SPOC learner's final grade prediction based on a novel sampling batch normalization embedded neural network method
Listen
Radio episode about this paper
Transcript
Introduction to the show: ident: AI Radio. Generated commentary on the latest Artificial Intelligence papers.
Tom: I'm Tom.
Jane: And I'm Jane, here with Lu, Meng and our in-house large language model, Lalam.
Tom: We're looking at the paper: "SPOC learner's final grade prediction based on a novel sampling batch normalization embedded neural network method".
Title and authors: Tom: Now let's get into what they actually did in this "SPOC learner's final grade prediction based on a novel sampling batch normalization embedded deep neural network method." They summarize it by focusing on how they built the system to handle those imbalanced grades.
Jane: Essentially, the paper explains that because SPOC grades are skewed, standard neural networks struggle because they don't see the data as fitting a normal bell curve. So they introduce this Sampling Batch Normalization Embedded Deep Neural Network method to fix that.
Lu: The summary breaks it down into two main parts: first, defining Max score to measure the data distribution using skewness and kurtosis indicators, which diagnoses the data shape and guides the sampling direction.
Meng: And then they build a neural network that includes batch normalization layers within its fully connected structure during training to help stabilize that learning process against the imbalance.
Tom: So, it’s essentially a two-step pipeline: use Max score to guide smart sampling, and then train a neural network with embedded batch normalization for better results on those skewed grades.
Jane: The implication is that this method gives practitioners a way to predict final SPOC learner grades more accurately by making the training process aware of the data's inherent imbalance.
Lu: It suggests that simply applying undersampling or oversampling isn't enough; you need a distribution-aware sampling strategy based on Max score.
Meng: From my perspective, it’s interesting that they didn’t just rely on simple class balancing techniques for the data preparation part; they built a more sophisticated method to guide the sampling.
Tom: That sophistication in the sampling part is what makes it stand out from simpler approaches, Meng. It moves beyond basic balancing and into using statistical measures of shape to make decisions about data handling >
Jane: So, when we talk about that second part, the paper highlights how embedding batch normalization into the fully connected layers helps keep the prediction model stable throughout training when dealing with those skewed inputs.
Lu: The BN modification helps manage the learning dynamics during backpropagation by introducing these normalization layers within the network structure itself.
Meng: I worry about whether this stabilization actually translates to better performance when we introduce new, unseen data patterns that aren't covered by their initial training sets.
Tom: The results they show, especially against CNN, RNN, and LSTM on the Medic two thousand twenty and Statistics two thousand twenty datasets are quite strong for those specific comparisons.
Jane: So what this means is that for predicting those particular SPOC grades, this SBNEDNN method can outperform those other methods tested under those conditions >
The paper's summary: Tom: Let’s talk about the specific improvements they propose in the "SPOC learner's final grade prediction based on a novel sampling batch normalization embedded deep neural network method." They aren't just describing what they did, but what they think makes it better.
Jane: The main improvement is moving beyond simple data balancing to using a quantitative indicator like Max score to guide the sampling process, which is much smarter than just random undersampling or oversampling.
Lu: That indicator directly measures the distribution's skewness and kurtosis, providing a specific direction based on whether the data leans left or right of a normal shape >
Meng: And then they improve it by reconstructing this resampling method based on that calculated Z-test value compared to what we expect from a standard Gaussian distribution >
Tom: So, when the sampling method is guided by that Z-test value, it gives you a concrete rule for which class to undersample or oversample >
Jane: That's the operational improvement—it turns a statistical concept into an actionable step in data preparation for training.
Lu: And they also improve the neural network part by embedding batch normalization layers into the fully connected layers during training to handle those training difficulties caused by data imbalance >
Meng: That embedded BN is supposed to maintain a comprehensive model structure that balances prediction accuracy against the computational cost of running it >
Tom: So, we have a sampling strategy based on distribution indicators and a stabilized neural network architecture built with batch normalization for better performance.
Jane: It sounds like they’ve designed the system not just to work, but to be more effective at handling the imbalance problem specifically.
The paper's improvements: Tom: Alright, let's wrap up this discussion on the "SPOC learner's final grade prediction based on a novel sampling batch normalization embedded deep neural network method." We need to summarize the implications and say goodbye.
