Medical Equipment Comprehensive Management System Based on Cloud Computing and Internet of Things
Medical Equipment Comprehensive Management System Based on Cloud Computing and Internet of Things
Yao, Lin;Shang, Danmei;Zhao, Hui;Hu, Shuyu
2021-03-03 00:00:00
Hindawi Journal of Healthcare Engineering Volume 2021, Article ID 6685456, 12 pages https://doi.org/10.1155/2021/6685456 Research Article Medical Equipment Comprehensive Management System Based on Cloud Computing and Internet of Things Lin Yao, Danmei Shang , Hui Zhao, and Shuyu Hu College of Public Basic Sciences, Jinzhou Medical University, Jinzhou, Liaoning 121001, China Correspondence should be addressed to Danmei Shang; wzhsdm@jzmu.edu.cn Received 19 November 2020; Revised 17 December 2020; Accepted 18 February 2021; Published 3 March 2021 Academic Editor: Yang Gao Copyright © 2021 Lin Yao et al. -is is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. -e continuous progress in modern medicine is not only the level of medical technology, but also various high-tech medical auxiliary equipment. With the rapid development of hospital information construction, medical equipment plays a very important role in the diagnosis, treatment, and prognosis observation of the disease. However, the continuous growth of the types and quantity of medical equipment has caused considerable difficulties in the management of hospital equipment. In order to improve the efficiency of medical equipment management in hospital, based on cloud computing and the Internet of -ings, this paper develops a comprehensive management system of medical equipment and uses the improved particle swarm optimization algorithm and chicken swarm algorithm to help the system reasonably achieve dynamic task scheduling. -e purpose of this paper is to develop a comprehensive intelligent management system to master the procurement, maintenance, and use of all medical equipment in the hospital, so as to maximize the scientific management of medical equipment in the hospital. Scientific Management. It is very necessary to develop a preventive maintenance plan for medical equipment. From the experimental data, it can be seen that when the system simultaneously accesses 100 simulated users online, the corresponding time for submitting the equipment maintenance application form is 1228 ms, and the accuracy rate is 99.8%. When there are 1000 simulated online users, the corresponding time for submitting the equipment maintenance application form is 5123 ms, and the correct rate is 99.4%. On the whole, the medical equipment management information system has excellent performance in stress testing. It not only predicts the initial performance requirements, but also provides a large amount of data support for equipment management and maintenance. equipment in hospitals, the speed of equipment upgrades 1. Introduction and updates has accelerated, and the information items for In recent years, the rapid development of medical tech- maintenance management have become more and more nology has made the average medical level of the entire complicated. -e requirements for equipment maintenance society continue to rise, and various advanced medical management and information retrieval have become higher equipment have been developed and put on the market [1]. and higher. As the number and types of medical equipment purchased In foreign countries, many scholars have conducted by hospitals increase, the maintenance and maintenance large-scale research and discussion on the management of requirements for medical equipment are also higher. How to medical equipment. Amerieon et al. conducted a qualitative manage and maintain these pieces of medical equipment study on the factors affecting the maintenance and man- with a large number of brands and advanced science and agement of medical equipment in military hospitals. He used technology and give full play to their role in medical the framework analysis method to investigate the managers treatment is a very important issue for the hospital de- and medical equipment experts of a military area hospital in partment managers and maintenance engineers and tech- a targeted manner. Semistructured interviews are used for nicians. With the continuous expansion of medical data analysis and descriptive statistics are used to rank the 2 Journal of Healthcare Engineering frequency of many factors affecting medical equipment Compared with traditional computer technology, the biggest maintenance management. From the experimental data, difference of cloud computing is that it is based on virtu- equipment management training has a very important alization technology [8], using the network as the carrier, proportion. Of course, due to the limited sample data, they and integrating large-scale and scalable computing, storage, have considered the convincing power of the results to a data, applications, and other distributed computing re- certain extent [2]. Ulickey conducted research on rich cases sources for collaborative work (the supercomputing model) of integrated facility management systems. Networking and [9, 10]. the innovation of digital control systems have enabled the In this environment of explosive growth in the amount integration of different control strategies in the past. -ese of information, more and more industries are beginning to strategies are not only suitable for building systems, but also use various Internet emerging technologies to achieve in- in the field of medical management. Scientific innovation telligent system optimization and management, and the provides a more powerful mathematical basis for the rational advancement of cloud computing technology provides a use of various equipment in the hospital. In the future, powerful way for large-scale task mobilization (technical people should focus on how to correctly understand these support) [11]. In the medical field, the problem information data and promote the intelligent scheduling effect of the involved is usually diverse and highly specialized. Taking system [3]. medical equipment management as an example, if you want With the development of emerging science and tech- to