Design of Informatization College and University Teaching Management System Based on Improved Decision Tree Algorithm

Liu, Yafei; Ren, Zhaoxu; Li, Jiye; Li, Jun

doi:https://doi.org/10.1155/2022/3127487

Wireless Communications and Mobile Computing

On this page

Abstract Introduction Conclusion Data Availability Conflicts of Interest References Copyright Related Articles

Special Issue

Advanced Information Security in Next Generation Wireless Communication-Enabled Internet of Things

View this Special Issue

Research Article | Open Access

Volume 2022 | Article ID 3127487 | https://doi.org/10.1155/2022/3127487

Design of Informatization College and University Teaching Management System Based on Improved Decision Tree Algorithm

Yafei Liu,¹Zhaoxu Ren,¹Jiye Li,¹and Jun Li²

Academic Editor: Zhiguo Qu

Received17 Feb 2022

Revised09 Mar 2022

Accepted21 Mar 2022

Published14 Apr 2022

Abstract

At present, the teaching management system used in colleges cannot classify and store the teaching material information well and also has some problems, such as inaccurate calculation results of resource information weight, long response time, and large data query error. Therefore, this study designs an information college teaching management system based on improved decision tree algorithm. The hardware structure of the system consists of information communication structure, information teaching resource sharing structure, processor, and crystal oscillator circuit, and the core module is the data output control module. This study designs the system software based on the improved decision tree algorithm, creates a decision tree recursively, uses the CART decision tree to calculate the weight of teaching resource information, and constructs the fitness objective function of teaching resource information according to the mean clustering algorithm, so as to accurately extract the teaching resource information and realize the efficient processing of college teaching resource. The experimental results show that the response time of the system in this study is only 8 ms, the maximum convergence value is only 40, there is only one wrong data in the data query, and the storage time is 40 s. This system has a short response time, fast convergent rate, and a low probability of data search error when more than one client access the database at the same time.

1. Introduction

With the deepening of education informationization, many schools have built their own internal teaching systems, which have a variety of internal teaching resources, including the course of video, audio, text materials, teaching courseware, electronic books, and teaching software; these resources can bring great help to school teachers and students’ work and learning [1]. However, the teaching resources in different schools are often isolated because of the different teaching systems, and it is difficult to share the resources and other operations. This is due to the fact that these systems are often developed by different vendors at different times and therefore often difficult to operate such as cross-sharing [2]. With the rapid development of network communication technology and computer technology, colleges and universities have begun to establish network learning platforms and integrate various excellent resources. Although this method broadens the vision of students but also has certain limitations, there is no unified communication platform between schools and schools, and excellent resources can only be digested within the school, resulting in a waste of resources [3]. At the same time, teaching resources are the main auxiliary resources in current teaching activities, which are characterized by various forms, fast propagation speed, and large amount of information [4]. However, due to this feature, it is difficult to classify, manage, and search. Therefore, efficient resource management is very necessary, and this issue has gradually become a hot research topic of scholars.

At present, there are many research results on the research of teaching management system in colleges and universities. Reference [5] designs a comprehensive teaching management system in colleges and universities based on EITP protocol. On the basis of EIO software development framework, the system uses EITP protocol and related concepts of blockchain to transform the communication mode between the submodules of the original teaching management system and realizes a highly compatible college teaching management system, which has certain practicability and reference value. In reference [6], the paper puts forward some suggestions on how to optimize the top-level design, strengthen the information integration, and share the information and puts forward some suggestions on how to develop the informationization of teaching management by focusing on the needs of students. Reference [7] studies the education management system based on ArcGIS technology. This system analyzes the requirements of the education management system and then builds the corresponding overall architecture and designs the corresponding functional requirements. In the whole system design, ArcGIS engine control and component GIS technology are used to make the system more simple and convenient and more convenient for maintenance.

However, the existing systems cannot classify and store the teaching materials, and the calculation results of resource information weights are not accurate, which leads to the long response time and large error. Therefore, an informatization college and university teaching management system based on improved decision tree algorithm is designed.

2. Hardware Design of Teaching Management System

The system hardware framework of this study is shown in Figure 1.

In this research, the system hardware takes the processor as the core to improve the execution speed of the system. The specific design contents are as follows.

