視覺監控電腦化實作評量之效度化研究以感覺統合臨床觀察為例

The Sensory Integration Clinical Observation Using Visual Surveillance Based Computerized Performance Assessment and Its Validation

吳慧珉(Huey-Min Wu)

指導教授 ： 林世華

國立臺灣師範大學/教育學院/教育心理與輔導學系/博士(2009年)

摘要

本研究是以「感覺統合臨床觀察」為主要研究領域，從實作評量之觀點，探討使用視覺監控分析人物目標之姿勢動作並結合樣式辨識，應用於診斷受試者感覺統合障礙之有效性。
研究結論彙整如下：
一、本研究根據感覺統合臨床觀察電腦計分模式所發展的感覺統合臨床觀察電腦化診斷工具，具有良好之信度與效度，適用於診斷感覺統合臨床觀察之障礙類別。
二、「趴姿伸直」與「臥姿彎曲」之重要觀測向度（頭部、胸部、手部、腳部、協同性、穩定度）診斷，最大概似分類器之診斷正確率最高。
三、原始資料型態在「趴姿伸直」與「臥姿彎曲」各重要觀測向度之訊息融合時，具有較高之診斷正確率。
四、在「趴姿伸直」整體診斷時，選取頭部、手部、腳部之向度在最大概似分類器可以提升診斷正確率；在「臥姿彎曲」整體診斷時，選取頭部、手部、協同性、穩定度之向度在最大概似分類器可以提升診斷正確率。
五、年齡層不同之受試者在「趴姿伸直」與「臥姿彎曲」之量的表現（持久度）有顯著差異， 5歲的受試者優於4歲的受試者。
六、在4歲年齡層，不同性別之受試者在「趴姿伸直」之量的表現有顯著差異，女生在「趴姿伸直」之量的表現優於男生；在5歲～6歲之年齡層，性別之不同在「趴姿伸直」與「臥姿彎曲」之量的表現有顯著差異，女生均優於男生。
七、不同性別受試者在「趴姿伸直」與「臥姿彎曲」之質的表現有顯著性差異，男生感覺統合功能障礙的人數在「趴姿伸直」與「臥姿彎曲」皆多於女生。

關鍵字

視覺監控 ； 感覺統合臨床觀察 ； 感覺統合功能障礙 ； 實作評量 ； 樣式辨識

並列摘要

Abstract
The purpose of this study is to develop a computerized assessment tool for sensory integration clinical observation. Based on the view of performance assessments, the pattern recognition is combined with the visual surveillance procedures to analyze the posture movements (prone extension and supine flexion) and to diagnose the sensory integration dysfunction of subjects in this study.
The major findings of this study are summarized as follows:
1. With good properties in both reliability and validity, the computerized assessment tool for sensory integration clinical observation developed in this study has good performances in diagnosing disorder of sensory integration functions of subjects.
2. The prediction rates for employing the maximum likelihood classifier are best in diagnosing disorder of sensory integration functions in terms of important features of prone extension and supine flexion.
3. The prediction rates for raw data information are best in diagnosing deficits of sensory integration functions in terms of prone extension and supine flexion.
4. Selecting the features of head, hands, and feet can improve the prediction rates in the maximum likelihood classifier in terms of prone extension; selecting the features of head, hands, coordination, and stability can improve the prediction rates in the maximum likelihood classifier in terms of supine flexion.
5. Analysis of variance (ANOVA) indicates that there were statistically significances on year groups in terms of quantity performances of prone extension and supine flexion. The performance of the 5-year olds subjects is better than the 4-year olds subjects.
6. From the 4-year olds to the 6-year olds , ANOVA indicates that there were statistically significances on gender groups in terms of quantity performances of prone extension and supine flexion. The performance of girls is better than boys.
7. Chi-square testing indicates that there were statistically significances on gender groups in terms of quality performances of prone extension and supine flexion. The number of boys with sensory integration dysfunction is much more than girls.

並列關鍵字

pattern recognition ； performance assessments ； sensory integration clinical observation ； sensory integration dysfunction ； visual surveillance

參考文獻

鄭裕達(2004)。人臉追蹤與辨識。臺灣大學機械工程學研究所碩士論文，未出版，台北市。

林巾凱、曾美惠（2001）。小兒職能治療評估工具使用調查。台灣醫學，5， 636-644。

胡名霞、林慧芬（1994）。 成年人站立平衡之研究-感覺整合與年齡效應之分析。 中華民國物理治療雜誌，19，66-77。

姚開屏（1997）。另一點不同的聲音：再談感覺統合治療。職能治療學會雜誌， 15，45-50。

黃妙玲、蔡長海、李政淳（1998）。均一性第一型肌纖維過多及第二型肌生長不良之先天性肌病變：一病例報告。中華民國小兒科醫學會雜誌，39（1）， 62-74。