Enhancing genome-wide populus trait prediction through deep convolutional neural networks.

As a promising model, genome-based plant breeding has greatly promoted the improvement of agronomic traits. Traditional methods typically adopt linear regression models with clear assumptions, neither obtaining the linkage between phenotype and genotype nor providing good ideas for modification. Nonlinear models are well characterized in capturing complex nonadditive effects, filling this gap under traditional methods. Taking populus as the research object, this paper constructs a deep learning method, DCNGP, which can effectively predict the traits including 65 phenotypes. The method was trained on three datasets, and compared with other four classic models-Bayesian ridge regression (BRR), Elastic Net, support vector regression, and dualCNN. The results show that DCNGP has five typical advantages in performance: strong prediction ability on multiple experimental datasets; the incorporation of batch normalization layers and Early-Stopping technology enhancing the generalization capabilities and prediction stability on test data; learning potent features from the data and thus circumventing the tedious steps of manual production; the introduction of a Gaussian Noise layer enhancing predictive capabilities in the case of inherent uncertainties or perturbations; fewer hyperparameters aiding to reduce tuning time across datasets and improve auto-search efficiency. In this way, DCNGP shows powerful predictive ability from genotype to phenotype, which provide an important theoretical reference for building more robust populus breeding programs.

Optimized encoder-decoder cascaded deep convolutional network for leaf disease image segmentation.

Nowadays, Deep Learning (DL) techniques are being used to automate the identification and diagnosis of plant diseases, thereby enhancing global food security and enabling non-experts to detect these diseases. Among many DL techniques, a Deep Encoder-Decoder Cascaded Network (DEDCNet) model can precisely segment diseased areas from the leaf images to differentiate and classify multiple diseases. On the other hand, the model training depends on the appropriate selection of hyperparameters. Also, this network structure has weak robustness with different parameters. Hence, in this manuscript, an Optimized DEDCNet (ODEDCNet) model is proposed for improved leaf disease image segmentation. To choose the best DEDCNet hyperparameters, a brand-new Dingo Optimization Algorithm (DOA) is included in this model. The DOA depends on the foraging nature of dingoes, which comprises exploration and exploitation phases. In exploration, it attains many predictable decisions in the search area, whereas exploitation enables exploring the best decisions in a provided area. The segmentation accuracy is used as the fitness value of each dingo for hyperparameter selection. By configuring the chosen hyperparameters, the DEDCNet is trained to segment the leaf disease regions. The segmented images are further given to the pre-trained Convolutional Neural Networks (CNNs) followed by the Support Vector Machine (SVM) for classifying leaf diseases. ODEDCNet performs exceptionally well on the PlantVillage and Betel Leaf Image datasets, attaining an astounding 97.33% accuracy on the former and 97.42% accuracy on the latter. Both datasets achieve noteworthy recall, F-score, Dice coefficient, and precision values: the Betel Leaf Image dataset shows values of 97.4%, 97.29%, 97.35%, and 0.9897; the PlantVillage dataset shows values of 97.5%, 97.42%, 97.46%, and 0.9901, all completed in remarkably short processing times of 0.07 and 0.06 seconds, respectively. The achieved outcomes are evaluated with the contemporary optimization algorithms using the considered datasets to comprehend the efficiency of DOA.

A hybrid deep CNN model for brain tumor image multi-classification.

The current approach to diagnosing and classifying brain tumors relies on the histological evaluation of biopsy samples, which is invasive, time-consuming, and susceptible to manual errors. These limitations underscore the pressing need for a fully automated, deep-learning-based multi-classification system for brain malignancies. This article aims to leverage a deep convolutional neural network (CNN) to enhance early detection and presents three distinct CNN models designed for different types of classification tasks. The first CNN model achieves an impressive detection accuracy of 99.53% for brain tumors. The second CNN model, with an accuracy of 93.81%, proficiently categorizes brain tumors into five distinct types: normal, glioma, meningioma, pituitary, and metastatic. Furthermore, the third CNN model demonstrates an accuracy of 98.56% in accurately classifying brain tumors into their different grades. To ensure optimal performance, a grid search optimization approach is employed to automatically fine-tune all the relevant hyperparameters of the CNN models. The utilization of large, publicly accessible clinical datasets results in robust and reliable classification outcomes. This article conducts a comprehensive comparison of the proposed models against classical models, such as AlexNet, DenseNet121, ResNet-101, VGG-19, and GoogleNet, reaffirming the superiority of the deep CNN-based approach in advancing the field of brain tumor classification and early detection.