2.1. Information Communication Structure

The purpose of information and communication networks is to provide technical support for the transmission of teaching resources, real-time teaching data, and the latest dynamic data, improve the transmission performance and speed of communication networks, and thus enhance the informatization efficiency of the system. The communication network is mainly composed of three parts: the client, the server, and the connection link. The concrete communication network result is shown in Figure 2.

In the communication network, the client is the main receiving end of the teaching information. The client does not have the requirement of installation and form. It can log in the system by the embedded plug-in after the web server logs in. In order to ensure the safe operation of the system, it is necessary to install the data transmission protocol on the client port. Under the restriction of the HTTP protocol, the client can transmit the data to the system server through the firewall [8]. The communication network adopts IIS server based on Windows. The server is mainly used for registering, logging in, user privilege management, system management, and information release. Under the server’s management mechanism, the client can apply to the system for task scheduling. When the server passes the application, it automatically generates a transmission link to realize the fast transmission and informatization. It is necessary to configure the switching device in the network, define two vlans, modify the IP address without modifying the mask, and add a route between the two vlans, activating routing functions using the “enable” command [9]. Finally, a default gateway is added to the switch, and “default” is entered to define the default route, which is the IP address of the router in the information communication network.

2.2. Information-Based Teaching Resource Sharing Structure

The information-based teaching resource sharing structure consists of four parts, and the architecture is shown in Figure 3.

As can be seen from Figure 3, the four levels work together and are inseparable. The main task of the top-level resource collection and processing module is to collect and preprocess the teaching resources; the next is the feature extraction module, in which the feature words in the teaching resources are selected through the feature extraction algorithm; the next is the classifier classification module, which classifies the teaching resources according to the result of feature extraction, then carries on the sharing module, and classifies and stores the teaching resources through the classification results, and teachers can directly find the needed information and share it [10].

2.3. Processor Design

S3c2440 chip is applied to the teaching management system. The chip is rich in resources, and its basic parameters are shown in Table 1.

In addition, the chip has the following characteristics: (1)The chip contains a USB host controller, which facilitates the export of student data when required(2)There are a large number of GPIOs in the chip, which makes the system upgrading very convenient(3)It has a 12S bus to facilitate the driving of audio chips(4)PWM output with 2~8 channels(5)Contains four ordinary clock timers and one watchdog timer

2.4. Crystal Oscillator Circuit and Other Interface Circuits

The crystal oscillator circuit is mainly used to provide the working clock to the system CPU and other circuit equipment [11]. The design connection results of the crystal oscillator circuit are shown in Figure 4.

Under the effect of crystal oscillator circuit, the hardware system can obtain higher working frequency with lower external clock signal and effectively control the high-frequency noise caused by high-speed switch clock.

Other interface circuits include memory interface circuit, serial interface circuit, JTAG interface circuit, and expansion board interface circuit. Take the serial interface circuit for example; this circuit uses RS-232-C standard, which is a serial data transmission bus standard. This standard uses 9-core D plug to connect. The connection of each pin in the serial circuit is shown in Table 2.

2.5. Memory Module Design

Based on the need of information teaching management system, Flash is extended by Nor Flash and Nand Flash. Nor Flash can reduce the system static storage and read data randomly. The Nor Flash is connected to the external memory of the processor and is mapped to the system BANK0. The S3C2440 chip can read and write the Nor Flash chip as the running space of the program. When applied, the read-write timing of the processor chip can satisfy the Nor Flash read-write timing [12]. K9F1G08 is NAND flash memory. The chip adopts voltage control between 2.7 V and 3.6 V. The eight pins of K9F1G08 are connected with S3C2440 chip by low eight bit data line.. Through the extension, it is easy to port the operating system.

2.6. Design of Wireless Transceiver Module

Wireless transceiver module is an important part of information teaching management system [13, 14], using nrf24l01 RF chip to achieve multipoint wireless communication. The basic parameters of the chip are shown in Table 3.

In addition, the communication protocol of the chip is completely transparent to users, and free communication can be realized between the same products.

2.7. Design of Data Output Control Module

The LCM12864ZK liquid crystal display module produced by a company in Beijing is applied to the system design. The power supply operation range of the module is between 2.7 V and 5.5 V, and the power consumption is very low. The main performance of the module is as follows: (1)It contains 8 serial and 4 dual-use interfaces(2)Support the STN yellow-green mode(3)The working voltage is 3 V or 5 V, excluding the backlight working current

The pins of the module function are shown in Table 4.

