祖添 約聘專任一般講座教授 會議論文 發佈 Automatic On-Road Driving Dataset Generation Based on Object Detection and Segmentation Networks , [107-2] :Automatic On-Road Driving Dataset Generation Based on Object Detection and Segmentation Networks會議論文Automatic On-Road Driving Dataset Generation Based on Object Detection and Segmentation NetworksHao-Ting Chang; Yu-Kai Su; Chi-Yi Tsai; Tsu-Tiau Leeen國際無20190707~20190710是JPN2019 International Conference on Machine Learning and CyberneticsKobe, Japan
11 106/2 機械系 李宜勳 副教授 會議論文 發佈 Design of a Fuzzy-PID-Based 3-DOF Translational Parallel Manipulator with Rodless Pneumatic Actuator , [106-2] :Design of a Fuzzy-PID-Based 3-DOF Translational Parallel Manipulator with Rodless Pneumatic Actuator會議論文Design of a Fuzzy-PID-Based 3-DOF Translational Parallel Manipulator with Rodless Pneumatic ActuatorL.-W. Lee; I-H. Li; H.H. Chiangen國際無20180707~20180710是JPNInternational Conference on Machine Learning and CyberneticsKobe, Japan
12 106/2 機電系 楊智旭 副教授 會議論文 發佈 Evaluating Machine Learning Varieties for NBA Players Winning Contribution , [106-2] :Evaluating Machine Learning Varieties for NBA Players Winning Contribution會議論文Evaluating Machine Learning Varieties for NBA Players Winning ContributionEnglishP. Hsu; S. Galsanbadam; Jr-Syu Yang; C. YangMaching LearningICSSE 2018The reputation of NBA breach its boundary worldwide and have numerous fans around all the world. As the league concerns a lot of money and fans, several of researches have been challenged trying to predict its results and winning teams. Through its history a lot of data and statistics are collected for NBA and it’s still becoming more rich and detailed. Even though, such enormous data available, it is still complicated to analyze and predict the outcome of match. In order to achieve exceptional prediction rating we will be focusing on how individual player’s achievement influences the team win rating. For our learning techniques, we choose SVR, polynomial regression and random forest regression as they are able to give consistent result regardless of complex d
13 106/2 資管系 戴敏育 副教授 會議論文 發佈 Artificial Intelligence for Automatic Text Summarization , [106-2] :Artificial Intelligence for Automatic Text Summarization會議論文Artificial Intelligence for Automatic Text SummarizationMin-Yuh Day; Chao-Yu ChenArtificial Intelligence;Sequence-to-Sequence;Automatic Text Summarization, Long Short-Term Memory;Recurrent Neural NetworkProceedings of the 2018 IEEE 18th International Conference on Information Reuse and Integration (IEEE IRI 2018)Automatic text summarization has played a critical role in helping people obtain key information from increasing huge data with the advantaged development of technology. In the past, few literatures are related to solve the problem of generating titles (short summaries) by using artificial intelligence (AI). The purpose of this study is that we proposed an AI approach for automatic text summarization. We developed an AI text summarization system architecture with three models, namely, statistical model, machine learning model, and deep learning model as well as evaluating the performance of three models. Essay titles a