A Novel Approach to Detect Drones Using Deep Convolutional Neural Network Architecture.

Over the past decades, drones have become more attainable by the public due to their widespread availability at affordable prices. Nevertheless, this situation sparks serious concerns in both the cyber and physical security domains, as drones can be employed for malicious activities with public safety threats. However, detecting drones instantly and efficiently is a very difficult task due to their tiny size and swift flights. This paper presents a novel drone detection method using deep convolutional learning and deep transfer learning. The proposed algorithm employs a new feature extraction network, which is added to the modified YOU ONLY LOOK ONCE version2 (YOLOv2) network. The feature extraction model uses bypass connections to learn features from the training sets and solves the "vanishing gradient" problem caused by the increasing depth of the network. The structure of YOLOv2 is modified by replacing the rectified linear unit (relu) with a leaky-relu activation function and adding an extra convolutional layer with a stride of 2 to improve the small object detection accuracy. Using leaky-relu solves the "dying relu" problem. The additional convolution layer with a stride of 2 reduces the spatial dimensions of the feature maps and helps the network to focus on larger contextual information while still preserving the ability to detect small objects. The model is trained with a custom dataset that contains various types of drones, airplanes, birds, and helicopters under various weather conditions. The proposed model demonstrates a notable performance, achieving an accuracy of 77% on the test images with only 5 million learnable parameters in contrast to the Darknet53 + YOLOv3 model, which exhibits a 54% accuracy on the same test set despite employing 62 million learnable parameters.

PSTCNN: Explainable COVID-19 diagnosis using PSO-guided self-tuning CNN.

Since 2019, the coronavirus disease-19 (COVID-19) has been spreading rapidly worldwide, posing an unignorable threat to the global economy and human health. It is a disease caused by severe acute respiratory syndrome coronavirus 2, a single-stranded RNA virus of the genus Betacoronavirus. This virus is highly infectious and relies on its angiotensin-converting enzyme 2-receptor to enter cells. With the increase in the number of confirmed COVID-19 diagnoses, the difficulty of diagnosis due to the lack of global healthcare resources becomes increasingly apparent. Deep learning-based computer-aided diagnosis models with high generalisability can effectively alleviate this pressure. Hyperparameter tuning is essential in training such models and significantly impacts their final performance and training speed. However, traditional hyperparameter tuning methods are usually time-consuming and unstable. To solve this issue, we introduce Particle Swarm Optimisation to build a PSO-guided Self-Tuning Convolution Neural Network (PSTCNN), allowing the model to tune hyperparameters automatically. Therefore, the proposed approach can reduce human involvement. Also, the optimisation algorithm can select the combination of hyperparameters in a targeted manner, thus stably achieving a solution closer to the global optimum. Experimentally, the PSTCNN can obtain quite excellent results, with a sensitivity of 93.65%±1.86%, a specificity of 94.32%±2.07%, a precision of 94.30%±2.04%, an accuracy of 93.99%±1.78%, an F1-score of 93.97%±1.78%, Matthews Correlation Coefficient of 87.99%±3.56%, and Fowlkes-Mallows Index of 93.97%±1.78%. Our experiments demonstrate that compared to traditional methods, hyperparameter tuning of the model using an optimisation algorithm is faster and more effective.

Deep SE-BiLSTM with IFPOA Fine-Tuning for Human Activity Recognition Using Mobile and Wearable Sensors.