The chip has strong control and display function and is suitable for teaching management system.

3. College Teaching Resource Processing Based on Improved Decision Tree Algorithm

Decision tree algorithm is a typical classification algorithm. It constructs a decision tree and processes the training set of teaching data from top to bottom recursively according to the idea of decision tree [15]. The basic implementation flow of the decision tree algorithm is shown in Figure 5.

According to the algorithm implementation flow in Figure 5, the readable rule and decision tree are generated from the data training set and the corresponding associated class label based on the teaching data filling processing results. After building the decision tree, the training set is gradually recursively merged into several smaller subsets. Because of the complexity of teaching data types and the large amount of data, in the process of data classification, we set up a number of decision trees to achieve synchronous algorithm classification, which can improve the classification speed while ensuring the classification results [16]. Generally speaking, constructing decision tree can be divided into five steps. Firstly, the result of teaching resource data is taken as the collected data and divided into groups. Then, take all the data records as a node of a decision tree, traverse each partition of each variable, and determine the position of the optimal partition point [17]. If the sample data belongs to the same category, the node is the leaf node in the decision tree; otherwise, the optimal attribute of classification ability is selected as the current node. The gain rate of each attribute is calculated, and the attribute corresponding to the maximum gain rate is selected for splitting processing. After the attribute splitting, the single node is divided into two nodes, and then, the splitting continues according to the above steps. When the splitting process of the decision tree meets the stop condition, the decision tree stops the classification [18].

3.1. Create a Single Decision Tree Recursively

Because of the large number of teaching data classification items needs to be processed and classified, in the process of classification, we first establish a number of single decision trees and fuse the results of several single decision trees, and then, we get the results of teaching data processing by decision tree algorithm [19, 20]. Suppose there are samples in the teaching data obtained by data filling, and the teaching data in the samples belong to different data categories. Define attribute as test attribute, has different discrete values, is divided into subsets, the number of samples in including class is , and the decision tree information gain with as the root node can be expressed as follows:

Parameter represents the expected information entropy corresponding to attribute [21], and its calculation formula is

By solving the above formulas together, it can be obtained that the information gain rate function of a single decision tree is

Select the attribute with the maximum information gain rate as the test attribute of the current node [22].

3.2. College Teaching Information Extraction Based on CART Decision Tree

CART decision tree is used to calculate the weights of teaching resource information, and the perturbation vector is calculated by combining the decision tree vector of teaching resource information with the mean clustering algorithm. Through constructing the target function of information suitability of teaching resources, we can adjust and reconstruct the category of teaching resource information and achieve the extraction of teaching resource information [23–25].

Assuming that represents a feature vector data set with uniform and convenient instructional resource information, and an instructional resource information decision tree is composed of individual instructional resource information branches and leaves of , then under the optimal goal strategy, the limited data set satisfying the instructional resource information search is where represents the clustering eigenvalue of the teaching resource information branch in the feature vector data set of teaching resource information. The optimal weight of the teaching resource information clustering branch in is calculated by means of coordinated query [26]. The calculation formula is where represents the initial value of teaching resource information, represents the initial value weight of teaching resource information, and the number of input teaching resource information samples is in the optimal position of teaching resource information [27]. For the large data set containing teaching resource information samples, is used to represent the teaching resource information cluster center and the disturbance vector. The calculation formula is

According to the above formula, the optimal solution of teaching resource information and the clustering center disturbance vector of CART decision tree can be calculated to obtain the clustering matrix of teaching resource information [28], which is expressed as where represents the number of differencing steps of teaching resource information and represents the decision-making matrix of teaching resource information. In order to reflect the changing characteristics of teaching resource information in the decision-making and classification process [29], the fitness objective function of teaching resource information under the CART decision tree is calculated, which is expressed as follows: where represents the maximum value of teaching resource information vector, represents the Euclidean distance between teaching resource information samples and , and the calculation formula is

According to the calculation process of the above formula, it can be concluded that the decision-making of teaching resource information is in a stable state. The chaotic components [30–32] of NP disturbance variables of teaching resource information are added to the CART decision tree, expressed as

In order to avoid falling into a local optimal state in the extraction process of teaching resource information, represents the threshold value and calculates the diversity factor of teaching resource information in decision-making, that is,

