1. Introduction

Pneumonia is an infection inflaming air sacs in the lungs, it can be bacterial or viral including covid-19 virus, but symptoms are often similar independently of the factors causing the disease [1]. Doctors need additional analysis or X-ray imaging to identify the cause of the pneumonia. The X-ray imaging of the lungs allows them to identify only if a lung has pneumonia or not [2].

Many germs can cause pneumonia including viruses, bacteria, and fungi commonly collected from the air and can overpower the immune system which leads to critical health situations. Therefore, early diagnosis [3] based on X-ray image classification is very important at first in order to prevent complications and make treatment efficient. Then advanced diagnosis is needed to determine the type and the cause of the pneumonia using medical tests and X-Ray scans.

Manual classification of pneumonia disease still the most efficient way, usually used by radiologists. The principle inconvenient of this method is about the time-consuming, which is a very important factor in the case of a pandemic.

Nowadays, many researchers become very interested in applications of artificial neural networks (ANN), especially convolutional neural networks (CNN). This method is efficient for medical image classification tasks. It makes computers capable of solving many pattern recognition and object extraction problems using datasets of 2D or 3D images. In case of 3D MRI images classification task  it requires a huge processing capacity which can be bypassed by adopting a parallel algorithms [4], [5]. In  [6], an example of the above parallel approach where the authors propose a parallel c-mean algorithm applied to MRI images classification showing good time complexity on its results.

To overcome the constrain of execution time, using Graphical Processing Units (GPU) become crucial today in medical image processing applications, especially in a context of machine and deep learning algorithms. They can significantly accelerate parallel processing, therefore almost all works related to medical image processing in medical field uses GPUs as accelerators to achieve better and fast results [7], [8].

However, machine learning algorithms and convolutional neural networks (CNNs) models have gained a lot of attention for almost all diseases classification and prediction problematic including breast cancer detection [9],  cardio vascular prediction and diagnosis [10], [11], diabetes mellitus prediction [12], [13], etc.

In this work, we make an implementation of some CNN models using transfer learning technique. We used these models to perform pneumonia detection. Results evaluation and comparison is made in order to adapt and select the best model for the task according to certain parameters.

The rest of this paper is organized as follows: In section 2, we present a brief overview of some different classification techniques on relevant related work used for the prediction of various human diseases, and we focused on studies conducted on the prediction of pneumonia disease from lung X-ray images. Section 3 present the used dataset and CNN models. In section 4, we present the models experimental results and discuss the performance evaluation measures. Section 5 concludes this article and presents some perspectives at this work.

2. Related work

In this section, we review some related and similar works that matches classification task for pneumonia diseases using different machine and deep learning models. These models are evaluated within different metrics and reached less or more important performances, depending on their architecture and conception.

Recently many researches published about the pneumonia disease detection, especially ANN based models achieving great results which are very suitable for this type of disease. Note that COVID-19 virus causes severe pneumonia disease.

In 2019, the authors in [14] published a work concerning pneumonia detection applying a combination of mRMR feature selection and machine learning models on the Chest X-ray images. Features extraction is performed using existing CNN models: AlexNet, VGG16 and VGG19 and then combining the results as an input features set to feed and train five different machine learning models: decision tree, k-nearest neighbors, linear discriminant analysis, linear regression, and support vector. The experiment shows the best results for linear discriminant analysis obtaining 99.41% accuracy.

In January of 2020, the authors published in [15] a model based on transfer learning technique for Chest X-ray images of pneumonia disease. This model consists of combining AlexNet, DenseNet121, InceptionV3, resNet18 and GoogleNet generating a new architecture and reaching 96.39% accuracy on test images. The dataset used in this work is from Guangzhou-women-and-Children’s Medical Center dataset [16].

Lately, the authors in [17] published a work about another method of automatic pneumonia detection based also on chest X-ray images focusing this time on specific region of interest (ROI) to classify and segment images. The method was compared in this study with five different classifiers: Multilayer perceptron, sequential minimal optimization (SMO), random forest, Classification via regression and classification via logistic regression. The proposed study shows a higher accuracy on logistic regression classifier with accuracy of 95.63% on test dataset.

In [18], another work published about a machine learning algorithm for pneumonia classification. In this work, the authors built a CNN model from scratch in order to classify images of pneumonia disease based on X-ray chest images obtaining a validation accuracy of 93.7%; where an augmentation method was adopted to increase the dataset size. In table 1, we summarize main information’s about these works.

Based on these works and others, we develop and compare in this paper some convolutional neural networks in the goal to enhance the test accuracy on pneumonia disease detection from Lung X-ray images. In fact, we will introduce only automatic methods related to deep learning techniques which are the most adapted for the task of classifying 2D images based of lung X-ray datasets.

3. Materials and methods

3.1. Dataset description

The original dataset used in this work is called “Labeled Optical Coherence Tomography (OCT) and Chest X-Ray images for Classification” version 3 [19]. Only Chest X-Ray part is used in experiments. All models developed in this paper are trained and tested on this part of dataset. The concerned lung X-ray database

Table 1: Summary of related works methods and results.

Table 2: Dataset distribution over training, validation and testing sub sets.

is composed of 2 types of images: Images for normal patients (NORMAL) and images for patients with pneumonia disease (PNEUMONIA). In table 2, we summarize the structure of the dataset (Training, validation and Testing).

Figure 1 present some samples of normal and pneumonia lung x-ray images.

Figure 1: Example of Normal (a & b) and pneumonia (c & d) X-ray samples from the dataset.

3.2. Artificial Neural Network (ANN)

Artificial neural network (ANN) concept is inspired from the human brain being the smarter system that can process real data. The treatment ability came from connections between neurons of the brain. This structure forms a huge natural neural network able to resolve complicated operations in the real world. ANN is about superposing a lot of  artificial neurons just like the natural neural network [20]. The elementary ANN (perceptron) is the simplest architecture of an artificial neural network, illustrated in figure 2.

The perceptron composed from input layer having a vector {xi} as inputs, sharable weights in the form of a vector {w_i} too and a bias. {y_i} presents the output of the perceptron in the form of a vector of probabilities of predictions.

3.3. Convolutional Neural Network (CNN)

Convolutional Neural Network (CNN) is an ANN network but the inverse is not true. CNN are most commonly applied to automatically process visual images. A CNN contains one or more convolution layer.

Figure 2: Architecture for a single layer perceptron.

The notion of CNN is old. This abstraction had been verified to work more accurately for recognition of hand written characters [21]. However, this type of networks loses the challenge to process large and heavy images. Therefore, this method was impractical because of the constraints of processing power, lack of memory and datasets availability. Nowadays, these limitations are relatively passed out, because of the technological evolution of storage, memory and methods optimization.

3.4. CNN Architecture

CNNs architecture consists of concatenating multiple types of layers successively which are input layers, convolutional layers and dense layers. In general, convolutional neural networks are based on its process on two principle factors: sharing weights and connectivity between neurons of each convolutional layer.