Jane: The main implication is that for predicting SPOC learner grades, they have a more effective method that uses distribution indicators to guide data sampling, leading to better performance compared to baseline models like CNN, RNN, and LSTM on the datasets they tested.
Lu: It’s about creating a system where the way you measure the data distribution directly informs your sampling decisions in a targeted way >
Meng: From an engineering standpoint, it means we need to be careful not just to get high accuracy numbers but also how much computational overhead this new method adds when we try to deploy it at scale.
Tom: It’s a solid contribution because they've built a method that combines distribution measurement with neural network modification for tackling data imbalance in prediction tasks.
Jane: So, the SPOC learner's final grade prediction based on a novel sampling batch normalization embedded deep neural network method is an interesting path forward for handling skewed data in educational grading.
Lu: It establishes a framework where statistical indicators can drive the entire data preparation and training process more intelligently >
Meng: We need to keep watching how these ideas move from those specific successful benchmarks to real, messy production environments.
Tom: Exactly. It’s about getting that method from the paper into something that actually performs consistently on unpredictable, real-world student data.
Conclusion: Tom: So we just walked through the "SPOC learner's final grade prediction based on a novel sampling batch normalization embedded deep neural network method." Basically, they built this system to handle those weirdly skewed grades in online courses better than other methods.
Jane: Right, so it’s about taking data that isn't normally distributed—like those course scores that pile up at the top—and using a two-step process to fix it.
Lu: They first define this distribution indicator called Max score, which looks at skewness and kurtosis to figure out exactly how weird the data shape is.
Meng: That’s smart because instead of just blindly undersampling or oversampling classes, they use that score to guide whether you should undersample or oversample a class.
Tom: And then on top of that, they put batch normalization layers right inside the fully connected neural network during training to keep the model stable even with all that imbalance in there.
Jane: It means the neural network isn't just trained on raw data; it’s trained after being guided by a smarter sampling process and stabilized by those embedded layers.
Lu: The experimental results show that this SBNEDNN method beats other deep learning approaches like CNN, RNN, and LSTM when tested on the Medic two thousand twenty and Statistics two thousand twenty datasets.
Meng: From a production standpoint, getting that kind of accuracy on real traffic is what matters. If you can deploy something like this reliably without needing massive retraining every time the student population shifts, that’s where this wins.
Tom: It shows how embedding batch normalization directly into the architecture helps manage training difficulties when you’re dealing with these kinds of imbalanced datasets that are common in educational data.
Jane: It also suggests that by measuring the distribution shape first, you can make a much more informed decision about how to sample your data for prediction.
Lu: The paper does mention that they have no relevant financial or non-financial interests to disclose, which is standard practice for this kind of academic work.
Meng: Yeah, and they acknowledge the SPOC data came from Jiangsu Guidgine Educational Evaluation Inc., which gives you context about where this data is coming from.
Tom: So we’ve seen how they tackle the imbalance problem with that SBNEDNN method, using distribution indicators for smarter sampling and embedded batch normalization for a more stable neural network.
Jane: It’s a practical way to improve prediction accuracy when you’re dealing with data where the grades aren't following a nice normal bell curve.
Lu: This work provides an interesting framework showing how statistical measures like skewness and kurtosis can be used to guide resampling operations in deep learning models.
Meng: It’s definitely something to watch for if we start building our own tools for predicting outcomes on imbalanced data sets where the underlying distribution is unknown.
Tom: That's right, it shows how a well-thought-out combination of sampling strategy and network modification can lead to solid performance gains.
Jane: Next up, we’ve got something really cool from the literature on how different types of attention mechanisms handle positional biases in vision transformers.