14 106/2 電機系 許駿飛 教授 會議論文 發佈 Vision-based line-following control of a two-wheel self-balancing robot , [106-2] :Vision-based line-following control of a two-wheel self-balancing robot會議論文Vision-based line-following control of a two-wheel self-balancing robotChun-Fei Hsu; Chien-Ting Su; Wei-Fu Kao; Bore-Kuen Leep.319-p.324en國際無20180715~20180718是CHN2018 International Conference of Machine Learning and CyberneticsChengdu, China
15 105/2 電機系 衛信文 副教授 會議論文 發佈 MACHINE LEARNING BASED MULTI-USER CONFLICT RESOLUTION MECHANISM FOR SMART HOME SYSTEM , [105-2] :MACHINE LEARNING BASED MULTI-USER CONFLICT RESOLUTION MECHANISM FOR SMART HOME SYSTEM會議論文MACHINE LEARNING BASED MULTI-USER CONFLICT RESOLUTION MECHANISM FOR SMART HOME SYSTEMYuan-Jie Tsai; Hsin-Wen WeiThe proceedings of NETs 2017en國際無20170714~20170716是TWNInternational Conference on Internet StudiesBali, Indonesia
16 105/1 資管系 戴敏育 副教授 會議論文 發佈 Deep Learning for Financial Sentiment Analysis on Finance News Providers , [105-1] :Deep Learning for Financial Sentiment Analysis on Finance News Providers會議論文Deep Learning for Financial Sentiment Analysis on Finance News ProvidersMin-Yuh Day; Chia-Chou LeeDeep Learning; Financial Sentiment Analysis; Financial Technology (FinTech); Finance News Providers; Stock PredictionProceedings of the 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2016)Investors have always been interested in stock price forecasting. Since the development of electronic media, hundreds pieces of financial news are released on different media every day. Numerous studies have attempted to examine whether the stock price forecasting through text mining technology and machine learning could lead to abnormal returns. However, few of them involved the discussion on whether using different media could affect forecasting results. Financial sentiment analysis is an important research area of financial technology (FinTech). This research focuses on investi
17 104/2 資管系 戴敏育 副教授 會議論文 發佈 A Study on Machine Learning for Imbalanced Datasets with Answer Validation of Question Answering , [104-2] :A Study on Machine Learning for Imbalanced Datasets with Answer Validation of Question Answering會議論文A Study on Machine Learning for Imbalanced Datasets with Answer Validation of Question AnsweringMin-Yuh Day; Cheng-Chia TsaiAnswer Validation;Imbalanced Datasets;Machine Learning;Question Answering;QA-Lab;Support Vector MachineProceedings of the 2016 IEEE 17th International Conference on Information Reuse and Integration (IEEE IRI 2016)Question Answering is a system that can process and answer a given question. In recent years, an enormous number of studies have been made on question answering; little is known about the effects of imbalanced datasets with answer validation of question answer system. The objective of this paper is to provide a better understanding of the effects of imbalanced datasets model for answer validation in a real world university entrance exam question answering system. In this paper, we proposed a question answer system and provided a comprehensive analysis of i
