Chung Cheng University Institutional Repository
Not a member yet
889 research outputs found
Sort by
探討影響麻醉資訊系統導入之關鍵因素-以雲嘉南地區醫療院所為例;A Study on the Critical Factors for Affecting AIMS Implementation – Taking Yunlin, Chiayi, and Tainan Areas for Examples
No full text[[abstract]]近二十年來，歐美地區各醫療院所之麻醉醫療單位開始導入麻醉資訊系統(Anesthesia Information Management Systems, AIMS)，用以協助麻醉人員執行臨床醫療措施，降低麻醉醫療人員工作負擔、提升麻醉紀錄的完整性，進而確保麻醉安全，亦協助臨床人員日後追蹤與醫療研究使用。 適當的運用資訊科技輔助臨床上的醫療行為，有效提升病人安全及醫療品質是當前醫療科技管理領域中重要的議題之一，以合適且安全的醫療資訊科技介入醫療行為，將傳統手寫紀錄轉變成為電子病歷資訊化，降低人員因醫療過程繁忙而造成的醫療疏失，進而達到麻醉安全性及病人安全的目的。 本研究採用科技接受模式為研究架構之基礎，結合資訊系統成功模式，探討影響麻醉資訊系統導入之關鍵因素，針對麻醉科醫事人員進行問卷，回收有效樣本問卷共計為177份，並以統計軟體Smart PLS 3.2與SPSS 22.0去驗證各變數之間的假設關係及依變數間之解釋能力；研究結果發現，系統品質與資訊品質此兩項構面對於知覺有用性及知覺易用性具有顯著之影響；組織系統對於知覺有用性具正向的影響力，進而再影響使用意圖。
Anesthesia Information Management Systems have been introduced into the anesthesia unit in medical institutions in Europe and America for the past 20 years. Using AIMS to assist the anesthesia staff to nurse clinical medical measures, reduce the burden of anesthesia staff and enhance completely of the anesthesia record. Not only to ensure the anesthesia safety, but also to assist staff in the follow-up study and medical research.Appropriately use information technology to assist clinical behavior, improve patient safety and quality of medical care is an important issue in the field of medical technology management. With appropriate and safe medical information technology to intervene in medical behavior to transform the traditional handwritten records into electronic medical record information, to reduce the medical errors caused by busy medical procedures, and then achieve the purpose of anesthesia and patient safety.This research is mainly based on Technology Acceptance Model and puts it into Information System Successful model in order to know about what kind of factors affecting AIMS implementationcan. To have anesthesiology staff questionnaire distributed who use the AIMS. We have gathered 177 effective questionnaires and use the Statistics Software Smart PLS 3.2 and SPSS 22 to validate the assumption of relationship between each variable and explanation ability between variables. According to the survey, we found that system quality and information quality are positive affect perceived usefulness and perceived ease of use; organization system also positive affect perceived usefulness, and then affect the usage intentions
應用資料探勘技術建構老人慢性病人流失預測模型;Application of Data Mining Technology to Construct the Predicting Model of Elderly Patients Loss with Chronic Diseases
No full text[[abstract]]高齡化之趨勢，慢性疾病的盛行率高，在競爭激烈的醫療市場環境，如何深化顧客關係管理，提升醫療服務品質，病人的忠誠度，減少顧客流失是目前醫療院所的永續經營之道，而資料探勘已是廣泛使用探討顧客流失的研究方法及技術。 本研究以南部某區域教學醫院65歲以上開立慢性病處方箋病人，總共收集28,261筆就醫資料，採資料探勘分類技術之決策樹J48 (C4.5)、隨機森林，羅吉斯迴歸及支援向量機四種分類器建立65歲以上開立慢性病處方箋病人流失預測模式，實驗資料再將10組訓練樣本分別進行資料分析。隨後採用10疊交叉驗證法(10-fold cross-validation)驗證預測模式效能。 實驗結果顯示以隨機森林分類技術所建構的預測模型最佳，AUC：91.33%，其次為邏輯斯迴歸，AUC：90.12%。本研究中預測因素包括最近一次門診天數、全年門診次數、門診業務量及全年門診費用是預測流失有高度相關性。期能經由本研究結果供醫院管理者針對可能造成流失之病人能即早介入預防措施，進而減少病人流失，建構完善顧客關係管理。
Currently, the trend of aging and the prevalence rate of chronic diseases has become higher. As a result, how to deepen Customer relationship management, improve the quality of medical services, patient loyalty and reduce customer loss in the highly competitive medical market environment is the way of sustainable development to current medical institutions. Moreover, the research methods and technology of data mining has been widely used to explore customer loss. In this study, a total of 28,261 medical information was collected from the teaching hospitals in the southern part of Taiwan in the area of 65 years old and adopting four kinds of classifier—the