• Sharing weights:  At each convolutional layer, every neuron has its weights that need to be shared to all neurons of the next layer. Those weights need also to be shared to all neurons in the previous layer in order to achieve back propagation process.
• Connectivity: All neurons of each layer are locally connected only to all neurons in the next layer. This connectivity conception reduces the complexity of the network.

Generally, to build a CNN network, an input layer is required with specific configuration including image shapes and patch. Then a convolutional layer’s type must follow, also configured with specific number of neurons and specific function of optimization and activation. Each convolutional layer needs a pooling layer to follow with a specific filter of pooling. After that a number of Dense layers must be created before the output layer that requires a loss function to be configured [22].

3.5. Proposed methodology for lung pneumonia classification using CNN

The main steps for any image classification system are: image preprocessing, feature processing included in the convolution process, training the network and validating the resulted model. At the end testing the final CNN model.

Figure 3 shows the general architecture of a CNN model used to detect lung pneumonia containing input layer, convolution layers with ReLU activation function, pooling layers and fully connected layers.

Figure 3: Illustration of CNN architecture used for pneumonia detection on lung X-ray images.

• Dataset preprocessing: it consists of preparing data to feed the network, this preparation is about reshaping and resizing images, dropping out unusable images and adapting contrast. Also converting raw data to victors and normalizing it [21]. The output of this process feeds a CNN network for training in order to become a pre-trained model, ready for the testing phase [23].
• Features selection and extraction: This step is included in the convolution layers, and consists of extracting useful features only, then converted to the adequate format.

The selection part consists of selecting the most useful features to achieve the classification case of study [24].

• Training: At this phase the network is trained by updating weights of neurons across layers, it’s called the learning process. This is done by minimizing the loss function and maximizing the accuracy rate of the validation part. If there is only two classes to predict, a sigmoid function is used for the loss optimization [24].

The learning goal of the model is achieved using an optimizer from a huge scale of optimizers existing in the literature but the back-propagation algorithms are the most used in classification case [21].

• Classification evaluation metrics

Almost all metrics to process the performance of a model are based on some primordial parameters to be calculated:

True positive abbreviated by TP: Number of images accurately classified as pneumonia matching the ground truth.

True negative abbreviated by TN: Number of images accurately classified as normal matching the true labels.

False positive abbreviated by FP: CNN classifies images as containing pneumonia but that it’s actually normal according to the ground truth.

False negative abbreviated by FN: Number of images which the CNN classifies as not containing pneumonia but are actually containing pneumonia according to the ground truth labels [25].

Based on those calculated parameters, we can compute the precision abbreviated as P, recall abbreviated as R, the F1 score and the accuracy as:

F1 result is obtained by processing parameters in (Eq.2) and (Eq.3). The formula of this parameter is in (Eq.4).

• Testing: On this step we use test set as a different dataset and new one for the model. In order to well testing the model, the ground truth of the test set must be similar to the training set but not correlated. This makes the test more valid and accurate [26].
• Classification: This is the last step on the CNN model, it consists of affecting a label to each image from the input features with a specific confidence of decision:

Initialization: Before to start the learning stage where the weights are updated over epochs. Those weights must have initiated by the initial values, in some cases those values are random. Otherwise those values are generated by a predefined function. The   Xavier initialization  is the usually used method of initialization [21].

Activation function: This is the function representing the processing part of a neuron. It depends on the type a layer of the neural network. Most used activation function for layers in CNN network is ReLU function [27].

Pooling: This phase consists of reducing the size of features by applying a filter and keeping only the most important elements. The most popular pooling method in CNN models is max pooling and average pooling. The max pooling consists of selecting only the maximum element in the filter and the average pooling consists of averaging all elements inside the filter [21].

Regularization: This technic is about reducing over fitting problems and improving performance of the model. There are many methods to ensure regularization, and the most popular method is dropout. The dropout method is based on eliminating the less important features on each iteration  [27].

Loss Function: This hyper parameter defines the function that evaluates how much the trained model can fail predicting the affected task. Its value is reverse to the accuracy value. More the loss is minimal the more the accuracy must be maximal. The quadratic error is the most used for loss function in CNNs [28].

4. Results and discussion

CNNs models have proven interesting results in many applications lately. These models existed in literature differ in the network size, defined optimizers and the type of layers used.

Training task require a big processing capacity which leads us to choose a parallel architecture of processing, by adopting graphical processing unit (GPU), in the virtual environment to accelerate the training step offered by KAAGLE platform. In our experiment we used dual cores of CPU with 13 GB of RAM memory equipped with a GPU of 16 GB of RAM memory.

4.1. Building proposed CNN models using transfer learning approach

In our experiment, we build and compile five different models based on existing models in the literature using transfer learning technique.

Depending on the case, each model can succeed or fail the classification task. For our case of pneumonia detection problematic and after running many algorithms many times by trying at each different configuration, we select those architectures in figure 4. With given configurations relatively presenting better results in term of accuracy and loss taking in consideration the over-fitting and the under-fitting problems.

4.2. Compiling and training CNN models

In all models experimented in this work, we add two dropout layers and one dense layer with SOFTMAX activation at the output layer as a classifier. We used a logistic regression algorithm called “RMSProp” optimizer and categorical cross entropy accuracy as a metric during the model compilation.

Weights are initialized using image-net. We decide to not freeze any layer of the original model, because of the nature of pneumonia detection problematic compared to the originally trained dataset.

In order to reduce over fitting on training layers, we used a callback parameter specifying to stop training when no accuracy improvement happened within three successive iterations. That obliges the training process to stop at the epoch where no accuracy improvement happened.

4.3. Validation and testing the given CNN models

While training our proposed models, the validation process goal consists of checking the accuracy of the model in each epoch. Then update weights on the back-propagation process to use in the next epoch for learning. For this task, we used validation dataset as described in figure 1.

Figure 4: Architecture of proposed transfer learning-based models: (a) VGG16, (b) VGG19, (c) NasNetMobile, (d), ResNet152V2 (e) Inception-Resnet-v2.

In this step, we can get the performance and evaluation metrics for our models before trust them for real case classification.

In general VGG16 gets good results in many cases for fine-tuning task [29], this is the mean reason of choosing this model at first for transfer learning to process pneumonia classification.

As shown in figure 5, for the VGG16 based transfer learning model we get the best accuracy and very interesting accuracy evolution over iterations compared to other tested models. The accuracy continues improving until the 30th epoch and the convergence between the validation and the training accuracy is very good, which makes this model the most adapted for our task. The first 10 epochs show a fast improvements and convergence of the accuracy then the next epochs converge very well but improves slowly without losing convergence aspect.

Figure 5: Evolution of training and validation accuracy over epochs for different models: a) NasNetMobile based model, b) ResNet152V2, c) Inception-Resnet-v2 based model, d) VGG19 based model, e) VGG16 based model.

