Department of Computer Science and Engineering, Kyung Hee University, (Global Campus), 1732, Deogyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do 17104, Korea.
Department of Smart ICT Convergence, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul 05029, Korea.
Sensors (Basel). 2018 Nov 13;18(11):3910. doi: 10.3390/s18113910.
The most significant barrier to success in human activity recognition is extracting and selecting the right features. In traditional methods, the features are chosen by humans, which requires the user to have expert knowledge or to do a large amount of empirical study. Newly developed deep learning technology can automatically extract and select features. Among the various deep learning methods, convolutional neural networks (CNNs) have the advantages of local dependency and scale invariance and are suitable for temporal data such as accelerometer (ACC) signals. In this paper, we propose an efficient human activity recognition method, namely Iss2Image (Inertial sensor signal to Image), a novel encoding technique for transforming an inertial sensor signal into an image with minimum distortion and a CNN model for image-based activity classification. Iss2Image converts real number values from the , , and axes into three color channels to precisely infer correlations among successive sensor signal values in three different dimensions. We experimentally evaluated our method using several well-known datasets and our own dataset collected from a smartphone and smartwatch. The proposed method shows higher accuracy than other state-of-the-art approaches on the tested datasets.
在人类活动识别中，成功的最大障碍是提取和选择正确的特征。在传统方法中，特征是由人类选择的，这需要用户具有专业知识或进行大量的经验研究。新开发的深度学习技术可以自动提取和选择特征。在各种深度学习方法中，卷积神经网络（CNN）具有局部相关性和尺度不变性的优点，适用于加速度计（ACC）信号等时间数据。在本文中，我们提出了一种有效的人类活动识别方法，即 Iss2Image（惯性传感器信号到图像），这是一种将惯性传感器信号转换为图像的新颖编码技术，可最大限度地减少失真，以及用于基于图像的活动分类的 CNN 模型。Iss2Image 将 、 和 轴的实数值转换为三个颜色通道，以精确推断三个不同维度中连续传感器信号值之间的相关性。我们使用几个著名的数据集和我们自己从智能手机和智能手表收集的数据集对我们的方法进行了实验评估。所提出的方法在测试数据集上的准确性高于其他最先进的方法。
