A deep learning-based approach for predicting COVID-19 diagnosis.

This paper focuses on forecasting the total count of confirmed COVID-19 cases in Saudi Arabia through a range of methodologies, including ARIMA, mathematical modeling, and deep learning network (DQN) techniques. Its primary aim is to anticipate the verified COVID-19 cases in Saudi Arabia, aiding in decision-making for life-saving interventions by enhancing awareness of COVID-19 infection. Mathematical modeling and ARIMA are employed for their efficacy in forecasting, while DQN approaches, particularly through comparative analysis, are utilized for prediction. This comparative analysis evaluates the predictive capacities of ARIMA, mathematical modeling, and DQN techniques, aiming to pinpoint the most reliable method for forecasting positive COVID-19 cases. The modeling encompasses COVID-19 cases in Saudi Arabia, the United Kingdom (UK), and Tunisia (TU) spanning from 2020 to 2021. Predicting the number of individuals likely to test positive for COVID-19 poses a challenge, requiring adherence to fundamental assumptions in mathematical and ARIMA projections. The proposed methodology was implemented on a local server. The DQN algorithm formulates a reward function to uphold target functional performance while balancing training and testing periods. The findings indicate that DQN technology surpasses conventional approaches in efficiency and accuracy for predictions.

Using a Resnet50 with a Kernel Attention Mechanism for Rice Disease Diagnosis.

The domestication of animals and the cultivation of crops have been essential to human development throughout history, with the agricultural sector playing a pivotal role. Insufficient nutrition often leads to plant diseases, such as those affecting rice crops, resulting in yield losses of 20-40% of total production. These losses carry significant global economic consequences. Timely disease diagnosis is critical for implementing effective treatments and mitigating financial losses. However, despite technological advancements, rice disease diagnosis primarily depends on manual methods. In this study, we present a novel self-attention network (SANET) based on the ResNet50 architecture, incorporating a kernel attention mechanism for accurate AI-assisted rice disease classification. We employ attention modules to extract contextual dependencies within images, focusing on essential features for disease identification. Using a publicly available rice disease dataset comprising four classes (three disease types and healthy leaves), we conducted cross-validated classification experiments to evaluate our proposed model. The results reveal that the attention-based mechanism effectively guides the convolutional neural network (CNN) in learning valuable features, resulting in accurate image classification and reduced performance variation compared to state-of-the-art methods. Our SANET model achieved a test set accuracy of 98.71%, surpassing that of current leading models. These findings highlight the potential for widespread AI adoption in agricultural disease diagnosis and management, ultimately enhancing efficiency and effectiveness within the sector.

IoT based smart home automation using blockchain and deep learning models.

For the past few years, the concept of the smart house has gained popularity. The major challenges concerning a smart home include data security, privacy issues, authentication, secure identification, and automated decision-making of Internet of Things (IoT) devices. Currently, existing home automation systems address either of these challenges, however, home automation that also involves automated decision-making systems and systematic features apart from being reliable and safe is an absolute necessity. The current study proposes a deep learning-driven smart home system that integrates a Convolutional neural network (CNN) for automated decision-making such as classifying the device as "ON" and "OFF" based on its utilization at home. Additionally, to provide a decentralized, secure, and reliable mechanism to assure the authentication and identification of the IoT devices we integrated the emerging blockchain technology into this study. The proposed system is fundamentally comprised of a variety of sensors, a 5 V relay circuit, and Raspberry Pi which operates as a server and maintains the database of each device being used. Moreover, an android application is developed which communicates with the Raspberry Pi interface using the Apache server and HTTP web interface. The practicality of the proposed system for home automation is tested and evaluated in the lab and in real-time to ensure its efficacy. The current study also assures that the technology and hardware utilized in the proposed smart house system are inexpensive, widely available, and scalable. Furthermore, the need for a more comprehensive security and privacy model to be incorporated into the design phase of smart homes is highlighted by a discussion of the risks analysis' implications including cyber threats, hardware security, and cyber attacks. The experimental results emphasize the significance of the proposed system and validate its usability in the real world.

