Journal: Expert Systems with Applications

Article Title: Advanced deep learning approaches to predict supply chain risks under COVID-19 restrictions

doi: 10.1016/j.eswa.2022.118604

Figure Lengend Snippet: Summary of the Literature Review.

Article Snippet: It can be seen from the results that ANN with stacked LSTM had shown the highest classification accuracy. (a, b, c, d, e, and f) represent the confusion matrix for the stacked LSTM based on Softmax, RT, RF, KNN, ANN, and SVM respectively, and each row of the matrix illustrates the instance in the predicated classes.

Techniques: Control, Selection, Formulation, Disruption

Journal: Expert Systems with Applications

Article Title: Advanced deep learning approaches to predict supply chain risks under COVID-19 restrictions

doi: 10.1016/j.eswa.2022.118604

Figure Lengend Snippet: Deep learning model based on the LSTM Layers.

Article Snippet: It can be seen from the results that ANN with stacked LSTM had shown the highest classification accuracy. (a, b, c, d, e, and f) represent the confusion matrix for the stacked LSTM based on Softmax, RT, RF, KNN, ANN, and SVM respectively, and each row of the matrix illustrates the instance in the predicated classes.

Techniques:

Journal: Expert Systems with Applications

Article Title: Advanced deep learning approaches to predict supply chain risks under COVID-19 restrictions

doi: 10.1016/j.eswa.2022.118604

Figure Lengend Snippet: Parameters of the RNN LSTM network layers.

Article Snippet: It can be seen from the results that ANN with stacked LSTM had shown the highest classification accuracy. (a, b, c, d, e, and f) represent the confusion matrix for the stacked LSTM based on Softmax, RT, RF, KNN, ANN, and SVM respectively, and each row of the matrix illustrates the instance in the predicated classes.

Techniques: Sequencing, Activation Assay

Journal: Expert Systems with Applications

Article Title: Advanced deep learning approaches to predict supply chain risks under COVID-19 restrictions

doi: 10.1016/j.eswa.2022.118604

Figure Lengend Snippet: Parameters of the training options for the proposed RNN Models.

Article Snippet: It can be seen from the results that ANN with stacked LSTM had shown the highest classification accuracy. (a, b, c, d, e, and f) represent the confusion matrix for the stacked LSTM based on Softmax, RT, RF, KNN, ANN, and SVM respectively, and each row of the matrix illustrates the instance in the predicated classes.

Techniques: Biomarker Discovery

Journal: Expert Systems with Applications

Article Title: Advanced deep learning approaches to predict supply chain risks under COVID-19 restrictions

doi: 10.1016/j.eswa.2022.118604

Figure Lengend Snippet: Training and loss curves of the stacked LSTM model for shipments prediction.

Article Snippet: It can be seen from the results that ANN with stacked LSTM had shown the highest classification accuracy. (a, b, c, d, e, and f) represent the confusion matrix for the stacked LSTM based on Softmax, RT, RF, KNN, ANN, and SVM respectively, and each row of the matrix illustrates the instance in the predicated classes.

Techniques:

Journal: Expert Systems with Applications

Article Title: Advanced deep learning approaches to predict supply chain risks under COVID-19 restrictions

doi: 10.1016/j.eswa.2022.118604

Figure Lengend Snippet: The results of the stacked LSTM model on the validation data in terms of various statistical performance measurements.

Article Snippet: It can be seen from the results that ANN with stacked LSTM had shown the highest classification accuracy. (a, b, c, d, e, and f) represent the confusion matrix for the stacked LSTM based on Softmax, RT, RF, KNN, ANN, and SVM respectively, and each row of the matrix illustrates the instance in the predicated classes.

Techniques: Biomarker Discovery

Journal: Expert Systems with Applications

Article Title: Advanced deep learning approaches to predict supply chain risks under COVID-19 restrictions

doi: 10.1016/j.eswa.2022.118604

Figure Lengend Snippet: The results of the stacked LSTM model on the test data in terms of various statistical performance measurements.

Article Snippet: It can be seen from the results that ANN with stacked LSTM had shown the highest classification accuracy. (a, b, c, d, e, and f) represent the confusion matrix for the stacked LSTM based on Softmax, RT, RF, KNN, ANN, and SVM respectively, and each row of the matrix illustrates the instance in the predicated classes.

Techniques:

Journal: Expert Systems with Applications

Article Title: Advanced deep learning approaches to predict supply chain risks under COVID-19 restrictions

doi: 10.1016/j.eswa.2022.118604

Figure Lengend Snippet: ROC of the stacked LSTM model using various classifiers on the shipments test data prediction.

Article Snippet: It can be seen from the results that ANN with stacked LSTM had shown the highest classification accuracy. (a, b, c, d, e, and f) represent the confusion matrix for the stacked LSTM based on Softmax, RT, RF, KNN, ANN, and SVM respectively, and each row of the matrix illustrates the instance in the predicated classes.

Techniques:

Journal: Expert Systems with Applications

Article Title: Advanced deep learning approaches to predict supply chain risks under COVID-19 restrictions

doi: 10.1016/j.eswa.2022.118604

Figure Lengend Snippet: Confusion matrix of the stacked LSTM model using various classifiers on the shipments test data prediction.

Article Snippet: It can be seen from the results that ANN with stacked LSTM had shown the highest classification accuracy. (a, b, c, d, e, and f) represent the confusion matrix for the stacked LSTM based on Softmax, RT, RF, KNN, ANN, and SVM respectively, and each row of the matrix illustrates the instance in the predicated classes.

Techniques: