人體行爲識別可以被直接建模爲圖像識別任務，我們可以藉助於CNN模型來實現我們的需求，圖像本質上來說是二維的矩陣數據，CNN神經網絡模型非常適合用於處理和計算這種類型的數據，對於一維的數據，同樣可以基於CNN模型來實現，同時也是可以基於機器學習模型來進行實現的。
今天找到一個很有意思的數據集——人體行爲姿勢數據集WISDM，這個數據集中一共有36個人，每個人都會有6種動作，如下所示：
{'Sitting':0,'Downstairs':1,'Standing':2,'Walking':3,'Upstairs':4,'Jogging':5}
爲了方便轉化計算，我對其構建了映射字典。
這個數據集是按照一定的採樣頻率對被測試人進行採樣獲取的數據。
首先我們來簡單看下數據集樣例，下面是前100條數據樣本：
1,33,0.04,0.09,0.14,0.12,0.11,0.1,0.08,0.13,0.13,0.08,0.09,0.1,0.11,0.11,0.08,0.04,0.16,0.13,0.1,0.03,0.12,0.08,0.09,0.12,0.1,0.1,0.08,0.11,0.12,0.1,0,8.4,1.76,2075,293.94,1550,3.29,7.21,4,4.05,8.17,4.05,11.96,Jogging
2,33,0.12,0.12,0.06,0.07,0.11,0.1,0.11,0.09,0.12,0.1,0.12,0.11,0.07,0.1,0.13,0.13,0.06,0.11,0.1,0.04,0.11,0.11,0.11,0.09,0.12,0.1,0.11,0.1,0.07,0.08,0,7.62,1.43,1525,269.44,1233.33,4.23,6.88,4.05,5.43,8.19,5.43,12.05,Jogging
3,33,0.14,0.09,0.11,0.09,0.09,0.11,0.12,0.08,0.05