From figure 6, it’s clear that all well predicted features show probability over 80% (green aspect), and the only miss predicted feature (red aspect) here shows a 68% probability of confidence which is also a clear indication for experts to give more interest of verification and correction for non-confident classifications. Therefore, the model can be a good tool to help for pneumonia disease diagnosis. Time and effort for medical experts in diagnosing pneumonia cases specially in the case of COVID-19 can be saved. In fact, human visual system has many limitations about detecting the gray-scale resolutions even with high brightness and contrast, X-Ray images can present a large scale of gray-scale shades than the human eye could detect. This is another reason why the automatic diagnosis is primordial for improving the disease detection.

VGG19 based transfer learning model shows also good accuracy convergence, where the maximum value is achieved on the 10^th epoch and relatively starts to stabilize for the next epochs, therefore the algorithm ends to avoid over-fitting.

Models: Inception-Resnet-v2 based model and ResNet152V2 based shows similar accuracy evolution results. Speed of convergence for the first one is performed after 18 epochs but for the second in just 10 epochs. That gives an advantage for the second one. The NasNetMobile based model shows a very bad accuracy results in term of convergence or accuracy values, which makes this model badly ranked for this task.

Figure 6: Example of predicted features using a VGG 16 based transfer learning model showing in the left the id number of the feature in the testing dataset and the probability of prediction in the right.

Loss curve is also an important tool to evaluate models just like the accuracy curve. In our experiment, results of loss functions are illustrated in figure 7.

Similarly, to accuracy curve analysis, this tool confirms that VGG16 based model is the best model achieving pneumonia detection task.  NasNetMobile based model shows again the worst results for this task. Regarding confusion matrix tool, our models shows the following results:

Figure 7: Evolution of training and validation loss over epochs for different models: a) NasNetMobile based model, b) ResNet152V2, c) Inception-Resnet-v2 based model, d) VGG19 based model, e) VGG16 based model.

VGG19 based model failed on predicting the 26 case of pneumonia but succeed on predicting 615 of 641 features. The model also failed to predict normal for only 4 cases. In general, this is a good result regarding the total number of cases.

VGG16 based model fails detecting 21 pneumonia cases which make it better than VGG19 based model. But not efficient on detecting pneumonia cases compared to Resnet152V2 based.

However, ResNet152V2 based total fails of 32 predictions including normal and pneumonia cases. Which is more than VGG16 based model. Therefore VGG 16 based model presents the best confusion matrix results in this experiment. The other models in this experiment show fewer interesting results on their confusion matrix. Classification based on CNN methods for Medical images gets the better performance (accuracy) on fine-tuning the model VGG16 modeled by Google Company, showing the results of almost: 97% for pneumonia detection, 11.51% loss. It is clear that

• Table 3: Comparison of different implemented CNN models.

Figure 1: Confusion matrix of all trained and tested models.

loss function of the model VGG16 based model is minimal; also, its accuracy presents the maximum of all trained models. VGG16 based model get into its maximum value of accuracy on epoch 33 with loss value of 11.51% and precision of 91%. VGG19 based model is very close to the VGG16 based one in term of accuracy, but the rest of the models as showed in table 3 presents relatively bad accuracy results to trust for our task.

ROC curve is a fundamental tool for model performance evaluation based on sensitivity/specificity reports or true positive rate and false positive rate, in this ROC graph each curve the sensitivity (true positive rate) is plotted as a function of a specificity value (false positive rate). Area under the curve (AUC) represents how well the model can distinguish between a normal and pneumonia image called.

Figure 2: ROC curve comparison for all implemented models.

In general, more the area is big, more the curve is near to the left corner of the graph and more the represented model is better in terms of performance.

5. Conclusion and perspectives

Pneumonia disease classification is a primordial step for diagnosing lung infections which can be caused by several factors including covid-19.

Machine learning methodology especially convolutional neural networks are a very interesting techniques to automatically, efficiently and rapidly output results.

This method faces sense the beginning many problems like the leak of datasets in the world and algorithms complexities in time and processing.

To improve prediction accuracy more and more some extensions must be done, like increasing the dataset by combining multiple independent datasets to set a bigger database of samples that conduct us to use higher processing performances in order to train all the given dataset in a reasonable time and epochs, we need also to preprocess differently the input images by cropping and correcting contrast on X-Ray images based on processing concentration while training, and also proposing the best adapted optimizer on training.

Also, we plan in the future to make our conception of optimized novel model adapted specially for chest X-Ray images. Training stage takes relatively a lot of time depending on the complexity of the algorithm that must be optimized as much as possible and the capacity of available resources.  Therefore, there is a lot of required work to achieve by researchers’ efforts to take benefits of this magic field in our world.

Conflict of Interest

The authors declare no conflict of interest.

Acknowledgment

This work is a part of a project supported by co-financing from the CNRST (Centre National pour la Recherche Scientifique et Technique) and the Hassan II University of Casablanca, Morocco.  The project is selected in the context of a call for projects entitled “Scientific and Technological Research Support Program in Link with COVID-19” launched in April 2020 (Reference: Letter to the Director of “Ecole Normale Supérieure de l’Enseignement Technique de Mohammedia” dated the 10th June 2020).