Pervasive computing, human-computer interaction, human behavior analysis, and human activity recognition (HAR) fields have grown significantly. Deep learning (DL)-based techniques have recently been effectively used to predict various human actions using time series data from wearable sensors and mobile devices. The management of time series data remains difficult for DL-based techniques, despite their excellent performance in activity detection. Time series data still has several problems, such as difficulties in heavily biased data and feature extraction. For HAR, an ensemble of Deep SqueezeNet (SE) and bidirectional long short-term memory (BiLSTM) with improved flower pollination optimization algorithm (IFPOA) is designed to construct a reliable classification model utilizing wearable sensor data in this research. The significant features are extracted automatically from the raw sensor data by multi-branch SE-BiLSTM. The model can learn both short-term dependencies and long-term features in sequential data due to SqueezeNet and BiLSTM. The different temporal local dependencies are captured effectively by the proposed model, enhancing the feature extraction process. The hyperparameters of the BiLSTM network are optimized by the IFPOA. The model performance is analyzed using three benchmark datasets: MHEALTH, KU-HAR, and PAMPA2. The proposed model has achieved 99.98%, 99.76%, and 99.54% accuracies on MHEALTH, KU-HAR, and PAMPA2 datasets, respectively. The proposed model performs better than other approaches from the obtained experimental results. The suggested model delivers competitive results compared to state-of-the-art techniques, according to experimental results on four publicly accessible datasets.

Haulage Cycles Identification for Wheeled Transport in Underground Mine Using Neural Networks.

The task of ore transportation is performed in all mines, regardless of their type (open pit/underground) or mining process. A substantial number of enterprises utilize wheeled machines to perform ore haulage, especially haul trucks and loaders. These machines' work consists of repeating cycles, and each cycle can be divided into 4 operations: loading, driving with full box/bucket, unloading and driving with empty box/bucket. Monitoring this process is essential to create analytical tools that support foremen and other management crew in achieving effective and optimal production and planning activities. Unfortunately, information gathered regarding the process is frequently based on operators' oral testimony. This process not only allows for abuse but is also a repetitive and tedious task that must be performed by foremen. The time and attention of foremen is valuable as they are responsible for managing practically everything in their current mine section (machines, operators, works, repairs, emergencies, safety, etc.). Therefore, the automatization of the described process of information gathering should be performed. In this article, we present two neural network models (one for haul trucks and one for loaders) build for detecting work cycles of the ore haulage process. Both models were built utilizing a 2-stage approach. In the first stage, the models' structures were optimized, while the second was focused on optimizing hyperparameters for the structure with best performance. Both of the proposed models were trained using data collected from on-board monitoring systems over hundreds of the machines' work hours and utilized the same input features: vehicle speed, fuel consumption, selected gear and engine rotational speed. Models have been subjected to comprehensive testing during which the efficiency and stability of the model responsible for haul trucks was proven. Results for loaders were not as high quality for haul trucks; however, some interesting facts were discovered that indicate possible directions for future development.

Optimal Reactive Power Dispatch in ADNs using DRL and the Impact of Its Various Settings and Environmental Changes.

Modern active distribution networks (ADNs) witness increasing complexities that require efforts in control practices, including optimal reactive power dispatch (ORPD). Deep reinforcement learning (DRL) is proposed to manage the network's reactive power by coordinating different resources, including distributed energy resources, to enhance performance. However, there is a lack of studies examining DRL elements' performance sensitivity. To this end, in this paper we examine the impact of various DRL reward representations and hyperparameters on the agent's learning performance when solving the ORPD problem for ADNs. We assess the agent's performance regarding accuracy and training time metrics, as well as critic estimate measures. Furthermore, different environmental changes are examined to study the DRL model's scalability by including other resources. Results show that compared to other representations, the complementary reward function exhibits improved performance in terms of power loss minimization and convergence time by 10-15% and 14-18%, respectively. Also, adequate agent performance is observed to be neighboring the best-suited value of each hyperparameter for the studied problem. In addition, scalability analysis depicts that increasing the number of possible action combinations in the action space by approximately nine times results in 1.7 times increase in the training time.

