Design of diversified teaching platform of college aerobics course based on artificial intelligence

Abstract

In order to improve the diversified teaching effect of a college aerobics course, effectively improve the accuracy of student grouping on the teaching platform, a diversified teaching platform of college aerobics course based on artificial intelligence is designed. First of all, it puts forward the construction idea and design process of the network teaching platform, then designs the interface and function module of the teaching platform, and finally designs the grouping function of teaching objects, so as to complete the design of the diversified teaching platform of a college aerobics course based on artificial intelligence. The experimental results show that the grouping accuracy of students on the diversified teaching platform of college aerobics course based on artificial intelligence is greater than 75%, and the average score of students studying on the platform is 74.66. This explains why the designed platform can effectively provide the accuracy of grouping and the students’ performance.

Keywords

Artificial intelligence college aerobics curriculum diversification teaching platform

1. Introduction

Body calisthenics is an emerging leisure and ornamental sports project, which can improve students’ aesthetic awareness and personal cultivation, and promote the healthy development of students’ physical and mental health. Therefore, many non-sports majors in colleges and universities offer aerobics courses. But in many colleges and universities, the effectiveness of aerobics classes is not high, the main reasons for this situation are: uneven student foundation, school attention is not enough, teachers’ own quality is not high. Diversified teaching strategy is a very popular teaching method in the field of education. It is a typical practice of the teaching concept of “facing all students, based on students’ diversified development”.

According to the requirements of cultivating and improving students’ innovation ability and comprehensive ability, Document [1] takes the basis of aerobics teaching to establish diversified aerobics teaching mode. Build a diversified aerobics teaching network teaching platform based on Internet technology, to provide theoretical basis and practical strategies for the combination of traditional aerobics teaching, diversified teaching mode and network teaching platform. On the development of educational information, Document [2] makes a comparative analysis of the existing teaching platform. The key contents of network course development design and course teaching implementation are discussed.

Based on the above research results, a diversified teaching platform for college aerobics course based on artificial intelligence is designed. The construction idea and design process of network teaching platform, three levels and various functional modules of teaching platform based on artificial intelligence technology and automatic grouping algorithm to complete the overall design of diversified teaching platform. Experiments prove that the platform designed in this paper can accurately group students, and the student performance in this platform is significantly improved.

2. Construction of network teaching platform

The aerobics course focuses on skills and functional play, on the one hand, to cultivate students’ aerobics skills, on the other hand, to reflect their fitness, body, heart function, is a highly artistic, humanistic combination of sports. Combining the aerobics course with the network teaching platform which has the thought of “leading subject combination” and “paying equal attention to learning and teaching”, combining the advantages of the two, we not only pay attention to the function of the network teaching platform, but also highlight the practicality of offline teaching. That is “online theory + offline practice” mixed mode, provides more learning channels and more learning resources for students to learn aerobics, constantly enriches and optimizes the teaching content, making the aerobics course more interesting under the diversified aerobics teaching network platform. The design of diversified aerobics teaching network platform must follow the scientific education theory, guide practice through the theory, objectively reflect the development process of both teaching theory and learning theory, and maximize the realization of scientific network education process. The construction of the diversified aerobics teaching network platform is based on the constructivism theory and behaviorism learning theory, and jointly realizes the effective guidance process of the network course design process, and follows the following four principles: The first is the approach principle, that is, the response appears immediately after stimulation; The second is the principle of repetition, which exerts students’ ability of repeated learning and memory; The third is the principle of feedback and reinforcement, which provides information related to the correctness of response and effectively promotes students’ learning process; The fourth is the principle of prompting and attenuating, under the premise of reducing prompting, students are expected to be guided reversely to complete the learning task. The above four principles highlight the idea of building a diversified aerobics teaching network platform, and integrate the construction concept of “student-centered” network teaching platform, with students as the center, and reemphasize the leading role of teachers. These theoretical contents are reflected in the classroom teaching design one by one, highlighting the construction of diversified aerobics teaching network platform teaching design connotation. After fully combining the advantages of the leading and the main body, the new teaching design concept of “paying equal attention to learning and teaching” has basically formed and played its unique function.