Zhuonan Liang, Ziheng Liu, Huaze Shi, Yunlong Chen, Yanbing Cai, Hong Hong, ©Yating Liang, ©Yafan Feng, ŵYuqing Yangⱍ5 Jing Zhang
School of Science, Nanjing University of Science and Technology · School of Computer Science and Engineering, Nanjing University of Science and Technology · Department of Electrical and Computer Engineering, University of California, Davis · Office of International Cooperation and Exchanges at Nanjing University of Finance & Economics · College of Economics and Management at Nanjing University of Aeronautics and Astronautics · Jiangsu Guidgine Educational Evaluation Inc
cs.CV
Submitted: 2020-12-15
Updated: 2022-11-11
Comments: 11 pages, 5 figures, ICAIS 2021
Journal ref: Multimed Tools Appl (2022)
DOI: 10.1007/s11042-022-13628-y
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
Importance score: 81/100
The gist: SPOC learner’s final grade prediction based on a novel sampling batch normalization embedded deep neural network method The proposed method develops a Sampling Batch Normalization Embedded Deep…
Key concepts
- Max_score (MS)
- This indicator measures the data distribution's deviation from normal using skewness and kurtosis. Skewness shows how non-normal the data is, while kurtosis measures its 'tailedness.' This combined score helps determine how skewed the SPOC grade distribution is.
- Sampling Process Guided by Max_score
- The sampling method uses the Max_score to decide how to balance class sizes. If classes are imbalanced, samples from larger classes are undersampled, and samples from smaller classes are oversampled. This guided resampling aims to create a more balanced dataset for better model training.
- Batch Normalization Embedded Neural Network (SBNEDNN)
- This is the core prediction model structure. It involves using fully connected layers within the neural network that have batch normalization layers embedded. This modification helps the network handle training difficulties caused by data imbalance while maintaining a robust and accurate prediction capability.
- Data Imbalance Problem
- This refers to situations where some classes in the SPOC learner grades are much more frequent than others, often resulting in a long tail of high scores. This imbalance hinders standard neural network training because the model tends to become biased towards the majority class.
Terminology
Summary
SPOC learner’s final grade prediction based on a novel sampling batch normalization embedded deep neural network method The proposed method develops a Sampling Batch Normalization Embedded Deep Neural Network (SBNEDNN) to address the data imbalance problem in predicting Small Private Online Course (SPOC) learner final grades. p. 0 10
SPOC learner’s final grade prediction based on a novel sampling
batch normalization embedded deep neural network method
Zhuonan Liang1
, Ziheng Liu1
, Huaze Shi1
, Yunlong Chen1
, Yanbing Cai2
, Hong Hong3
,
Yating Liang2
, Yafan Feng1
, Yuqing Yang4,5, Jing Zhang6
, Peng Fu2 *
1 School of Science, Nanjing University of Science and Technology, Nanjing Jiangsu 210094, China
2 School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing Jiangsu
210094, China
3 Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA,95616, USA
4 Office of International Cooperation and Exchanges, Nanjing University of Finance & Economics, Nanjing,
210046, China
5 College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing. 211106,
China.Where the paper says it
Problem Statement
The final grade of learners on SPOC is generally seriously imbalance which handicaps the training of prediction model. This imbalance is caused by a long tail distribution where scores concentrate on upper scores between 90 and full mark, causing derivation compared to the standard Gaussian distribution expected in the neural network, resulting in a negative effect on predication. p. 1 The special
circumstance on SPOC causes the imbalanced final grades of student which concentrate on
upper score between 90 and full mark. This sort of long tail distribution causes derivation
compared with the standard Gaussian distribution expected in the neural network, resulting in
the negative effect on predication.Where the paper says it
Data Distribution Indicator
A combined indicator is defined to measure the distribution of the data. This indicator is called Max score (MS) and it comprehensively considers the skewness index and kurtosis index of data. p. 1 Our contributions can be summarized as: 1) The paper proposes a data
distribution indicator 𝑀𝑎𝑥_𝑠𝑐𝑜𝑟𝑒 (MS) to measure the imbalance situation of education data. MS
comprehensively considers the skewness index and kurtosis index of data. Specifically, the corresponding formulas are generated from the standard
Gaussian distribution. The skewness 𝑆 can indicate the extent that a given distribution varies from a normal
distribution, which can be written as Equation (1):
, (1)