18 104/2 資管系 戴敏育 副教授 會議論文 發佈 IMTKU Question Answering System for World History Exams at NTCIR-12 QA Lab2 , [104-2] :IMTKU Question Answering System for World History Exams at NTCIR-12 QA Lab2會議論文IMTKU Question Answering System for World History Exams at NTCIR-12 QA Lab2Min-Yuh Day; Cheng-Chia Tsai; Wei-Chun Chuang; Jin-Kun Lin; Hsiu-Yuan Chang; Tzu-Jui Sun; Yuan-Jie Tsai; Yi-Heng Chiang; Cheng-Zhi Han; Wei-Ming Chen; Yun-Da Tsai; Yi-Jing Lin; Yue-Da Lin; Yu-Ming Guo; Ching-Yuan Chien; Cheng-Hung LeeIMTKU;NTCIR 12;QA Lab-2;World History;Question Answering;Machine Learning;University Entrance Examination;Essay Question;Answer ValidationThe 12th NTCIR Conference on Evaluation of Information Access Technologies (NTCIR-12)In this paper, we describe the IMTKU (Information Management at Tamkang University) question answering system for Japanese university entrance exams at NTCIR-12 QA Lab-2. We proposed a question answering system that integrates natural language processing and machine learning techniques for Japanese university entrance exams at NTCIR-12 QA Lab-2. In phase-1, we submitted 6 End-to-End QA
19 104/1 資管系 戴敏育 副教授 會議論文 發佈 Machine Learning for Imbalanced Datasets of Recognizing Inference in Text with Linguistic Phenomena , [104-1] :Machine Learning for Imbalanced Datasets of Recognizing Inference in Text with Linguistic Phenomena會議論文Machine Learning for Imbalanced Datasets of Recognizing Inference in Text with Linguistic PhenomenaMin-Yuh Day; Cheng-Chia TsaiImbalanced Datasets;Linguistic Phenomena;Machine Learning;Recognizing Inference in Text;Textual EntailmentProceedings of the 2015 IEEE 16th International Conf2015), Sanerence on Information Reuse and Integration, pp. 562-568Recognizing inference in text (RITE) plays an important role in the answer validation modules for a Question Answering (QA) system. The problem of class imbalance has received increased attention in the machine learning community. In recent years, several attempts have been made on the linguistic phenomena analysis, however, little is known about the effects of imbalanced datasets with linguistic phenomenon in recognizing inference in text. The objective of this paper is to provide an empirical study on learning imbalanced datasets of recog
20 105/1 機電系 王銀添 教授 會議論文 發佈 Fuzzy Data Association of Aerial Robot Monocular SLAM , [105-1] :Fuzzy Data Association of Aerial Robot Monocular SLAM會議論文Fuzzy Data Association of Aerial Robot Monocular SLAMWang, Yin-Tien; Chen, Ting-WeiVisual localization and mapping;Aerial robot navigation;Detection of image features;Robot visionProceedings of the 3rd International Conference on Machine Vision and Machine Learning (MVML'16), pp.MVML 103This study investigates the issues of visual sensor assisted aerial robot navigation. The major objectives are to provide the aerial robot the capabilities of localization and mapping in global positioning system (GPS) denied environments. When the aerial robot navigates in a GPS-denied environment, the visual sensor could provide the measurement for robot state estimation and environmental mapping. Considering the carrying capacity of the aerial robot, a single camera is used in this study and the image is transmitted to PC-based controller for image processing using a radio frequency module. The extended Kalman filter is used as the state es
21 104/2 電機系 許駿飛 教授 會議論文 發佈 Fuzzy rule-based line following control for wheeled inverted pendulum robots , [104-2] :Fuzzy rule-based line following control for wheeled inverted pendulum robots會議論文Fuzzy rule-based line following control for wheeled inverted pendulum robotsHsu, Chun-Fei; Kao, Wei-Fu2016 International Conference on Machine Learning and Cyberneticsen國際無20160710~20160713Hsu, Chun-Fei是KOR2016 International Conference on Machine Learning and CyberneticsJeju Island, South Korea