1. S. Kang, W. Peng, Y. Zhu, S. Lu, M. Zhou, W. Lin, W. Wu, S. Huang, L. Jiang, X. Luo, M. Deng, “Recent progress in understanding 2019 novel coronavirus (SARS-CoV-2) associated with human respiratory disease: detection, mechanisms and treatment,” International Journal of Antimicrobial Agents, 105950, 2020, doi:10.1016/j.ijantimicag.2020.105950.
2. A. Jacobi, M. Chung, A. Bernheim, C. Eber, “Portable chest X-ray in coronavirus disease-19 (COVID-19): A pictorial review,” Clinical Imaging, 64, 35–42, 2020, doi:10.1016/j.clinimag.2020.04.001.
3. J. Gong, J. Ou, X. Qiu, Y. Jie, Y. Chen, L. Yuan, J. Cao, M. Tan, W. Xu, F. Zheng, Y. Shi, B. Hu, “A Tool to Early Predict Severe Corona Virus Disease 2019 (COVID-19): A Multicenter Study using the Risk Nomogram in Wuhan and Guangdong, China,” Clinical Infectious Diseases, ciaa443, 2020, doi:10.1093/cid/ciaa443.
4. H. Moujahid, B. Cherradi, L. Bahatti, Convolutional Neural Networks for Multimodal Brain MRI Images Segmentation: A Comparative Study, Springer International Publishing, Cham: 329–338, 2020, doi:10.1007/978-3-030-45183-7_25.
5. N.A. Ali, B. Cherradi, A. El Abbassi, O. Bouattane, M. Youssfi, “Parallel Implementation and Performance Evaluation of some Supervised Clustering Algorithms for MRI Images Segmentation,” in Proceedings of the 4th International Conference on Big Data and Internet of Things, ACM, Rabat Morocco: 1–7, 2019, doi:10.1145/3372938.3373007.
6. O. Bouattane, B. Cherradi, M. Youssfi, M.O. Bensalah, “Parallel c-means algorithm for image segmentation on a reconfigurable mesh computer,” Parallel Computing, 37(4), 230–243, 2011, doi:10.1016/j.parco.2011.03.001.
7. N. Ait Ali, B. Cherradi, A. El Abbassi, O. Bouattane, M. Youssfi, “GPU fuzzy c-means algorithm implementations: performance analysis on medical image segmentation,” Multimedia Tools and Applications, 77(16), 21221–21243, 2018, doi:10.1007/s11042-017-5589-6.
8. N.A. Ali, B. Cherradi, A.E. Abbassi, O. Bouattane, M. Youssfi, “Modelling the behavior of the CPU and the GPU versus the clusters number variation for sequential and parallel implementations of BCFCM algorithm,” ARPN Journal of Engineering and Applied Sciences, 12(21), 6030–6038, 2017.
9. S. Laghmati, A. Tmiri, B. Cherradi, “Machine Learning based System for Prediction of Breast Cancer Severity,” in 2019 International Conference on Wireless Networks and Mobile Communications (WINCOM), IEEE, Fez, Morocco: 1–5, 2019, doi:10.1109/WINCOM47513.2019.8942575.
10. O. Terrada, A. Raihani, O. Bouattane, B. Cherradi, “Fuzzy cardiovascular diagnosis system using clinical data,” in 2018 4th International Conference on Optimization and Applications (ICOA), IEEE: 1–4, 2018.
11. O. Terrada, B. Cherradi, A. Raihani, O. Bouattane, “Atherosclerosis disease prediction using Supervised Machine Learning Techniques,” in 2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), IEEE, Meknes, Morocco: 1–5, 2020, doi:10.1109/IRASET48871.2020.9092082.
12. O. Daanouni, B. Cherradi, A. Tmiri, “Predicting diabetes diseases using mixed data and supervised machine learning algorithms,” in Proceedings of the 4th International Conference on Smart City Applications – SCA ’19, ACM Press, Casablanca, Morocco: 1–6, 2019, doi:10.1145/3368756.3369072.
13. O. Daanouni, B. Cherradi, A. Tmiri, “Diabetes Diseases Prediction Using Supervised Machine Learning and Neighbourhood Components Analysis,” in Proceedings of the 3rd International Conference on Networking, Information Systems & Security, ACM, Marrakech Morocco: 1–5, 2020, doi:10.1145/3386723.3387887.
14. M. Toğaçar, B. Ergen, Z. Cömert, F. Özyurt, “A Deep Feature Learning Model for Pneumonia Detection Applying a Combination of mRMR Feature Selection and Machine Learning Models,” IRBM, S1959031819301174, 2019, doi:10.1016/j.irbm.2019.10.006.
15. V. Chouhan, S. Singh, A. Khamparia, D. Gupta, P. Tiwari, C. Moreira, R. Damasevicius, V. Albuquerque, “A Novel Transfer Learning Based Approach for Pneumonia Detection in Chest X-ray Images,” Applied Sciences, 10, 559, 2020, doi:10.3390/app10020559.
16. D.S. Kermany, M. Goldbaum, W. Cai, C.C.S. Valentim, H. Liang, S.L. Baxter, A. McKeown, G. Yang, X. Wu, F. Yan, J. Dong, M.K. Prasadha, J. Pei, M.Y.L. Ting, J. Zhu, C. Li, S. Hewett, J. Dong, I. Ziyar, A. Shi, R. Zhang, L. Zheng, R. Hou, W. Shi, X. Fu, Y. Duan, V.A.N. Huu, C. Wen, E.D. Zhang, et al., “Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning,” Cell, 172(5), 1122-1131.e9, 2018, doi:10.1016/j.cell.2018.02.010.
17. B.B. Chaudhuri, M. Nakagawa, P. Khanna, S. Kumar, Proceedings of 3rd International Conference on Computer Vision and Image Processing: CVIP 2018, Volume 1, Springer Nature, 2019.
18. O. Stephen, M. Sain, U.J. Maduh, D.-U. Jeong, “An Efficient Deep Learning Approach to Pneumonia Classification in Healthcare,” Journal of Healthcare Engineering, 2019, 1–7, 2019, doi:10.1155/2019/4180949.
19. D. Kermany, K. Zhang, M. Goldbaum, “Large Dataset of Labeled Optical Coherence Tomography (OCT) and Chest X-Ray Images,” 3, 2018, doi:10.17632/rscbjbr9sj.3.
20. C. Senaras, M.N. Gurcan, “Deep learning for medical image analysis,” Journal of Pathology Informatics, 9(1), 25, 2018, doi:10.4103/jpi.jpi_27_18.
21. Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, 86(11), 2278–2324, 1998, doi:10.1109/5.726791.
22. S. Srinivas, R.K. Sarvadevabhatla, K.R. Mopuri, N. Prabhu, S.S.S. Kruthiventi, R.V. Babu, An Introduction to Deep Convolutional Neural Nets for Computer Vision, Elsevier: 25–52, 2017, doi:10.1016/B978-0-12-810408-8.00003-1.
23. N. Tajbakhsh, J.Y. Shin, R.T. Hurst, C.B. Kendall, J. Liang, Automatic Interpretation of Carotid Intima–Media Thickness Videos Using Convolutional Neural Networks, Elsevier: 105–131, 2017, doi:10.1016/B978-0-12-810408-8.00007-9.
24. S. Miao, J.Z. Wang, R. Liao, Convolutional Neural Networks for Robust and Real-Time 2-D/3-D Registration, Elsevier: 271–296, 2017, doi:10.1016/B978-0-12-810408-8.00016-X.
25. H. Chen, Q. Dou, L. Yu, J. Qin, L. Zhao, V.C.T. Mok, D. Wang, L. Shi, P.-A. Heng, Deep Cascaded Networks for Sparsely Distributed Object Detection from Medical Images, Elsevier: 133–154, 2017, doi:10.1016/B978-0-12-810408-8.00008-0.
26. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Journal of Machine Learning Research, 15(56), 1929–1958, 2014.
27. H.-I. Suk, An Introduction to Neural Networks and Deep Learning, Elsevier: 3–24, 2017, doi:10.1016/B978-0-12-810408-8.00002-X.
28. F.C. Ghesu, B. Georgescu, J. Hornegger, Efficient Medical Image Parsing, Elsevier: 55–81, 2017, doi:10.1016/B978-0-12-810408-8.00005-5.
29. S.S. Yadav, S.M. Jadhav, “Deep convolutional neural network based medical image classification for disease diagnosis,” Journal of Big Data, 6(1), 113, 2019, doi:10.1186/s40537-019-0276-2.

