Smart transportation and smart healthcare are considered as essential industrial applications in the era of Smart City. The emerging wireless technologies facilitates the network expansion by connected all various kinds of devices, sensors, algorithms, and applications together. Therefore, a huge number of wearable sensors such as smart watches, headbands, chest straps etc. have been developed recently. The integration of those wearable sensors is usually defined as wireless body network (WBN). WBN facilitates real-time monitoring humans' status in numerous applications such as worker safety and patient tracking. As such, it is found that more than 60% of adult drivers felt sleepy while driving and more than 40% of traffic accidents are caused by drunk drivers. In this paper, an electrocardiogram (ECG) based humans' status detection (ECG-HSD) scheme is proposed to detect both drowsy and drunk status. The proposed ECG-HSD extracted similarities of ECG signals under normal, drowsy and drunk conditions and the corresponding feature vector was built. Then, the important data points on ECG samples were weighted and this improves the detection accuracy. Besides, two criteria of classifier which are accuracy and testing were considered with the aid of multiple criteria decision making (MCDM). After that, K-fold validation was carried out for training and validating the classifiers. The results revealed that the proposed ECG-HSD achieved satisfied accuracy and short testing time.