3. Design process of network teaching platform

The design and construction process of diversified aerobics teaching network platform should include five main application process stages: preliminary analysis and investigation, teaching goal establishment, teaching content resource design, teaching strategy activity design and evaluation design.

3.1 Preliminary analysis and survey design

The advantage of network teaching platform is that it can apply network technology to achieve rapid and extensive pre analysis and investigation. As far as aerobics course is concerned, it includes the preliminary analysis and investigation of teaching background, students’ will, learning tasks and other aspects, to preliminarily understand the basic reflection of teachers and students on the implementation of aerobics course, and ask them to put forward relevant suggestions at the same time, and determine the starting point of teaching, individual differences, students’ learning style, learning task content and so on through network survey data. Combined with these index parameters to understand the students’ learning task type, subject content structure, and ultimately targeted to develop teaching objectives, select matching teaching strategies, and prepare for the final teaching implementation results evaluation, the above is a set of scientific and reasonable teaching design process.

3.2 Determination of teaching objectives

After analyzing the survey design and collecting relevant data in the early stage, we can make clear the teaching objectives, that is, the selection and clarification of the subsequent teaching content development process. In the process of investigation and analysis, teachers have carried out a lot of research on teaching objectives, and formed a relatively mature theoretical system. For example, to understand the students’ willingness to carry out the aerobics course and the course content they want to learn, they have a preliminary understanding of aerobics and gradually accept it, which also enriches the diversity and multi-level connotation of teaching objectives and caters to the construction characteristics of network course teaching platform.

The construction of network teaching platform of aerobics course should be based on cognitive field, action skill field and emotional field to determine the teaching objectives. First of all, the teaching objectives under the background of cognitive field include to let students initially understand and learn the basic knowledge content and related technical methods of aerobics, to be familiar with the language of aerobics, and to understand its related sports science theory. Secondly, in the field of movement skills, it is necessary to make clear the specific Aerobics movements and combined movements taught to students, hoping that they can master and perform a complete set of aerobics. Finally, in the emotional field, students are expected to learn to appreciate and identify aerobics performance, establish correct aesthetic values based on aerobics, form relatively noble artistic taste, develop students’ good personality consciousness, independent consciousness, cooperative learning consciousness and health consciousness, and make aerobics become their personal interests.

Moreover, the construction of network teaching platform of aerobics course also hopes to meet the cultivation of students’ abilities in many aspects, such as the ability of students to use aerobics knowledge, the ability of innovation and creation of aerobics, the ability of teachers to organize aerobics competition and management, the ability of aerobics evaluation and the ability of forming aerobics teaching documents, etc.

3.3 Teaching content resource design

The design of network teaching platform content resources of aerobics course should pay attention to the integrity and comprehensiveness of its resource database composition, build a resource-based learning mode, and constantly enrich the teaching content to maintain students’ interest in learning aerobics. In the actual teaching process, teachers will constantly put forward the subject knowledge problems to be studied and explored. Students can obtain knowledge content by means of network, library and other information channels, so as to provide conditions for the realization of independent inquiry learning process, cultivate their basic ideas of solving problems independently or in teams, and optimize the learning experience of aerobics course. In the design of teaching content resources, teachers should design the teaching content in combination with students’ aerobics technology related items or students’ technical proficiency items, build the aerobics resource library targeted, and cultivate students’ aerobics skills [3]. Therefore, teachers need to classify the teaching content resources, match different resources for different students, optimize the teaching structure of aerobics course, enrich the content and lay a good design foundation for the subsequent teaching strategy design.

3.4 Teaching strategy activity design

The teaching strategy activity design of aerobics course mainly focuses on the established teaching tasks and students’ characteristics, highlights the relevance between the pertinence of teaching strategy and the combination of teaching strategy content, gives play to the joint function of teaching organization form and method technology, and shows the key attributes of the core content design of network course. At present, diversified teaching modes are designed in many online teaching vouchers of aerobics courses, such as real-time online Q&A, real-time online remote MOOC lectures, group online discussion, new media network platform of homework arrangement combined with homework evaluation, and group collaborative teaching mode based on online and offline joint promotion. These teaching models can be designed around the aerobics course and play the effectiveness of teaching strategy activities. Taking the course of “creating the combination of movements in aerobics” as an example. Based on the network teaching platform, this paper puts forward five strategies, and around these five strategies to build the teaching process to promote this link.