22 103/1 資工系 許輝煌 教授 會議論文 發佈 A Crowdsourcing Approach to Promote Safe Walking for Visually Impaired People , [103-1] :A Crowdsourcing Approach to Promote Safe Walking for Visually Impaired People會議論文A Crowdsourcing Approach to Promote Safe Walking for Visually Impaired PeopleChi-Yi Lin; Shih-Wen Huang; Hui-Huang HsuAndroid (operating system);Global Positioning System;accelerometers;handicapped aids;learning (artificial intelligence);mobile computing;smart phonesInternational Conference on Smart Computing (SMARTCOMP 2014), pp.7-12Visually impaired people have difficulty in walking freely because of the obstacles or the stairways along their walking paths, which can lead to accidental falls. Many researchers have devoted to promoting safe walking for visually impaired people by using smartphones and computer vision. In this research we propose an alternative approach to achieve the same goal - we take advantage of the power of crowdsourcing with machine learning. Specifically, by using smartphones carried by a vast amount of visually normal people, we can collect the tri-axial accelerometer data along w
23 97/2 資管系 李鴻璋 副教授 會議論文 發佈 以螞蟻、塔布基因為基礎的混合式雞尾酒分群法之探討 , [97-2] :以螞蟻、塔布基因為基礎的混合式雞尾酒分群法之探討會議論文以螞蟻、塔布基因為基礎的混合式雞尾酒分群法之探討李鴻璋; 朱芳儀淡江大學資訊管理學系螞蟻分群法;基因演算法;塔布搜尋法;K均值法;分群效度指標資訊管理學會第二十屆國際資訊管理學術研討會論文集=Proceedings of the 20th International Conference Information Management,11頁世新大學分群是將物件分類成群,在分群的許多方法中,包含階層式分群法、分割式分群法、密度分群法,近來更有啟發式演算法在分群上的應用。而對於傳統的分割式分群法,例如常見的K-means,使用者往往必須先決定群數,才能進行分群。本研究目的是建立一個不需事先輸入群數的分群法,並利用此方法探討使用各種分群效度指標作為目標函數的分群效果。提出一個能自動決定適合群數的演算法AGKT,混合了螞蟻分群、基因演算法、塔布搜尋法及K-means。演算法分為兩階段:第一階段由螞蟻分群法(ASCA)產生初始群組;第二階段使用基因、塔布的概念找出最適合的群數,並使用K-means分群,並以分群效度作為指標,找出最佳的分群數與分群結構。 使用UCI Machine Learning Repository和Gerrild and Lantz所提供的4個資料集,和其它七個分群方法進行比較。此外亦利用該資料集,探討目前提出之分群效度指標,並提出一種新的效度指標PBM+ index。實驗結果顯示,相較於其它7個分群方法,本方法AGKT能非常快速且正確分群,第一階段的初始分群配合第二階段基因遮罩,決定K-means的起始重心點,相較於ESTA分群法,AGKT平均約快40倍且在分群效度表現上差不多。此外利用UCI Machine Learning Repository和Gerrild and Lantz所提供的4個資料集,探討4種不同的分群效度指標,分別為:Dunn's index、Davies Boundin index、PBM index及我們所提出的PBM+ index。而實驗證實,4種分群效度指標中,以PBM+ index作為目標函數,得到了較好的分群結果。tku_id: 000089765;20140425補正 by 林明瑋;Made available in DSpace on 2
24 103/1 資管系 戴敏育 副教授 會議論文 發佈 Analysis of Identifying Linguistic Phenomena for Recognizing Inference in Text , [103-1] :Analysis of Identifying Linguistic Phenomena for Recognizing Inference in Text會議論文Analysis of Identifying Linguistic Phenomena for Recognizing Inference in TextDay, Min-Yuh; Wang, Ya-Jung淡江大學資訊管理學系Linguistic Phenomena; Recognizing Inference in Text; Textual Entailment; Knowledge-based; Machine LearningIEEEProceedings of the IEEE International Conference on Information Reuse and Integration (IEEE IRI 2014), pp.607-612IEEERecognizing Textual Entailment (RTE) is a task in which two text fragments are processed by system to determine whether the meaning of hypothesis is entailed from another text or not. Although a considerable number of studies have been made on recognizing textual entailment, little is known about the power of linguistic phenomenon for recognizing inference in text. The objective of this paper is to provide a comprehensive analysis of identifying linguistic phenomena for recognizing inference in text (RITE). In this paper, we focus on RITE-VAL System Validation subtask a
