一個具常模路徑比對功能的認知障礙者走失偵測系統與效能分析

Using Normals to Detect Real-Time Anomalies for Traveling Individuals with Cognitive Impairments

10.29948/JAE.201104.0010

馬瑱賢(Tien-Shyn Ma)；張耀仁(Yao-Jen Chang)；黃俊達(Jun-Da Huang)；王增勇(Tsen-Yung Wang)

社會服務 ； 走失偵測 ； 認知障礙 ； 輔助科技 ； social service ； anomaly detection ； cognitive impairments ； assistive technology

先進工程學刊

6卷2期（2011 / 04 / 01）

141 - 148

繁體中文

在身心障礙就業輔導體系中，認知障礙者無法在戶外單獨行動，常常需要別人的協助，但因為就業輔導員人力缺乏，可能無法同一時間照料所需照護的認知障礙者。認知障礙者常會因為情緒問題在上班途中離開，造成就輔員的負擔，就輔員往往要花費更多的時間以找尋認知障礙者，造成人力資源的耗損。為了減輕認知障礙就業輔導體系過於勞力密集的問題，本篇論文提出以輔具科技來協助就輔員與認知障礙者的家人，結合手持裝置及GPS定位系統，建立即時偵測走失系統。在系統中，我們將所有的移動軌跡做預處理，由原本的位置點變軌跡為一連串相連的矩形（稱為BOX），然後將學員的即時軌跡當作輸入，與事先蒐集的常模路徑比對，透過就業輔導員的篩選，總共找尋五位認知障礙學員，實際測試本系統。

Because individuals with cognitive impairments are frequently dependent on others for support across environments, strategies and skills must be introduced that directly lead to access of those supports. To relieve their job coaches from labor-intensive aids with traveling to work, a PDA is carried by the individual who has cognitive impairments. The PDA enables individuals to respond to unexpected situations such as being lost by effectively using the handheld device to alert themselves or call for assistance in the support system. In this paper, we build a real-time deviation detection system and conduct field experiments in community-based settings for individuals with cognitive impairments. We study real-time anomaly detection in a context that considers user trajectories as input and tries to identify anomaly for users following normal routes such as taking public transportation from the workplace to home or vice versa. Trajectories are modeled as a discrete-time series of axis-parallel constraints (”boxes”) in the 2D space. The incremental comparison between the current movement pattern and the norms which are previously constructed user transportation routines can be calculated. Finally, the proposed system was implemented and evaluated with five individuals with cognitive impairments.