In general, epilepsy is considered as one of most prevalent neurological disorders and frequently appears as sudden seizures, resulting in injuries, accidents, sudden unexpected deaths, etc. It is reported that around 60 million people across the globe experience various seizures due to epilepsy. So, there is a demand for ambulatory seizure detection devices to prevent such accidents and to improve the quality of life of epilepsy patients. In this work, an intelligent Internet of Medical Things (IoMT)-based wearable device is designed and developed to monitor seizures in epilepsy patients. Due to the lack of an accelerometer dataset for epileptic seizures, the proposed device is developed, and a dataset simulating seizure-like activities has been generated. Further, the proposed device utilises an MPU6500-based Inertial Measurement Unit (IMU), which is integrated to an ESP32 microcontroller board. The ESP32 has built-in Wireless Fidelity (WiFi) + Bluetooth (BLE) and supports MicroPython. Also, machine learning algorithms such as Decision Trees (DTs), Support Vector Machines (SVMs), Random Forests (RFs), etc., are implemented using MicroPython and are deployed on a tiny edge computing device to monitor the activity of epileptic patients. All the adopted machine learning algorithms were compared in terms of performance metrics, such as Accuracy, Precision, Recall, False Alarm Rate (FAR), etc., and the efficacy of the device is analysed. The results demonstrate that the proposed device is capable of identifying activities of individuals, which is highly useful for epilepsy patients in monitoring their epileptic seizures. Furthermore, it is demonstrated that the proposed device is best deployed with an RF algorithm, since it exhibits an accuracy of 94.17%, which is better compared to that of the other machine learning algorithms. Also, the proposed device is simple and cost-effective and alerts caretakers of epilepsy patients with an FAR of less than 4%.