Decision Tree J48 (C4.5), Random Forest, Logistic Regression and Support Vector Machine to establish the establishment of chronic disease prescription over 65 years of age patient loss prediction model. And then, use 10 groups of training samples to analyze data. The 10-fold cross-validation was then used to verify the predictive mode performance. The experimental results show that the prediction model constructed by random forest classification is the best—AUC: 91.33%, followed by logistic regression, —AUC: 90.12%. The predictors of this study included a high degree of correlation with the number of outpatient clinics, the number of outpatient visits, the outpatient service volume and the annual outpatient cost. I expect that the results of the study can be used to help the hospital managers to intervene early in preventive measures, thereby reducing the loss of patients and improve the customer relationship management
影響行動即時通訊軟體APP持續使用之因素研究;A Study on the Influencing Factors of Continuous Usage Intention of Mobile Instant Messaging APPs
No full text[[abstract]]在現今時代裡，由於網路快速發展，智慧型裝置與個人行動網路也日漸普及。因為行動網路普及的關係，現代人常常透過行動即時通訊軟體APP來傳遞訊息。在這個時代，人們常常使用行動即時通訊軟體APP來傳遞訊息。行動即時通訊軟體APP開發者亦把影響使用者持續使用的影響因素視做一個在開發過程中需被納入考慮的重要策略。本研究以Deng, Lu, Wei and Zhang (2011)建立的顧客價值與滿意度關係之模型為基礎架構，並整理過去使用者滿意度與持續使用意圖相關研究，延伸此模型並修改成適合本研究之情境，之後加入認知移動性及使用者體驗及認知互補性來探討使用者持續使用即時通訊軟體APP的影響因素，並使用問卷調查法來驗證假說。有效問卷共計有524份，並使用結構方程式(SEM)來進行資料分析。結果表明，使用者體驗、功能性價值、情緒性價值與認知互補性會正向影響使用者滿意度，使用者體驗會正向影響功能性價值、情緒性價值、社會性價值與持續使用意圖，使用者滿意度與認知移動性會正向影響持續使用意圖。
In today's era, smart devices and personal mobile networks have become increasingly popular due to the rapid growth of the Internet. Because of the popularity of mobile networks, people often use mobile instant messaging software APP to deliver messages. An APP developer needs to take the factors affecting users' continuous usage of the APPs into consideration in order to develop popular apps. Based on the model proposed by Deng, Lu, Wei, and Zhang in 2011, which addressed the relationship between customer value and user satisfaction, this study included perceived mobility, user experience, and perceived complementarity to explore the factors that affect users' continuous usage intention of instant messaging software (APP). A questionnaire survey was conducted to validate the hypotheses.524 valid responses were collected and analyzed with structural equation modeling technique. The results showed that user experience, functional value, emotional value, and perceived complementarity had positive effects on user satisfaction. User experience had a positive impact on functional value, emotional value, social value, and continuous usage intention. User satisfaction and perceived mobility had positive impacts on continuous usage intention
以評論可視性為基礎建構評論有益性之預測模型;Developing Prediction Models for Online Review Helpfulness Based on Review Visibility Features
No full text[[abstract]]在Web 2.0的快速發展與電子商務盛行的環境下，電子商務平台提供消費者一個完整的商品購買循環：購買前搜尋商品資訊與消費者意見、線上消費產生商品訂單與結帳支付、售後服務與反饋。消費者能以線上評論的方式，分享使用經驗及意見回饋，亦能自該社群獲取產品、服務資訊以作為產生最終消費行為之參考，經此互動所產生的訊息內容形成蘊含強大電子口碑的用戶生成內容資料庫，其中具有較高的有益性的評論不僅是影響消費者產生最終購買決定之參考，更成為影響對於商家銷售在產品、服務獲益之重要因素。每天產生龐大的評論內容，雖然可以充足地提供給消費者富有價值的訊息，卻也衍伸出資訊過載的問題，因此許多的商家加入排序機制與條件篩選幫助消費者在有限時間下選擇性地閱讀評論內容，並減少消費者在資訊搜尋程序所需之成本。本研究旨在以長期性地觀察線上評論因時間、條件篩選與排序機制後所陳列位置的移動狀況，從消費者的角度提出影響可視性之因子，探討其對於評論有益性之影響，並建構有效線上評論有益性的預測模型。透過Python 撰寫網路爬蟲程式，針對目標產品之線上評論內容及其於程式運行當天所在之網頁位置資訊，並利用自然語言處理產生自變數，以評論品質(Review Quality)、文本特徵(Text Characteristic)與評論可視性(Review Visibility)三個分類構面進行變數分類，採用線性迴歸(Linear Regression)、迴歸樹(Regression Tree)、支援向量機迴歸(Support Vector Regression)及最近鄰居法(k-Nearest Neighbors Algorithm)四種資料探勘技術進行線上評論有益性分析及預測。透過研究結果發現，以迴歸樹建立之有益性預測模型效能最好，並且加入評論可視性的變因便能顯著地提升評論有益性之預測模型效能，而對於商品評論及旅館評論兩者將有不同的最佳變數組合，藉此幫助消費者或是電子商務業者找出最有幫助的評論。