develop a system that can realize intelligent management, nology, domestic hospitals have paid more and more at- you cannot do this without the support of cloud computing tention to the maintenance and management of medical and the Internet of -ings technology. Cloud computing equipment. Qiang believes that advanced medical equip- task scheduling is mainly to study how to allocate resources ment is one of the important signs of modern hospital for tasks submitted by users. In other words, it is to allocate technology. -erefore, the hospital has the responsibility to multiple independent and diversified tasks to the large-scale establish an effective management model and manage the virtual resources in the cloud, so as to satisfy all tasks with medical equipment to keep it in a good operating condition the highest efficiency (user needs) [12, 13]. and ensure the safety of patients. He and his team used a Suppliers of cloud computing platforms pay most at- variety of methods such as literature research, questionnaire tention to the utilization of data resources, energy con- survey, and data analysis to summarize the problems in the sumption, and the level of profit during the use of the maintenance and management of hospital medical equip- platform; users pay attention to service quality and cost, no ment, the development and characteristics of the mainte- matter from which point of view, task scheduling is shared nance management model, and the current situation at by people (an important stage of virtual resources) [14]. Its home and abroad [4]. In the research, he proposed that the essence is the process of reasonably assigning tasks sub- use of advanced Internet technology to develop intelligent mitted by users to virtual resources. -erefore, the im- systems has a high feasibility in the management of medical provement of algorithm performance in task scheduling is equipment, but he did not prove its advantages in specific the root of the whole problem [15, 16]. practical research [5]. Based on cloud computing and the Internet of -ings technology, this paper has launched an in-depth study on the 2.2. Internet of )ings Intelligent Control System. -e In- integrated management system of medical equipment. -e ternet of -ings connects all items to the Internet through research is mainly carried out from the following parts: first, information sensing methods such as radio frequency this article describes the technologies and methods used in identification, infrared induction, optical induction, and the system development, including cloud computing and barcode scanning, so as to achieve information exchange task scheduling, IoT intelligent control system, particle and communication and achieve intelligent identification, swarm algorithm, and chicken swarm optimization algo- positioning, tracking, monitoring, and management [17, 18]. rithm. -en, this article starts with the network structure, Figure 1 shows a diagram of the IoT system architecture. software structure, development environment, database, and As shown in Figure 1, the basic system of the Internet of other aspects to develop a comprehensive medical equip- -ings can be divided into three parts: perception layer, ment management system platform. Finally, this article network layer, and application layer. -e perception layer is simulates the effect of the system in practical applications the foundation of the application and development of the and various possible problems from the perspective of the Internet of -ings. It is composed of various devices with procurement, allocation, maintenance, and use of medical perception capabilities. It mainly realizes information col- equipment. lection, object recognition, and other perception functions and has the ability to fully perceive the Internet of -ings; the network layer integrates various communication net- 2. Technology Based on Medical Equipment works and the Internet is used to build a collaboratively Integrated Management System aware network to optimize and improve the application 2.1. Cloud Computing and Task Scheduling. Cloud com- characteristics of the Internet of -ings; the application layer puting is an emerging technology model that pays on de- is the fundamental purpose of the development of the In- ternet of -ings, and its role is to combine the industry’s mand [6]. It can provide people with the resources they need in the shortest time, which is very convenient and fast [7]. informatization needs with the Internet of -ings Journal of Healthcare Engineering 3 Application Smart Industrial Personal Public safety Others layer transportation monitoring health Data information processing platform Network layer Mobile communication Information Internet network center Perception Video RFID tags Card reader Smart sensor layer capture Figure 1: IoT system architecture diagram. technology to provide different users with, for example, swarm algorithm, it is easier to implement in actual work. applications in the fields of transportation, security, envi- On the other hand, the particle swarm algorithm also has ronment, home furnishing, industry, and military and na- certain shortcomings. For example, the speed of particles tional defense [19]. cannot be dynamically adjusted, and it is easy to fall into a local optimal solution, which leads to low convergence accuracy and inability to solve discrete problems and 2.3. Particle Swarm Algorithm combinatorial optimization (question) [23]. In order to improve these situations, the particle swarm algorithm needs 2.3.1. Basic Particle Swarm Algorithm. In order to realize the to be improved appropriately. comprehensive management of medical equipment in the system based on cloud computing and the Internet of -ings, intelligent algorithms need to be optimized to 2.3.2. Improved Particle Swarm Algorithm. In order to solve achieve reasonable task scheduling [20]. -e essence of the problem that the particle swarm algorithm is easy to fall particle swarm optimization (PSO) is to focus on the ap- into the local optimal solution and affect the task completion propriate value of the target search space and to judge the time, this paper