Medical long-distance monitoring system based on internet of things
To allow doctors to monitor the physical parameters of the patient’s body in real time and to understand the changes in the patient’s condition in time, the medical remote monitoring system based on the Internet of Things was studied. From the perspective of practical application of hospital wards, a medical health monitoring system was designed with the help of CC2430 microcontroller, human information sensor, and microelectronic and modern wireless communication technology. In addition, a sensor node circuit and a coordinator node circuit for collecting medical signals were designed. Meanwhile, the software of wireless sensor network was designed. Finally, the online debugging of each system module was combined with hardware and software. The experimental result proved that the network node was reliable and the data transmission was accurate. It is concluded that the medical monitoring system basically meets the design requirements of this paper.
KeywordsMedicine Remote monitoring Monitoring system Sensor Coordinator
A True System-on-Chip solution for ZigBee
Linear discriminant analysis
Quadratic discriminant analysis
Radial basis function
Support vector machines
The Internet of Things (IoT) medical remote monitoring system is to establish a wireless monitoring network in a hospital ward. The patient collects physiological signals by carrying a small sensor node and sends it wirelessly to the user management center. In this way, the patient does not need to connect a variety of wires and even can wear a comfortable electronic fabric. Therefore, they can obtain more free space. This operation is convenient for the diagnosis work. Doctors and nurses can monitor the physiological status of each patient in real time through the user management platform. Finally, doctors’ work efficiency is improved, and they have more time to serve patients. Once an emergency occurs, it can be properly handled .
In foreign countries, the IoT technology has emerged earlier and its development is relatively mature. In the USA, a number of institutions have launched research on IoT medicine. Intel is currently developing a wireless sensor network system for home care. They embed sensors in shoes, furniture, and home appliances to help older people and people with disabilities live independently. Scientists at the University of Rochester use wireless sensors to create a smart medical room. They use dust to measure important signs of the occupants, sleeping position, and 24 h of activity every day . In China, the State Key Laboratory of Mobile Communications of Southeast University and China Mobile Jiangsu Corporation jointly developed a real-time health monitoring system to provide real-time health monitoring services for the elderly through the Internet of Things . However, at present, most of researches in China are still focused on theory, and it is rarely used in practice. In the case of IoT medical care, many jobs are just preliminary attempts, or more studies on electronic medical records and single disease detection, and less on in-patient physiological information monitoring. The design of this article applies the Internet of Things to medical monitoring very well.
2.1 Overall system design
Due to limited power, the distance of wireless communication is limited. The ZigBee protocol is used to set up a wireless sensor network to transmit information through wireless communication between a close-range node and a long-distance node. This process is just the same as information transmission between bees . ZigBee technology supports three network topologies, including star-type network, tree-type network, and mesh network. This design selects a tree-type network .
2.2 System hardware design
All three types of nodes use the CC2430 chip as the core controller. The CC2430 integrates an 8051 controller and a 2.4 GHz RF transceiver. It can process, convert, and store physiological parameter information and communicate data wirelessly. The sensor node is responsible for collecting patient physiological signals. It also includes various medical sensor interface circuits and corresponding conditioning circuits. The coordinator node needs to send all the received parameter information to the PC. Therefore, the serial communication module needs to be added.
The sensor node is mainly responsible for collecting the patient’s physiological parameter information and periodically sending this information wirelessly to the routing node. Based on the node of the coordinator, the design adds the sensor interface circuit and conditioning circuit and completes the design of the sensor node. The detection of physiological parameters is an important part of the daily examination of inpatients. Many critically ill patients and the elderly also need long-term physical monitoring. The common physiological parameters include body temperature, pulse, blood pressure, heart rate, electrocardiogram (ECG), respiration, oxygen partial pressure, oxygen saturation, and blood glucose. These physiological parameters generally require non-invasive or minimally invasive detection in the monitoring system . The design uses body temperature, pulse, and ECG signals as the collection object. A simple and convenient method of sensor and non-invasive measurement is chosen, and various physiological signal conditioning circuits are designed. Due to content restrictions, only the idea of ECG signal circuit design is listed here.
2.3 Algorithm for multivariate medical data modeling
Data mining techniques such as classification and clustering play a vital role in the development of medical decision support systems contributing to improved healthcare quality. The medical decision-making problems inherently involve complexities and uncertainties, and thus, the researchers have advocated the integration of fuzzy methodologies in medical data interpretation. The handling of uncertainties by capturing of knowledge using fuzzy sets and rules together with an interpretability offered by simple linguistic if-then rules are two most important features of fuzzy methodologies. The fuzzy approaches are commonly applied to medical data classification problems. In our previous work , we suggested to represent multi-dimensional medical data by means of an optimal fuzzy membership function, and a carefully designed data model is introduced in a completely deterministic framework where uncertain variables are characterized by fuzzy membership functions.
Treating all the variables as uncertain being characterized by fuzzy membership functions
Assuming that medical data, under the given status of a patient, is generated by a finite mixture of uncertain signal models
Determining the fuzzy membership functions on variables with the help of experimentally measured data samples in an analytical manner using variational optimization.
