Researchers explored the cognitive process of students by analyzing their eye-tracking data in some specified computer programming tasks. Although there are some quantified analysis and data visualization methods proposed in this area, none of them is designed to visualize the attention migration in debugging task. In this paper, we designed a novel kind of chart, i.e. Attention Cloud Map (ACM), for this purpose. We model the semantic code space into a polar coordinate system, and map the code lines and functions of the test program are mapped into points and sectors. We put the bug line in the center point, and mark the relevant code areas in the code space. By plotting the heat map of the amount of eye fixation attention in given time slices, we can obtain a serial of attention distributions in the code space. Experiment results show that, such attention cloud map can enable us to observe the debugging strategy of individual student, and abstract the average progress of one student group, which can be provide some references for the evaluation of students’ debugging performances.
Based on the index of faculty teaching development from 2000 to 2020, this paper analyzes the current situation of faculty teaching development in newly-established undergraduate universities from the aspects of region, province, school level and the composition of index. The research findings are as follows: the overall development of newly-established undergraduate universities is low, but there are many colleges with better development; Universities in east and northeast regions are better than those in middle and west regions, the development of each province is not sufficient and unbalanced; Universities with specialties in normal education, science, engineering and comprehensives perform better than others; there is a big gap between private and public universities; the teaching competition and teaching reform project are better than others among the dimensions of the index.
With the rapid development of Internet plus and big data, college students are facing many threats and risks of network security. Strengthening the education of network security for college students has become an important problem that needs to be solved urgently in higher education. By analyzing the causes of the problems existing in the current network security education, this paper puts forward some measures, such as building a solid network security barrier, building a perfect network security knowledge system and diversified forms of education, to strengthen the network security awareness and prevention skills of college students.
2020 is destined to be a difficult year. The rapid spread of COVID-19 has brought great impact on public life, public health and even the whole industry. But at the same time, online has been rising. As the most active marketing method in the Internet era, Brand Co branding still plays a role during the epidemic. At present, China has achieved phased victory in the epidemic prevention campaign, and we have also ushered in the post epidemic era of small-scale outbreak of the epidemic. As a major victim city of the epidemic, many brands in the post epidemic era are also continuing to explore new methods of Brand Co branding. In this case, in order to find a new method of liangpin Store Brand Co branding suitable for Wuhan in the new era, the author will use the form of big data and questionnaire to analyze the factors affecting the development of liangpin store Regional Brand Co branding in the post epidemic era through data: first, analyze the factors affecting regional brands from three aspects of packaging, category and policy and put forward suggestions; Second, analyze the factors affecting regional brands from three aspects: purchase convenience, word-of-mouth and selectivity, and put forward suggestions; Third, analyze the factors affecting regional brands from three aspects: purchase price, brand and publicity methods, and put forward suggestions to find the form of Brand Co branding suitable for the post epidemic era.
Walking is an aerobic exercise that can help prevent lifestyle-related diseases. Indoor training using a treadmill or ergometer can be used as a substitute for outdoor walking. However, during such indoor training, sensory conflicts between the vestibular and visual systems may occur, potentially inducing motion sickness. Notably, virtual reality (VR) can be used to create a realistic sensation of outdoor walking. Therefore, the purpose of this study was to develop a VR system for reducing sensory conflicts and evaluating patients' biological conditions. As a result, we gained a deeper understanding of the types of VR images able to reduce sensory conflicts.
The computer fundamentals course is an important course in computer education in higher education. It serves the role of cultivating students’ computational thinking and being able to use information technology to solve complex computational problems in various majors. However, the original objectives and teaching content of the course did not meet the needs of the new AI era, did not integrate with the disciplines, and the teaching method did not reflect the shortcomings of student-centered. This paper constructs a computational thinking hierarchical competency improvement model of, and adopts the OBE method to reverse the teaching content, teaching methods and evaluation methods. The teaching reform achieved good results in practical teaching and learning. Finally, this paper discusses the inefficient of teaching reform and the direction of improvement in the future.
In order to fully recognize the research status and development trend of the recommendation system, by using the software CiteSpace, taking reference to the literature in the recommendation system from 2012 to 2021 collected by the database Web of Science, this paper is to analyze the overall distribution characteristics on the years, journals, countries/regions, institutions/authors, important documents, research hotspots/research frontiers via the literature statistics and the visualization. As the result, there is going to be a knowledge map to be drawn to provide references for the researchers of the recommendation system.
In recent years, the relationship between doctors and patients in hospitals has been relatively tense. Doctors often comfort patients in hospital on the one hand, and manually record various information on the other hand. In order to facilitate the recording of nursing information and facilitate doctors' ward rounds, the hospital needs to establish a clinical intelligent interactive system. The system can use voice to input information in the case of inconvenient manual operation. For the speech recognition module in the system, the acoustic model for speech recognition based on Hidden Markov Model is used, and by combining the specific conditions of the hospital to collect the speech of all doctors, the interaction efficiency between doctors and patients is greatly improved.