Under the circumstances of rapid growing Web 2.0 and prevailing electronic commerce, e-commerce platforms offer consumers a complete product purchasing cycle, which includes searching for product information and consumer opinions before purchasing, completing an online purchase and paying for the order, enjoying post-purchase services and giving feedbacks. Consumers can share their own using experiences and opinions by posting online reviews. They can also obtain product or service information from the social networking site and take it as a reference when making final purchase decision. The review contents produced through interaction form a user generated content database which contains powerful electronic word-of-mouth. The reviews that have the highest helpfulness not only impact consumers' final purchase decision, but also are the factors that can affect a business's sales on product and service. There is an enormous amount of reviews generated every day. Although these reviews provide sufficient and valuable information, they derive the problem of information overload. Therefore, many businesses use sorting and filtering mechanism to help consumers reading the reviews selectively and reduce the costs of their information searching process.The main purpose of this research is to do a long-term observation on the moving situation of arrangement of online review positions based on time, sorting and filtering mechanism. We identified some factors that might affect the visibility from consumers' perspective, explored their influences on review helpfulness and constructed an effective forecasting model of online review helpfulness. We implement a web crawling program in Python which crawled the online reviews of target product as well as its web page location, and used natural language processing to generate independent variables. We classified the variables by three aspects, which are review quality, text characteristic, and review visibility. We also adopted linear regression, regression tree, support vector regression, and k-nearest neighbors algorithm, the four data mining technologies to do analysis and make prediction of online review helpfulness. There are some results found in this research. The forecasting model of helpfulness constructed with regression tree has the best effectiveness. Moreover, adding variable of review visibility can significantly increase the effectiveness of review helpfulness forecasting model. There are also different combinations of variables for product reviews and hotel reviews, which can help consumers or e-commerce businesses find the most helpful reviews
影響採用行動支付繳納政府規費或稅款意圖之因素;Factors Affecting the Adoption Intention of Paying Government Fees or Taxes through Mobile Payment Services
No full text[[abstract]]創新智慧金流工具—行動支付，已成為各先進國家及城市促進商圈發展和擬定市場行銷策略之利器，國內市場也正從萌芽期進入發展初期，但應用於公共費用支付之相關研究仍為罕見。政府在推動行動支付繳納規費和稅捐時，必須要了解究竟那些因素影響民眾使用這項服務的意願，才能制定有效措施，順利推動行動支付，具體實踐掌上政府理想，提供民眾便捷的生活環境。本研究以價值接受模式為基礎架構，加入知覺風險、信任及行動支付特性，探討影響民眾採用行動支付繳納政府規費或稅款意圖的關鍵因素。我們採用網路問卷調查曾經使用過行動支付者，共收集471份有效問卷，並透過結構方程模式分析資料。研究結果顯示知覺價值、知覺風險及信任對採用意圖有顯著影響；行動性、相容性及便利性對功能性利益有顯著影響；功能性利益、經驗性利益、象徵性利益及技術性對知覺價值有顯著影響。