According to the above process, the data value of teaching resource information in the decision-making process can be calculated by the following formula [33]:

Using the difference perturbation of the CART decision tree, an initial membership matrix of the teaching resource information is generated and placed in the decision tree to obtain the perturbation variables of the teaching resource information, namely [34], where represents the increase in the number of teaching resource information. CART decision tree is used to collect and process teaching resource information [35, 36], extract the sample value of teaching resource information, and adjust the category of teaching resource information: where refers to the amount of teaching resource information. The perturbation sequence of teaching resource information is added to the CART decision tree [36], and the teaching resource information is reconstructed for the second time to extract the reconstructed teaching resource information:

4. Experimental Design and Result Analysis

Publication and exchange of teaching information in colleges and universities is temporarily hosted on the web server of campus network, which is Windows 2020 Advanced Server SQL Server 2020, and the CPU equipment and network card equipment in the server are Pentium VI 2.4 GHz and 10/100/1000 M adaptive network card, respectively. The model of system client terminal used in the experiment is mainly Chinese Windows 95/98/2000/NT/XP computer equipment, and some mobile terminals are set as the client of the teaching system. The designed teaching system is developed under the Windows XP Professional, which is transplanted to the Windows 2000 Advanced Server environment in the course of system publishing. The ASP file codes in the software part of the information-based teaching system can be directly imported into the notepad for recording and finally stored as files in asp format. As for the production and decoration of the system interface, the Macromedia Studio tool is used to professionally process the animation, page, and graphics of the system’s front-end display effect and provide a visual page environment. In addition, in order to ensure the stable running of the system software program, C + running tool is installed in the main test computer. The tool can call files in asp format to realize the running of the system. In order to highlight the application effectiveness of the designed system, the university integrated teaching management system based on EITP protocol designed in reference [5] and the university teaching information management system based on information terminal optimization designed in reference [6] are used as experimental comparison systems, and the experimental results are compared with the test results of the designed system. In the experimental analysis, the system response time, the convergence, the number of data search errors, the time consumed to store the same data, and the user satisfaction under the access of multiple concurrent users are used as experimental performance indicators to test the performance of the three methods.

4.1. System Response Time under Multiconcurrent User Access

The teaching management system in colleges and universities is often accessed by multiple users at the same time. Therefore, when analyzing the system response time under the access of multiple concurrent users, the shorter the time, the better the system. The comparison results of the response time of different systems are shown in Figure 6.

According to Figure 6, the design system is least affected by the number of concurrent users. When the number of concurrent users is 2500, the system response time is only 8 ms. The response time of the system in [5] is 35 ms, and the response time of the system in [6] is 38 ms. Compared with the three systems, the response time of the designed system is reduced by 27 ms and 30 ms, respectively. Therefore, the designed system can respond quickly under multiple concurrent users, ensuring the normal operation of the system and meeting the performance requirements of the system.

4.2. System Convergence

The stable operation of the system is an important performance of the system. Therefore, the convergence of the three systems is used as the experimental index to test the convergence of the three systems to verify the stability of the system. The smaller the convergence value, the more stable the system is. The experimental results are shown in Figure 7.

The analysis of Figure 7 shows that the convergence curve of the teaching resource scheduling of the design teaching system is relatively stable, which is far lower than the convergence value of the document [5] system and document [6] system,and its maximum convergence value is only 40.The minimum convergence value of the document [6] system is 62, and that of document [5] system is 59. The convergence values of the design system are lower than those of document systems 22 and 19 respectively. Therefore, the resource scheduling convergence of this system is better, and the teaching system is more stable.

4.3. Comparison of the Number of Errors in Searching Teaching Data

The number of errors found in the teaching data of the school’s previous system and this research system was, respectively, applied. The lower the number of errors, the better the performance of the system. The comparison results are shown in Figure 8.

As can be seen from Figure 8, for data query, the design system can accurately find out the relevant teaching data, with fewer errors, while the literature system has a large number of errors in resource search, and the search effect is poor, of which the design system has a maximum of 1 error. There are 7 wrong data in the literature [5] system, and 6.5 in the literature [6] system. Therefore, the data query effect of the design system is the best, and the reason for the better effect is that the proposed system sets the data search sequence in the software part, which solves the problem of data collision and improves the accuracy of data search.