25 97/2 資工系 施國琛 教授 會議論文 發佈 RFID-Based Personalized Behavior Modeling , [97-2] :RFID-Based Personalized Behavior Modeling會議論文RFID-Based Personalized Behavior ModelingHsu, Hui-huang; Cheng, Zixue; Shih, Timothy K.; Chen, Chien-chen淡江大學資訊工程學系RFID;ambient intelligence;clustering analysis;elderly care;machine learningIEEE Computer SocietyProceedings of the Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing (UIC-ATC 2009), pp.350-355In this research, we aim at building an intelligent system that can detect abnormal behavior for the elderly at home. Deployment of RFID tags at home helps us collect the daily movement data of the elderly. The clustering technique is then used to build a personalized model of normal behavior based on these RFID data. After the model is built, any incoming datum outside the model can be seen as abnormal. In this paper, we present the design of the system architecture and show the preliminary results for data collection and preprocessing.Submitted by 輝煌 許 (h_hsu@mail.tku.edu.tw) on 2012-04-16T01:52:33Z No. of bitstreams:
26 83/1 電機系 蕭敏男 講師 會議論文 發佈 USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS , [83-1] :USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS會議論文USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS由類神經網路建立中文四聲辨認專家系統Su, Mu-Cbun; Hsieh, Ching-Tang; Shiau, Min-Nan淡江大學電機工程學系Neural Network;Fuzzy Systems;Speech Recognition;Machine Learning臺北市:中國模糊學會中華民國第二屆模糊理論與應用研討會論文集=1994 Second National Conference on Fuzzy Theory and Applications (Fuzzy 1994),頁423-428臺灣大學機械系; 臺灣工業技術學院電機系在大多數的專家系統中,無論是Crispy 或Fuzzy 的if-then 式的規則,大致上都是從人類專家口語上的敘述而得。然而,這些初始的口語規則是非常地籠統(雖然定性上是正確的) ,仍需進一步修改以達到更好的效果;因此設計專家系統的關鍵所在,就是如何從一 組資料中萃取出適當的規則來。這篇論文探討如何藉訓練類神經網路來解決這種規則萃取的問題。在經過充份的訓練之後,網路上的參數可被用來建立Cr ispy 和Fuzzy 的if-then規則。本論文的觀點及方法,是以一個連續的中文四聲辨認問題作為例證。;In most of expert systems, crispy or fuzzy if-then rules are generally derived from human experts using linguistic information. However, the initial linguistic rules are invariably rather crude and, although qualitatively correct, need to be refined to achieve better performance. Therefore the major issue in designing an
27 83/1 電機系 謝景棠 教授 會議論文 發佈 USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS , [83-1] :USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS會議論文USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS由類神經網路建立中文四聲辨認專家系統Su, Mu-Cbun; Hsieh, Ching-Tang; Shiau, Min-Nan淡江大學電機工程學系Neural Network;Fuzzy Systems;Speech Recognition;Machine Learning臺北市:中國模糊學會中華民國第二屆模糊理論與應用研討會論文集=1994 Second National Conference on Fuzzy Theory and Applications (Fuzzy 1994),頁423-428臺灣大學機械系; 臺灣工業技術學院電機系在大多數的專家系統中,無論是Crispy 或Fuzzy 的if-then 式的規則,大致上都是從人類專家口語上的敘述而得。然而,這些初始的口語規則是非常地籠統(雖然定性上是正確的) ,仍需進一步修改以達到更好的效果;因此設計專家系統的關鍵所在,就是如何從一 組資料中萃取出適當的規則來。這篇論文探討如何藉訓練類神經網路來解決這種規則萃取的問題。在經過充份的訓練之後,網路上的參數可被用來建立Cr ispy 和Fuzzy 的if-then規則。本論文的觀點及方法,是以一個連續的中文四聲辨認問題作為例證。;In most of expert systems, crispy or fuzzy if-then rules are generally derived from human experts using linguistic information. However, the initial linguistic rules are invariably rather crude and, although qualitatively correct, need to be refined to achieve better performance. Therefore the major issue in designing an
