scholarly journals Performance Prediction for Higher Education Students Using Deep Learning

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Shuping Li ◽  
Taotang Liu
Keyword(s):  
Neural Network ◽  
Higher Education ◽  
Deep Learning ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Warning Signs ◽  
Education Students ◽  
Squared Error ◽  
Data Prediction ◽  
Training Mode

Predicting students’ performance is very important in matters related to higher education as well as with regard to deep learning and its relationship to educational data. Prediction of students’ performance provides support in selecting courses and designing appropriate future study plans for students. In addition to predicting the performance of students, it helps teachers and managers to monitor students in order to provide support to them and to integrate the training programs to obtain the best results. One of the benefits of student’s prediction is that it reduces the official warning signs as well as expelling students because of their inefficiency. Prediction provides support to the students themselves through their choice of courses and study plans appropriate to their abilities. The proposed method used deep neural network in prediction by extracting informative data as a feature with corresponding weights. Multiple updated hidden layers are used to design neural network automatically; number of nodes and hidden layers controlled by feed forwarding and backpropagation data are produced by previous cases. The training mode is used to train the system with labeled data from dataset and the testing mode is used for evaluating the system. Mean absolute error (MAE) and root mean squared error (RMSE) with accuracy used for evolution of the proposed method. The proposed system has proven its worth in terms of efficiency through the achieved results in MAE (0.593) and RMSE (0.785) to get the best prediction.

scholarly journals HiCNN2: Enhancing the Resolution of Hi-C Data Using an Ensemble of Convolutional Neural Networks

Genes ◽  
2019 ◽  
Vol 10 (11) ◽  
pp. 862
Author(s):  
Tong Liu ◽  
Zheng Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
High Resolution ◽  
Convolutional Neural Network ◽  
Mean Squared Error ◽  
Correlation Coefficients ◽  
Chromatin Interactions ◽  
Squared Error ◽  
Genome Wide

We present a deep-learning package named HiCNN2 to learn the mapping between low-resolution and high-resolution Hi-C (a technique for capturing genome-wide chromatin interactions) data, which can enhance the resolution of Hi-C interaction matrices. The HiCNN2 package includes three methods each with a different deep learning architecture: HiCNN2-1 is based on one single convolutional neural network (ConvNet); HiCNN2-2 consists of an ensemble of two different ConvNets; and HiCNN2-3 is an ensemble of three different ConvNets. Our evaluation results indicate that HiCNN2-enhanced high-resolution Hi-C data achieve smaller mean squared error and higher Pearson’s correlation coefficients with experimental high-resolution Hi-C data compared with existing methods HiCPlus and HiCNN. Moreover, all of the three HiCNN2 methods can recover more significant interactions detected by Fit-Hi-C compared to HiCPlus and HiCNN. Based on our evaluation results, we would recommend using HiCNN2-1 and HiCNN2-3 if recovering more significant interactions from Hi-C data is of interest, and HiCNN2-2 and HiCNN if the goal is to achieve higher reproducibility scores between the enhanced Hi-C matrix and the real high-resolution Hi-C matrix.

A Grey Wolf Optimization-Based Method for Segmentation and Evaluation of Scaling in Reinforced Concrete Bridges

2021 ◽  
pp. 1-54
Author(s):  
Eslam Mohammed Abdelkader ◽  
Osama Moselhi ◽  
Mohamed Marzouk ◽  
Tarek Zayed
Keyword(s):  
Neural Network ◽  
Reinforced Concrete ◽  
Mean Squared Error ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Concrete Bridges ◽  
Grey Wolf Optimization ◽  
Elman Neural Network ◽  
Reinforced Concrete Bridges ◽  
Squared Error

Bridges are prone to severe deterioration agents which promote their degradation over the course of their lifetime. Furthermore, maintenance budgets are being trimmed. This state of circumstances entails the development of a computer vision-based method for the condition assessment of bridge elements in an attempt to circumvent the drawbacks of visual inspection-based models. Scaling is progressive local flaking or loss in the surface portion of concrete that affects the functional and structural integrity of reinforced concrete bridges. As such, this research study proposes a self-adaptive three-tier method for the automated detection and assessment of scaling severity levels in reinforced concrete bridges. The first tier relies on the integration of cross entropy function and grey wolf optimization (GWO) algorithm for the segmentation of scaling pixels. The second tier is designated for the autonomous interpretation of scaling area. In this model, a hybrid feature extraction algorithm is proposed based on the fusion of singular value decomposition and discrete wavelet transform for the efficient and robust extraction of the most dominant features in scaling images. Then an integration of Elman neural network and GWO algorithm is proposed for the sake of improving the prediction accuracies of scaling area though optimization of both structure and parameters of Elman neural network. The third tier aims at establishing a unified scaling severity index to assess the extent of severities of scaling according to its area and depth. The developed method is validated through multi-layered comparative analysis that involved performance evaluation comparisons, statistical comparisons and box plots. Results demonstrated that the developed scaling detection model significantly outperformed a set of widely-utilized classical segmentation models achieving mean squared error, mean absolute error, peak signal to noise ratio and cross entropy of 0.175, 0.407, 55.754 and 26011.019, respectively. With regards to the developed scaling evaluation model, it accomplished remarkable better and more robust performance that other meta-heuristic-based Elman neural network models and conventional prediction models. In this context, it obtained mean absolute percentage error, root-mean squared error and mean absolute error 1.513%, 29.836 and 12.066, respectively, as per split validation. It is anticipated that the developed integrated computer vision-based method could serve as the basis of automated, reliable and cost-effective inspection platform of reinforced concrete bridges which can assist departments of transportation in taking effective preventive maintenance and rehabilitation actions.

