Evaluation of the impact of artificial intelligence on the learning of college students in the Electrician Cup B question
Artificial intelligence, referred to as AI, was first proposed by scientists such as McCarthy and Minsky in 1956 when they held a meeting at Dartmouth College in the United States.
In 2016, artificial intelligence AlphaGo defeated South Korean Go master Lee Sedol 4:1. Later, Boston Dynamics' humanoid robot Atlas also demonstrated superb perception and control capabilities. In 2022, the artificial intelligence painting "Space Opera House" won the first prize in the art competition of the Colorado State Fair. On March 16, 2023, Baidu launched a new artificial intelligence product "Wen Xin Yi Yan".
In order to seize the major strategic opportunities for the development of artificial intelligence, the State Council issued the "New Generation Artificial Intelligence Development Plan" in 2017, pointing out that a technologically powerful country should give full play to the power of artificial intelligence technology, deploy and build a first-mover advantage in the development of artificial intelligence in my country, and accelerate the construction of innovative National and world technological powerhouse. The Ministry of Education released the "Education Informatization 2.0 Action Plan" in 2018, proposing an action guideline for realizing "Intelligence Leading Education Informatization", emphasizing the development of intelligent education.
Background analysis: This background introduces the development history and some important events of artificial intelligence (AI), as well as the strategic planning and policy guidance proposed by relevant departments on the development prospect and application direction of artificial intelligence in my country. no use
The development of artificial intelligence has varying degrees of impact on all levels of society, and also affects the learning of college students. In order to understand the impact of artificial intelligence on college students' learning in different aspects, we designed a questionnaire, see Appendix 1 for details, and Appendix 2 for the survey feedback results.
Background analysis: This topic mainly allows us to analyze the impact of artificial intelligence on college students' learning in different aspects, and the required data sets are attachments 1 and 2. These two attachments will be analyzed later.
According to a certain aspect you are interested in, combined with the data given in Annex 1 and Annex 2, please establish a corresponding mathematical model, analyze the impact of artificial intelligence on college students' learning, and solve the following problems:
1. Analyze and numerically process the data given in Annex 2, and give the processing method;
Analysis of Question 1: The first question requires the analysis and numerical processing of the data given in Annex 2,
Observing Annex 2, it is found that there are a large amount of non-numeric data, so quantitative analysis of these data is required, that is, the numerical processing mentioned in the title. Here's how to handle it:
1 Label encoding
Label encoding is a method of quantizing non-numeric data by converting a set of possible values into integers. For example, in the field of machine learning, for a variable with multiple categories, we can assign a unique integer value to each category, so that it can be converted into numeric data.
2 one hot encoding one hot
One-hot encoding is a method of converting multiple possible values into a binary array. In one-hot encoding, each possible value corresponds to a binary array whose length is the total number of possible values, in which only one element is 1, and the rest are 0. For example, for a gender variable, one-hot encoding can be used to convert "male" and "female" to [1, 0] and [0, 1] respectively.
3 category count
Categorical counts are an easy way to convert non-numeric data into numeric data. In categorical counting, we classify data according to some specific attributes (such as education, occupation, etc.), and then count the number or frequency of each category. For example, in a survey questionnaire, we can classify the responses to a question into the categories "yes", "no", and "not sure" and count the number or frequency of each category.
4 Principal component analysis
Principal component analysis is a method of converting multidimensional data into a low-dimensional representation. In principal component analysis, we perform dimensionality reduction on raw data by finding the principal components that best explain the variation in the data. This converts non-numeric data to numeric data.
Then there is data analysis, that is, EDA (Exploratory Data Analysis), which can use box plots to eliminate a field of data and then visualize it. The two parts are introduced below:
Box plots are a common data visualization tool that can show the distribution of data and outliers. In a box plot, the boxes show the interquartile range of the data, and outliers are shown as scatter points above and below the boxes.
The steps to eliminate abnormal data according to the box plot are as follows: (Because there are many non-numeric data conversions, you can also use the prediction algorithm here to predict the indicators you want to judge and see the difference from the real value)
l Draw a box plot, and observe whether there are obviously deviated data points in the scatter points above and below the box. In most cases, outliers are defined as data points falling outside the upper and lower 1.5 interquartile ranges of the box.
l Determine the location and number of outliers, then remove them from the dataset or correct them. Methods for handling outliers include replacing with the mean or median, linear interpolation, using a model for prediction, and more.
l Redraw the box plots on the processed data to ensure that outliers have been properly handled.
Common EDA visualization methods:
l Histogram and Density Plot: Displays the distribution of numerical variables.
l Scatterplot: Shows the relationship between two continuous variables.
l Boxplot: Shows the distribution and outliers of numerical variables.
l Bar and pie charts: Show the distribution of categorical variables.
l Line chart: shows the trend over time or sequence.
l Heat map: Shows the correlation between different variables.
l Scatter matrix plot: Displays a scatter plot matrix between multiple variables.
l Geographic map: displays geographic location data and spatial distribution information.
2. Select evaluation indicators based on your data analysis results, discuss their rationality in terms of priority, scientificity, and operability, and build an evaluation index system;
Analysis of problem 2: The proposed evaluation algorithms include gray comprehensive evaluation method and fuzzy comprehensive evaluation method to establish links between various indicators. The process of selecting evaluation indicators is to perform correlation analysis or dimensionality reduction on the indicators. The common methods of correlation analysis are:
l Pearson correlation coefficient: It is used to measure the linear relationship between two variables, and its value range is between -1 and 1. The closer the value is to 1 or -1, the stronger the correlation is.
l Spearman rank correlation coefficient: used to measure the monotonic relationship between two variables (non-linear but with the same trend), which is calculated based on rank or order data, the data can be converted into ranks, and then the correlation coefficient between ranks can be calculated .
l Kendall rank correlation coefficient: Used to measure the monotonic relationship between two variables, similar to Spearman rank correlation coefficient, but calculates the logarithm of coordination based on all possible pairings in each variable.
l Discriminant analysis: based on a statistical model, by measuring the degree of association between input variables and output variables to predict the classification or label of new observations. It is often used for supervised learning tasks such as classification and prediction.
l Factor Analysis: An unsupervised dimensionality reduction technique that can be used to discover underlying structures and factors among multiple variables. It explains the variability in the data by finding common variances and factors, and transforms the original variables into fewer factors for simplification and interpretation.
Data dimensionality reduction methods include Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Local Linear Embedding (LLE), t-SNE, etc. These methods can compress high-dimensional data to lower dimensions and preserve the information of the original data as much as possible. Among them, PCA and LDA are one of the most commonly used dimensionality reduction methods. PCA achieves dimensionality reduction by performing eigenvalue decomposition on the covariance matrix; while LDA is a supervised dimensionality reduction method that projects data into a new low-dimensional space so that the distance between different categories is as large as possible , the distance within the same category is as small as possible. LLE and t-SNE are more suitable for nonlinear problems.
3. Establish mathematical models, evaluate the impact of artificial intelligence on college students' learning, and give clear and convincing conclusions;
See the end of the article for questions 3-4 and subsequent codes, papers, etc.
4. Based on the data of the questionnaire, combined with your understanding, cognition and judgment of artificial intelligence, and the prospect of future artificial intelligence development, write an analysis report on the impact of artificial intelligence on college students' learning, which can include but not limited to positive or negative influence.
Appendix 1. Questionnaire
Annex 2. Survey Data
The topic selection suggestions are as follows:
For ideas, related codes, explanation videos, references and other related content, please click on the group business card below!