Mobile payment, an innovative payment instrument, has been widely applied to promoting the development of business districts and working out marketing strategies in technologically advanced countries and cities. While our domestic market starts stepping into the early stage of mobile payment development, studies on using mobile payment to pay public expenses are still seldom found. However, key factors affecting citizens’ intention to use mobile devices to pay government fees and taxes need to be identified and appropriate measures be developed and applied to ensure successful promotion of this service to public.Based on the Value-Based Adoption Model, VAM, this study integrated perceived risk, trust, and M-payment characteristics into the research model to explore the key factors that affect the usage intention of mobile devices to pay government fees and taxes. An online questionnaire survey was conducted to collect data. 471 valid responses were collected and analyzed with structural equation modeling, SEM, technique. The results showed that perceived value, perceived risk, and trust affected the intention to use mobile payment; mobility, compatibility, and convenience affected functional benefits; and functional benefits, experiential benefits, symbolic benefits and technicality affected perceived value
基於心率變異度數據之駕駛員疲勞偵測和預測系統;Heart-Rate Variability based Driver Fatigue Detection and Prediction System Design
No full text[[abstract]]由於過去的駕駛員疲勞偵測系統大多沒有考量到駕駛收到警告後，欲開車前往停車地點休息需要一段緩衝的時間。若系統無法提供這段時間，將無法確保駕駛陷入疲勞後的行車安全。因為駕駛有可能在疲勞的狀態將車輛開往停車地點，而這段時間將是非常危險的。為解決此問題，本文提出一個可以同時進行即時偵測與預測駕駛員疲勞的駕駛員疲勞監測系統。本系統使用倒傳遞式類神經網路模型構建即時偵測與預測之模組。即時偵測模組藉由分析駕駛員的心率變異度來判斷駕駛員的疲勞狀態，並在駕駛員陷入疲勞時發出警告使其避開危險。預測模組藉由分析過去駕駛員疲勞狀態的變化預測駕駛員未來的疲勞狀態，並在適當的時機發出早期預警使駕駛得以提前準備停車。然而，考量到心率變異度易受干擾，數據震盪頻繁的特性，本文提出基於數據品質的動態權重移動平均方法，藉由分析數據的品質動態調整各個時段數據在移動平均上的權重以降低干擾對最後分析結果造成的影響，進而提高偵測與預測的準確率。在實驗中表明本文所提出的系統能夠有效的即時偵測駕駛員的疲勞，其準確率高達96%，也驗證本系統能夠有效的預測駕駛員的疲勞狀態，在預測未來約15至17分鐘後駕駛員的疲勞狀況，準確率高於90%。而本論文所提出的動態權重移動平均方法比傳統的移動平均方法能更有效的抹平數據的震盪增加系統疲勞偵測與預測準確率約10%，此點也在實驗中得到證明。
Host existing driver fatigue detection systems are real-time; however, they do not allow drivers enough buffer time to park his/her vehicle after he is fatigued. As a result, the system is not able to ensure driving safety after the driver is fatigued, which is very dangerous. To solve this problem, this Thesis proposes a Driver Fatigue Monitoring System which can simultaneously detect and predict driver fatigue. In this Thesis, we use a back-propagation neural network (BPNN) model to perform real-time fatigue detection and prediction by analyzing a driver's heart rate variability. The prediction module predicts the driver's future fatigue situation by analyzing changes in the driver's past fatigue levels and sends an early warning so as to give the driver enough time to park safely. However, heart rate variability is susceptible to interferences or shocks and their occurrence frequency. In this Thesis, we propose a dynamic weight moving average method based on data quality, which can dynamically adjust the weight of each time slot on the moving average by analyzing the quality of the data to reduce the influence of the interference on the final analysis result and improve the accuracy of detection and prediction. Experiments show that the proposed system can effectively detect a driver's fatigue, with an accuracy rate of up to 96%. The proposed system can also effectively predict a driver's fatigue situation, by up to 15 to 17 minutes before being actually fatigued, and the accuracy is higher than 90%. The dynamic weight moving average method proposed in this Thesis is more accurate than the traditional moving average method, it improves 10% accurate in detection and prediction. This is also proved in the experiments
基於深度學習之雜訊分類的圖像復原方法;Deep Learning Based Image Restoration with the Approach of Noise Classification