combines the adaptive inertial weight and pros and cons of all individuals in between [21]. Each in- the random factor to better balance the local search and the dividual is like an example of movement in the group space global search, avoid falling into the local optimal solution, and contains two parameters: speed vi and position xi. Set improve global optimization ability, and then obtain a task the total number and dimension of examples in the pop- scheduling scheme with shorter task completion time and ulation as m, n, respectively, ω is the inertia weight, and c is lower cost [24]. the acceleration coefficient, that is, the learning factor. In the To apply the particle swarm algorithm to the cloud process of population global optimization, the speed and computing task scheduling problem, the particles need to be position of the example satisfy the formula coded. If there are k tasks and t resources, each task cor- v � ωv + c r p − x + c r p − x , responds to 1 resource. Defining matrix time[i, j], the ex- id id 1 1 id id 2 2 gd id (1) ecution time for completing task i in resource j is x � x + v . id id id In the iterative process, the particle swarm optimization Time(j) � time[i, j] (1≤ j≤ t). (2) algorithm only transmits the information of the optimal i�t solution to other particles and completes the search faster through the particles. -is is a significant advantage of Among them, n represents the total number of tasks particle swarm optimization algorithm, which can minimize executed in the resource and the total time to complete all tasks in the system and the fitness function satisfy the the waste of time and improve the search efficiency [22]. Coupled with fewer parameters involved in the particle formula 4 Journal of Healthcare Engineering simulating the living habits and hierarchy of the entire task time � max(Time(j)) (1≤ j≤ t), chicken flock, the entire chicken flock is divided into several (3) 1 groups, and there is competition between groups, which fitness � . effectively reduces the time for the algorithm to perform (task time + cost) tasks and can solve problems more quickly; and there are -is experiment will compare the total completion time three members of rooster, hen, and chicken in each group. and cost of all tasks with other algorithms, so the objective Members of different species have following relationships functions are defined as and competition relationships, and members of the same species also have competitive relationships. -is hierarchical task time � finish time − start time. behavior within the group can improve the algorithm’s (4) cost � time cost + debt. global search capability and the efficiency of finding the optimal solution, so that the algorithm can efficiently solve P (t) is the success rate of the particle swarm iteration, practical problems [30, 31]. indicating the proportion of particles in the particle swarm Set the number of roosters, hens, chicks, and mother that are better positioned in this iteration than the last time. hens in the flock to be Nr, Nh, Nc, and Nm, respectively; -e calculation method of the success rate is as follows: then, the position update formula of the roosters, hens, and chicks satisfies S(i, t) i�1 (5) P (t) � . n k+1 k 2 x � x · 1 + randn0, σ , id id Among them, S(i, t) represents the sum of the k+1 k k k i�1 x � x + C1 · randn · x − x id id j d id success values of all particles, and ω(t) is the inertia weight 1 (10) k k during iteration, used to adjust the particle velocity during + C2 · randn · x − x , j d id iteration: k+1 k k k x � x + F · x − x . id id md id ω(t) � ω − ω P (t) + ω . (6) max min s min -e advantage of the chicken flock optimization algorithm Suppose the joint distribution function of random is that multiple groups can greatly reduce the probability of the variable x, y is H: R ⟶ [0, 1], and its marginal distri- algorithm searching for the optimal position and reduce the bution function is Fx, Fy, respectively. -e theorem con- task scheduling time, and there is a competitive relationship forms to the formula between various groups and individuals, which is beneficial to H x , x � C F x , F x , task allocation. For load balancing, improve the quality of 1 2 x 1 y 2 (7) service [32]. However, there are three types of individuals in the −1 −1 C u , u � HF x , F x . 1 2 x 1 y 2 algorithm: rooster, hen, and chicken. According to the char- acteristics of the flock’s activities, the leading rooster will in- For any (u, v) ∈ [0, 1] , the binary Copula function can evitably affect the trajectory of the hen and the chicken [33]. If be defined as the position of the head chicken is not the optimal position, the − 1 − 1 algorithm will fall into a local optimum; it is difficult for the C (u, v) � φ φ (u), φ (v) . (8) p p hens and chicks that follow to jump out at this time, so in order Among them, Φ is the standard normal distribution to preserve the advantages of the algorithm and apply it to task function and Φp is the joint distribution function of two- scheduling, the algorithm must be optimized [34]. dimensional normal variables [25]. Assuming that the random variable and the random factor meet a certain 2.4.2. Improved Chicken Optimization Algorithm. correlation, we can define that they conform to Considering that, in the chicken swarm optimization al- H r , r � C r , r . (9) gorithm, the chicken will follow the hen’s action, and the hen 1 2 1 2 will follow the lead of the rooster, which will easily lead to the By comparing the fitness of each particle with the global problem of local optimal solution in the calculation process optimal value, the position state of the particle can be de- [35]. -erefore, according to the characteristics of chaotic scribed more accurately [26]. By refining the particle state, a perturbation traversing individuals, perturbation is added to more accurate success value can be obtained, and the success the population to reduce the premature phenomenon caused rate of the particle can be further improved, thereby im- by blind following. -e disturbance formula satisfies proving the adaptability of the inertia weight and effectively S � 4S 1 − S , S ∈ (0, 