摘要
智能手机的功能越来越复杂,最新的智能手机配备许多各式各样且功能强大的传感器,这些传感器包括GPS传感器、视觉传感器(如摄像头)、听觉传感器(如耳机)、光传感器、温度传感器、方向传感器(如指南针)和加速度传感器(如加速计),它们在使用中所产生的大量数据为我们进行室内行为识别分析提供机会。通过智能手机加速度传感器、重力传感器和方向传感器,基于深度学习的方式,对智能手机传感器采集的数据进行标准化处理。分别运用Ten sorFlow及LSTM模型,根据深度特征学习方法实现不同活动的特征提取,进行活动的分类,最终实现对六大类人体活动(走、坐、站、上楼、下楼、慢跑)识别。
Mobile devices are becoming increasingly sophisticated and the latest generation of smartphones now incorporates many diverse and power ful sensors.These sensors include GPS sensors,vision sensors(i.e.,cameras),audio sensors(i.e.,microphones),light sensors,temperature sensors,direction sensors(i.e.,magnetic compasses),and acceleration sensors(i.e.,accelerometers).In this paper we describe and evalu ate a indoor activity recognition system based on smartphone accelerometers and LSTM model,to implement the system we collected la beled accelerometer data from users as they performed daily activities such as walking,climbing stairs,sitting,and standing,then aggregat ed this time series data into examples that summarize the user activity over 10 second intervals.We then used the resulting training data to induce a predictive model for activity recognition.
作者
董海山
徐晓姗
郑春红
DONG Hai-shan;XU Xiao-shan;ZHENG Chun-hong(School of Information,Qingdao Technical College,Qingdao 266555)
出处
《现代计算机》
2020年第6期55-59,共5页
Modern Computer
基金
山东省高等学校科技计划项目(No.J18KB148)。
作者简介
董海山(1981-),男,山东青岛人,硕士,讲师,研究方向为深度学习。