No full text[[abstract]]近幾年，因為電腦硬體與演算法的改進，深度學習成功的應用到各種用途上。諸如圍棋、藥物、或是影像辨識上的應用等皆由不同的類神經網路設計而成。此篇論文提出利用捲積網路結合傳統之圖像復原，將欲處理的圖像先分類後再行傳統圖像復原之方法。一般復原方法的測試集大多由已知原圖打入雜訊後製造出來，然而現實中的實作並沒有任何可供參考的對象或是標竿。論文中提出之雜訊分類模型NCM(Noise Classification Model)可用於對欲處理之圖像做雜訊的預先判別，並將相關參數或指標值讓接其後的圖像處理程序能有所依據的個別處理。 本研究中之NCM將會以判別圖像之加性高斯白雜訊為目的，並將判別出的標準差值當作NLM(Non-Local Means Algorithm)的參數帶入並作圖像復原。NCM的的模型訓練將由AWGN(Adaptive White Gaussian Noise)所產生之小圖像訓練集作出雜訊判別標準差值之。訓練完成後的NCM將被拿來測試對作了不同程度之AWGN雜訊模擬的“Lena”圖像之判別。其判別結果雖然不能十分精準，但是NCM所判別的標準差值和輸入的雜訊圖之標準差值成嚴格遞增函數。這意味著NCM不會將不同的雜訊圖分類預判成擁有相同的雜訊標準差值。如同人類一樣，雖然不能清楚說出絕對數值，但是能判別出相對的雜訊標準差值。最後，NCM僅僅是一個實作上圖像處理的可行方案，仍然有其他可以改進或是將其擴增判別依據之構想。本研究提出在處理圖像前先使用NCM做雜訊預測並再作圖像之復原，和未使用NCM相比可以解決現實環境中沒有參考數值的問題。
In recent years, deep learning has been successfully implemented in many different purposes because of the huge improvements in computer hardware and algorithms. Different neural networks are designed to fit different purposes, such as go (game), medicine, and image recognition. This thesis proposes a method which combines convolution neural networks and classic image restoration method to classify images before the restoration. Most of the testing data of restoration method are produced from known original images by adding noises on each pixel. However, there are no referenceable labels for restoration method in practices. The NCM (Noise Classification Model) proposed in the thesis can be used in predicting the noise of the input images, so the restoration method can restore the images with the prediction. The NCM model is designed to classify the deviation values of images produced by AWGN (Adaptive White Gaussian Noise). The deviation values of the prediction will be the parameter of NLM (Non-Local Algorithm) which is one of famous restoration methods in in the field of restoration. The model is trained by tens of thousands of small images which are all produced by AWGN based on different random single colors. After training, the NCM is tested with different noised Lena pictures. Although the results of predictions are not very accurate, the curve of the deviation values of the prediction and input images is a monotonic increasing function. That means the NCM will not predict two different noised images into the same deviation value. Finally, the proposed NCM is simply a new possible way to restore images, despite there are still some other improved or expand ideas. This study proposes a method which predicts the input images before the restoration and that solves the problem not having a referenceable variable in practice
基於LSTM類神經網路進行電器大數據特徵辨識之研究;Feature Identification Approach for Big Appliance Data Based on LSTM Neural Network
No full text[[abstract]]全球極端氣候加劇，節能減碳成為世界各國努力的目標，智慧電表的問世可幫助我們監控電器用電狀況，為環境保護貢獻一點心力。不過，監控用電狀況產生的大數據資料在進行電器標示卻需要透過人工來完成，手動標示可能會發生標示錯誤，或是由不同人工標示導致名稱不一致的狀況。為解決上述問題，本論文主要目的在採用RNN LSTM類神經網路建立模型，透過將一部分手動標示好電器名稱的電力資料，輸入訓練至模型中使其設法找出電器名稱與各種電器的關聯性，來提供未標示電器資料的可能名稱，減少手動標示的工作量。由於圖形處理器通用計算架構的普及，透過圖形處理器來處理適合平行處理運算的類神經網路模型，比起使用傳統中央處理器能夠達到不錯的加速效果，使得模型訓練可更快完成。本研究透過參數調整策略，得到實驗結果的最佳訓練模型為隱藏層使用512個LSTM節點，12層隱藏層，不設定Dropout，活化函數使用ReLU，學習速率設為0.000001，平均隨機辨識率可達到88%，單一電器連續資料辨識率平均可達83.6%。
Energy saving and carbon dioxide reducing are significant issue now. We can use the smart meters to monitor the power usage of applications to pay some offer to environment protection. Although the electrical feature collection can be done by smart meters, applications need to be labeled by human. There would be some mistakes as manually labeling or non-unified names. To solve this issue, we propose a novel approach to conquer this problem automatically. In this paper, we use the LSTM neural network in our model to achieve application recognition. First, we label part of data manually as input data to train our model to find the relationship between the name and the electric feature. Then we use the unlabeled data as input to let the model to recognize them. Now we have GPGPUs to help us to accelerate the parallel computing and the training progress of neural networks. Through the parameter adjustment policy, we set our model with 512 LSTM nodes per hidden layer, 12 hidden layers, no dropout, ReLU as activation function, learning rate to 0.000001. The result shows that we achieve 88% accuracy in random data testing and 83.6% accuracy in sequential data testing of single application
