應用序列樣式探勘技術於情境感知博物館推薦路徑系統

Applying Sequential Pattern Mining Technologies for a Context-Aware Museum Route Suggestion System

羅培恆(Pei-Heng Lo)

指導教授 ： 蔡介元

元智大學/工程學院/工業工程與管理學系/碩士(2008年)

https://doi.org/10.6838/YZU.2008.00056

摘要

導覽服務對於博物館而言是很重要的；如果沒有了導覽服務，遊客將會花很多時間找尋想要參觀的展覽品或甚至會在博物館迷路，如何發展一個滿足遊客需求的導覽系統就變成一個重要的議題。因此，本研究提出一個情境感知博物館推薦路徑系統來產生符合遊客需求的路徑。由於在博物館中展出的展覽品眾多，此系統首先會利用k-medoids演算法將展覽品分群，接著透過路徑轉換演算法，將原本以展覽品項目為依據的路徑轉換成以展覽品區域為依據的路徑，之後本系統應用I-PrefixSpan演算法在路徑資料庫中，進行時間間隔序列型樣的探勘。本系統為了推薦路徑的產生，將依照使用者在PDA上輸入的限制條件，如預計參觀時間及指定要參觀的展覽品，進行時間間隔序列型樣的篩選。此外透過RFID的技術，系統會偵測出每一個展覽區域的遊客人數，並延遲遊客進入非常擁擠的展覽區域。如果遊客沒有遵循推薦路徑上的安排，並且要求新的推薦路徑，此系統將會考慮新的限制，其中包含目前遊客所參觀過的展覽區域以及所花費的時間。最後，若有多數個符合遊客限制條件的推薦路徑，則會經由本研究所提出的評估方法來進行排序，並且將排序前三名的路線顯示回遊客的PDA上。

關鍵字

k-medoids演算法,序列樣式探勘,情境感知,導覽系統

並列摘要

uiding service plays an important role in museums. Without guiding service, visitors might spend much time for finding exhibits or get lost in the museums. Therefore, how to develop a guiding system to satisfy visitors’ requirements becomes an important issue for museums. This research proposes a context-aware museum route suggestion system that yields routes to fulfill visitors’ requirements. Because exhibit items in a museum could be large, the proposed system first apply k-medoids algorithm to conduct exhibit grouping. Next, after executing route transformation algorithm, the original route sequences with exhibit items will be replaced by the route sequences with exhibit sections. The original route sequences with exhibit items will be replaced by the route sequences with exhibit sections. Then, the I-PrefixSpan algorithm is applied to discover time-interval sequential patterns in a route database. The time-interval sequential patterns are filter out according to visitors’ requirements including intended-visiting time and must-see exhibits, which are inputted on the visitor’s PDA. In addition, the proposed system detects the total number of visitors in each exhibit section through RFID technology and postpones the time that visitors enter crowded areas. If a visitor doesn’t follow the suggested routes and want to request new suggested routes, the proposed system will consider the new constraints which contain the exhibit sections he/she has visited so far and the time he/she has spent so far. Finally, the suggested routes are prioritized by the evaluation method. The suggested routes with first three priorities will be sent back to the visitor’s PDA.

並列關鍵字

k-medoids algorithm,Sequential pattern mining,Context-aware,Guiding system

參考文獻

2.Antunes, C., and Oliveira, A.L., “Generalization of pattern-growth methods for sequential pattern mining with gap constraints,” Lecture Notes in Artificial Intelligence, 2734, pp. 239-251, 2003.

3.Asthana, A., Cravatts, M., and Krzyzanowski, P., “Indoor wireless system for personalized shopping assistance,” Proceedings of IEEE Workshop on Mobile Computing Systems and Applications, pp. 69-74, 1995.

4.Bellavista, P., Corradi, A., and Foschini, L., “Context-aware handoff middleware for transparent service continuity in wireless networks,” Pervasive and Mobile Computing, 3(4), pp. 439-466, 2007.

5.Bellavista, P., Corradi, A., Montanari, R., and Stefanelli, C., “A mobile computing middleware for location- and context-aware internet data services,” ACM Transactions on Internet Technology 6 (4), pp. 356-380, 2006.

6.Bellavista, P., Corradi, A., Montanari, R., and Stefanelli, C., “Context-aware middleware for resource management in the wireless Internet,” IEEE Transactions on Software Engineering, 29 (12), pp. 1086-1099, 2003.