4.4. It Takes Time to Store the Same Data

Select the amount of RDF data of different scale data sets, and compare the time spent on RDF data storage by using the proposed method, the university integrated teaching management system based on EITP protocol designed in reference [5], and the university teaching information management system based on information terminal optimization designed in reference [6]. The results obtained after comparison between literature [5] and literature [6] are shown in Figure 9.

The analysis of Figure 9 shows that when the amount of RDF data is 100 M, the storage consumption time of the system [5] is 40 s, the storage consumption time of the system [6] is 29 s, and the storage consumption time of the design system is 19 s; when the number is 250 M, the storage consumption time of the system in reference [5] is 70 s, the storage consumption time of the system in reference [6] is 60 s, and the storage consumption time of the designed system is 20 s; when the amount of RDF data is 400 M, the storage consumption time of the system in reference [5] is 60 s, the storage consumption time of the literature [6] system is 80 s, and the storage consumption time of the design system is 40 s. Therefore, when RDF data of the same size is stored, the storage time of the designed system is lower than that of reference [5] system and reference [6] system, which can effectively reduce the storage consumption time and improve the storage efficiency.

4.5. User Satisfaction

The designed system is a service system for university management. Therefore, the quality of the system service is based on user satisfaction as the experimental indicator to measure the performance of the three systems. The test results are shown in Figure 10.

According to Figure 10, the user satisfaction of the design system is above 92. The user satisfaction of the system in reference [5] only reached 88 at the beginning and then continued to decrease. The highest user satisfaction of the system in reference [6] was 77 and unstable, indicating that the system is not running well. Compared with the three systems, the satisfaction of the design system is higher than the highest value of the literature system by 4 and 15, respectively. Therefore, the design system has been recognized by most users, and its performance is better.

5. Conclusion

In order to optimize the response time and operation accuracy of college teaching management system, this study designs an information college teaching management system based on improved decision tree algorithm. This study designs the data output control module by using the improved decision tree algorithm, so as to effectively deal with the college teaching resource. The teaching management system obtains the processing results of the decision tree algorithm on the teaching data by establishing multiple single decision trees and integrating the processing results of multiple single decision trees. In addition, the system also uses CART decision tree to calculate the weight of teaching resource information and combines the decision tree vector of teaching resource information with mean clustering algorithm to construct the fitness objective function of teaching resource information, which realizes the effective classification and extraction of teaching resource information. After verification and analysis, it can be seen that the teaching management system has significantly improved in response time, data query accuracy, operation stability, and user satisfaction. Specifically, the system response is only 8 ms, the query data has only one error, and the user satisfaction has exceeded 92%. The college information teaching management system based on the improved decision tree algorithm has good performance and effectively solves the problems of unstable operation, slow response speed, and large data query error in the past, which greatly improves user satisfaction and has a high value of promotion and application. In the future research work, we should focus on analyzing the CPU occupancy rate of the system, further optimize the system ,and continuously improve the performance of the teaching management system.

Data Availability

The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation.

Conflicts of Interest

The authors declared that they have no conflicts of interest regarding this work.

