活动识别技术在智能家居、运动评估和社交等领域得到广泛应用。本文设计了一种基于卷积神经网络的活动识别分析与应用系统，通过分析基于Android搭建的前端采所集的三向加速度传感器数据，对用户的当前活动进行识别。实验表明活动识别准确率满足了应用需求。本文基于识别的活动进行卡路里消耗计算，根据用户具体的活动、时间以及体重计算出相应活动在相应时间内具体消耗的卡路里消耗，有助于建立健康生活模式。 Activity recognition technology has got widely used in smart home, sports assessment, social contact and other fields. This paper designs an activity recognition analysis and application system based on convolution neural network. By analyzing the data of three-way accelerometer collected in Android devices, the current activities of a user are identified. Experiments show that the accuracy of activity recognition meets the requirement of application. This paper calculates calorie expenditure based on identified activities, and calculates calorie expenditure based on a user’s specific activities according to time and weight for the corresponding activities in the corresponding time, which helps to establish a healthy lifestyle.
展开▼
机译：活动识别技术在智能家居、运动评估和社交等领域得到广泛应用。本文设计了一种基于卷积神经网络的活动识别分析与应用系统，通过分析基于Android搭建的前端采所集的三向加速度传感器数据，对用户的当前活动进行识别。实验表明活动识别准确率满足了应用需求。本文基于识别的活动进行卡路里消耗计算，根据用户具体的活动、时间以及体重计算出相应活动在相应时间内具体消耗的卡路里消耗，有助于建立健康生活模式。 Activity recognition technology has got widely used in smart home, sports assessment, social contact and other fields. This paper designs an activity recognition analysis and application system based on convolution neural network. By analyzing the data of three-way accelerometer collected in Android devices, the current activities of a user are identified. Experiments show that the accuracy of activity recognition meets the requirement of application. This paper calculates calorie expenditure based on identified activities, and calculates calorie expenditure based on a user’s specific activities according to time and weight for the corresponding activities in the corresponding time, which helps to establish a healthy lifestyle.
展开▼
