Activity recognition (AR) systems for older people are common in residential health care settings such as hospitals and nursing homes, thus numerous methodologies and studies have been developed to improve the effectiveness of AR systems. However, developing sufficiently robust AR systems using sensor data obtained is a challenging task. In this paper, a novel Smart Belt (S-Belt) for Monitoring of elder people using IoT is a smartphone application that predicts a health monitor for elder people and then sends that status together with the health state and anticipated behaviour to the family. Initially, the sensors in the smart belt such as temperature sensor, heartbeat sensor, oxygen sensor, and glucometer are used to gather data from the elders. The details from the sensors will be preprocessed using Stationary wavelet Transformer (SWT) technique and then classified using Multihead-CNN. Then the classified result will be sent to the end users such as doctors and their relatives through a mobile application. The simulation finding shows proposed method performance was evaluated in terms of ACU, PRE, REC, and F1S. The S-Belt model achieves the overall accuracy of 99.64%. MHCNN network improves the accuracy range by 9.5%, 4.42%, and 0.8% better than DNN, RNN, and CNN respectively.