1). (11) avoiding the particle from falling into the local optimum k+1 k k k early in the optimization process [27, 28]. -e improved chicken position update formula satisfies k+1 k k k x � ωx + F · x − x . (12) 2.4. Chicken Flock Optimization Algorithm id id md id 2.4.1. Basic Chicken Optimization Algorithm. Chicken flock Among them, ω represents the coefficient that the optimization algorithm (CSO) is a bionic algorithm gen- chicken learns by itself and F represents the following co- erated around the hierarchy of chicken flocks [29]. By efficient of the chicken following the hen foraging. From the Journal of Healthcare Engineering 5 supplier information addition, modification, and deletion experimental results, the improved chicken flock optimi- zation algorithm effectively reduces the local optimal functions in the equipment supplier management function module and queries the table through the query function problem caused by the chicken blindly following the hen. operating. -e equipment table is used to store equipment information data. -e system uses the supplier equipment 3. Experimental Research on Comprehensive information addition, modification, and deletion functions Management System of Medical Equipment in the equipment supplier management function module to 3.1. Experimental Background. -e development of modern add, delete, and modify the table. Use the query function to medicine needs the help of high-tech medical equipment. query the table, or through equipment information main- How to ensure the normal operation of these medical tenance and statistical query function to operate. -e device equipment and give full play to its maximum social and type table is a data dictionary table of the device type. -e system uses the device type information addition, modifi- economic benefits is the following problem, and the core of this problem is how to do a good job in equipment man- cation, and deletion functions in the system management agement. -is article aims to design a set of real-time in- function module to add, delete, and modify the table and formation management system for the current state of query the table through the query function [37]. medical equipment. For this reason, it is necessary to analyze the overall requirements of the system before the start of the 4. Medical Equipment Comprehensive experiment and to fully understand the functional re- Management System Based on Cloud quirements required by the current medical equipment Computing and Internet of Things management, in order to achieve more targeted system design. System development will perform unit testing during the code implementation process and will deploy to the test environment for simulation operation after the development 3.2. Experimental System Module Design. -is system is is completed, thereby testing the system as a whole. System based on ASP.NET dynamic website technology and SQL testing is a very important link in the software development Server database. According to the overall function of the process, which has a direct impact on the normal operation system, it can be roughly divided into maintenance man- and maintenance of the software system in the later stages. agement, equipment management, warehouse management, -is section will perform performance testing based on the and statistical query modules. -e maintenance manage- system functional requirements. Table 1 shows a description ment is divided into the following modules: maintenance of system operation links. application module, maintenance processing module, It can be seen from Table 1 that this system relies on the maintenance dispatch module, maintenance cost registra- B/S framework, so the physical content of the operating tion module, maintenance evaluation module, etc. -e environment includes two parts: server and client. -e server equipment warehouse management module is divided into is installed on the hardware server, including applications, equipment storage, storage, loan, and scrap and others. SQL server database, and FineReport service, and the client -ese functions involve four types of roles, each of which is an ordinary computer with a browser. -e client com- involves more people. -erefore, the system adopts the B/S municates with the server by sending an HTTP request, and structure, so it can be accessed through the web without the server communicates with the client by responding to the downloading the client. client’s request. -e management of medical equipment involves a wide range of businesses. -e functional modules of this system are mainly divided into the following aspects: equipment 4.1. Medical Equipment Procurement Based on Integrated archive management, contract management, warehouse Management System. If there is no integrated management management, maintenance management, equipment query system for medical equipment based on cloud computing statistics, etc. Each module is composed of different business and the Internet of -ings, then in the hospital for the functions. Figure 2 shows a block diagram of the medical purchase of medical equipment, the doctor needs to report equipment management system. to the hospital leader, and the leader will notify the logistics management department after approval, and they will 3.3. Experimental System Database Design. By comparing contact the different medical equipment suppliers. In order the entities included in the system with the database tables, it to reduce the process of medical equipment procurement, can be concluded that the system needs to be developed and this article adds a supplier management module and an implemented. -e database needs to include equipment equipment procurement management module to the supplier tables, equipment tables, equipment type tables, medical equipment integrated management system. Figure 3 equipment status tables, purchase order tables, purchase shows the statistics on the consumption of medical equip- schedules, and equipment change application form and user ment in the hospital. form. It can be seen from Figure 3 that, except for some large- -e equipment supplier table is used to store the basic scale high-end