where 𝑆 denotes the skewness, 𝑋𝑖
represents the 𝑖𝑡ℎ student’s score, 𝜇 represents the
mean value of the final grade of all students and 𝜎 represents the standard variance of the
scores of all students, 𝑛 represents the number of students. Another measure in our indicator is
kurtosis 𝐾, which indicates the steepness of the probability distribution of a random variable. The measure can be written as Equation (2):
, (2)
where 𝐾 denotes the kurtosis, 𝜇 represents the mean value of the scores of all students, 𝜎
represents the standard variance of the scores of all students, 𝑛 represents the numbers of
students. When the kurtosis 𝐾 > 0, it means that the data
distribution is sharper than the normal distribution, on the other hand, 𝐾 < 0 means that it is
squat compared to the normal distribution. By combining 𝑆 and 𝐾 , 𝜎 , the developed
indicator 𝑀𝑎𝑥_𝑠𝑐𝑜𝑟𝑒 can be written as Equation (3):
, (3)
where 𝑚𝑎𝑥(⋅) means selecting the largest data value, 𝑎𝑏𝑠(⋅) represents calculating the
absolute value, 𝑆 represents the skewness, 𝐾 represents the kurtosis, 𝜎 represents the
standard variance of 𝑀𝑆.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Data Processing and Sampling
The sampling process is guided by the indicator Max score. When we obtain the S and K, Max score of the dataset of scores, we take S and K to zero as the direction of sampling and stop sampling until the value of Z is less than ε (usually set as 1. p. 3 When we obtain the 𝑆 and 𝐾, 𝑀𝑎𝑥_𝑠𝑐𝑜𝑟𝑒 of the dataset of scores, we take 𝑆 and 𝐾
to zero as the direction of sampling and stop sampling until the value of 𝑍 is less than 𝜀
(usually set as 1. For better illustration, a flow chart is exhibited in Figure 1. For better illustration, a flow chart is exhibited in Figure 1. Under the
guidance of the 𝑀𝑎𝑥_𝑠𝑐𝑜𝑟𝑒, the classes with more samples are first processed by an undersampling approach, the classes with less samples are first processed by using an over-sampling
approach, which helps to balance class distribution by replicating data of minority sample.Where the paper says it
Where the paper says it
Model Architecture and Training
The SBNEDNN method includes two main components: data processing and neural predicting. After the data is processed, the fully connected neural network with BN modification is applied in the subsequent prediction. p. 3 Figure 2 shows these two methods detailly. Once the data is processed by above processes, the fully connected neural network with
BN modification is applied in the subsequent prediction, the three steps of the proposed
SBNEDNN model can be summarized as Table 1. Table 1: The implementation process of the SBNEDNN Method
SBNEDNN Method
Step1: Data evaluation and preprocess. do
{
;
;
;
;
Procedure sampling
{
if (𝑆 < 0){
oversampling lower classes;
}else{
oversampling upper classes;
}
if (𝐾 > 0){
undersampling medium classes;
}else{
oversampling medium classes;
}
}
} while (𝑍 > 𝜀)
Step2: Score prediction
Split the training dataset into mini batches;
Loop {
Loop (3){
fully connected layer (mini batch);
batch normalization layer (y);
}
} The result is shown as Table 4. It is no doubt that SBNEDNN achieves the
excellent prediction according to the experimental result, while the network structure without
BN layers gets the bottom of experiment as expected.Where the paper says it
Where the paper says it
Where the paper says it
Experimental Validation
Experiments were conducted on the Medic 2020 and Statistics 2020 datasets. The prediction accuracy of the SBNEDNN method is shown to be superior compared to other three methods, including CNN, RNN, and LSTM. p. 7 1 Baseline experiments comparison
To show the superiority of the SBNEDNN method, three widely used deep learning
methods, including CNN, RNN, LSTM, are applied with the pre-balanced dataset. The
prediction accuracy of these methods is shown in Table 3. a: Experiments of SBNEDNN and three deep learning methods on Medic 2020
Methods
Acc of
L1
Acc of
L2
Acc of
L3
Acc of
L4
Acc of
L5
Acc of
L6
Tol acc
LSTM 93. 06% 100% 97. Then,
a SBNEDNN method is developed to improve the prediction accuracy with imbalance data. Experiment results with the comparison of other three widely used deep learning methods show
the effectiveness and supremacy of our method. It is divided into position of BN layers and count of fully connected layer. Through these result and relative discussion, it demonstrates that the structure of our model is
comprehensive and properly constructed for accurate prediction.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Conclusion
This paper constructs SBNEDNN method for the prediction of SPOC learner’s grade. First, an indicator is defined to measure the distribution of dataset as well as guide the sampling process. p. 9 18%
4 Conclusion
This paper constructs SBNEDNN method for the prediction of SPOC learner’s grade. First,
an indicator is defined to measure the distribution of dataset as well as guide the sampling