Table 1
Teaching strategies of the network teaching platform

Strategies	Task definition
Task learning strategy	Arrange aerobics creation tasks for students, you can download and read on the network, students can discuss the task creation plan alone or jointly.
Resource learning strategy	Teachers encourages students to collect and edit action information through the network teaching platform, and the platform also provides resource sharing services.
Autonomous learning strategy	Teachers will upload the teaching video to the network teaching platform, encourage students to learn the new aerobics movements from the main combination according to the video, guide them to build their own curriculum resources, and carry out the creation process of aerobics combination movements in an all-round way.
Communication and interaction strategy	Teachers will set up special forums on the network teaching platform for teachers and students to discuss and exchange, and will arrange different learning tasks independently or cooperatively in the forum. Students can choose according to their own aerobics combination movements.
Intuitive feedback strategy	The combined movements of aerobics created by students will be uploaded to the platform in the form of video for teachers and students to repeatedly appreciate and evaluate [2]. In the process of communication and interaction, the arrangement will be changed to improve the learning content.

3.5 Learning evaluation design

The learning evaluation and assessment section of the network teaching platform of aerobics course is an objective test of learning achievements, which can promote the cultivation of students’ new learning objectives and the improvement of the teaching process. As far as the evaluation of diversified aerobics teaching network platform is concerned, it should be combined with teaching tasks and contents, set up 10 evaluation project indicators, and evaluate students’ Aerobics learning achievements in 7 grades. The evaluation items as shown in Table 2.

Table 2
Evaluation form of academic performance of aerobics

Grade Evaluate	Homework	Self-study situation	Self-study ability	Attitude	Attendance	Learning ability	Innovation ability	Action assessment	Written examination	Learning time
Grade1
Grade2
Grade3
Grade4
Grade5
Grade6
Grade7

Figure 1.

The entry process of the home page of aerobics teaching platform.

The evaluation platform system established according to the above evaluation projects is scientific and open, which can timely feedback the effective information of students’ learning, and realize the integration and automation level of evaluation, data collection, collation and analysis.

4. Interface design of aerobics teaching platform

The user interface of aerobics teaching platform is composed of user login interface and interface home page. It is designed with the help of PS, FLASH animation, AI, AE, PREMIERE and other software. Its content presents a variety of audio-visual multimedia elements, which are arranged in order, healthy and reasonable. The design of aerobics teaching platform has certain functionality and practicability. Through the presentation of the interface, users can use the teaching platform clearly and smoothly, which is conducive to students to quickly retrieve knowledge and improve learning efficiency [4]. The design of aerobics teaching platform is characterized by emotional expression. When users enter the interface, they can enjoy the artistic characteristics brought by Aerobics through visual impact. Aerobics teaching platform design focuses on the overall effect of the interface design, the interface font size and font color design is appropriate, the use of interface color is natural and soft, the overall style of the interface is consistent, and the overall design of the interface is simple and clear. The user enters the login interface and logs in by entering the account number and password. After successful login, the user enters the home page of aerobics teaching platform in Fig. 1.

Figure 2.

Diversified network teaching platform module of college aerobics.

There are two ways for teachers and students to enter the teaching platform through term search. One is to click the registration button to fill in the account name, password, identity, email number and other basic information for account registration. After successful registration, enter the account and password for login [5]. After login, the system will automatically identify the user’s identity and enter different interfaces according to the permissions of teachers and students; The other is not login directly into the teaching platform home page, teachers and students directly into the aerobics teaching platform home page can only browse learning, can not download, collection, enter the class, assessment and evaluation operation [6].

5. Module design of diversified network teaching platform for aerobics in colleges and universities

According to the educational objectives, the construction of diversified network teaching platform of college aerobics, as shown in the Fig. 2.

The platform is divided into three levels: expression layer, intermediate agent layer and data layer. The expression layer is the core of the platform, including the design of “information module”, “teaching module” and “extension module” [7].

