مطالعه موردی برای تشخیص و کنترل تشنج صرعی
Abstract
1- Introduction
2- Related work
3- Proposed cognitive IoT-cloud framework and seizure detection technique
4- Results
5- Conclusion
References
Abstract
We propose a cognitive Internet of Things (IoT)–cloud-based smart healthcare framework, which communicates with smart devices, sensors, and other stakeholders in the healthcare environment; makes an intelligent decision based on a patient’s state; and provides timely, low-cost, and accessible healthcare services. As a case study, an EEG seizure detection method using deep learning is also proposed to access the feasibility of the cognitive IoT–cloud smart healthcare framework. In the proposed method, we use smart EEG sensors (apart from general healthcare smart sensors) to record and transmit EEG signals from epileptic patients. Thereafter, the cognitive framework makes a real-time decision on future activities and whether to send the data to the deep learning module. The proposed system uses the patient’s movements, gestures, and facial expressions to determine the patient’s state. Signal processing and seizure detection take place in the cloud, while signals are classified as seizure or nonseizure with a probability score. The results are transmitted to medical practitioners or other stakeholders who can monitor the patients and, in critical cases, make the appropriate decisions to help the patient. Experimental results show that the proposed model achieves an accuracy and sensitivity of 99.2 and 93.5%, respectively.
Introduction
The Internet of Things (IoT), which can be considered an interconnected network of intelligent sensor devices, often has limited storage and low processing power capability. IoT, together with cloud computing, which has a large storage and sufficient processing power capability, has made essential services, such as smart healthcare [1, 2], possible in a smart city environment. However, monitoring and communicating remotely with patients are necessary in such environments. In addition, the need to provide low-cost, high-quality, and patient-centric smart healthcare to patients has emerged. The advancements in the field of IoT [3] and cloud technologies [4] has resulted in a tremendous demand for realtime, intelligent, and remote healthcare services under the paradigm of smart cities. Furthermore, the integration of IoT and cloud technologies has provided a seamless and ubiquitous framework for smart healthcare monitoring. At present, residents in smart cities have access to smart sensor devices and advanced mobile technologies. In an environment such as that of a smart city, finding specialized doctors, healthcare centers, and hospitals nearby is difficult. The movement of patients in critical conditions is also quite difficult. Hence, we need to create a smart healthcare monitoring framework by integrating the resources available at our disposal to improve the quality and accessibility of healthcare services. In such a smart healthcare monitoring framework, we can transmit and process medical-related multimedia signals from smart sensors and mobile devices to provide timely assistance and quality healthcare services to patients. However, such healthcare data and signals are often naturally large and challenging to handle because of their complexity. The healthcare industry has emerged as one of the major industries with tremendous demands. Apart from providing patients with critical and crucial services, this industry is also generating large revenues for the government and the private sector.