medical equipment that can be reused for information data of equipment suppliers [36]. -e system many years, the hospital consumes a large amount of dis- adds, deletes, and modifies the table through the basic posable medical equipment every day, including medical 6 Journal of Healthcare Engineering File entry File management File query Contract entry Contract management Contract query Equipment storage Medical Equipment out of Repair application equipment storage Warehouse integrated management management Equipment scrap Maintenance dispatch system Equipment loan Repair processing Maintenance Apply for reassignment management Query number of Maintenance cost repairs registration Maintenance number Maintenance query evaluation Statistical query Maintenance cost inquiry Warehouse query Figure 2: Module structure diagram of medical equipment management system. Table 1: System operation description. Application server Client Central processing unit: i7 6500U Central processing unit: i7 6500U Hardware configuration Memory size: DDR4 2400 Memory size: DDR4 2400 Hard disk capacity: 1TB 7200 Hard disk capacity: 1TB 7200 Operating system: Windows 7 Operating system: Windows 7 Software configuration Database: SQL Server 2015 Report service: FineReport Application: Device Manager System Browser: Google Chrome diagnostic equipment, treatment equipment, and various more intelligently. -e equipment administrator only needs auxiliary equipment. As the inventory data of medical to input data in the purchase order information module and equipment is in a constantly changing state, it is difficult to the purchase detailed information module, and the back- accurately monitor the consumption of all medical equip- ground can correctly verify the input data and give a re- ment and replenish the inventory in a timely manner if it is sponse. It can be seen that the design and implementation of manually recorded by management personnel. However, the module can meet the proposed functional requirements. with the assistance of the medical equipment intelligent management system, department leaders and equipment administrators can know the consumption of various 4.2. Medical Equipment Maintenance Based on Integrated Management System. In the medical equipment compre- equipment at any time and directly purchase products through the system. hensive management system, the repair application per- Among all kinds of medical equipment, hospitals will sonnel of the department can enter the system after passing stockpile products with a small footprint and a long shelf life the identity verification and select the equipment repair on a large scale at a frequency of half a year or even a year. application business module to fill in the repair application However, those devices with a shorter warranty period and form. -e repair personnel are required to enter the repair faster version update need to be replenished in real time information such as title, priority, contact person, contact based on inventory. Figure 4 shows the statistics of medical number, repair address, upload fault photos, and repair equipment procurement in the hospital. details. After filling in, click Submit Application for Repair. It can be seen from Figure 4 that, with the help of the If all required information has been filled out, it will prompt medical equipment intelligent management system, the that the submission is successful. Table 2 shows the main- tenance application form in the database, and Figure 5 shows hospital can realize the purchase of various medical products Journal of Healthcare Engineering 7 107.5 8 85.6 111.3 128.6 7 63.4 123.7 102.1 70.5 108.3 109.5 5 81.4 116.3 99.6 4 77.9 106.5 107.4 3 85.3 117.5 128.3 2 69.7 108.2 96.5 1 83.3 121.2 0 20 40 60 80 100 120 140 Survey data Auxiliary equipment Treatment equipment Diagnostic equipment Figure 3: Statistics on the consumption of medical equipment in the hospital. Investigation time Auxiliary equipment Treatment equipment Diagnostic equipment Figure 4: Statistics on procurement of medical equipment in the hospital. Table 2: Repair request form in the database. Field description Field name Types Primary key Nonempty Repair order number Service ID Var char (20) Yes Yes Device name Equipment name Var char (20) No No Device ID Equipment ID Var char (20) No No Fault description Malfunction ms Var char (20) No No Application time Time Var char (20) No No Applicant Application admin Var char (20) No No Use department Application department Var char (20) No No the equipment repair module work order statistics in the equipment management system. -e medical equipment medical equipment integrated management system. maintenance application module is mainly designed for It can be seen from Table 2 and Figure 5 that the hospital departments. Each department is assigned an administrator leaders and system administrators can clearly grasp the who is responsible for the medical equipment maintenance maintenance status of all medical equipment through the management application and acceptance of the Statistical data Investigation time 8 Journal of Healthcare Engineering 5 4.8 4.77 4.5 4.72 4.46 4.45 4.39 4.5 4.34 4.41 4.36 4.11 3.97 3.9 3.87 3.98 4 3.83 3.78 3.67 3.44 3.33 3.07 3 2.92 AB C D Group Unassigned Waiting for Repair In maintenance Completed Not evaluated Evaluated Figure 5: Equipment repair module work order statistics. undergraduate room. After the department administrator longer service life. -is article takes the monitor as an ex- registers the system, the system administrator assigns the ample and combines various data in the medical equipment corresponding authority. After the department adminis- management system to explore scientific and reasonable trator logs in to the system, he can inquire about the preventive maintenance methods for the monitor. Table 3 maintenance of the equipment in the undergraduate room in and Figure 7 show the breakdown reason classification daily situations, such as the equipment being repaired, repair statistics of the monitor. progress, past repair records, and repair details of these It can be seen from Table 3 and Figure 7 that the main