References

D. A. Endovitskiy and K. A. Gaidar, “University science and education in the context of artificial intelligence,” Vysshee Obrazovanie v Rossii = Higher Education in Russia, vol. 30, no. 6, pp. 121–131, 2021.
View at: Google Scholar
I. L. Zagoumennov, “Development of managerial competencies of students on the basis of democratization and informatization of educational process at the university,” Open Education, vol. 24, no. 2, pp. 55–64, 2020.
View at: Publisher Site | Google Scholar
N. Semeniuk, “Modern university in the light of lifelong learning challenges: the issues of philosophy of education,” Studia Warmińskie, vol. 56, no. 2, pp. 137–148, 2020.
View at: Google Scholar
N. Mikhaylova and S. Verkhoturov, “Sustainable development of education: a home bank of management decisions of the university in ensuring the minimum requirements of legislation,” in E3S Web of Conferences, vol. 208, no. 1, pp. 09007–09028, 2020.
View at: Google Scholar
L. Zheng, “Design and implementation of college teaching management system based on EITP protocol,” Modern Electronics Technique, vol. 42, no. 18, pp. 65–68, 2019, 72.
View at: Google Scholar
Z. Guangfu, “Practice and consideration on construction of teaching management informatization,” Computer Engineering and Science, vol. 41, no. z1, pp. 242–244, 2019.
View at: Google Scholar
L. Zhang, “Development of educational management system based on ArcGIS technology,” Modern Electronics Technique, vol. 44, no. 6, pp. 47–52, 2021.
View at: Google Scholar
P. Mashwama, S. G. Fashoto, E. Mbunge, and S. Gwebu, “Development of a mobile inter-vehicular communication system based on gossip algorithm,” International Journal of Interactive Mobile Technologies (iJIM), vol. 14, no. 11, pp. 4–15, 2020.
View at: Publisher Site | Google Scholar
A. E. Hassani, A. Sahel, and A. Badri, “IRH-OF: a new objective function for RPL routing protocol in IoT applications,” Wireless Personal Communications, vol. 119, no. 1, pp. 1–17, 2021.
View at: Google Scholar
T. F. Pereira, J. Montevechi, F. Leal, R. . C. Miranda, and A. P. G. Scheidegger, “Application of a management and storage system for knowledge generated from simulation projects as a teaching and assessment tool,” SIMULATION: Transactions of The Society for Modeling and Simulation International, vol. 97, no. 12, pp. 795–808, 2021.
View at: Publisher Site | Google Scholar
M. E. Sahin, A. S. Demirkol, H. Guler, and S. E. Hamamci, “Design of a hyperchaotic memristive circuit based on wien bridge oscillator,” Computers & Electrical Engineering, vol. 88, no. 5, pp. 106826–106837, 2020.
View at: Publisher Site | Google Scholar
G. Zhu, J. Han, and Y. Son, “A preliminary study: towards parallel garbage collection for NAND flash-based SSDs,” IEEE Access, vol. 8, no. 99, pp. 223574–223587, 2020.
View at: Publisher Site | Google Scholar
M. K. Oh, S. Lee, Y. Kang, and D. Choi, “Wireless transceiver aided run-time secret key extraction for IoT device security,” IEEE Transactions on Consumer Electronics, vol. 66, no. 1, pp. 11–21, 2020.
View at: Publisher Site | Google Scholar
K. S. Rijab and S. M. Sadiq, “Implementing a reconfigurable Internet of Things nodes using non-IP network based on wireless sensor network,” Journal of Engineering Sciences, vol. 12, no. 4, pp. 60–66, 2020.
View at: Google Scholar
A. I. B. Ayinla, “An improved collaborative pruning using ant colony optimization and pessimistic technique of C5.0 decision tree algorithm,” International Journal of Computer Science and Information Security, vol. 18, no. 12, pp. 111–123, 2021.
View at: Google Scholar
X. Y. Zhang and W. Shi, “Research about the university teaching performance evaluation under the data envelopment method,” Cognitive Systems Research, vol. 56, no. 3, pp. 108–115, 2019.
View at: Publisher Site | Google Scholar
Q. K. Lin, Y. F. Zhu, S. F. Zhang, P. Shi, Q. Guo, and Z. Niu, “Lexical based automated teaching evaluation via students’ short reviews,” Computer Applications in Engineering Education, vol. 27, no. 1, pp. 194–205, 2019.
View at: Publisher Site | Google Scholar
W. Ho and X. Ma, “The state-of-the-art integrations and applications of the analytic hierarchy process,” European Journal of Operational Research, vol. 267, no. 2, pp. 399–414, 2018.
View at: Publisher Site | Google Scholar
T. Isabel and E. H. Benjamin, “Nomological consistency: a comprehensive test of the equivalence of different trait indicators for the same constructs,” Journal of Personality, vol. 87, no. 3, pp. 715–730, 2019.