Citations by Dimensions

Citations by PlumX

Google Scholar

Crossref Citations

1. Vikas Thammanna Gowda, Landis Humphrey, Aiden Kadoch, YinBo Chen, Olivia Roberts, "Multi Attribute Stratified Sampling: An Automated Framework for Privacy-Preserving Healthcare Data Publishing with Multiple Sensitive Attributes", Advances in Science, Technology and Engineering Systems Journal, vol. 11, no. 1, pp. 51–68, 2026. doi: 10.25046/aj110106
2. Kohinur Parvin, Eshat Ahmad Shuvo, Wali Ashraf Khan, Sakibul Alam Adib, Tahmina Akter Eiti, Mohammad Shovon, Shoeb Akter Nafiz, "Computationally Efficient Explainable AI Framework for Skin Cancer Detection", Advances in Science, Technology and Engineering Systems Journal, vol. 11, no. 1, pp. 11–24, 2026. doi: 10.25046/aj110102
3. David Degbor, Haiping Xu, Pratiksha Singh, Shannon Gibbs, Donghui Yan, "StradNet: Automated Structural Adaptation for Efficient Deep Neural Network Design", Advances in Science, Technology and Engineering Systems Journal, vol. 10, no. 6, pp. 29–41, 2025. doi: 10.25046/aj100603
4. Jenna Snead, Nisa Soltani, Mia Wang, Joe Carson, Bailey Williamson, Kevin Gainey, Stanley McAfee, Qian Zhang, "3D Facial Feature Tracking with Multimodal Depth Fusion", Advances in Science, Technology and Engineering Systems Journal, vol. 10, no. 5, pp. 11–19, 2025. doi: 10.25046/aj100502
5. Glender Brás, Samara Leal, Breno Sousa, Gabriel Paes, Cleberson Junior, João Souza, Rafael Assis, Tamires Marques, Thiago Teles Calazans Silva, "Machine Learning Methods for University Student Performance Prediction in Basic Skills based on Psychometric Profile", Advances in Science, Technology and Engineering Systems Journal, vol. 10, no. 4, pp. 1–13, 2025. doi: 10.25046/aj100401
6. khawla Alhasan, "Predictive Analytics in Marketing: Evaluating its Effectiveness in Driving Customer Engagement", Advances in Science, Technology and Engineering Systems Journal, vol. 10, no. 3, pp. 45–51, 2025. doi: 10.25046/aj100306
7. François Dieudonné Mengue, Verlaine Rostand Nwokam, Alain Soup Tewa Kammogne, René Yamapi, Moskolai Ngossaha Justin, Bowong Tsakou Samuel, Bernard Kamsu Fogue, "Explainable AI and Active Learning for Photovoltaic System Fault Detection: A Bibliometric Study and Future Directions", Advances in Science, Technology and Engineering Systems Journal, vol. 10, no. 3, pp. 29–44, 2025. doi: 10.25046/aj100305
8. Surapol Vorapatratorn, Nontawat Thongsibsong, "AI-Based Photography Assessment System using Convolutional Neural Networks", Advances in Science, Technology and Engineering Systems Journal, vol. 10, no. 2, pp. 28–34, 2025. doi: 10.25046/aj100203
9. Khalifa Sylla, Birahim Babou, Mama Amar, Samuel Ouya, "Impact of Integrating Chatbots into Digital Universities Platforms on the Interactions between the Learner and the Educational Content", Advances in Science, Technology and Engineering Systems Journal, vol. 10, no. 1, pp. 13–19, 2025. doi: 10.25046/aj100103
10. Win Pa Pa San, Myo Khaing, "Advanced Fall Analysis for Elderly Monitoring Using Feature Fusion and CNN-LSTM: A Multi-Camera Approach", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 6, pp. 12–20, 2024. doi: 10.25046/aj090602
11. Ahmet Emin Ünal, Halit Boyar, Burcu Kuleli Pak, Vehbi Çağrı Güngör, "Utilizing 3D models for the Prediction of Work Man-Hour in Complex Industrial Products using Machine Learning", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 6, pp. 01–11, 2024. doi: 10.25046/aj090601
12. Joshua Carberry, Haiping Xu, "GPT-Enhanced Hierarchical Deep Learning Model for Automated ICD Coding", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 4, pp. 21–34, 2024. doi: 10.25046/aj090404
13. Haruki Murakami, Takuma Miwa, Kosuke Shima, Takanobu Otsuka, "Proposal and Implementation of Seawater Temperature Prediction Model using Transfer Learning Considering Water Depth Differences", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 4, pp. 01–06, 2024. doi: 10.25046/aj090401
14. Brandon Wetzel, Haiping Xu, "Deploying Trusted and Immutable Predictive Models on a Public Blockchain Network", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 3, pp. 72–83, 2024. doi: 10.25046/aj090307
15. Anirudh Mazumder, Kapil Panda, "Leveraging Machine Learning for a Comprehensive Assessment of PFAS Nephrotoxicity", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 3, pp. 62–71, 2024. doi: 10.25046/aj090306
16. Nguyen Viet Hung, Tran Thanh Lam, Tran Thanh Binh, Alan Marshal, Truong Thu Huong, "Efficient Deep Learning-Based Viewport Estimation for 360-Degree Video Streaming", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 3, pp. 49–61, 2024. doi: 10.25046/aj090305
17. Sami Florent Palm, Sianou Ezéckie Houénafa, Zourkalaïni Boubakar, Sebastian Waita, Thomas Nyachoti Nyangonda, Ahmed Chebak, "Solar Photovoltaic Power Output Forecasting using Deep Learning Models: A Case Study of Zagtouli PV Power Plant", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 3, pp. 41–48, 2024. doi: 10.25046/aj090304
18. Taichi Ito, Ken’ichi Minamino, Shintaro Umeki, "Visualization of the Effect of Additional Fertilization on Paddy Rice by Time-Series Analysis of Vegetation Indices using UAV and Minimizing the Number of Monitoring Days for its Workload Reduction", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 3, pp. 29–40, 2024. doi: 10.25046/aj090303
19. Henry Toal, Michelle Wilber, Getu Hailu, Arghya Kusum Das, "Evaluation of Various Deep Learning Models for Short-Term Solar Forecasting in the Arctic using a Distributed Sensor Network", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 3, pp. 12–28, 2024. doi: 10.25046/aj090302
20. Tinofirei Museba, Koenraad Vanhoof, "An Adaptive Heterogeneous Ensemble Learning Model for Credit Card Fraud Detection", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 3, pp. 01–11, 2024. doi: 10.25046/aj090301
21. Toya Acharya, Annamalai Annamalai, Mohamed F Chouikha, "Enhancing the Network Anomaly Detection using CNN-Bidirectional LSTM Hybrid Model and Sampling Strategies for Imbalanced Network Traffic Data", Advances in Science, Technology and Engineering Systems Journal, vol. 9, no. 1, pp. 67–78, 2024. doi: 10.25046/aj090107
22. Toya Acharya, Annamalai Annamalai, Mohamed F Chouikha, "Optimizing the Performance of Network Anomaly Detection Using Bidirectional Long Short-Term Memory (Bi-LSTM) and Over-sampling for Imbalance Network Traffic Data", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 6, pp. 144–154, 2023. doi: 10.25046/aj080614
23. Renhe Chi, "Comparative Study of J48 Decision Tree and CART Algorithm for Liver Cancer Symptom Analysis Using Data from Carnegie Mellon University", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 6, pp. 57–64, 2023. doi: 10.25046/aj080607