medical equipment. reason for the failure of the monitor lies in the accessories. Among them, the blood pressure cuff, the ECG lead wire, In order to further grasp the use effect of the medical equipment maintenance template, this paper conducts a and the blood oxygen probe have a relatively high number of failures; among the equipment failures, the number of oc- system performance test on it. System performance test is divided into two parts: system stress test and system com- currences is relatively high. It is the blood pressure module, patibility test. -e system stress test is mainly used to test the fan failure, and encoder failure. -rough data analysis, it is concurrent operation of multiuser login system. -e test possible to provide reference opinions on the quantity and system can support multiuser access. During the testing quality of the purchase of monitor accessories every year, phase, a large number of users cannot be found for si- and it is recommended to maintain a corresponding number multaneous access system, so this article uses a testing tool of vulnerable module accessories for equipment failures, so for stress testing. -e result of the system stress test is shown as to effectively prevent long-term downtime from affecting in Figure 6. clinical work and improve equipment utilization. Fan failure is mainly due to fan aging and dust accumulation. For It can be seen from Figure 6 that when there are 100 simultaneous online simulated users, the corresponding machines with poor heat dissipation, replace the fan and time for submitting the equipment maintenance application clean up internal dust in time. Encoder failure is the failure form is 1228 ms, and the correct rate is 99.8%; when there are of the keys. Replace the encoder with a new one in time for 1000 simultaneous online simulated users, the equipment the machine with key problems. Since most of the moni- maintenance application form is submitted. -e corre- toring consumables are plastic products, they will harden sponding time is 5123 ms, and the correct rate is 99.4%. and become unusable if stored for too long. Comprehensively observing the engineer’s handling of maintenance reports, maintenance equipment inquiries, and information reminders, it can be found that as the number of 4.3. Medical Equipment Management Based on Cloud Com- simulated users increases, the corresponding time of the puting and Internet of )ings. -e integrated management of medical equipment is essentially a dynamic task scheduling system is improving, while the accuracy rate has decreased. Taking into account the limited number of people using the problem, and the research of task scheduling has always been system at the same time in the hospital in actual work, a hot issue of scientific research in the cloud environment. maintaining a correct rate of over 99% is already a relatively -e problem of cloud computing task scheduling is the good performance for the system. process of matching different tasks from different users to If we can understand the causes of medical equipment cloud computing virtual resources in a reasonable manner failure, we can further promote the hospital preventive through scheduling requirements under certain constraints maintenance plan smoothly, so that the equipment has a to meet customer needs. In order to meet the needs of the Value Journal of Healthcare Engineering 9 4.62 4.44 4.09 3.89 3.47 2.76 4.72 4.25 4.1 4.03 3.36 2.94 4.61 4.24 4.13 4.15 3.68 2.9 4.69 4.32 3.91 4.08 3.58 3.55 Value Response time B Response time C Correct rate C Correct rate A Correct rate B Response time A Figure 6: Statistical results of system stress test. Table 3: Monitor breakdown reason classification statistics table. Cause of issue Number of failures Blood oxygen probe 162 Accessories failure ECG lead wire 130 Blood pressure cuff 195 Blood oxygen module 28 Blood pressure module 70 ECG module 28 Power board 11 Equipment failure Fan 43 Display screen 8 Keyboard 12 Encoder 46 Main control board 9 4.53 4.59 4.5 4.18 4.38 3.99 3.98 3.92 3.89 3.57 3.6 3.64 3.97 3.8 3.5 3.79 3.43 3… 3.64 3.37 2.5 1.5 0.71 0.63 0.61 0.58 0.48 0.47 0.5 2 48610 12 Fault reason serial number Data 1 Data 3 Data 2 Data 4 Figure 7: Classification statistics chart of monitor failure causes. Group Statistical dData 10 Journal of Healthcare Engineering 10 20 30 40 50 60 70 80 90 100 Number of iterations PSO NPSO CPSO EPSO Figure 8: Time statistics for particle swarm optimization task optimization. 0.9 0.82 0.77 0.8 0.73 0.72 0.7 0.68 0.7 0.65 0.63 0.61 0.6 0.6 0.60 0.58 0.58 0.56 0.6 0.53 0.51 0.46 0.5 0.42 0.42 0.37 0.4 0.3 0.2 0.1 20 30 40 50 60 70 80 Number of tasks CSO WCSO NCSO Figure 9: Comparison chart of the improved CSO algorithm fitness value. times, this paper appropriately improves the heuristic in- comparison chart of the fitness value of the improved telligent task scheduling algorithm—particle swarm algo- chicken flock algorithm. rithm and chicken swarm optimization algorithm—to It can be seen from Figure 9 that when the number of tasks is the same, the fitness function value of the im- improve the accuracy of the scheduling of medical equip- ment in the system. Figure 8 shows the optimization time proved ECSO algorithm in this paper is higher than the statistics of particle swarm optimization when the number of original two types of CSO algorithm, which shows that the tasks is 50. degree of load balancing is better. When the fitness It can be seen from Figure 8 that when the number of function value is close to 1, the longest time it takes for the tasks is 50, the task completion time of the particle swarm task to complete is closer to the total time for task algorithm will fluctuate differently as the number of itera- completion, and the more balanced the task allocation is tions changes. Compared with the other three types of when performing scheduling. On the whole, the im- particle swarm algorithms, the improved EPSO algorithm in provement of the chicken flock algorithm can effectively this paper has significantly shorter optimization time. When improve the utilization rate of the system and the effi- the number of tasks is low, the