應用卷積與遞歸神經網路於跌倒偵測中之姿態分析;Convolutional Recurrent Neural Networks for Posture Analysis in Fall Detection
No full text[[abstract]]近年來已經有許多方法使用穿戴式裝置能夠偵測在智慧家庭中的異常事件。然而，穿戴式裝置面臨許多的困難，像是電池容量受到限制與穿戴上的麻煩。因此，非穿戴式的裝置成為一個能提供予用者更舒服的體驗及能持續提供偵測的模型。不過使用非穿戴式裝置並得到高的準確率依舊存在許多的困難。在本論文中，我們實作了一個連續性的深度學習模型。這個模型能夠在獲得一連串連續的影像之後，判斷異常事件的發生，並且我們使用微軟的Kinect感應器作為我們的非穿戴式裝置。除此之外我們使用了另外一種深度學習的技術稱為遞歸神經網路(RNN)其中的一個分支Long short-term memory. LSTM在連續性的判斷有很好的成果。另外，我們使用了不同的高解析度圖片，以及一些經過預處理的圖片與深度圖作為我們模型的輸入。最後我們實驗結果顯示我們在居家異常事件判斷中有不錯的表現。
Existing methods have extensively addressed the issue of detecting ab-normal events in a smart home environment through wearable sensors in thepast years. However, the limitations of wearable sensors include the limitedbattery power as well as the use and adoption challenges of wearable activ-ities on a daily basis. The use of non-wearable and non-intrusive sensors isnecessary for providing better user experiences and achieving a sustainableand reliable detection model. However, it is still very challenging to analyzesuch non-wearable sensor data with a high level of accuracy. In this paper,we present a continuous deep learning model which receives a set of con-secutive images for classifying posture types using a Microsoft Kinect as ournon-wearable sensor. We adopt a deep learning technique called the recurrentneural network (RNN) using the long short-term memory (LSTM) architec-ture to construct our detection model by identifying human postures in falldetection. Furthermore, we investigate the inputs for our model by extractingthe features from the pre-processed high-resolution RGB images, includingbody shape, depth and optical flow. As a result, the body shape with genuinemotion and depth information are considered. Finally, we present the experi-mental results to demonstrate the performance and novelty of our approach.Keywords: Posture analysis
基於SVM分類方法之 設計電線使用品質評估;Power Line Quality Assessment Based on Support Vector Machine
No full text[[abstract]]由於物聯網技術日漸發展，其應用範圍正不斷的擴展中，而在當中智慧電力系統有關之發展一直是熱門的議題之一，因此廠商致力於開發相關智慧設備，然而目前發展重點大都注重在於智慧電器或智慧插座等，卻甚少注意隱藏於住宅當中不起眼角落之電力線，電力線隨著時間或外在等因素，將會造成其品質逐漸劣化，而劣化之電力線不但容易造成額外功耗，更可能造成觸漏電、甚至電線走火等等危害，然而目前主要之電力線防護措施，皆為被動式之機制，必須當電力系統發生明顯問題後，才能進行反應。鑑此，本論文主要目的在於嘗試建立各類型電力線樣本，並且收集其電力線特徵值，再利用SVM分析方法進行電力線品質評估，最後透過即時網頁將分析成果，顯示於頁面之中，使用者即可輕易地得到電力線資訊以及相關提醒。
Due to the fast development of Internet of Things in the recent years, the applied fields gradually expanded. And one of the hot topics is smart electric applications. Many manufacturers are devoted to create smart related appliances. However, now, most of the developments focus on smart appliance and smart socket and less focus on the quality of power line which in house corner. Because of the time passed or the influence by man-made and external reasons, power line’s quality will decline by degrees. The deteriorating power line make not only additional power consumption but also the higher probability of electric shock, even cause an electric fire. But the major power line protection mechanisms are passive type. They work only when a evident problem happened. Due to the above reasons, the main purpose of this paper is trying to make power line samples, collect the power line features, and then evaluate the power line quality by support vector machine. As the result has done, the real-time web will show it immediately. Users can get the power line information and the alert easily