The teaching module mainly focuses on the theoretical knowledge of aerobics, teaching videos and related teaching documents [8]. The theoretical knowledge of Aerobics mainly includes the overview of aerobics, aerobics interest and development and characteristics, aerobics teaching methods and other theoretical knowledge. Aerobics teaching video mainly includes competitive aerobics and public aerobics teaching video and level of action. Aerobics teaching documents mainly include aerobics teaching syllabus, aerobics teaching plan, aerobics teaching plan and aerobics teaching courseware.

The information module utilizes AI search technology where students can quickly retrieve what they want to learn, while language and image understanding techniques can directly display charts of competitive aerobics and mass aerobics, technical movements of aerobics and aerobics clothing and styling movements in the picture file module. Data include video area, chart area, music area. The video zone includes competitive aerobics competition video, popular aerobics competition video and different styles of aerobics video. The biggest feature of the music zone is to provide different types of aerobics music download services, and can be supplemented and updated. Through the music zone, we can not only download the music needed for teaching and competition, but also appreciate the music styles of different aerobics styles with different characteristics and changes. The picture file module can directly present the diagrams of competitive aerobics and popular aerobics, the diagrams of technical actions and aerobics clothing and modeling actions.

Expansion module, expansion module is a bright spot of diversified aerobics network teaching platform. The expansion plate fully considers the individual differences and interests of students, and designs different plates for different needs, different units, different levels and different depths. It includes Fitness Zone and innovation ability. The fitness zone provides scientific fitness knowledge and methods as well as domestic or international well-known aerobics course videos to provide theoretical and practical guidance for students’ extracurricular fitness exercise. The innovation ability zone displays the learning contents of aerobics, such as action arrangement, leading and leading exercises, formation change, music selection, action development and aerobics referee method, etc. in the form of videos, pictures and words. Teachers and students can continuously draw more inspiration from teaching, arrangement and practice, and complete the tasks of teaching, creation and self-study. Teachers can upload individual or student competition videos, teaching videos and creative works to this section to stimulate the learning enthusiasm between teachers and students. It not only cultivates students’ aerobics practice ability and self-learning ability, but also enables students to master the skills of Aerobics arrangement, design and leading, so as to truly realize students’ all-round development, adding weight for future employment [9].

In the Data layer, the storage format of teachers’ basic information table is shown in the table. The storage method of teachers’ basic information is shown in Table 3.

Table 3
Basic information of teachers

Field name	Data type	Length	Explain
Teacher ID	char	5	Unique identity teacher
Password	var	12
Gender	vaar	20	Default: female
Date of birth	char	12
User category	var	8	05 for teachers
Department	vhat	10

Ordinary teachers have basic management, personal information, teaching tasks and other functions. Through the basic management, they can realize the safe exit of the platform. Personal information refers to the modification of personal password, and teaching tasks refer to the teaching tasks assigned to individuals. They can supplement teaching information and distribute teaching materials. When the managers log in, they input the account number and password. If they match, they can enter the system. If they do not, they will be prompted. In addition, students can view the detailed introduction of the ideological and political course and have a simple and intuitive understanding of the course. Through the data maintenance subsystem, we can change the course information, teaching tasks and so on, and maintain these data at the same time. In order to facilitate the management of Ideological and political teaching task management platform, it is necessary to analyze these processes reasonably. Using fuzzy mathematics theory to establish database is the basis of the design of ideological teaching task management platform, which can increase the expansibility of database and facilitate teaching task management.

The agent layer in Fig. 2 reflects the design idea of student evaluation, and comprehensively evaluates the teaching effect from the three levels of student evaluation, teacher evaluation, teacher evaluation and mutual evaluation, which makes the results more objective, but also strengthens the interaction between teachers and students in learning. The core of this layer is in communication. Communication and interaction module is to build a three-dimensional, interactive and positive interactive timely and effective communication and interaction platform with the help of the Internet. There are online interaction modes such as the guide of famous teachers, online tutoring and online forums. There are also interactive modes such as public mailboxes, QQ communication groups, WeChat official account and so on. Realize the effective communication and interaction between teachers and students, students, share knowledge and resources, and form a good learning atmosphere.

6. Grouping of aerobics teaching objects in colleges and universities

Using the automatic grouping algorithm in AI machine learning technology, on the basis of the above teaching modules and database, the teaching objects were grouped. The basic process of grouping is shown in Fig. 3.

Figure 3.

Basic process of grouping.