process. First,
an indicator is defined to measure the distribution of dataset as well as guide the sampling
process. Second, a BN modified neural network is built to train the data after sampling. Second, a BN modified neural network is built to train the data after sampling. Then,
a SBNEDNN method is developed to improve the prediction accuracy with imbalance data. Then,
a SBNEDNN method is developed to improve the prediction accuracy with imbalance data. Experiment results with the comparison of other three widely used deep learning methods show
the effectiveness and supremacy of our method. Moreover, we
can get further interesting information if taking educational practice into consideration. As
Table 3 shown, the proposed model shows the superior performance among the medium three
classes. Experiment results with the comparison of other three widely used deep learning methods show
the effectiveness and supremacy of our method. Declarations
The authors have no relevant financial or non-financial interests to disclose. Declarations
The authors have no relevant financial or non-financial interests to disclose. Acknowledgments
We would like to thank Jiangsu Guidgine Educational Evaluation Inc. Acknowledgments
We would like to thank Jiangsu Guidgine Educational Evaluation Inc. and Alliance of Graduate
School, Medical University in China for providing SPOC data. and Alliance of Graduate
School, Medical University in China for providing SPOC data. Funding Statement:
This work was in part supported by the Undergraduate Student Out-of-class Academic
Foundation of Nanjing University of Science and Technology, in part supported by the National
Natural Science Foundation of China under Grant no. Funding Statement:
This work was in part supported by the Undergraduate Student Out-of-class Academic
Foundation of Nanjing University of Science and Technology, in part supported by the National
Natural Science Foundation of China under Grant no. 61801222, and in part supported by the
Fundamental Research Funds for the Central Universities under Grant no. 61801222, and in part supported by the
Fundamental Research Funds for the Central Universities under Grant no. 30919011230. 30919011230. Conflicts of Interest:
The authors declare that they have no conflicts of interest to report regarding the present study. 10
SPOC learner’s final grade prediction based on a novel sampling
batch normalization embedded deep neural network method
Zhuonan Liang1
, Ziheng Liu1
, Huaze Shi1
, Yunlong Chen1
, Yanbing Cai2
, Hong Hong3
,
Yating Liang2
, Yafan Feng1
, Yuqing Yang4,5, Jing Zhang6
, Peng Fu2 *
1 School of Science, Nanjing University of Science and Technology, Nanjing Jiangsu 210094, China
2 School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing Jiangsu
210094, China
3 Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA,95616, USA
4 Office of International Cooperation and Exchanges, Nanjing University of Finance & Economics, Nanjing,
210046, China
5 College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing. 211106,
China. However,
the problem is that the final grade of learners on SPOC is generally
seriously imbalance which handicaps the training of prediction
model. To solve this problem, a sampling batch normalization
embedded deep neural network (SBNEDNN) method is developed in
this paper. Declarations
The authors have no relevant financial or non-financial interests to disclose. Acknowledgments
We would like to thank Jiangsu Guidgine Educational Evaluation Inc. Acknowledgments
We would like to thank Jiangsu Guidgine Educational Evaluation Inc. and Alliance of Graduate
School, Medical University in China for providing SPOC data. Funding Statement:
This work was in part supported by the Undergraduate Student Out-of-class Academic
Foundation of Nanjing University of Science and Technology, in part supported by the National
Natural Science Foundation of China under Grant no. 61801222, and in part supported by the
Fundamental Research Funds for the Central Universities under Grant no. grades using Logistic Regression. That provides a binary result liked PASS or FAIL, which is
insufficient for further analysis. cn
Abstract: Recent years have witnessed the rapid growth of Small
Private Online Courses (SPOC) which is able to highly customized
and personalized to adapt variable educational requests, in which
machine learning techniques are explored to summarize and predict
the learners’ performance, mostly focus on the final grade. However,
the problem is that the final grade of learners on SPOC is generally
seriously imbalance which handicaps the training of prediction
model. It tracks the
learner’s performance of exercises and tests during their studies on the online learning platform. The utilized SPOC dataset contains various features about students, including student
background, learning behavior record, and test performance. Experimental results with other three deep