2.4 System software design
The CC2430 chip integrates the 8051 core. The 8051 supports more development languages, including assembly, PL/M, BASIC, and C. In high-level languages, C is a language that is relatively close to hardware. It has good portability, high hardware control capabilities, strong expression, and computing power. C programming is more in line with people’s thinking habits. The freedom degree of program design is large, and modular programming is also available, which increases the readability and portability of the program. If the system needs to achieve the same or similar functions in subsequent development, the developer can make changes to the previous module to maximize resource sharing. Compared with assembly language, C language has good portability. The C language has obvious advantages over the operating system and system utilities and where the hardware needs to be operated on . Programmers who use C programming will feel less restricted, more flexible, and more powerful. They can write any type of program. At the same time, the system selects IAR Embedded Workbench as the development environment. IAREWRM is an integrated development environment developed by IARsystems Company. Users can develop applications for many different target processors. IAR Embedded Workbench is suitable for a large number of 8-bit, 16-bit, and 32-bit microprocessors and microcontrollers. Therefore, users can also develop in the familiar development environment when developing new projects. It provides users with a development environment that is easy to learn and has the greatest amount of code inheritance, as well as support for most and special goals. With IAR tools, users can save time .
Bluetooth vs. ZigBee
< 32 kb (4 kb)
Network join time
PIN, 64 bit, 128 Bit
128 bit, AES
Among them, P0_0 is set as general I/O to directly collect DS18B20 temperature value. P0_1 is set to the external interruption (rising edge trigger), and the heart rate value is calculated by reading the time difference between the two interrupts. The P0_6 pin is configured as an ADC input (the corresponding bit in the ADCCFG register is set to 1). The 6th channel is selected with single-ended input mode and 14-bit resolution. The 1.25 V reference voltage is internally generated. When the ADCCON1.ST bit is set to 1, a conversion sequence is initiated and the analog ECG voltage signal is converted to a digital quantity. At the end of the conversion, the status bit ADCCON1.ECO is set to high level. The conversion result is stored in ADCH and ADCL in the form of two complement to complete the ECG signal acquisition. There are mainly three types of nodes in the monitoring network, namely sensor nodes, routing nodes, and coordinator nodes. After the coordinator node is powered on, it is responsible for establishing and initializing the network, sending a network beacon, determining the network operating channel, and allocating a 16-bit network address. After the routing node joins the network, it receives the data sent by the sensor node and forwards the data to the coordinator node. The sensor node only sends and receives the signal and does not have the forwarding function. After powering on, it automatically initiates a bind request. After the binding with the parent (routing) node is established, the collected body temperature, pulse, and ECG data are sent to the routing node. In addition, the coordinator node sends data to the PC through the serial port. Doctors can query and analyze data through the user management interface.
3 Results and discussion
Firstly, a monitoring system for real-time remote monitoring of inpatient physiological signals is designed. The hardware circuit design of the sensor node and the coordinator node and the corresponding software program design are achieved. Among them, the sensor node can collect three physiological signals, including body temperature, pulse, and ECG. The sensor node forms a wireless network with the routing node and the coordinator node. Then, the collected physiological information is transmitted to the information management system of the upper computer for the doctor to view at any time. Finally, the hardware and software are combined to debug the system modules online. The experiment proves that the network node is reliable and the data transmission is accurate, basically meeting the design requirements of this paper. And the analytically derived expressions for fuzzy membership functions we present in this work should facilitate a system theoretic approach to mathematically design the medical expert systems.
This work was supported by the National Natural Science Foundation of China (61662045) and the Special Program of talents Development for Excellent Youth Scholars in Tianjin.
Availability of data and materials
The materials and data are true and reliable in this paper.
Y-JZ is the corresponding author. Z-WP and Y-JZ conceived the proposed scheme. Z-WP and M-K conducted the detailed derivation of the proposed algorithm and carried out the most experiments and data analysis. Y-JZ and Y-JF carried out the part experiments and data analysis. Y-JF helped to improve the experimental simulation. All authors have read and approved the final manuscript.
The authors declare that they have no competing interests.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
- 2.R Piyare, Internet of things: ubiquitous home control and monitoring system using android based smart phone. Int J Internet Things 2(1), 5–11 (2013)Google Scholar
- 7.R Prakash, Australian journal of Basic and applied sciences internet of things (IoT) enabled wireless patient monitoring system using CC3200. Aust J Basic Appl Sci 9(916), 275–281 (2015)Google Scholar
- 8.HS Kim, JS Seo, J Seo, A daily activity monitoring system for internet of things-assisted living in home area networks. Kor J Pathol 6(1), 399 (2016)Google Scholar
- 11.L Gui, TY Ruan, ZZ Wang, et al., CNC online monitoring system based on internet of things. Adv Mat Res 1079-1080(6), 672–678 (2015)Google Scholar
Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.