The basic process of grouping is shown in Fig. 3. The specific grouping process is as follows. The automatic grouping algorithm is used to group the data. First, the data is cleaned [10, 11, 12, 13, 14, 15]. The calculation formula is as follows:

$\displaystyle D=\sum\limits_{e}^{o}i*\frac{m}{f+n}$ (1)

In Eq. (1), $D$ represents the data of students, $\sum_{e}^{o}i$ represents the data cleaning factor, among it, $i$ representative group coefficients, $o$ representative factor maximum, $e$ representative factor initial value, and $\frac{m}{f+n}$ represents the indicators of students, $m$ representative the number of groups classified, $f$ represents the number of classification indicators, $n$ represents the number of students. This calculation does not do directional analysis.

On the basis of the completion of data cleaning, the gap of each index of the students in the platform is analyzed [16, 17, 18]. Considering the basic differences, each group is designed in the way of mixing boys and girls, and the academic performance is divided into good, medium and poor to balance. Because the accuracy of ordinary grouping method is low, cosine similarity algorithm is used to judge the similarity between the comprehensive qualities of students in the platform [19, 20, 21, 22]. Let each index of the two students to be matched be $M_{1},M_{2},M_{3}\ldots M_{r}$ and $N_{1},N_{2},N_{3}\cdots N_{r}$ respectively, then cosine similarity is expressed as:

$\displaystyle\cos\theta=\left\{{\begin{array}[]{l}\frac{n*r}{\sqrt{N_{1},N_{2}% ,N_{3}\ldots+N_{r}}}\\ \frac{m*r}{M_{1},M_{2},M_{3}\ldots M_{r}}\\ \end{array}}\right.$ (2)

In the above calculation, the cosine value is between 0 and 1. If the $\cos\theta$ value is close to 1, it means that the comprehensive abilities of $M$ and $N$ students are close to each other. If the $\cos\theta$ value is close to 0, it means that the comprehensive abilities of the two students are quite different, so they are divided into the same group to achieve the purpose of learning from each other [23]. The similarity matrix is as follows:

$\displaystyle\left[{\begin{array}[]{l}\cos\theta_{1},\cos\theta_{2}\ldots\cos% \theta_{n}\\ \cos\theta_{1.1},\cos\theta_{1.2}\ldots\cos\theta_{1.n}\\ \ldots\\ \cos\theta_{m.1},\cos\theta_{m.2}\ldots\cos\theta_{m.n}\\ \end{array}}\right]$ (3)

Equation (3) is the similarity matrix between students. After calculating the similarity matrix, the rows or columns in the matrix are sorted to find out the maximum difference value in each row or column. Because it is arranged by row in the computer, this time it choose to group by row. Before grouping, it needs to select the students with strong ability as the group leader in each group, so we need to rank the students’ comprehensive ability. On the basis of the previous data, the students with higher comprehensive ability are selected, and the calculation formula is as follows:

$\displaystyle Q=\sqrt{X_{t}+X_{y}+\ldots X_{n}}$ (4)

In Eq. (4), $Q$ represents the students’ comprehensive ability value, and $X_{t}$ represents a vector in the students’ comprehensive ability value. For each student, the formula is used to calculate the comprehensive ability of students, and the $Q$ value is arranged from large to small, which is put into each group to complete the selection of group leader.

On this basis, the automatic grouping algorithm is used for automatic grouping, and the calculation formula is as follows:

$\displaystyle M=\log\left\{{\frac{v}{vc*b}}\right.$ (5)

In Eq. (5), $M$ represents the automatic grouping factor, $\log$ represents the basic data of students introduced, and $\frac{v}{vc*b}$ represents the similarity ranking of students, $v$ represents the overall similarity, $c$ represents the sorort of the student matrix, $b$ represents similarity of comprehensive abilities. Directional analysis is not performed in this calculation.

According to the above formula calculation, the students with the least similarity are added to the corresponding groups, and the automatic grouping function is realized through the algorithm, so as to complete the design of diversified teaching platform of college aerobics course based on artificial intelligence through the above process.

7. Experimental analysis

To ensure the effectiveness of the platform design, the experiments were performed. The student scoring interface of this design platform is shown in Fig. 4, with part of the information deleted to maintain privacy.