scholarly journals Human Gait Analysis and Prediction Using the Levenberg-Marquardt Method

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Abdullah Alharbi ◽  
Kamran Equbal ◽  
Sultan Ahmad ◽  
Haseeb Ur Rahman ◽  
Hashem Alyami
Keyword(s):  
Neural Network ◽  
Lower Limb ◽  
Mean Squared Error ◽  
Human Gait ◽  
Network Function ◽  
Squared Error ◽  
Data Prediction ◽  
The Neural Network ◽  
Movement Artifacts ◽  
Human Gait Analysis

A high-accuracy gait data prediction model can be used to design prosthesis and orthosis for people having amputations or ailments of the lower limb. The objective of this study is to observe the gait data of different subjects and design a neural network to predict future gait angles for fixed speeds. The data were recorded via a Biometrics goniometer, while the subjects were walking on a treadmill for 20 seconds each at 2.4 kmph, 3.6 kmph, and 5.4 kmph. The data were then imported into Matlab, filtered to remove movement artifacts, and then used to design a neural network with 60% data for training, 20% for validation, and remaining 20% for testing using the LevenbergMarquardt method. The mean-squared error for all the cases was in the order of 10−3 or lower confirming that our method is correct. For further comparison, we randomly tested the neural network function with untrained data and compared the expected output with actual output of the neural network function using Pearson’s correlation coefficient and correlation plots. We conclude that our framework can be successfully used to design prosthesis and orthosis for lower limb. It can also be used to validate gait data and compare it to expected data in rehabilitation engineering.

scholarly journals Deep Learning Approach in DOA Estimation: A Systematic Literature Review

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Shengguo Ge ◽  
Kuo Li ◽  
Siti Nurulain Binti Mohd Rum
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
Array Signal Processing ◽  
Mean Squared Error ◽  
Doa Estimation ◽  
Absolute Error ◽  
Future Research ◽  
Great Success ◽  
Learning Technology

In array signal processing, the direction of arrival (DOA) of the signal source has drawn broad research interests with its wide applications in fields such as sonar, radar, communications, medical detection, and electronic countermeasures. In recent years, the application of deep learning (DL) to DOA estimation has achieved great success. This study provides a systematic review of research on DOA estimation using deep neural network methods. We manually selected twenty-five papers related to this research from five prominent databases (SpringerLink, IEEE Xplore, ScienceDirect, Scopus, and Google Scholar) for exploration. Six questions describing the overall trend of DOA estimation using deep learning are put forward. Then, we answered these questions by reviewing the literature. This review is helpful for researchers in this field because it provides more specific and comprehensive information needed for future research. Specifically, we first analyzed the background of the selected papers, including the type of publication, the number of citations, and the country of origin. Then, the DL technology used in DOA estimation is systematically analyzed, including the purpose of using DL in DOA estimation, various DL models (convolutional neural network, deep neural network, and combination network), and various DOA estimation schemes. Finally, various evaluation criteria (root-mean-squared error, accuracy, and mean absolute error) are used to evaluate the DL technology in DOA estimation, and various factors (signal-to-noise ratio, number of snapshots, number of antennas, and number of signal sources) affecting DOA estimation are analyzed. Based on our findings, we believe that deep learning can perform DOA estimation well, and there is still room for improvement in deep learning technology. In this study, the factors affecting DOA estimation can be used as the direction for researchers to conduct in-depth research.

scholarly journals Rainfall Analysis and Forecasting Using Deep Learning Technique

2021 ◽  
Vol 2 (2) ◽  
pp. 1-11
Author(s):  
Pragati Kanchan ◽  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Mean Squared Error ◽  
Predictive Accuracy ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Root Mean Squared Error ◽  
Rainfall Prediction ◽  
Absolute Percentage Error ◽  
Squared Error