Finding the Right Solvent: A Novel Screening Protocol for Identifying Environmentally Friendly and Cost-Effective Options for Benzenesulfonamide.

This study investigated the solubility of benzenesulfonamide (BSA) as a model compound using experimental and computational methods. New experimental solubility data were collected in the solvents DMSO, DMF, 4FM, and their binary mixtures with water. The predictive model was constructed based on the best-performing regression models trained on available experimental data, and their hyperparameters were optimized using a newly developed Python code. To evaluate the models, a novel scoring function was formulated, considering not only the accuracy but also the bias-variance tradeoff through a learning curve analysis. An ensemble approach was adopted by selecting the top-performing regression models for test and validation subsets. The obtained model accurately back-calculated the experimental data and was used to predict the solubility of BSA in 2067 potential solvents. The analysis of the entire solvent space focused on the identification of solvents with high solubility, a low environmental impact, and affordability, leading to a refined list of potential candidates that meet all three requirements. The proposed procedure has general applicability and can significantly improve the quality and speed of experimental solvent screening.

Compressive Sensing via Variational Bayesian Inference under Two Widely Used Priors: Modeling, Comparison and Discussion.

Compressive sensing is a sub-Nyquist sampling technique for efficient signal acquisition and reconstruction of sparse or compressible signals. In order to account for the sparsity of the underlying signal of interest, it is common to use sparsifying priors such as Bernoulli-Gaussian-inverse Gamma (BGiG) and Gaussian-inverse Gamma (GiG) priors on the components of the signal. With the introduction of variational Bayesian inference, the sparse Bayesian learning (SBL) methods for solving the inverse problem of compressive sensing have received significant interest as the SBL methods become more efficient in terms of execution time. In this paper, we consider the sparse signal recovery problem using compressive sensing and the variational Bayesian (VB) inference framework. More specifically, we consider two widely used Bayesian models of BGiG and GiG for modeling the underlying sparse signal for this problem. Although these two models have been widely used for sparse recovery problems under various signal structures, the question of which model can outperform the other for sparse signal recovery under no specific structure has yet to be fully addressed under the VB inference setting. Here, we study these two models specifically under VB inference in detail, provide some motivating examples regarding the issues in signal reconstruction that may occur under each model, perform comparisons and provide suggestions on how to improve the performance of each model.

An Enhanced Hyper-Parameter Optimization of a Convolutional Neural Network Model for Leukemia Cancer Diagnosis in a Smart Healthcare System.

Healthcare systems in recent times have witnessed timely diagnoses with a high level of accuracy. Internet of Medical Things (IoMT)-enabled deep learning (DL) models have been used to support medical diagnostics in real time, thus resolving the issue of late-stage diagnosis of various diseases and increasing performance accuracy. The current approach for the diagnosis of leukemia uses traditional procedures, and in most cases, fails in the initial period. Hence, several patients suffering from cancer have died prematurely due to the late discovery of cancerous cells in blood tissue. Therefore, this study proposes an IoMT-enabled convolutional neural network (CNN) model to detect malignant and benign cancer cells in the patient's blood tissue. In particular, the hyper-parameter optimization through radial basis function and dynamic coordinate search (HORD) optimization algorithm was used to search for optimal values of CNN hyper-parameters. Utilizing the HORD algorithm significantly increased the effectiveness of finding the best solution for the CNN model by searching multidimensional hyper-parameters. This implies that the HORD method successfully found the values of hyper-parameters for precise leukemia features. Additionally, the HORD method increased the performance of the model by optimizing and searching for the best set of hyper-parameters for the CNN model. Leukemia datasets were used to evaluate the performance of the proposed model using standard performance indicators. The proposed model revealed significant classification accuracy compared to other state-of-the-art models.