Figure 4.

Diversified teaching platform of university aerobics courses.

In order to ensure the effectiveness of the platform design, simulation experiments are carried out. At the same time, in order to ensure the preciseness of the experiment, this platform is compared with the traditional platform. Take a school aerobics course management effect comparison. More than 3000 teaching tasks in three semesters are put into the task management platform to manage them. In the statistical results, there is no statistical difference in the basic data of students in each group, which is comparable. The D38IJN88 software is used to make statistics and analysis on the grouping. The specific results are as follows.

7.1 Accuracy comparison of student grouping

The comparison results of grouping accuracy of the two methods are shown in Fig. 5.

Figure 5.

Experimental comparison results.

According to the analysis of Fig. 5, the accuracy of traditional platform grouping is low. Because the method is not perfect to understand the basic situation of students, can not understand the requirements of students with different class needs and different foundation, so the accuracy of grouping is low. The grouping accuracy of the design platform in this paper is above 75%, which is significantly higher than the traditional methods. Because the platform can fully understand the students’ comprehensive ability, can divide the groups according to the comprehensive ability, and provide different learning content for different groups of students.

7.2 Student achievement comparison

After the completion of the above grouping, the two groups of students went through a period of learning, and their scores were compared. The comparison results are as follows in Table 4.

Table 4
Comparison of learning ability between the two groups

Rating	Average score of experimental group	Number of qualified persons	Average score of control group	Number of qualified persons
A	92.7	21	90.1	2
B	85.2	30	80.6	11
C	70.6	25	60.4	26
D	50.2	2	40.1	18
Total	74.66	78	37.8	57

Table 4 shows that after the completion of the two groups, the average score of the experimental group is 74.66, and the number of qualified people is 78. It can be seen that the students’ learning effect is better after grouping through the platform, only two of them are not qualified, which indicates that the platform designed in this paper can fully understand the students’ learning situation and reasonably group the students. However, the average score of the students who are grouped by the traditional grouping method is only 37.8, and the number of unqualified students is large. Because of the low accuracy of the grouping method, the learning effect of the students is poor.

8. Conclusion

In order to improve the diversified teaching effect of college aerobics courses, a diversified teaching platform based on artificial intelligence is designed. According to the characteristics of aerobics teaching, the construction idea and design process of teaching platform are proposed; The interface and functional module of teaching platform are designed, and finally the grouping function of teaching objects is designed. Experimental results show that the paper design platform can effectively provide the accuracy of grouping and student achievement. The platform will be applied to aerobics classroom teaching to innovate the traditional aerobics teaching mode and improve the disadvantages of traditional aerobics teaching. It can be applied to extracurricular independent learning, which also plays a certain role in promoting the dissemination of aerobics theoretical knowledge, teaching skills, training methods and competition information.

However, due to the limited conditions, this paper only conducts a network platform design for aerobics teaching, but the compatibility of the teaching platform is not studied. The future research can develop a teaching platform suitable for a variety of courses.

Footnotes

Acknowledgments

This paper is supported by Online Course Construction project of Shandong University of Science and Technology (No. ZXK2020095).

References

Yang

Huang

. Research on design and construction of diversified network teaching platform for aerobics in colleges and universities. Journal of Lanzhou University of Arts and Science (Natural Science Edition). 2019; 33(3): 113-119.

Xiang

. Analysis of the effect of curriculum development and implementation based on network teaching platform. Vocational Education Research. 2020; (2): 58-62.

Kanth

Skön

Toppinen

Lehtomäk

Laakso

Heikkonen

. Innovative and efficient teaching methodology for digital communication systems using an e-learning platform. Journal of Communications. 2019; 14(8): 689-695.

Wagman

. Artificial intelligence and human cognition. Quarterly Review of Biology. 2019; 68(1): 232-239.

Licato

Zhang

. Correction to: Evaluating representational systems in artificial intelligence. Artificial Intelligence Review. 2019; 52(4): 2743-2743.

Bossuyt

Séverine

Bisschops

. Assessing disease activity in ulcerative colitis using artificial intelligence: Can “equally good” be seen as “better”. Gastroenterology. 2020; 159(4): 1-7.