Rainfall forecasting is very challenging due to its uncertain nature and dynamic climate change. It's always been a challenging task for meteorologists. In various papers for rainfall prediction, different Data Mining and Machine Learning (ML) techniques have been used. These techniques show better predictive accuracy. A deep learning approach has been used in this study to analyze the rainfall data of the Karnataka Subdivision. Three deep learning methods have been used for prediction such as Artificial Neural Network (ANN) - Feed Forward Neural Network, Simple Recurrent Neural Network (RNN), and the Long Short-Term Memory (LSTM) optimized RNN Technique. In this paper, a comparative study of these three techniques for monthly rainfall prediction has been given and the prediction performance of these three techniques has been evaluated using the Mean Absolute Percentage Error (MAPE%) and a Root Mean Squared Error (RMSE%). The results show that the LSTM Model shows better performance as compared to ANN and RNN for Prediction. The LSTM model shows better performance with mini-mum Mean Absolute Percentage Error (MAPE%) and Root Mean Squared Error (RMSE%).

scholarly journals Radial basis function neural network for 2 satisfiability programming

2020 ◽  
Vol 18 (1) ◽  
pp. 459 ◽  
Author(s):  
Shehab Alzaeemi ◽  
Mohd. Asyraf Mansor ◽  
Mohd Shareduwan Mohd Kasihmuddin ◽  
Saratha Sathasivam ◽  
Mustafa Mamat
Keyword(s):  
Neural Network ◽  
Radial Basis Function ◽  
Basis Function ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Percentage Error ◽  
Squared Error ◽  
Training Technique ◽  
Radial Basis ◽  
Hidden Neurons

<span>Radial Basis Function Neural Network (RBFNN) is very prominent in data processing. However, improving this technique is vital for the NN training process. This paper presents an integrated 2 Satisfiability in radial basis function neural network (RBFNN-2SAT). There are two different types of training in RBFNN, namely no-training technique and half-training technique. The performance of the solutions via Genetic Algorithm (GA) training was investigated by comparing the Radial Basis Function Neural Network No-Training Technique (RBFNN- 2SATNT) and Radial Basis Function Neural Network Half-Training Technique (RBFNN- 2SATHT). The comparison of both techniques was examined on 2 Satisfiability problem by using a C# software that was developed for this experiment. The performance of the RBFNN-2SATNT and RBFNN-2SATHT in performing 2SAT is discussed in terms of root mean squared error (RMSE), sum squared error (SSE), mean absolute percentage error (MAPE), mean absolute error (MAE), number of the hidden neurons and CPU time. Results obtained from a computer simulation showed that RBFNN-2SATHT outperformed RBFNN-2SATNT.</span>

scholarly journals Artificial intelligence with deep learning algorithms to model relationships between total tree height and diameter at breast height

2020 ◽  
Vol 29 (2) ◽  
pp. e013
Author(s):  
İlker Ercanli
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Mean Squared Error ◽  
Tree Height ◽  
Absolute Error ◽  
Diameter At Breast Height ◽  
Root Mean Squared Error ◽  
Squared Error ◽  
Hidden Layer ◽  
Total Tree

Aim of Study: As an innovative prediction technique, Artificial Intelligence technique based on a Deep Learning Algorithm (DLA) with various numbers of neurons and hidden layer alternatives were trained and evaluated to predict the relationships between total tree height (TTH) and diameter at breast height (DBH) with nonlinear least squared (NLS) regression models and nonlinear mixed effect (NLME) regression models.Area of Study: The data of this study were measured from even-aged, pure Turkish Pine (Pinus brutia Ten.) stands in the Kestel Forests located in the Bursa region of northwestern Turkey.Material and Methods: 1132 pairs of TTH-DBH measurements from 132 sample plots were used for modeling relationships between TTH, DBH, and stand attributes such as dominant height (Ho) and diameter (Do).Main Results: The combination of 100 # neurons and 8 # hidden layer in DLA resulted in the best predictive total height prediction values with Average Absolute Error (0.4188), max. Average Absolute Error (3.7598), Root Mean Squared Error (0.6942), Root Mean Squared error % (5.2164), Akaike Information Criteria (-345.4465), Bayesian Information Criterion (-330.836), the average Bias (0.0288) and the average Bias % (0.2166), and fitting abilities with r (0.9842) and Fit Index (0.9684). Also, the results of equivalence tests showed that the DLA technique successfully predicted the TTH in the validation dataset.Research highlights: These superior fitting scores coupled with the validation results in TTH predictions suggested that deep learning network models should be considered an alternative to the traditional nonlinear regression techniques and should be given importance as an innovative prediction technique.Keywords: Prediction; artificial intelligence; deep learning algorithms; number of neurons; hidden layer alternatives.Abbreviations: TTH (total tree height), DBH (diameter at breast height), OLS (ordinary least squares), NLME (nonlinear mixed effect), AIT (Artificial Intelligence Techniques), ANN (Artificial Neural Network), DLA (Deep Learning Algorithm), GPU (Graphical Processing Units), NLS (nonlinear least squared), RMSE (root mean squared error), AIC (Akaike information criteria), BIC (Bayesian information criterion), FI (fit index), AAE (average absolute error), BLUP (best linear unbiased predictor), TOST (two one-sided test method). 