A Probability-Based Models Ranking Approach: An Alternative Method of Machine-Learning Model Performance Assessment.

Performance measures are crucial in selecting the best machine learning model for a given problem. Estimating classical model performance measures by subsampling methods like bagging or cross-validation has several weaknesses. The most important ones are the inability to test the significance of the difference, and the lack of interpretability. Recently proposed Elo-based Predictive Power (EPP)-a meta-measure of machine learning model performance, is an attempt to address these weaknesses. However, the EPP is based on wrong assumptions, so its estimates may not be correct. This paper introduces the Probability-based Ranking Model Approach (PMRA), which is a modified EPP approach with a correction that makes its estimates more reliable. PMRA is based on the calculation of the probability that one model achieves a better result than another one, using the Mixed Effects Logistic Regression model. The empirical analysis was carried out on a real mortgage credits dataset. The analysis included a comparison of how the PMRA and state-of-the-art k-fold cross-validation ranked the 49 machine learning models, an example application of a novel method in hyperparameters tuning problem, and a comparison of PMRA and EPP indications. PMRA gives the opportunity to compare a newly developed algorithm to state-of-the-art algorithms based on statistical criteria. It is the solution to select the best hyperparameters configuration and to formulate criteria for the continuation of the hyperparameters space search.

Classification of Ear Imagery Database using Bayesian Optimization based on CNN-LSTM Architecture.

The external and middle ear conditions are diagnosed using a digital otoscope. The clinical diagnosis of ear conditions is suffered from restricted accuracy due to the increased dependency on otolaryngologist expertise, patient complaint, blurring of the otoscopic images, and complexity of lesions definition. There is a high requirement for improved diagnosis algorithms based on otoscopic image processing. This paper presented an ear diagnosis approach based on a convolutional neural network (CNN) as feature extraction and long short-term memory (LSTM) as a classifier algorithm. However, the suggested LSTM model accuracy may be decreased by the omission of a hyperparameter tuning process. Therefore, Bayesian optimization is used for selecting the hyperparameters to improve the results of the LSTM network to obtain a good classification. This study is based on an ear imagery database that consists of four categories: normal, myringosclerosis, earwax plug, and chronic otitis media (COM). This study used 880 otoscopic images divided into 792 training images and 88 testing images to evaluate the approach performance. In this paper, the evaluation metrics of ear condition classification are based on a percentage of accuracy, sensitivity, specificity, and positive predictive value (PPV). The findings yielded a classification accuracy of 100%, a sensitivity of 100%, a specificity of 100%, and a PPV of 100% for the testing database. Finally, the proposed approach shows how to find the best hyperparameters concerning the Bayesian optimization for reliable diagnosis of ear conditions under the consideration of LSTM architecture. This approach demonstrates that CNN-LSTM has higher performance and lower training time than CNN, which has not been used in previous studies for classifying ear diseases. Consequently, the usefulness and reliability of the proposed approach will create an automatic tool for improving the classification and prediction of various ear pathologies.

Split-slice training and hyperparameter tuning of RAKI networks for simultaneous multi-slice reconstruction.

PURPOSE: Simultaneous multi-slice acquisitions are essential for modern neuroimaging research, enabling high temporal resolution functional and high-resolution q-space sampling diffusion acquisitions. Recently, deep learning reconstruction techniques have been introduced for unaliasing these accelerated acquisitions, and robust artificial-neural-networks for k-space interpolation (RAKI) have shown promising capabilities. This study systematically examines the impacts of hyperparameter selections for RAKI networks, and introduces a novel technique for training data generation which is analogous to the split-slice formalism used in slice-GRAPPA. METHODS: RAKI networks were developed with variable hyperparameters and with and without split-slice training data generation. Each network was trained and applied to five different datasets including acquisitions harmonized with Human Connectome Project lifespan protocol. Unaliasing performance was assessed through L1 errors computed between unaliased and calibration frequency-space data. RESULTS: Split-slice training significantly improved network performance in nearly all hyperparameter configurations. Best unaliasing results were achieved with three layer RAKI networks using at least 64 convolutional filters with receptive fields of 7 voxels, 128 single-voxel filters in the penultimate RAKI layer, batch normalization, and no training dropout with the split-slice augmented training dataset. Networks trained without the split-slice technique showed symptoms of network over-fitting. CONCLUSIONS: Split-slice training for simultaneous multi-slice RAKI networks positively impacts network performance. Hyperparameter tuning of such reconstruction networks can lead to further improvements in unaliasing performance.