24. Ng Kah Kit, Hafeez Ullah Amin, Kher Hui Ng, Jessica Price, Ahmad Rauf Subhani, "EEG Feature Extraction based on Fast Fourier Transform and Wavelet Analysis for Classification of Mental Stress Levels using Machine Learning", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 6, pp. 46–56, 2023. doi: 10.25046/aj080606
25. Nizar Sakli, Chokri Baccouch, Hedia Bellali, Ahmed Zouinkhi, Mustapha Najjari, "IoT System and Deep Learning Model to Predict Cardiovascular Disease Based on ECG Signal", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 6, pp. 08–18, 2023. doi: 10.25046/aj080602
26. Zobeda Hatif Naji Al-azzwi, Alexey N. Nazarov, "MRI Semantic Segmentation based on Optimize V-net with 2D Attention", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 4, pp. 73–80, 2023. doi: 10.25046/aj080409
27. Kohei Okawa, Felix Jimenez, Shuichi Akizuki, Tomohiro Yoshikawa, "Investigating the Impression Effects of a Teacher-Type Robot Equipped a Perplexion Estimation Method on College Students", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 4, pp. 28–35, 2023. doi: 10.25046/aj080404
28. Yu-Jin An, Ha-Young Oh, Hyun-Jong Kim, "Forecasting Bitcoin Prices: An LSTM Deep-Learning Approach Using On-Chain Data", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 3, pp. 186–192, 2023. doi: 10.25046/aj080321
29. Yehan Kodithuwakku, Chanuka Bandara, Ashan Sandanayake, R.A.R Wijesinghe, Velmanickam Logeeshan, "Smart Healthcare Kit for Domestic Purposes", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 3, pp. 170–177, 2023. doi: 10.25046/aj080319
30. Kitipoth Wasayangkool, Kanabadee Srisomboon, Chatree Mahatthanajatuphat, Wilaiporn Lee, "Accuracy Improvement-Based Wireless Sensor Estimation Technique with Machine Learning Algorithms for Volume Estimation on the Sealed Box", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 3, pp. 108–117, 2023. doi: 10.25046/aj080313
31. Chaiyaporn Khemapatapan, Thammanoon Thepsena, "Forecasting the Weather behind Pa Sak Jolasid Dam using Quantum Machine Learning", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 3, pp. 54–62, 2023. doi: 10.25046/aj080307
32. Kangrong Tan, Shozo Tokinaga, "Markov Regime Switching Analysis for COVID-19 Outbreak Situations and their Dynamic Linkages of German Market", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 3, pp. 11–18, 2023. doi: 10.25046/aj080302
33. Mario Cuomo, Federica Massimi, Francesco Benedetto, "Detecting CTC Attack in IoMT Communications using Deep Learning Approach", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 2, pp. 130–138, 2023. doi: 10.25046/aj080215
34. Der-Jiun Pang, "Hybrid Machine Learning Model Performance in IT Project Cost and Duration Prediction", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 2, pp. 108–115, 2023. doi: 10.25046/aj080212
35. Ivana Marin, Sven Gotovac, Vladan Papić, "Development and Analysis of Models for Detection of Olive Trees", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 2, pp. 87–96, 2023. doi: 10.25046/aj080210
36. Paulo Gustavo Quinan, Issa Traoré, Isaac Woungang, Ujwal Reddy Gondhi, Chenyang Nie, "Hybrid Intrusion Detection Using the AEN Graph Model", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 2, pp. 44–63, 2023. doi: 10.25046/aj080206
37. Víctor Manuel Bátiz Beltrán, Ramón Zatarain Cabada, María Lucía Barrón Estrada, Héctor Manuel Cárdenas López, Hugo Jair Escalante, "A Multiplatform Application for Automatic Recognition of Personality Traits in Learning Environments", Advances in Science, Technology and Engineering Systems Journal, vol. 8, no. 2, pp. 30–37, 2023. doi: 10.25046/aj080204
38. Ossama Embarak, "Multi-Layered Machine Learning Model For Mining Learners Academic Performance", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 850–861, 2021. doi: 10.25046/aj060194
39. Anh-Thu Mai, Duc-Huy Nguyen, Thanh-Tin Dang, "Transfer and Ensemble Learning in Real-time Accurate Age and Age-group Estimation", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 6, pp. 262–268, 2022. doi: 10.25046/aj070630
40. Fatima-Zahra Elbouni, Aziza EL Ouaazizi, "Birds Images Prediction with Watson Visual Recognition Services from IBM-Cloud and Conventional Neural Network", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 6, pp. 181–188, 2022. doi: 10.25046/aj070619
41. Roy D Gregori Ayon, Md. Sanaullah Rabbi, Umme Habiba, Maoyejatun Hasana, "Bangla Speech Emotion Detection using Machine Learning Ensemble Methods", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 6, pp. 70–76, 2022. doi: 10.25046/aj070608
42. Bahram Ismailov Israfil, "Deep Learning in Monitoring the Behavior of Complex Technical Systems", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 5, pp. 10–16, 2022. doi: 10.25046/aj070502
43. Deeptaanshu Kumar, Ajmal Thanikkal, Prithvi Krishnamurthy, Xinlei Chen, Pei Zhang, "Analysis of Different Supervised Machine Learning Methods for Accelerometer-Based Alcohol Consumption Detection from Physical Activity", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 4, pp. 147–154, 2022. doi: 10.25046/aj070419
44. Nosiri Onyebuchi Chikezie, Umanah Cyril Femi, Okechukwu Olivia Ozioma, Ajayi Emmanuel Oluwatomisin, Akwiwu-Uzoma Chukwuebuka, Njoku Elvis Onyekachi, Gbenga Christopher Kalejaiye, "BER Performance Evaluation Using Deep Learning Algorithm for Joint Source Channel Coding in Wireless Networks", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 4, pp. 127–139, 2022. doi: 10.25046/aj070417
45. Zhumakhan Nazir, Temirlan Zarymkanov, Jurn-Guy Park, "A Machine Learning Model Selection Considering Tradeoffs between Accuracy and Interpretability", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 4, pp. 72–78, 2022. doi: 10.25046/aj070410
46. Ayoub Benchabana, Mohamed-Khireddine Kholladi, Ramla Bensaci, Belal Khaldi, "A Supervised Building Detection Based on Shadow using Segmentation and Texture in High-Resolution Images", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 3, pp. 166–173, 2022. doi: 10.25046/aj070319
47. Tiny du Toit, Hennie Kruger, Lynette Drevin, Nicolaas Maree, "Deep Learning Affective Computing to Elicit Sentiment Towards Information Security Policies", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 3, pp. 152–160, 2022. doi: 10.25046/aj070317
48. Kaito Echizenya, Kazuhiro Kondo, "Indoor Position and Movement Direction Estimation System Using DNN on BLE Beacon RSSI Fingerprints", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 3, pp. 129–138, 2022. doi: 10.25046/aj070315
49. Jayan Kant Duggal, Mohamed El-Sharkawy, "High Performance SqueezeNext: Real time deployment on Bluebox 2.0 by NXP", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 3, pp. 70–81, 2022. doi: 10.25046/aj070308