28 88/2 運管系 范俊海 副教授 會議論文 發佈 智慧型車牌自動辨識系統之研究與實作 A Study and Implementation on Automatic Intelligent Vehicle License Plate Recognition Systems , [88-2] :智慧型車牌自動辨識系統之研究與實作 A Study and Implementation on Automatic Intelligent Vehicle License Plate Recognition Systems會議論文智慧型車牌自動辨識系統之研究與實作 A Study and Implementation on Automatic Intelligent Vehicle License Plate Recognition Systems洪文斌; 李奇霖; 范俊海淡江大學資訊工程學系影像處理;車牌辨識;類神經網路;電腦視覺;機械學習;Image Processing;License Plate Recognition;Artificial Neural Network;Computer Vision;Machine Learning公元二000年台灣智慧型運輸系統國際研討暨展覽會論文集(上冊)=Proceedings of the Taiwan's International Conference and Exhibition on ITS 2000,頁419-431交通部; 中華智慧型運輸系統協會本論文提出一智慧型車牌自動辨識系統,利用類神經網路的強大學習能力,能快速有正確地辨識出車牌號碼。本系統主要由定位模組和辨識模組所構成。前者利用簡單的水平掃描線一次導數,找出車牌位置所在,後者使用一個先進的加權值共享類神經網路來學習與辨識車牌號碼。本系統設計的主要特點之一在於使用原本灰階車牌資訊進行辨識,以避免影像二值化後資訊的遺失以及切割的不正確。本系統使用Pentium-266 CPU以及64M RAM個人電腦做實驗,初步結果顯示:在取樣的173張車牌影像中,有172張定位正確,時間約為0.01秒。取其中119張車牌為訓練資料,其餘53張為測試用。類神經網路經訓練後,對原先訓練車牌辨識有116張正確,辨識率達97.4%;訓練資料亦有49張正確,辨識率達92.4﹪,辨識時間約為0.08秒。;In this paper an automatic intelligent vehicle license plate recognition system is proposed, based on the powerful learning capabili
29 88/2 資工系 洪文斌 教授 會議論文 發佈 智慧型車牌自動辨識系統之研究與實作 A Study and Implementation on Automatic Intelligent Vehicle License Plate Recognition Systems , [88-2] :智慧型車牌自動辨識系統之研究與實作 A Study and Implementation on Automatic Intelligent Vehicle License Plate Recognition Systems會議論文智慧型車牌自動辨識系統之研究與實作 A Study and Implementation on Automatic Intelligent Vehicle License Plate Recognition Systems洪文斌; 李奇霖; 范俊海淡江大學資訊工程學系影像處理;車牌辨識;類神經網路;電腦視覺;機械學習;Image Processing;License Plate Recognition;Artificial Neural Network;Computer Vision;Machine Learning公元二000年台灣智慧型運輸系統國際研討暨展覽會論文集(上冊)=Proceedings of the Taiwan's International Conference and Exhibition on ITS 2000,頁419-431交通部; 中華智慧型運輸系統協會本論文提出一智慧型車牌自動辨識系統,利用類神經網路的強大學習能力,能快速有正確地辨識出車牌號碼。本系統主要由定位模組和辨識模組所構成。前者利用簡單的水平掃描線一次導數,找出車牌位置所在,後者使用一個先進的加權值共享類神經網路來學習與辨識車牌號碼。本系統設計的主要特點之一在於使用原本灰階車牌資訊進行辨識,以避免影像二值化後資訊的遺失以及切割的不正確。本系統使用Pentium-266 CPU以及64M RAM個人電腦做實驗,初步結果顯示:在取樣的173張車牌影像中,有172張定位正確,時間約為0.01秒。取其中119張車牌為訓練資料,其餘53張為測試用。類神經網路經訓練後,對原先訓練車牌辨識有116張正確,辨識率達97.4%;訓練資料亦有49張正確,辨識率達92.4﹪,辨識時間約為0.08秒。;In this paper an automatic intelligent vehicle license plate recognition system is proposed, based on the powerful learning capabili
30 88/1 資工系 洪文斌 教授 會議論文 發佈 使用決策樹來抽取文件自動分類系統中之分類規則 Extracting Classification Rules in Automatic Document Classification Systems by Using Decision Trees , [88-1] :使用決策樹來抽取文件自動分類系統中之分類規則 Extracting Classification Rules in Automatic Document Classification Systems by Using Decision Trees會議論文使用決策樹來抽取文件自動分類系統中之分類規則 Extracting Classification Rules in Automatic Document Classification Systems by Using Decision Trees洪文斌淡江大學資訊工程學系自動文件分類;決策樹;資訊檢索;機器學習;Automatic Document Classification;Decision Tree;Information Retrieval;Machine Learning第四屆人工智慧與應用研討會論文集,頁160-166大葉大學資訊工程學系; 人工智慧學會自從Maron於1961年提出首篇文件自動分類的論文以來,傳統的分類方法不外乎機率模式與向量模式。近年來的研究也加入了統計分析、專家系統、自然語言處理、和類神經網路等先進的技術,以提高分類的正確性。以上所提的諸方法中,其對文件自動分類而言,均可視為是黑箱作業,因其分類行為或分類規則無從得知。本研究利用機械學習技術中之Quinlan的C4.5決策樹(Decision trees)來抽取文件自動分類系統中之分類規則,期使文件自動分類系統之分類行為透明化,而人們可藉由所抽取之分類規則進一步來驗證文件自動分類之正確性。在本研究中,我們採用ACM Computing Reviews的分類法作為分類的依據。我們從該期刊共收錄了56個中類別,6424篇論文為實驗用資料。再以其中的論文題目和出處當作該文件的素描(Profile)。取其中十分之一作為測試資料,其餘為訓練資料。我們從訓練資料中,使用 Quinlan的決策樹共抽取出1162條分類規則。再利用此分類規則分別對訓練文件及測試文件做分類,實驗結果分別為:訓練資料召回率為67.7%,測試資料為 45.5%。若將上述規則再精簡成 29O條分類規則,則訓練資料召回率變為52.3%,而測試資料略降為 43.0%。;Since Maron proposed the first paper on automatic
[第一頁][上頁]12[次頁][最末頁]目前在第 1 頁 / 共有 43 筆查詢結果