The Whale Optimization Algorithm Approach for Deep Neural Networks.

One of the biggest challenge in the field of deep learning is the parameter selection and optimization process. In recent years different algorithms have been proposed including bio-inspired solutions to solve this problem, however, there are many challenges including local minima, saddle points, and vanishing gradients. In this paper, we introduce the Whale Optimisation Algorithm (WOA) based on the swarm foraging behavior of humpback whales to optimise neural network hyperparameters. We wish to stress that to the best of our knowledge this is the first attempt that uses Whale Optimisation Algorithm for the optimisation task of hyperparameters. After a detailed description of the WOA algorithm we formulate and explain the application in deep learning, present the implementation, and compare the proposed algorithm with other well-known algorithms including widely used Grid and Random Search methods. Additionally, we have implemented a third dimension feature analysis to the original WOA algorithm to utilize 3D search space (3D-WOA). Simulations show that the proposed algorithm can be successfully used for hyperparameters optimization, achieving accuracy of 89.85% and 80.60% for Fashion MNIST and Reuters datasets, respectively.

Intelligent Fault Diagnosis of Rotary Machinery by Convolutional Neural Network with Automatic Hyper-Parameters Tuning Using Bayesian Optimization.

Intelligent fault diagnosis can be related to applications of machine learning theories to machine fault diagnosis. Although there is a large number of successful examples, there is a gap in the optimization of the hyper-parameters of the machine learning model, which ultimately has a major impact on the performance of the model. Machine learning experts are required to configure a set of hyper-parameter values manually. This work presents a convolutional neural network based data-driven intelligent fault diagnosis technique for rotary machinery which uses model with optimized hyper-parameters and network structure. The proposed technique input raw three axes accelerometer signal as high definition 1-D data into deep learning layers with optimized hyper-parameters. Input is consisted of wide 12,800 × 1 × 3 vibration signal matrix. Model learning phase includes Bayesian optimization that optimizes hyper-parameters of the convolutional neural network. Finally, by using a Convolutional Neural Network (CNN) model with optimized hyper-parameters, classification in one of the 8 different machine states and 2 rotational speeds can be performed. This study accomplished the effective classification of different rotary machinery states in different rotational speeds using optimized convolutional artificial neural network for classification of raw three axis accelerometer signal input. Overall classification accuracy of 99.94% on evaluation set is obtained with the CNN model based on 19 layers. Additionally, more data are collected on the same machine with altered bearings to test the model for overfitting. Result of classification accuracy of 100% on second evaluation set has been achieved, proving the potential of using the proposed technique.

Neural Architecture Search for 1D CNNs-Different Approaches Tests and Measurements.

In the field of sensors, in areas such as industrial, clinical, or environment, it is common to find one dimensional (1D) formatted data (e.g., electrocardiogram, temperature, power consumption). A very promising technique for modelling this information is the use of One Dimensional Convolutional Neural Networks (1D CNN), which introduces a new challenge, namely how to define the best architecture for a 1D CNN. This manuscript addresses the concept of One Dimensional Neural Architecture Search (1D NAS), an approach that automates the search for the best combination of Neuronal Networks hyperparameters (model architecture), including both structural and training hyperparameters, for optimising 1D CNNs. This work includes the implementation of search processes for 1D CNN architectures based on five strategies: greedy, random, Bayesian, hyperband, and genetic approaches to perform, collect, and analyse the results obtained by each strategy scenario. For the analysis, we conducted 125 experiments, followed by a thorough evaluation from multiple perspectives, including the best-performing model in terms of accuracy, consistency, variability, total running time, and computational resource consumption. Finally, by presenting the optimised 1D CNN architecture, the results for the manuscript's research question (a real-life clinical case) were provided.