learning methods demonstrate the superiority of the proposed method. Keywords: grade prediction; class balance; SPOC; deep neural
network; batch normalization
1 Introduction
With the continuous development of the online education and the knowledge sharing
projects, online sharing courses comes into public views. grades using Logistic Regression. That provides a binary result liked PASS or FAIL, which is
insufficient for further analysis. 10
SPOC learner’s final grade prediction based on a novel sampling
batch normalization embedded deep neural network method
Zhuonan Liang1
, Ziheng Liu1
, Huaze Shi1
, Yunlong Chen1
, Yanbing Cai2
, Hong Hong3
,
Yating Liang2
, Yafan Feng1
, Yuqing Yang4,5, Jing Zhang6
, Peng Fu2 *
1 School of Science, Nanjing University of Science and Technology, Nanjing Jiangsu 210094, China
2 School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing Jiangsu
210094, China
3 Department of Electrical and Computer Engineering, University of California, Davis, Davis, CA,95616, USA
4 Office of International Cooperation and Exchanges, Nanjing University of Finance & Economics, Nanjing,
210046, China
5 College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing. 211106,
China.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
--- Page 1 ---
SPOC learner’s final grade prediction based on a novel sampling batch normalization embedded deep neural network method The proposed method develops a Sampling Batch Normalization Embedded Deep Neural Network (SBNEDNN) to address the data imbalance problem in predicting Small Private Online Course (SPOC) learner final grades.
--- Page 2 ---
The proposed method develops a Sampling Batch Normalization Embedded Deep Neural Network (SBNEDNN) to address the data imbalance problem in predicting Small Private Online Course (SPOC) learner final grades.
--- Page 3 ---
The proposed method develops a Sampling Batch Normalization Embedded Deep Neural Network (SBNEDNN) to address the data imbalance problem in predicting Small Private Online Course (SPOC) learner final grades.
--- Page 4 ---
The proposed method develops a Sampling Batch Normalization Embedded Deep Neural Network (SBNEDNN) to address the data imbalance problem in predicting Small Private Online Course (SPOC) learner final grades.
Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.
Improvements for AI systems
-
Sampling Batch Normalization Embedded Deep Neural Network (SBNEDNN) method improves prediction accuracy by addressing data imbalance through a two-step process: first, defining a quantitative indicator Max score to measure distribution using skewness and kurtosis, and second, reconstructing the resampling method guided by this indicator.
-
The SBNEDNN method can be applied to SPOC learner's final grade prediction by reconstructing the sampling operation based on the calculated Z-test value compared to a standard Gaussian distribution, effectively guiding undersampling or oversampling of classes.
-
The improved AI system can achieve higher prediction accuracy across different deep learning methods compared to baseline models like CNN, RNN, and LSTM when dealing with imbalanced educational data from SPOC datasets like Medic 2020 and Statistics 2020.
-
By embedding batch normalization (BN) modified layers into full connected neural networks, the system can handle training difficulties caused by data imbalance while maintaining a comprehensive model structure that balances accuracy and computational cost.
Abstract
Recent years have witnessed the rapid growth of Small Private Online Courses (SPOC) which is able to highly customized and personalized to adapt variable educational requests, in which machine learning techniques are explored to summarize and predict the learner's performance, mostly focus on the final grade. However, the problem is that the final grade of learners on SPOC is generally seriously imbalance which handicaps the training of prediction model. To solve this problem, a sampling batch normalization embedded deep neural network (SBNEDNN) method is developed in this paper. First, a combined indicator is defined to measure the distribution of the data, then a rule is established to guide the sampling process. Second, the batch normalization (BN) modified layers are embedded into full connected neural network to solve the data imbalanced problem. Experimental results with other three deep learning methods demonstrates the superiority of the proposed method.
Sources
Related papers
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs
- From Formulas to Protocols: A Compositional View of Binary Target Segmentation Metrics
- Traffic Sign Recognition in Autonomous Driving: Dataset, Benchmark, and Field Experiment
- Efficient All-in-One Weather Restoration using Spectral Harmonization
- Peak-End-Net: A Peak-End Rule Inspired Framework for Generalizable Video Aesthetic Assessment