View at: Publisher Site | Google Scholar
P. Amenta, A. Ishizaka, A. Lucadamo, G. Marcarelli, and V. Vyas, “Computing a common preference vector in a complex multi-actor and multi-group decision system in analytic hierarchy process context,” Annals of Operations Research, vol. 284, no. 1, pp. 33–62, 2020.
View at: Publisher Site | Google Scholar
T. Dinesh, “Higher classification of fake political news using decision tree algorithm over naive Bayes algorithm,” Revista Gestão Inovação e Tecnologias, vol. 11, no. 2, pp. 1084–1096, 2021.
View at: Publisher Site | Google Scholar
R. V. Varade and B. Thankanchan, “Academic performance prediction of undergraduate students using decision tree algorithm,” SAMRIDDHI A Journal of Physical Sciences Engineering and Technology, vol. 13, SUPPLEMENT 1, pp. 97–100, 2021.
View at: Publisher Site | Google Scholar
C. Kaun, N. Z. Jhanjhi, W. G. Wei, and S. Sukumaran, “Implementation of decision tree algorithm to classify knowledge quality in a knowledge intensive system,” MATEC Web of Conferences, vol. 335, no. 3, pp. 04002–04014, 2021.
View at: Publisher Site | Google Scholar
J. Keuangan, P. Dan, A. Muditomo, and S. Broto, “IPO performance prediction during Covid-19 pandemic in Indonesian using decision tree algorithm,” Jurnal Keuangan dan Perbankan, vol. 25, no. 1, pp. 132–143, 2021.
View at: Google Scholar
M. M. Mijwil and R. A. Abttan, “Utilizing the genetic algorithm to pruning the C4.5 decision tree algorithm,” Asian Journal of Applied Sciences, vol. 9, no. 1, pp. 45–52, 2021.
View at: Google Scholar
M. R. R. B. S. Kumar, “A C4.5 decision tree algorithm with MRMR features selection based recommendation system for tourists,” Psychology (Savannah, Ga.), vol. 58, no. 1, pp. 3640–3643, 2021.
View at: Google Scholar
Z. J. Wang, X. Yang, and X. T. Jin, “And-like-uninorm-based transitivity and analytic hierarchy process with interval-valued fuzzy preference relations,” Information Sciences, vol. 539, no. 2, pp. 375–396, 2020.
View at: Publisher Site | Google Scholar
P. S. Liu, H. Cui, Y. Cao, X. Hou, and L. Zou, “A method of multimedia teaching evaluation based on fuzzy linguistic concept lattice,” Multimedia Tools and Applications, vol. 78, no. 21, pp. 30975–31001, 2019.
View at: Publisher Site | Google Scholar
F. K. Gündoğdu and C. Kahraman, “A novel spherical fuzzy analytic hierarchy process and its renewable energy application,” Soft Computing, vol. 24, no. 6, pp. 4607–4621, 2020.
View at: Publisher Site | Google Scholar
Z. M. Zhang and W. Pedrycz, “Intuitionistic multiplicative group analytic hierarchy process and its use in multicriteria group decision-making,” IEEE transactions on cybernetics, vol. 48, no. 7, pp. 1950–1962, 2018.
View at: Publisher Site | Google Scholar
M. Razali, R. B. Saian, Y. B. Wah, and K. R. Ku-Mahamud, “A class skew-insensitive ACO-based decision tree algorithm for imbalanced data sets,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 21, no. 1, pp. 412–428, 2021.
View at: Publisher Site | Google Scholar
H. F. Zhou, J. W. Zhang, Y. Q. Zhou, X. J. Guo, and Y. M. Ma, “A feature selection algorithm of decision tree based on feature weight,” Expert Systems with Applications, vol. 164, no. 4, pp. 113842–113859, 2021.
View at: Publisher Site | Google Scholar
S. M. Hejri, A. Mirzazadeh, and M. Jalili, “Peer observation of teaching for formative evaluation of faculty members,” Medical Education, vol. 52, no. 5, pp. 567-568, 2018.
View at: Publisher Site | Google Scholar
S. Wiyono, D. S. Wibowo, M. F. Hidayatullah, and D. Dairoh, “Comparative study of KNN, SVM and decision tree algorithm for student's performance prediction,” International Journal of Computing Science and Applied Mathematics, vol. 6, no. 2, pp. 50–60, 2020.
View at: Publisher Site | Google Scholar
B. Lalithadevi, “Novel technique for price prediction by using logistic, linear and decision tree algorithm on deep belief network,” International Journal of Psychosocial Rehabilitation, vol. 24, no. 5, pp. 1751–1761, 2020.
View at: Publisher Site | Google Scholar
H. Oztekin, F. Temurtas, and A. Gulbag, “On the improvement of the teaching quality and learning effectiveness in the computer organization course through FPGA and modular centered microcomputer design,” Computer Applications in Engineering Education, vol. 26, no. 5, pp. 1825–1840, 2018.
View at: Publisher Site | Google Scholar

Copyright

Copyright © 2022 Yafei Liu et al. This 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.

PDF Download Citation

Download other formats

Order printed copies