NSGA-II as feature selection technique and AdaBoost classifier for COVID-19 prediction using patient's symptoms.

Nowadays, humanity is facing one of the most dangerous pandemics known as COVID-19. Due to its high inter-person contagiousness, COVID-19 is rapidly spreading across the world. Positive patients are often suffering from different symptoms that can vary from mild to severe including cough, fever, sore throat, and body aches. In more dire cases, infected patients can experience severe symptoms that can cause breathing difficulties which lead to stern organ failure and die. The medical corps all over the world are overloaded because of the exponentially myriad number of contagions. Therefore, screening for the disease becomes overwrought with the limited tools of test. Additionally, test results may take a long time to acquire, leaving behind a higher potential for the prevalence of the virus among other individuals by the patients. To reduce the chances of infection, we suggest a prediction model that distinguishes the infected COVID-19 cases based on clinical symptoms and features. This model can be helpful for citizens to catch their infection without the need for visiting the hospital. Also, it helps the medical staff in triaging patients in case of a deficiency of medical amenities. In this paper, we use the non-dominated sorting genetic algorithm (NSGA-II) to select the interesting features by finding the best trade-offs between two conflicting objectives: minimizing the number of features and maximizing the weights of selected features. Then, a classification phase is conducted using an AdaBoost classifier. The proposed model is evaluated using two different datasets. To maximize results, we performed a natural selection of hyper-parameters of the classifier using the genetic algorithm. The obtained results prove the efficiency of NSGA-II as a feature selection algorithm combined with AdaBoost classifier. It exhibits higher classification results that outperformed the existing methods.

An optimized deep learning architecture for the diagnosis of COVID-19 disease based on gravitational search optimization.

In this paper, a novel approach called GSA-DenseNet121-COVID-19 based on a hybrid convolutional neural network (CNN) architecture is proposed using an optimization algorithm. The CNN architecture that was used is called DenseNet121, and the optimization algorithm that was used is called the gravitational search algorithm (GSA). The GSA is used to determine the best values for the hyperparameters of the DenseNet121 architecture. To help this architecture to achieve a high level of accuracy in diagnosing COVID-19 through chest x-ray images. The obtained results showed that the proposed approach could classify 98.38% of the test set correctly. To test the efficacy of the GSA in setting the optimum values for the hyperparameters of DenseNet121. The GSA was compared to another approach called SSD-DenseNet121, which depends on the DenseNet121 and the optimization algorithm called social ski driver (SSD). The comparison results demonstrated the efficacy of the proposed GSA-DenseNet121-COVID-19. As it was able to diagnose COVID-19 better than SSD-DenseNet121 as the second was able to diagnose only 94% of the test set. The proposed approach was also compared to another method based on a CNN architecture called Inception-v3 and manual search to quantify hyperparameter values. The comparison results showed that the GSA-DenseNet121-COVID-19 was able to beat the comparison method, as the second was able to classify only 95% of the test set samples. The proposed GSA-DenseNet121-COVID-19 was also compared with some related work. The comparison results showed that GSA-DenseNet121-COVID-19 is very competitive.

Meta-Strategy for Learning Tuning Parameters with Guarantees.

Online learning methods, similar to the online gradient algorithm (OGA) and exponentially weighted aggregation (EWA), often depend on tuning parameters that are difficult to set in practice. We consider an online meta-learning scenario, and we propose a meta-strategy to learn these parameters from past tasks. Our strategy is based on the minimization of a regret bound. It allows us to learn the initialization and the step size in OGA with guarantees. It also allows us to learn the prior or the learning rate in EWA. We provide a regret analysis of the strategy. It allows to identify settings where meta-learning indeed improves on learning each task in isolation.