50. Edgard Musafiri Mimo, Troy McDaniel, Jeremie Biringanine Ruvunangiza, "COVIDFREE App: The User-Enabling Contact Prevention Application: A Review", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 2, pp. 149–155, 2022. doi: 10.25046/aj070215
51. Sreela Sreekumaran Pillai Remadevi Amma, Sumam Mary Idicula, "A Unified Visual Saliency Model for Automatic Image Description Generation for General and Medical Images", Advances in Science, Technology and Engineering Systems Journal, vol. 7, no. 2, pp. 119–126, 2022. doi: 10.25046/aj070211
52. Seok-Jun Bu, Hae-Jung Kim, "Ensemble Learning of Deep URL Features based on Convolutional Neural Network for Phishing Attack Detection", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 5, pp. 291–296, 2021. doi: 10.25046/aj060532
53. Osaretin Eboya, Julia Binti Juremi, "iDRP Framework: An Intelligent Malware Exploration Framework for Big Data and Internet of Things (IoT) Ecosystem", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 5, pp. 185–202, 2021. doi: 10.25046/aj060521
54. Arwa Alghamdi, Graham Healy, Hoda Abdelhafez, "Machine Learning Algorithms for Real Time Blind Audio Source Separation with Natural Language Detection", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 5, pp. 125–140, 2021. doi: 10.25046/aj060515
55. Baida Ouafae, Louzar Oumaima, Ramdi Mariam, Lyhyaoui Abdelouahid, "Survey on Novelty Detection using Machine Learning Techniques", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 5, pp. 73–82, 2021. doi: 10.25046/aj060510
56. Radwan Qasrawi, Stephanny VicunaPolo, Diala Abu Al-Halawa, Sameh Hallaq, Ziad Abdeen, "Predicting School Children Academic Performance Using Machine Learning Techniques", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 5, pp. 08–15, 2021. doi: 10.25046/aj060502
57. Fatima-Ezzahra Lagrari, Youssfi Elkettani, "Traditional and Deep Learning Approaches for Sentiment Analysis: A Survey", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 5, pp. 01–07, 2021. doi: 10.25046/aj060501
58. Zhiyuan Chen, Howe Seng Goh, Kai Ling Sin, Kelly Lim, Nicole Ka Hei Chung, Xin Yu Liew, "Automated Agriculture Commodity Price Prediction System with Machine Learning Techniques", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 4, pp. 376–384, 2021. doi: 10.25046/aj060442
59. Hathairat Ketmaneechairat, Maleerat Maliyaem, Chalermpong Intarat, "Kamphaeng Saen Beef Cattle Identification Approach using Muzzle Print Image", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 4, pp. 110–122, 2021. doi: 10.25046/aj060413
60. Anjali Banga, Pradeep Kumar Bhatia, "Optimized Component based Selection using LSTM Model by Integrating Hybrid MVO-PSO Soft Computing Technique", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 4, pp. 62–71, 2021. doi: 10.25046/aj060408
61. Md Mahmudul Hasan, Nafiul Hasan, Dil Afroz, Ferdaus Anam Jibon, Md. Arman Hossen, Md. Shahrier Parvage, Jakaria Sulaiman Aongkon, "Electroencephalogram Based Medical Biometrics using Machine Learning: Assessment of Different Color Stimuli", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 3, pp. 27–34, 2021. doi: 10.25046/aj060304
62. Eralda Gjika, Lule Basha, Llukan Puka, "An Analysis of the Reliability of Reported COVID-19 Data in Western Balkan Countries", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 1055–1064, 2021. doi: 10.25046/aj0602120
63. Nadia Jmour, Slim Masmoudi, Afef Abdelkrim, "A New Video Based Emotions Analysis System (VEMOS): An Efficient Solution Compared to iMotions Affectiva Analysis Software", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 990–1001, 2021. doi: 10.25046/aj0602114
64. Bakhtyar Ahmed Mohammed, Muzhir Shaban Al-Ani, "Follow-up and Diagnose COVID-19 Using Deep Learning Technique", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 971–976, 2021. doi: 10.25046/aj0602111
65. Showkat Ahmad Dar, S Palanivel, "Performance Evaluation of Convolutional Neural Networks (CNNs) And VGG on Real Time Face Recognition System", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 956–964, 2021. doi: 10.25046/aj0602109
66. Dominik Štursa, Daniel Honc, Petr Doležel, "Efficient 2D Detection and Positioning of Complex Objects for Robotic Manipulation Using Fully Convolutional Neural Network", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 915–920, 2021. doi: 10.25046/aj0602104
67. Kenza Aitelkadi, Hicham Outmghoust, Salahddine laarab, Kaltoum Moumayiz, Imane Sebari, "Detection and Counting of Fruit Trees from RGB UAV Images by Convolutional Neural Networks Approach", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 887–893, 2021. doi: 10.25046/aj0602101
68. Binghan Li, Yindong Hua, Mi Lu, "Advanced Multiple Linear Regression Based Dark Channel Prior Applied on Dehazing Image and Generating Synthetic Haze", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 790–800, 2021. doi: 10.25046/aj060291
69. Md Mahmudul Hasan, Nafiul Hasan, Mohammed Saud A Alsubaie, "Development of an EEG Controlled Wheelchair Using Color Stimuli: A Machine Learning Based Approach", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 754–762, 2021. doi: 10.25046/aj060287
70. Abraham Adiputra Wijaya, Inten Yasmina, Amalia Zahra, "Indonesian Music Emotion Recognition Based on Audio with Deep Learning Approach", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 716–721, 2021. doi: 10.25046/aj060283
71. Antoni Wibowo, Inten Yasmina, Antoni Wibowo, "Food Price Prediction Using Time Series Linear Ridge Regression with The Best Damping Factor", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 694–698, 2021. doi: 10.25046/aj060280
72. Nestor Alvarado-Bravo, Florcita Aldana-Trejo, Almintor Torres-Quiroz, Carlos Aliaga-Valdez, William Angulo-Pomiano, Frank Escobedo-Bailón, Katherin Rodriguez-Zevallos, Carlos Dávila-Ignacio, Omar Chamorro-Atalaya, "The Context of the Covid-19 Pandemic and its Effect on the Self-Perception of Professional Competences by University Students of Business Administration", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 665–670, 2021. doi: 10.25046/aj060277
73. Javier E. Sánchez-Galán, Fatima Rangel Barranco, Jorge Serrano Reyes, Evelyn I. Quirós-McIntire, José Ulises Jiménez, José R. Fábrega, "Using Supervised Classification Methods for the Analysis of Multi-spectral Signatures of Rice Varieties in Panama", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 552–558, 2021. doi: 10.25046/aj060262
74. Phillip Blunt, Bertram Haskins, "A Model for the Application of Automatic Speech Recognition for Generating Lesson Summaries", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 526–540, 2021. doi: 10.25046/aj060260
75. Abdulla M. Alsharhan, "Survey of Agent-Based Simulations for Modelling COVID-19 Pandemic", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 439–447, 2021. doi: 10.25046/aj060250