Tivani

AEA

Murdocca

Paez

CFS

Gazzano

JDD

. Didactic prototype for teaching the MQTT protocol based on free hardware boards and Node-RED. IEEE Latin America Transactions. 2020; 18(2): 376-382.

Wei

Luo

Chen

. The reform of computer experiment teaching based on O2O model. Computer Applications in Engineering Education. 2019; 27(1): 102-111.

Chen

Lee

Tseng

Deng

Chang

Lee

. Cognitive learning performance assessment and analysis with CSCL applied on the NetGuru platform and CSPL applied on the TAoD platform for the network experiment class. Journal of Supercomputing. 2020; 76(1): 16-46.

10.

Clarke

. Individual and collective agencies in China’s curriculum reform: A case of physics teachers. Journal of Research in Science Teaching. 2019; 56(1): 45-63.

11.

Freeze

Kelly

Batista

. Search for catalysts by inverse design: Artificial intelligence, mountain climbers, and alchemists. Chemical Reviews. 2019; 119(11): 15-19.

12.

Chimeno-Trinchet

Murru

Díaz-García

Fernández-González

Badía-Laíño

. Artificial intelligence and fourier-transform infrared spectroscopy for evaluating water-mediated degradation of lubricant oils. Talanta. 2020; 219(15): 121312.

13.

Jueng

Dupuis

Kunadia

Dellavalle

Brooks

Sinha

Maner

Siddiqui

Burton

Seyffert

Solomon

. LB945 Using artificial intelligence to understand patient perspectives towards treatment of dermatological diseases. Journal of Investigative Dermatology. 2020; 140(7): B10.

14.

Blaivas

Abbasi

Philips

Merchant

Levy

Corl

. Development of an artificial intelligence deep learning algorithm that utilizes IVC collapse to predict fluid responsiveness. Annals of Emergency Medicine. 2020; 76(4): S114.

15.

Schuster

Lange

Backhaus

Strohmeyer

Matz

Kowallick

Lotz

Steinmetz

Kutty

Bigalke

Gutberlet

Hasenfuß

Thiele

Stiermaier

Eitel

. Artificial intelligence based fully automated myocardial function assessment for diagnostic and prognostic stratification following myocardial infarction. Journal of the American College of Cardiology. 2020; 75(11): 1565.

16.

Breen

Carter

Johnson

Routman

Kapa

. An artificial intelligence-enabled analysis of ECG changes after androgen deprivation therapy (ADT) for prostate cancer. Journal of Clinical Oncology. 2020; 38(15_suppl): e17535.

17.

Tanguay-Sela

Benrimoh

Perlman

Israel

Margolese

. Evaluating the usability and impact of an artificial intelligence-powered clinical decision support system for depression treatment. Biological Psychiatry. 2020; 87(9): S171.

18.

Knott

Seraphim

Augusto

Xue

Moon

. The Prognostic Significance of Quantitative Myocardial Perfusion: An artificial intelligence based approach using perfusion mapping. Circulation. 2020; 141(16): 5-19.

19.

Guerriero

Pascual

Rodríguez

Ajossa

Neri

Musa

Graupera

Alcazar

. VP62.16: Artificial intelligence in the detection of rectosigmoid deep endometriosis. Ultrasound in Obstetrics and Gynecology. 2020; 56(S1): 340-341.

20.

Raju

Jumah

Ashraf

Narayan

Nanda

. Big data, machine learning, and artificial intelligence: A field guide for neurosurgeons. Journal of Neurosurgery. 2020; (1): 1-11.

21.

Memeti

Imeri

Selimi

. Empirical analysis of CASE tool impact on the development process in North Macedonian IT companies. Journal of Computational Methods in Sciences and Engineering. 2020; 20(2): 91-596.

22.

Yang

Meng

Pan

Burget

. Finding the optimal number of low dimension with locally linear embedding algorithm. Journal of Computational Methods in Sciences and Engineering. 2020; 20(4): 1163-1173.

23.

Swann

Silvermann

Lindemann

Boland

Gibson

Lick

Knoll

Pakhomov

Melton

Tignanelli

. Artificial intelligence facilitates performance review and characterization of prehospital emergency medical services treatment. Journal of the American College of Surgeons. 2020; 231(4): S305-S306.