Aiming at the problems of the integration of computer course teaching with international teaching and engineering certification, this study designs a multi-dimensional teaching mode of computer courses through the support of Artificial Intelligence. It analyzes the teaching resources, learning services, teaching process and teaching means involved in computer course teaching. Taking the course of "Computer Introduction" as an example, this study explores the multi-dimensional bilingual teaching mode supported by Artificial Intelligence, trains computer talents who meet the ability requirements of the era of Artificial Intelligence, and provides ideas for the teaching innovation of other courses.
At present, online teaching has become more and more popular especially in the context of the current epidemic, and quality governance has become the internal needs of modern education development, while there is no simple and easy to use learning situation risk cognition method for specific online teaching class. In order to deal with this problem, in this study a data-driven method of learning situation risk cognition and measurement for online teaching is provided, which uses student initiative degree, concentration degree, duration degree and interaction degree to measure comprehensive learning effective degree and reflect student learning situation risk in an online class. Besides, normalized score earned by student in knowledge point test after online class is used to validate the calculation method designed, and the obtained results show that it is promising and easy to calculation. It provides a basis for decision making of students' learning situation risk early warning and also provides a data-driven management method for the guarantee of online teaching quality, which has both academic and practical significance.
Under the general direction of information technology in education, traditional teaching methods are gradually integrating with intelligent technology. The notebook used for recording past mistakes on exams or exercises will be referred to as the "mistake notebook", which has been proved to be an effective learning tool in practice, but due to its difficulty in recording, retrieval and low efficiency, it also needs to be transformed into intelligent and electronic. The research group has proposed and designed a smart mistake notebook based on AI and big data. By automatically collating and analysing students' mistakes, it will help students to use the mistake notebook more efficiently and review more effectively and accurately to improve their academic performance.
The school establishes a leading group through investigation and research, The division of labor is in place for work arrangement, the hardware is combined with the school network to build facilities for follow-up, the teachers establish and constantly update the information concept, and initially establish the school digital teaching resource library platform. In addition, the formulation, supervision and implementation of the resource library program, as well as training, have promoted the initial application of the school's digital teaching resource library.
In view of the serious issues commonly existing with coursework in Chinese universities at present, such as its original function weakening or being suppressed, its form being too abstract and lack of elaborate design. In order to resolve these problems observed in usual homework, this paper proposes a reform scheme for cloud coursework based on Extended Reality and Bloom model. It mainly includes five key parts, such as interaction, scene, comprehensive evaluation, digital twin and data analysis. In addition, the reform's effectiveness is illustrated through amassing and comparing the feedback of college students for teaching.
This study attempts to find a way to solve the problem of unsatisfactory interaction effectiveness in online synchronous elementary and advanced oral Chinese teaching, and to provide teachers with effective and intuitive teaching discourse guidance. The number of words output by students is the measure index. Firstly, this study analyzes the differences in the interaction effectiveness between different categories and forms of teacher discourse in the offline elementary and advanced oral Chinese demonstration courses based on the ELAN video annotation tool and Python, and proposes "Six Principles" for the usage of teacher discourse. Then, based on the DingTalk teaching platform, the "Six Principles" was applied to the online synchronous elementary and advanced oral Chinese courses. The interaction effectiveness before and after the application were compared experimentally to verify the effectiveness of the "six principles" suggestion. It was found that after teachers consciously adjusted discourse categories according to the "Six Principles", the teaching interaction effectiveness was improved. The research ideas in this study have reference value for improving the interaction effectiveness of other online synchronous language teaching.
Food recommendation is a crucial task in the field of food computing, which aims to match a user's preferences with appropriate food options by uncovering their latent preferences. However, traditional content-based and collaborative filtering methods may not effectively capture these preferences, as they overlook the rich information contained in food data. To address this issue, this paper explores the use of a Knowledge Graph-based approach to food recommendation. Specifically, we construct a food knowledge graph that contains abundant relational information and data on food products. We propose a novel recommendation model called the Knowledge-Aware Attention Graph Convolutional Network, which aggregates neighbor information using knowledge-aware attention and captures higher-order neighbor information by stacking multiple layers. We also employ different aggregation methods for user entities and internal entities of the knowledge graph. We conducted experiments on a large food recommendation dataset, and our results show that our proposed model significantly outperforms the benchmark approach.
