Smart Health Solution Integrating IoT and Cloud: A Case Study of Voice Pathology Monitoring
The integration of the IoT and cloud technology is very important to have a better solution for an uninterrupted, secured, seamless, and ubiquitous framework. The complementary nature of the IoT and the could in terms of storage, processing, accessibility, security, service sharing, and components makes the convergence suitable for many applications. The advancement of mobile technologies adds a degree of flexibility to this solution. The health industry is one of the venues that can benefit from IoT–Cloud technology, because of the scarcity of specialized doctors and the physical movement restrictions of patients, among other factors. In this article, as a case study, we discuss the feasibility of and propose a solution for voice pathology monitoring of people using IoT–cloud. More specifically, a voice pathology detection system is proposed inside the monitoring framework using a local binary pattern on a Mel-spectrum representation of the voice signal, and an extreme learning machine classifier to detect the pathology. The proposed monitoring framework can achieve high accuracy of detection, and it is easy to use.
Smart wristbands can communicate via Bluetooth to nearby personal smartphones; wearable devices can communicate with smartphones using a dedicated wireless protocol, while the internal or stationary devices can communicate wirelessly. There are different types of sensors that can be used in the medical domain for simplicity and ubiquitous nature. For example, HealthPatch MD is a biosensor attached to the chest that can measure and track a person’s heart rate, body temperature, respiratory rate, and body movement, in addition to fall detection. Zio XT Patch can detect an abnormal heartbeat rate over a certain period. Figure 1 shows a framework of the integration of the IoT and the cloud. A hosting device, most preferably a smart device, captures data from different IoT through a local area network (LAN) interface (e.g., using Bluetooth). The device then sends the heterogeneous data to the cloud using a wide area network (WAN) interface. The data transfer can be realized by using WiFi or fourth/ fifth generation (4G/5G) technology. One of the concerns is secured transmission, which can be a task of the service provider.
In the proposed system, the IoT related to capturing voice, body temperature, electrocardiogram, and ambient humidity is used. We exclude devices such as laryngoscope and stroboscope because they are difficult for a patient to operate. The data captured by the IoT are sent by Bluetooth technology to the patient’s smartphone using a developed app. For authentication purposes, a simple but robust watermark is embedded into the signals. The watermark is a personalized identification of the patient, which is created by the patient himself. Watermark embedding is a very important step in the proposed system, because it protects the ownership of the personal data. For watermarking, we use the algorithm proposed in  because of its robustness against different attacks. In this watermarking scheme, a discrete wavelet transform (DWT) and a singular value decomposition (SVD) based algorithm is utilized. The patient ID is used as the watermark, and it is embedded using SVD in the detailed coefficients subband at level 2 of the voice signal decomposition using DWT. The watermarked signals are transmitted to the cloud through the Internet.
A healthcare framework based on the IoT and the cloud is discussed and proposed. A voice pathology monitoring system inside the framework is developed using the LBP features and the ELM classifier. The proposed system experimentally proved to be accurate. There are several issues that need to be addressed before this type of system can be fully operative in a trustable manner. These issues include dynamic scalability, secured transmission, availability, ease of users, and interoperability. In the proposed system, interoperability and ease of users are solved. Secure transmission can be guaranteed by the service provider; however, we embed a watermark into the signal for authenticity.
 A. Botta et al., “Integration of Cloud Computing and Internet of Things: A Survey,” Future Generation Computer Systems, vol. 56, Mar. 2016, pp. 684–700.
 M. S. Hossain and G. Muhammad, “Cloud-Assisted Industrial Internet of Things (IIoT)-Enabled Framework for Health Monitoring,” Computer Networks, vol. 101, 2016, pp. 192– 202, DOI: 10.1016/j.comnet.2016.01.009.
 M. Henze et al., “A Comprehensive Approach to Privacy in the Cloud-Based Internet of Things,” Future Generation Computer Systems, vol. 56, Mar. 2016, pp. 701–18.
 G. Muhammad et al., “Voice Pathology Detection Using Interlaced Derivative Pattern on Glottal Source Excitation,” Biomedical Signal Processing and Control, vol. 31, Jan. 2017, pp. 156–64, DOI: 10.1016/j.bspc.2016.08.002.
 L. Hu et al., “Software Defined Healthcare Networks,” IEEE Wireless Commun., vol. 22, no. 6, Dec. 2015.
 M. Alhussein and G. Muhammad, “Watermarking of Parkinson Disease Speech in Cloud-Based Healthcare Framework,” Int’l. J. Distributed Sensor Networks, vol. 2015, article ID 264575, 2015, 9 pages, DOI: 10.1155/2015/264575.
 A. Al-Fuqaha et al., “Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications,” IEEE Commun. Surveys & Tutorials, vol. 17, no. 4, 4th qtr. 2015, pp. 2347–76.
 Y. Sun et al., “Internet of Things and Big Data Analytics for Smart and Connected Communities,” IEEE Access, vol. 4, 2016, pp. 766–73.
 G. Muhammad, “Automatic Speech Recognition Using Interlaced Derivative Pattern for Cloud Based Healthcare System,” Cluster Computing, vol. 18, no. 2, June 2015, pp. 795–802.
 T. Ahonen, A. Hadid, and M. Pietikainen, “Face Description with Local Binary Patterns: Application to Face Recognition,” IEEE Trans. Pattern Anal. Machine Intell., vol. 28, no. 12, 2006, pp. 2037–41.