運用智慧型手機感測資訊進行人類行為辨識

Using Smart Phone Sensor Data for Human Activity Recognition

潘郁薇(YU-WEI PAN)

指導教授 ： 柯仁松

國立中正大學/工學院/資訊工程學系/碩士(2016年)

摘要

摘要
對於一個成功的手機應用程式，最重要的是能夠了解使用者的需求與目的，結合使用者的習慣。經由取得使用者的資訊，可以提供更好的服務。使用者行為辨識可以經由探勘使用者的資訊，擬定出模型。
資料探勘(Data Mining)的概念是利用資料來建立一些模擬真實世界的模式(Model)，利用這些模式來描述資料中的特徵(Pattern)以及關係(Relation)。經由這些模式可以瞭解資料的特徵與關係，進而提供決策所需要的資訊或幫助做預測。
隨著數位時代的來臨，行動裝置的應用也越來越廣泛，智慧型手機能提供的使用者感測資訊也越來越多，如：定位感測器、溫度感測器、濕度感測器、加速度感測器，利用這些感測器資訊可以建立新的資料探勘應用。
本論文目的是希望能蒐集使用者手機上的資訊來做人類日常生活行為辨識，運用手機上的感測資訊，擷取即時的加速度值和定位資訊，蒐集使用者進行四個日常生活的行為的資訊，分別為走路、跑步、乘車、休息(靜止狀態)。透過儲存這些資訊得到的數據進行記錄與分析，並使用Weka這個資料探勘工具將儲存這些資訊得到的數據進行記錄與分析來做資料預先處理和分類，可判斷出使用者的日常行為。

關鍵詞：資料探勘、行為辨識、感測資訊

關鍵字

資料探勘 ； 行為辨識 ； 感測資訊

並列摘要

Abstract
In order to run a successful application, the most important is to understand users’ intentions and desires, then, combine with user habits. By capturing these information, they can provide better service and enhance marketing strategy to achieve this goal. Human activity recognition is an application that can help people to explore the useful data of users’ information.
Data Mining is a process to find model from a amount of data, use data to build the model which is use to simulate the real world, then, use these models to describe the patterns and relations from the data. It can provide useful information when making decision or help to making predictions.
Nowadays, applications for mobile devices become more widely. Smart phones supply a lot of user’s sensor data such as location sensor data, temperature sensor data, humidity sensor data and acceleration sensor data. Those sensor data build different point of view for data mining applications.
In this study, the goal is expect that every day activities are recognized from data collected using smartphones accelerometer sensors and location information. We collected sensor data from users as they performed daily activities such as walking, running, riding and relaxing(static). We use data mining tools for data preprocessing and classification by analyzing and storing data so that we can recognize human activity.

Keywords：Data Mining、Sensor data、Activity recognition

並列關鍵字

Data Mining ； Sensor data ； Activity recognition

參考文獻

[1] Koskimaki, Heli; Siirtola, Pekka “Recognizing gym exercises using acceleration data from wearable sensors”, 2014 IEEE Symposium on Computational Intelligence and Data Mining (CIDM), pp.321-328, 9-12 Dec. 2014.

Self-calibration of walking speed estimations using smartphone sensors”,2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) ,Vol.2, pp. 368-375, 6-9 Dec. 2015.

[8] M. Mayilvaganan; D. Kalpanadevi, “Comparison of classification techniques for predicting the performance of students academic environment”, 2014 International Conference on Communication and Network Technologies (ICCNT), pp. 113-118, 18-19 Dec. 2014

[10] Yongjin Kwon; Kyuchang Kang; Changseok Bae, “Analysis and evaluation of smartphone-based human activity recognition using a neural network approach” , 2015 International Joint Conference on Neural Networks (IJCNN), pp.1-5, 12-17 July 2015.

[13] Chao Shen; Yufei Chen ; Gengshan Yang “On Motion-Sensor Behavior Analysis for Human-Activity Recognition via Smartphones”,2016 IEEE International Conference on Identity, Security and Behavior Analysis (ISBA), pp. 1 - 6, Feb. 29 2016-March 2 2016.