Discouraged by COVID-19 pandemic restrictions, many international students resort to studying online in their home countries despite their enrollment in universities outside of their own countries. In order to ensure academic achievement and prevent dropping out, it is necessary to investigate the influences on online learning engagement of international students who are still staying in their home country. With an explanatory sequential mixed method, this study first delivered a questionnaire to the class of international students who were learning Chinese as a foreign language (CFL) online away from China, by which the researchers collect preliminary data about their learning engagement as online learners, and identified participants who would consent to attend further qualitative research. In the second phase of the study, qualitative data from learning profiles and further interviews were collected, explaining the general data that emerged in the previous quantitative research phase. It is found that online CFL learners may suffer from many negative factors, including internet problems, lack of online learning strategies, cultural differences, low Chinese proficiency, and pessimistic personality. Meanwhile, some other factors, including strong motivation to learn and language identity as CFL learners, as well as multilingual aptitude may stimulate them to overcome these difficulties and engage in Chinese learning positively. In addition, three components of engagements display an interdependent relationship with non-linear interaction. This complex relationship may result in at least three categories of emotional and cognitive engagements: nervous CFL learners, anticipating CFL learners, and confident CFL learners. Some implications are concluded for the improvement of learning engagement in online Chinese courses for international students away from China.
Nowadays, more and more data are produced in our life. The rapid development of big data and intelligent computing industry has put forward new demands for talents, while colleges and universities with limited industry experiences are striving to promote the talent cultivation. Therefore, the "Innovative Community of Industry-Education Convergence", named THOUGHT (innovaTive Hub for the cO-development of indUstry and hiGHer educaTion) [1], was founded in 2019. THOUGHT aims to improve education cooperation between teaching staff and industry professionals in the related field. The industry-university converged courses are different from technical trainings in enterprises or the speeches of the leaders. In order to cultivate talents, both sides of industry and education cooperate closely in nearly every aspects in course building, e.g., targets, contents, methods, and assessments. And it is necessary to make the courses systematic for learners in terms of knowledge transmission, ability training and value shaping, so as to make them more competent for challenging work in the future of big data and AI. The industry-university converged courses focus on breaking the barrier of the traditional campus. Compared with the emphasis on theories and ideal experiments of traditional campus, it focuses more on practices and applications. Therefore, it needs to rely on a bridge which is convenient for both sides to participate in. Compared with traditional tools of business platforms, open source platforms are better choices. And open source makes it easier for more learners to stand on the giants’ shoulders. This paper shares the experience of a case of THOUGHT: the industry-university converged course "Foundamentals and Application of Distributed Data System" jointly built by Tsinghua University and Greenplum open source community. The target, team, organization, structure and contents, practice project, and future work of this course are all introduced in this paper, which may be a vivid case for professors and professionals in this field.
The goal of engineering doctorate (EngD) training is a unique educational programme in that improves information literacy of a doctoral study with the needs and innovations of the respective industrial sector. Based on the six core concepts of The Framework of Information Literacy in Higher Education, this paper extracted the specific requirements for the literacy of engineering doctoral students, and proposed to improve their information literacy ability from the comprehensive ability (innovation, leadership, execution). In view of the interdisciplinary integration and innovation of EngD students, this paper proposes an information literacy promotion framework based on team role model, which links the knowledge innovation process, information literacy ability and role positioning, and integrates conventional information literacy cultivation methods and promotion methods into the education process of EngD students. This team role model is illustrated through the use of a case study based on the work of AI electron Microscopy.
Broad Learning System (BLS) is a new model to expand the neural network from a horizontal perspective in recent years. Based on its outstanding performance in various aspects, this paper intends to apply it to the analysis and prediction of the stock market. Stock market data is a kind of time series data with strong correlation in time. After analyzing and summarizing the advantages and disadvantages of various existing time series prediction and analysis methods, this paper selects the LSTM (long - short term memory network) model, which is outstanding in time series prediction, to compare with the BLS model, and to examine the ability of these two methods in stock market data analysis and prediction. The experimental results show that the cyclic BLS system also has good performance in the prediction of time series data, especially in reducing the training time. The main reason is that the weight of each layer of LSTM is updated by gradient layer by layer, while the weight from hidden layer to output layer in BLS model is solved by pseudo-inverse calculation, which avoids the gradient update method and ensures the efficiency of network training. In addition, the BLS-based loop structure is adopted in this paper. The nodes in the feature layer or enhancement unit are connected circularly. The nodes can capture the dynamic characteristics of the time series, and well acquire and calculate the time-related information in the time series.
Under the background of "The New Engineering", the original computer educational concept has been unable to meet the needs of the great development of social informatization. This study tries to utilize the student-centered approach, puts forward a "Two Learning and Two Education" talents cultivation mode including Case-Based Learning, Project-Based Learning, Competition Inspire Education and Industry Cooperative Education, states its frame structure and connotation. After several years of teaching practice, the innovation and entrepreneurship education in our college has achieved a good result and produced a good social effect.