scholarly journals Radar Echo Spatiotemporal Sequence Prediction Using an Improved ConvGRU Deep Learning Model

Atmosphere ◽  
2022 ◽  
Vol 13 (1) ◽  
pp. 88
Author(s):  
Wei He ◽  
Taisong Xiong ◽  
Hao Wang ◽  
Jianxin He ◽  
Xinyue Ren ◽  
...  
Keyword(s):  
Deep Learning ◽  
Input Data ◽  
Prediction Models ◽  
Mean Squared Error ◽  
Mean Absolute Error ◽  
Weather Prediction ◽  
Absolute Error ◽  
Sequence Prediction ◽  
Squared Error ◽  
Radar Echo

Precipitation nowcasting is extremely important in disaster prevention and mitigation, and can improve the quality of meteorological forecasts. In recent years, deep learning-based spatiotemporal sequence prediction models have been widely used in precipitation nowcasting, obtaining better prediction results than numerical weather prediction models and traditional radar echo extrapolation results. Because existing deep learning models rarely consider the inherent interactions between the model input data and the previous output, model prediction results do not sufficiently meet the actual forecast requirement. We propose a Modified Convolutional Gated Recurrent Unit (M-ConvGRU) model that performs convolution operations on the input data and previous output of a GRU network. Moreover, this adopts an encoder–forecaster structure to better capture the characteristics of spatiotemporal correlation in radar echo maps. The results of multiple experiments demonstrate the effectiveness of the proposed model. The balanced mean absolute error (B-MAE) and balanced mean squared error (B-MSE) of M-ConvGRU are slightly lower than Convolutional Long Short-Term Memory (ConvLSTM), but the mean absolute error (MAE) and mean squared error (MSE) of M-ConvGRU are 6.29% and 10.25% lower than ConvLSTM, and the prediction accuracy and prediction performance for strong echo regions were also improved.

scholarly journals Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks

Mathematics ◽  
2020 ◽  
Vol 8 (12) ◽  
pp. 2258
Author(s):  
Madhab Raj Joshi ◽  
Lewis Nkenyereye ◽  
Gyanendra Prasad Joshi ◽  
S. M. Riazul Islam ◽  
Mohammad Abdullah-Al-Wadud ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
User Study ◽  
Mean Squared Error ◽  
Color Image ◽  
Machine Learning Techniques ◽  
Global Features ◽  
Black And White ◽  
Historical Images ◽  
Learning Techniques

Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results.

scholarly journals A Novel Computational Intelligence Approach for Coal Consumption Forecasting in Iran

2021 ◽  
Vol 13 (14) ◽  
pp. 7612
Author(s):  
Mahdis sadat Jalaee ◽  
Alireza Shakibaei ◽  
Amin GhasemiNejad ◽  
Sayyed Abdolmajid Jalaee ◽  
Reza Derakhshani
Keyword(s):  
Hybrid Method ◽  
Computational Intelligence ◽  
Energy Demand ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Coal Consumption ◽  
Squared Error ◽  
Artificial Neural ◽  
Socio Economic Variables ◽  
Intelligence Approach

Coal as a fossil and non-renewable fuel is one of the most valuable energy minerals in the world with the largest volume reserves. Artificial neural networks (ANN), despite being one of the highest breakthroughs in the field of computational intelligence, has some significant disadvantages, such as slow training, susceptibility to falling into a local optimal points, sensitivity of initial weights, and bias. To overcome these shortcomings, this study presents an improved ANN structure, that is optimized by a proposed hybrid method. The aim of this study is to propose a novel hybrid method for predicting coal consumption in Iran based on socio-economic variables using the bat and grey wolf optimization algorithm with an artificial neural network (BGWAN). For this purpose, data from 1981 to 2019 have been used for modelling and testing the method. The available data are partly used to find the optimal or near-optimal values of the weighting parameters (1980–2014) and partly to test the model (2015–2019). The performance of the BGWAN is evaluated by mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), standard deviation error (STD), and correlation coefficient (R^2) between the output of the method and the actual dataset. The result of this study showed that BGWAN performance was excellent and proved its efficiency as a useful and reliable tool for monitoring coal consumption or energy demand in Iran.

Sign in / Sign up

Export Citation Format

Share Document