gap is relatively small, but as ciency of task execution, so that the system can be better the number of tasks continues to grow, the time efficiency applied to practical problems, and the scientific man- advantage of the improved particle swarm algorithm will agement and scheduling of medical equipment in the become more and more significant. Figure 9 shows a hospital can be realized. Experimental data Fitness function value Journal of Healthcare Engineering 11 equipment integrated management system, some modules’ 5. Conclusions functions are not complete enough. (3) It is necessary to -is article analyzes the purchase, maintenance, manage- propose a multifaceted fitness function for the fusion al- ment, and query of medical equipment based on the inte- gorithm according to the requirements of task scheduling. grated management system. -rough multiple stress tests on (4) Take advantage of the information age and actively the system, the results show that the medical equipment explore a comprehensive management system for medical management information system designed and imple- equipment based on mobile terminals. mented in this paper has excellent effects in terms of system reflection sensitivity, system compatibility, and system Data Availability stability and fully realizes the initial performance of the prediction. Claim. In this paper, according to the system No data were used to support this study. function modules, the supplier management, equipment purchase management, equipment maintenance manage- Conflicts of Interest ment, statistical query, and system management functions were tested in turn. From the results, it can be seen that each -e authors declare that they have no conflicts of interest module can play a good effect. Due to the full use of the regarding the publication of this paper. advantages of the Internet of -ings and cloud computing task scheduling, the medical equipment management system Acknowledgments developed in this paper not only reduces the implementation cost, but also effectively reduces the cost of hospital use. -is work was supported by the Science Research Funding From the perspective of the supplier, it is also beneficial to Project JYTJCRW2020089 of Liaoning Provincial Education increase economic benefits. Department in 2020, Research on Information Sharing of When scheduling tasks, whether it is time or cost, the Regional Medical Alliance for Major Diseases Based on more tasks there are, the greater the difference between the Cloud Computing. JYTJCRW2020089 scheduling scheme obtained by the improved particle swarm algorithm and the scheduling schemes of the other References three algorithms, and the trend of EPSO algorithm change is relatively stable. -is is because when the number of tasks [1] K. G. Srinivasa, B. J. Sowmya, A. Shikhar, R. Utkarsha, and A. Singh, “Data analytics assisted Internet of things towards is small, each algorithm performs small-scale search, which building intelligent healthcare monitoring systems: iot for cannot reflect the advantages of adaptive inertial weight healthcare,” Journal of Organizational and End User Com- balancing local and global search, and the recognition of puting, vol. 30, no. 4, pp. 83–103, 2018. individual optimal solutions and global optimal solutions [2] A. Amerieon, M. Alijanzadeh, and E. Teymourzadeh, “Ef- in the particle optimization process relationship. As the fective factors on the management of medical equipment number of tasks increases, the inertial weight adaptation maintenance in a military hospital: a qualitative study in and the correlation of random factors have a more sig- Iran,” Invertebrate Reproduction and Development, vol. 59, nificant impact on the particle optimization process, which no. 1, pp. 73–84, 2015. can better balance the global and local search, thereby [3] J. M. Ulickey, “One dashboard to rule them all: case study of obtaining a better scheduling plan. When the fitness an integrated facility management system,” Energy Engi- function value is close to 1, the longest time it takes for the neering, vol. 113, no. 5, pp. 52–63, 2016. [4] T. Grubljesic, P. S. Coelho, and J. Jaklic, “-e shift to socio- task to complete is closer to the total time for task com- organizational drivers of business intelligence and analytics pletion and the more balanced the task allocation is when acceptance,” Journal of Organizational and End User Com- performing scheduling. In the case of the same number of puting, vol. 31, no. 2, pp. 37–64, 2019. tasks, the fitness function value of the improved ECSO [5] Z. Qiang, D. Wen-Yan, and C. Kui, “Discussion on man- algorithm in this paper is higher than the original two types agement model of medical equipment maintenance in hos- of CSO algorithm, which shows that the degree of load pital,” China Medical Equipment, vol. 31, no. 5, pp. 1–4, 2016. balancing is better. [6] S. Namasudra and P. Roy, “PpBAC,” Journal of Organiza- In the diagnosis and treatment of diseases, medical tional and End User Computing, vol. 30, no. 4, pp. 14–31, 2018. equipment has become an indispensable auxiliary means. [7] X. Chen, L. Jiao, W. Li, and X. Fu, “Efficient multi-user Whether the medical equipment is advanced or not rep- computation offloading for mobile-edge cloud computing,” IEEE/ACM Transactions on Networking, vol. 24, no. 5, resents the level of hospital diagnosis and treatment. pp. 2795–2808, 2016. -erefore, it is very important to carry out effective and [8] R. C. Shah and Y. Wang, “Cloud -ings Construction - the scientific management of hospital medical equipment. integration of Internet of things and cloud computing,” Fu- Judging from the experimental results, the research in this ture Generation Computer Systems, vol. 56, no. C, pp. 684– paper has achieved certain results, but limited by various 700, 2016. conditions, there are still some shortcomings. In the follow- [9] Z. Lv and W. Xiu, “Interaction of edge-cloud computing based up research, more thoughts can be made from the following on SDN and NFV for next generation IoT,” IEEE Internet of aspects: (1) Further define the judgment standard of load )ings Journal, no. 99, p. 1, 2019. balancing