查詢結果分析
來源資料
相關文獻
- 中醫脈診之類神經網路辨識系統
- 中文字型資料結構之分析與數值化
- 提升電機機械實習實作能力的電腦輔助教學
- 電子績效支援系統之原理與設計
- CMM Inspection Planning from CAD Models
- Modeling Ethane Cracker with Application to Flowsheet Simulation of an Ethylene Plant
- 電腦輔助神經外科手術模擬暨定位系統之發展
- 案例式建築設計中案例調適之行為探討
- A Computer-Aided Environment for Concurrent Design of Products and Assembly Processes
- 牙醫系師生電腦使用能力與對電腦輔助學習之態度
頁籤選單縮合
題名 | 中醫脈診之類神經網路辨識系統 |
---|---|
作者姓名(中文) | 傅式恩; | 書刊名 | 中醫藥年報 |
卷期 | 15:3 1997.05[民86.05] |
頁次 | 頁170-251 |
分類號 | 413.2441 |
關鍵詞 | 中醫脈診; 電腦輔助; 波形辨識; Chinese medicine; Pulse diagnosis; Computer-aided; Pattern recognition; |
語文 | 中文(Chinese) |
中文摘要 | 本研究係發展一套中醫診脈電腦輔助系統以提供中醫師在把脈上,診斷與研究的 輔助工具。本系統共由五項模組所構成的,其分為 (1) 病患資料管理系統 (2) 脈波與心電 圖訊號擷取系統 (3) 脈波訊號分析系統 (4) 脈波訊號辨識系統 (5) 脈診資料庫系統。 藉 由這套系統我們期望能對中醫脈診做更客觀詳實的診斷與研究,揭開以往中醫把脈的神祕面 紗。另外透過與中國醫藥學院的合作,廣泛的收集各種脈象的脈波建立一完備資料庫,再藉 由圖形識別的技巧使本系統對臨床診得的脈波有自動辨識的能力,以協助中醫師在脈象的診 斷,這也是本系統最終努力的目標。在本研究中,我們主要以形為主要評估的脈象,並輔以 可直接量化歸類之勢、位、數、律所組成的脈象。 由結果統計得知: 在 18 例正常脈象有 16 例辨識無誤,在 8 例弦脈中有 7 例辨識正確,在 3 例澀脈中有 2 例正確,在 7 例滑 脈中有 6 例辨識正確,以及在 11 例弦澀脈中有 9 例正確。總體而言,成功率有八成以上 ,而在二十八脈中本系統可辨識的脈象有浮、沉、遲、緩、數、疾、促、結、濡、弱、澀、 弦、滑等以及其相關的複合脈。 而其它未能辨識之脈象主要原因有: 1. 樣本取得不易 2. 無客觀標準的依據。 3. 脈象的量測方式超出硬體能力所及 (如長短脈須三指同時量測才能 得知,而本系統只作單指單點的量測,因此無法測得此類脈象 )。故此後續對波形的收集與 標準的訂定將是研究重點方向,待有朝一日其波形的訂定能如心電圖譜一樣明確時,自動辨 識的結果才會更有意義與完備。 |
英文摘要 | The research was to develop a computer-aided system for pulse diagnosis in Chinese medicine. The system is composed of five modes:1) patient data management mode 2) pulse and ECG signals acquisition mode 3) pulse signal analysis mode 4) pulse signal recognition mode 5) pulse diagnosis database. With this system the pulse diagnosis can be more scientific and objective than that with Chinese doctor's finger tips. In the results, mainly pulse attribute that consists of "pulse shape" was estimated. In addition, pulse attributes consisting of "pulse strength" and "pulse position" and "pulse rate" and "pulse regularity", were directly estimated from the quantitative values which reach to certain levels. In the study, there was 16/18 correctness for "nomral pulse" in pattern recognition, 7/8 correctness for "string pulse", 2/3 correctness for "rough pulse", 6/7 correctness for "sliding pulse", and 9/11 correctness for "string-rough pulse," the total correctness is about 80%. In the system, we can recognize "float pulse", "profundity pulse", "tardy pulse", "soon pulse", "scud pulse", "soon-unreqularity pulse", "slow-unreqularity pulse", "weak pulse", "soft pulse", "rough pulse", "string pulse", "sliding pulse" and the complex pulses about them. In the system, some pulse attributes could not be recognized that for the reasons as follows: (1). To get some special pulse attribute samples is not easy. (2). Some pulse attributes have not standard rules to recognize. (3). Some pulse attributes must detect with three finger tips, but the system hardware uses one finger tip mole (one sensor) to detect. Thereafter, the collections of pulse waves and the definitions of pulse recognizable standards will be the most work in the future research. If the pulse diagnosis was precise definition as ECG patterns, the auto recognition of pulse wave will be more efficient and perfect. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。