76. Shahnaj Parvin, Liton Jude Rozario, Md. Ezharul Islam, "Vehicle Number Plate Detection and Recognition Techniques: A Review", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 423–438, 2021. doi: 10.25046/aj060249
77. Majda Lakhal, Mohamed Benslimane, Mehdi Tmimi, Abdelali Ibriz, "Architecture of Real-Time Patient Health Monitoring Based on 5G Technologies", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 351–358, 2021. doi: 10.25046/aj060240
78. Sebastianus Bara Primananda, Sani Muhamad Isa, "Forecasting Gold Price in Rupiah using Multivariate Analysis with LSTM and GRU Neural Networks", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 245–253, 2021. doi: 10.25046/aj060227
79. Meng-Chang Jong, Chin-Hong Puah, Ann-Ni Soh, "The Impact of COVID-19 Pandemic and Commodities Prices on Booking.com Share Price", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 185–189, 2021. doi: 10.25046/aj060221
80. Tan Pey Fang, Wan Ramli Wan Daud, Lilia Halim, Mohd Shahbudin Masdar, "How Ready is Renewable Energy? A Review Paper on Educational Materials and Reports Available for the Teaching of Hydrogen Fuel Cells in Schools", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 01–11, 2021. doi: 10.25046/aj060201
81. Prasham Shah, Mohamed El-Sharkawy, "A-MnasNet and Image Classification on NXP Bluebox 2.0", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 1378–1383, 2021. doi: 10.25046/aj0601157
82. Byeongwoo Kim, Jongkyu Lee, "Fault Diagnosis and Noise Robustness Comparison of Rotating Machinery using CWT and CNN", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 1279–1285, 2021. doi: 10.25046/aj0601146
83. Almahasees Zakaryia, Al-Taher Mohammad, Helene Jaccomard, "Evaluation of Facebook Translation Service (FTS) in Translating Facebook Posts from English into Arabic in Terms of TAUS Adequacy and Fluency during Covid-19", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 1241–1248, 2021. doi: 10.25046/aj0601141
84. Teodoro Díaz-Leyva, Nestor Alvarado-Bravo, Jorge Sánchez-Ayte, Almintor Torres-Quiroz, Carlos Dávila-Ignacio, Florcita Aldana-Trejo, José Razo-Quispe, Omar Chamorro-Atalaya, "Variation in Self-Perception of Professional Competencies in Systems Engineering Students, due to the COVID -19 Pandemic", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 1024–1029, 2021. doi: 10.25046/aj0601113
85. Alisson Steffens Henrique, Anita Maria da Rocha Fernandes, Rodrigo Lyra, Valderi Reis Quietinho Leithardt, Sérgio D. Correia, Paul Crocker, Rudimar Luis Scaranto Dazzi, "Classifying Garments from Fashion-MNIST Dataset Through CNNs", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 989–994, 2021. doi: 10.25046/aj0601109
86. Md Mahmudul Hasan, Nafiul Hasan, Mohammed Saud A Alsubaie, Md Mostafizur Rahman Komol, "Diagnosis of Tobacco Addiction using Medical Signal: An EEG-based Time-Frequency Domain Analysis Using Machine Learning", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 842–849, 2021. doi: 10.25046/aj060193
87. Abdulla M. Alsharhan, "Simulating COVID-19 Trajectory in the UAE and the Impact of Possible Intervention Scenarios", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 791–797, 2021. doi: 10.25046/aj060188
88. Reem Bayari, Ameur Bensefia, "Text Mining Techniques for Cyberbullying Detection: State of the Art", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 783–790, 2021. doi: 10.25046/aj060187
89. Inna Valieva, Iurii Voitenko, Mats Björkman, Johan Åkerberg, Mikael Ekström, "Multiple Machine Learning Algorithms Comparison for Modulation Type Classification Based on Instantaneous Values of the Time Domain Signal and Time Series Statistics Derived from Wavelet Transform", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 658–671, 2021. doi: 10.25046/aj060172
90. Carlos López-Bermeo, Mauricio González-Palacio, Lina Sepúlveda-Cano, Rubén Montoya-Ramírez, César Hidalgo-Montoya, "Comparison of Machine Learning Parametric and Non-Parametric Techniques for Determining Soil Moisture: Case Study at Las Palmas Andean Basin", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 636–650, 2021. doi: 10.25046/aj060170
91. Imane Jebli, Fatima-Zahra Belouadha, Mohammed Issam Kabbaj, Amine Tilioua, "Deep Learning based Models for Solar Energy Prediction", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 349–355, 2021. doi: 10.25046/aj060140
92. Ndiatenda Ndou, Ritesh Ajoodha, Ashwini Jadhav, "A Case Study to Enhance Student Support Initiatives Through Forecasting Student Success in Higher-Education", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 230–241, 2021. doi: 10.25046/aj060126
93. Lonia Masangu, Ashwini Jadhav, Ritesh Ajoodha, "Predicting Student Academic Performance Using Data Mining Techniques", Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 153–163, 2021. doi: 10.25046/aj060117
94. Yen-Hung Chen, Tin-Chang Chang, "Analysis and Evaluation of Competitiveness in Medical Tourism Industry in Taiwan", Advances in Science, Technology and Engineering Systems Journal, vol. 5, no. 6, pp. 1690–1697, 2020. doi: 10.25046/aj0506201
95. Xianxian Luo, Songya Xu, Hong Yan, "Application of Deep Belief Network in Forest Type Identification using Hyperspectral Data", Advances in Science, Technology and Engineering Systems Journal, vol. 5, no. 6, pp. 1554–1559, 2020. doi: 10.25046/aj0506186
96. Bilal Babayigit, Eda Nur Hascokadar, "A Software-Defined Network Approach for The Best Hospital Localization Against Coronavirus (COVID-19)", Advances in Science, Technology and Engineering Systems Journal, vol. 5, no. 6, pp. 1537–1544, 2020. doi: 10.25046/aj0506184
97. Sara Ftaimi, Tomader Mazri, "Handling Priority Data in Smart Transportation System by using Support Vector Machine Algorithm", Advances in Science, Technology and Engineering Systems Journal, vol. 5, no. 6, pp. 1422–1427, 2020. doi: 10.25046/aj0506172
98. Othmane Rahmaoui, Kamal Souali, Mohammed Ouzzif, "Towards a Documents Processing Tool using Traceability Information Retrieval and Content Recognition Through Machine Learning in a Big Data Context", Advances in Science, Technology and Engineering Systems Journal, vol. 5, no. 6, pp. 1267–1277, 2020. doi: 10.25046/aj0506151
99. Majdouline Meddad, Chouaib Moujahdi, Mounia Mikram, Mohammed Rziza, "Optimization of Multi-user Face Identification Systems in Big Data Environments", Advances in Science, Technology and Engineering Systems Journal, vol. 5, no. 6, pp. 762–767, 2020. doi: 10.25046/aj050691
100. Zakaryia Almahasees, Helene Jaccomard, "Facebook Translation Service (FTS) Usage among Jordanians during COVID-19 Lockdown", Advances in Science, Technology and Engineering Systems Journal, vol. 5, no. 6, pp. 514–519, 2020. doi: 10.25046/aj050661