in task scheduling in the cloud computing en- [10] Z. Xia, X. Wang, L. Zhang et al., “A privacy-preserving and vironment. (2) In the development process of the medical copy-deterrence content-based image retrieval scheme in 12 Journal of Healthcare Engineering cloud computing,” IEEE Transactions on Information Fo- [27] A. Francis Saviour Devaraj, M. Elhoseny, S. Dhanasekaran, E. Laxmi Lydia, and K. Shankar, “Hybridization of firefly and rensics & Security, vol. 11, no. 11, pp. 2594–2608, 2017. [11] R. S. Bhadoria and N. S. Chaudhari, “Pragmatic sensory data improved multi-objective particle swarm optimization algo- rithm for energy efficient load balancing in cloud computing semantics with service-oriented computing,” Journal of Or- ganizational and End User Computing, vol. 31, no. 2, environments,” Journal of Parallel and Distributed Comput- ing, 2020, In Press. pp. 22–36, 2019. [12] Q. Yan, F. R. Yu, Q. Gong, and J. Li, “Software-defined [28] V. Viswanathan and I. Krishnamurthi, “Finding relevant semantic association paths using semantic ant colony opti- networking (sdn) and distributed denial of service (DDoS) mization algorithm,” Soft Computing, vol. 19, no. 1, attacks in cloud computing environments: a survey, some pp. 251–260, 2015. research issues, and challenges,” IEEE Communications [29] Y. Huan, “Image edge detection based on ant colony opti- Surveys & Tutorials, vol. 18, no. 1, pp. 602–622, 2016. mization algorithm,” International Journal of Advanced [13] C.-S. Chen, W.-Y. Liang, and H.-Y. Hsu, “A cloud computing Pervasive and Ubiquitous Computing, vol. 8, no. 1, pp. 1–12, platform for ERP applications,” Applied Soft Computing, vol. 27, no. C, pp. 127–136, 2015. [30] T. Liao and Y. Yu, “Mixed variable and any time optimization [14] B. Xu, L. Xu, H. Cai, L. Jiang, Y. Luo, and Y. Gu, “-e design of oriented ant colony optimization algorithm,” Systems Engi- an m-Health monitoring system based on a cloud computing neering and Electronics, vol. 39, no. 3, pp. 675–680, 2017. platform,” Enterprise Information Systems, vol. 11, no. 1, [31] M.-Y. Cheng, D. Prayogo, Y.-W. Wu, and M. M. Lukito, “A pp. 17–36, 2017. Hybrid Harmony Search algorithm for discrete sizing opti- [15] Y. Chen, W. Zheng, W. Li, and Y. Huang, “-e robustness and mization of truss structure,” Automation in Construction, sustainability of port logistics systems for emergency supplies vol. 69, no. SEP, pp. 21–33, 2016. from overseas,” Journal of Advanced Transportation, [32] H. Zhang, S. Qu, H. Li, J. Luo, and W. Xu, “A moving shadow vol. 2020, Article ID 8868533, 10 pages, 2020. elimination method based on fusion of multi-feature,” IEEE [16] D. He and S. Zeadally, “An analysis of RFID authentication Access, vol. 8, pp. 63971–63982, 2020. schemes for Internet of things in healthcare environment [33] B. Gonzalez, ´ F. Valdez, P. Melin, and G. Prado-Arechiga, using elliptic curve cryptography,” IEEE Internet of )ings “Fuzzy logic in the gravitational search algorithm for the Journal, vol. 2, no. 1, pp. 72–83, 2015. optimization of modular neural networks in pattern recog- [17] S. R. Shanmugham and S. Paramasivam, “Survey on power nition,” Expert Systems with Applications, vol. 42, no. 14, analysis attacks and its impact on intelligent sensor networks,” pp. 5839–5847, 2015. IET Wireless Sensor Systems, vol. 8, no. 6, pp. 295–304, 2018. [34] G. Zhang and Y. Li, “A memetic algorithm for global opti- [18] T. Onoue, M. Goto, T. Kobayashi et al., “Randomized con- mization of multimodal nonseparable problems,” IEEE trolled trial for assessment of Internet of -ings system to Transactions on Cybernetics, vol. 46, no. 6, pp. 1375–1387, guide intensive glucose control in diabetes outpatients: nagoya Health Navigator Study protocol,” Nagoya Journal of [35] L. Yin, W. Pan, J. Kuang, and M. Zhuang, “Application of Medical Science, vol. 79, no. 3, pp. 323–329, 2017. bootstrap-DEA with fuzzy computing in performance eval- [19] J. Sun, X. Wu, V. Palade et al., “Random drift particle swarm uation of forklift leasing supplier,” IEEE Access, vol. 8, optimization algorithm: convergence analysis and parameter pp. 66095–66104, 2020. selection,” Machine Learning, vol. 101, no. 1-3, pp. 345–376, [36] R. Parada, J. Melia-Segu ` ´ı, and R. Pous, “Anomaly detection using rfid-based information management in an iot context,” [20] X. I. Maolong, W. U. Xiaojun, F. Wei et al., “Quantum-behaved Journal of Organizational and End User Computing, vol. 30, particle swarm optimization algorithm with self-renewal no. 3, pp. 1–23, 2018. mechanism,” Computer Engineering and Applications, vol. 2, [37] Z. Lv and N. Kumar, “Software defined solutions for sensors no. 10, pp. 100–114, 2015. in 6G/IoE,” Computer Communications, vol. 153, pp. 42–47, [21] X. Li and M. Yin, “A particle swarm inspired cuckoo search algorithm for real parameter optimization,” Soft Computing, vol. 20, no. 4, pp. 1389–1413, 2016. [22] A. Rana and D. Sharma, “Mobile ad-hoc clustering using inclusive particle swarm optimization algorithm,” Interna- tional Journal of Electronics and Information Engineering, vol. 8, no. 1, pp. 1–8, 2018. [23] A. A. A. Esmin, R. A. Coelho, and S. Matwin, “A review on particle swarm optimization algorithm and its variants to clustering high-dimensional data,” Artificial Intelligence Re- view, vol. 44, no. 1, pp. 23–45, 2015. [24] E. Demirci, O. E. Sahin, M. Ocak, B. Akovali, J. Nematyazar, and L. Kabasakal, “Normal distribution pattern and physio- logical variants of 68Ga-PSMA-11 PET/CT imaging,” Nuclear Medicine Communications, vol. 37, no. 11, pp. 1169–1179, [25] N. K. Jain, U. Nangia, and J. Jain, “A review of particle swarm optimization,” Journal of the Institution of Engineers, vol. 99, no. 4, pp. 1–5, 2018. [26] Y. Tang and X. Guan, “Parameter estimation for time-delay chaotic system by particle swarm optimization,” Chaos Sol- itons and Fractals, vol. 40, no. 3, pp. 1391–1398, 2017.
http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png
Journal of Healthcare Engineering
Hindawi Publishing Corporation
http://www.deepdyve.com/lp/hindawi-publishing-corporation/medical-equipment-comprehensive-management-system-based-on-cloud-M3VatPxgnK