Turbine recommender: The selection of wind turbine type using one of a machine learning technique

This study aims to utilize the machine learning technique to build a model to recommend the suitable wind turbine type based on some variables, such as air speed and air density, as well as visualize the location of the recommended wind turbine selection on a 3D map. Particularly, we applied the K-nearest neighbor model (KNN) to determine the amount of energy produced by a single wind turbine. We applied it on 10 separate wind farms in Saudi Arabia. The results indicate that the model performs very well in predicting the best wind turbine type with the mean accuracy of 88%, where ten wind stations resulted from the optimized model with the suggested turbine type in each station. Adding more wind attributes and other factors may assist in increasing the model mean accuracy. The project’s findings will assist decision-makers in Saudi Arabia to make informed decisions as to what kind of wind turbine is suitable for a specific location. In the long run, this will help to make wind energy-a sustainable source of energy-one of the main goals of the 2030 vision, specifically under National Industrial Development and Logistics Program.

Malware Classification Using Machine Learning and Image Processing

Malware is routinely used for illegal reasons, and new malware variants are discovered every day. Computer vision in computer security is one of the most significant disciplines of research today, and it has witnessed tremendous growth in the preceding decade due to its efficacy. We employed research in machine-learning and deep-learning technology such as Logistic Regression, ANN, CNN, transfer learning on CNN, and LSTM to arrive at our conclusions. We have published analysis-based results from a range of categorization models in the literature. InceptionV3 was trained using a transfer learning technique, which yielded reasonable results when compared with other methods such as LSTM. On the test dataset, the transferring learning technique was about 98.76 percent accurate, while on the train dataset, it was around 99.6 percent accurate. Keywords: Malware, illegal activity, Deep learning, Network Security,

Automatic Diagnosis of Alzheimer’s disease using Hybrid Model and CNN

Since the past decade, the deep learning techniques are widely used in research. The objective of various applications is achieved using these techniques. The deep learning technique in the medical field helps to find medicines and diagnosis of diseases. The Alzheimer’s is a physical brain disease, on which recently many research are experimented to develop an efficient model that diagnoses the early stages of Alzheimer’s disease. In this paper, a Hybrid model is proposed, which is a combination of VGG19 with additional layers, and a CNN deep learning model for detecting and classifying the different stages of Alzheimer’s and the performance is compared with the CNN model. The Magnetic Resonance Images are used to analyse both models received from the Kaggle dataset. The result shows that the Hybrid model works efficiently in detecting and classifying the different stages of Alzheimer’s.

Classification of Stages Diabetic Retinopathy Using MobileNetV2 Model

Diabetic retinopathy (DR) is a complication of diabetes mellitus that causes retinal damage that can lead to vision loss if not detected and treated promptly. The common diagnosis stages of the disease take time, effort, and cost and can be misdiagnosed. In the recent period with the explosion of artificial intelligence, deep learning has become the most popular tool with high performance in many fields, especially in the analysis and classification of medical images. The Convolutional Neural Network (CNN) is more widely used as a deep learning method in medical imaging analysis with highly effective. In this paper, the five-stage image of modern DR (healthy, mild, moderate, severe, and proliferative) can be detected and classified using the deep learning technique. After cross-validation training and testing on the corresponding 5,590-image dataset, a pre-MobileNetV2 training model is proposed in classifying stages of diabetic retinopathy. The average accuracy of the model achieved was 93.89% with the precision of 94.00%, recall 92.00% and f1-score 90.00%. The corresponding thermal image is also given to help experts for evaluating the influence of the retina in each different stage.

A Transfer Learning Evaluation of Deep Neural Networks for Image Classification

Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages in achieving high performance while saving training time, memory, and effort in network design. In this paper, we investigate how to select the best pre-trained model that meets the target domain requirements for image classification tasks. In our study, we refined the output layers and general network parameters to apply the knowledge of eleven image processing models, pre-trained on ImageNet, to five different target domain datasets. We measured the accuracy, accuracy density, training time, and model size to evaluate the pre-trained models both in training sessions in one episode and with ten episodes.

Privacy-Preserving Federated Learning Using Homomorphic Encryption

Federated learning (FL) is a machine learning technique that enables distributed devices to train a learning model collaboratively without sharing their local data. FL-based systems can achieve much stronger privacy preservation since the distributed devices deliver only local model parameters trained with local data to a centralized server. However, there exists a possibility that a centralized server or attackers infer/extract sensitive private information using the structure and parameters of local learning models. We propose employing homomorphic encryption (HE) scheme that can directly perform arithmetic operations on ciphertexts without decryption to protect the model parameters. Using the HE scheme, the proposed privacy-preserving federated learning (PPFL) algorithm enables the centralized server to aggregate encrypted local model parameters without decryption. Furthermore, the proposed algorithm allows each node to use a different HE private key in the same FL-based system using a distributed cryptosystem. The performance analysis and evaluation of the proposed PPFL algorithm are conducted in various cloud computing-based FL service scenarios.

Virtual Healthcare Center for COVID-19 Patient Detection Based on Artificial Intelligence Approaches

At the end of 2019, the infectious coronavirus disease (COVID-19) was reported for the first time in Wuhan, and, since then, it has become a public health issue in China and even worldwide. This pandemic has devastating effects on societies and economies around the world, and poor countries and continents are likely to face particularly serious and long-lasting damage, which could lead to large epidemic outbreaks because of the lack of financial and health resources. The increasing number of COVID-19 tests gives more information about the epidemic spread, and this can help contain the spread to avoid more infection. As COVID-19 keeps spreading, medical products, especially those needed to perform blood tests, will become scarce as a result of the high demand and insufficient supply and logistical means. However, technological tests based on deep learning techniques and medical images could be useful in fighting this pandemic. In this perspective, we propose a COVID-19 disease diagnosis (CDD) tool that implements a deep learning technique to provide automatic symptoms checking and COVID-19 detection. Our CDD scheme implements two main steps. First, the patient’s symptoms are checked, and the infection probability is predicted. Then, based on the infection probability, the patient’s lungs will be diagnosed by an automatic analysis of X-ray or computerized tomography (CT) images, and the presence of the infection will be accordingly confirmed or not. The numerical results prove the efficiency of the proposed scheme by achieving an accuracy value over 90% compared with the other schemes.

A deep learning technique-based data-driven model for accurate and rapid flood prediction

An accurate and rapid urban flood prediction model is essential to support decision-making on flood management, especially under increasing extreme precipitation conditions driven by climate change and urbanization. This study developed a deep learning technique-based data-driven flood prediction model based on an integration of LSTM network and Bayesian optimization. A case study in north China was applied to test the model performance and the results clearly showed that the model can accurately predict flood maps for various hyetograph inputs, meanwhile with substantial improvements in computation time. The model predicted flood maps 19,585 times faster than the physical-based hydrodynamic model and achieved a mean relative error of 9.5 %. For retrieving the spatial patterns of water depths, the degree of similarity of the flood maps was very high. In a best case, the difference between the ground truth and model prediction was only 0.76 % and the spatial distributions of inundated paths and areas were almost identical. The proposed model showed a robust generalizability and high computational efficiency, and can potentially replace and/or complement the conventional hydrodynamic model for urban flood assessment and management, particularly in applications of real time control, optimization and emergency design and plan.