An Ensemble of Deep Learning Enabled Brain Stroke Classification Model in Magnetic Resonance Images.

Brain stroke is a major cause of global death and it necessitates earlier identification process to reduce the mortality rate. Magnetic resonance imaging (MRI) techniques is a commonly available imaging modality used to diagnose brain stroke. Presently, machine learning (ML) and deep learning (DL) models can be extremely utilized for disease detection and classification processes. Amongst the available approaches, the convolutional neural network (CNN) models have been widely used for computer vision and image processing issues such as ImageNet, facial detection, and digit classification. In this article, a novel computer aided diagnosis (CAD) based brain stroke detection and classification (CAD-BSDC) model has been developed for MRI images. The proposed CAD-BSDC technique aims in classifying the provided MR brain image as normal or abnormal. The CAD-BSDC technique involves different subprocesses such as preprocessing, feature extraction, and classification. Firstly, the input image undergoes preprocessing using adaptive thresholding (AT) technique for improving the image quality. Followed by, an ensemble of feature extractors such as MobileNet, CapsuleNet, and EfficientNet models are used. Besides, the hyperparameter tuning of the deep learning models takes place using the improved dragonfly optimization (IDFO) algorithm. Moreover, satin bowerbird optimization (SBO) based stacked autoencoder (SAE) is used for the classification of brain stroke. The design of optimal SAE using the SBO algorithm shows the novelty of the work. The performance of the presented technique was validated utilizing benchmark dataset which includes T2-weighted MR brain image collected from the axial axis with size of 256 × 256. The simulation outcomes indicated the promising efficiency of the proposed CAD-BSDC technique over the latest state of art approaches in terms of various performance measures.

Atom Search Optimization with the Deep Transfer Learning-Driven Esophageal Cancer Classification Model.

Esophageal cancer (EC) is a commonly occurring malignant tumor that significantly affects human health. Earlier recognition and classification of EC or premalignant lesions can result in highly effective targeted intervention. Accurate detection and classification of distinct stages of EC provide effective precision therapy planning and improve the 5-year survival rate. Automated recognition of EC can aid physicians in improving diagnostic performance and accuracy. However, the classification of EC is challenging due to identical endoscopic features, like mucosal erosion, hyperemia, and roughness. The recent developments of deep learning (DL) and computer-aided diagnosis (CAD) models have been useful for designing accurate EC classification models. In this aspect, this study develops an atom search optimization with a deep transfer learning-driven EC classification (ASODTL-ECC) model. The presented ASODTL-ECC model mainly examines the medical images for the existence of EC in a timely and accurate manner. To do so, the presented ASODTL-ECC model employs Gaussian filtering (GF) as a preprocessing stage to enhance image quality. In addition, the deep convolution neural network- (DCNN-) based residual network (ResNet) model is applied as a feature extraction approach. Besides, ASO with an extreme learning machine (ELM) model is utilized for identifying the presence of EC, showing the novelty of the work. The performance of the ASODTL-ECC model is assessed and compared with existing models under several medical images. The experimental results pointed out the improved performance of the ASODTL-ECC model over recent approaches.

Intelligent Deep Learning Enabled Oral Squamous Cell Carcinoma Detection and Classification Using Biomedical Images.

Oral cancer is one of the lethal diseases among the available malignant tumors globally, and it has become a challenging health issue in developing and low-to-middle income countries. The prognosis of oral cancer remains poor because over 50% of patients are recognized at advanced stages. Earlier detection and screening models for oral cancer are mainly based on experts' knowledge, and it necessitates an automated tool for oral cancer detection. The recent developments of computational intelligence (CI) and computer vision-based approaches help to accomplish enhanced performance in medical-image-related tasks. This article develops an intelligent deep learning enabled oral squamous cell carcinoma detection and classification (IDL-OSCDC) technique using biomedical images. The presented IDL-OSCDC model involves the recognition and classification of oral cancer on biomedical images. The proposed IDL-OSCDC model employs Gabor filtering (GF) as a preprocessing step to eliminate noise content. In addition, the NasNet model is exploited for the generation of high-level deep features from the input images. Moreover, an enhanced grasshopper optimization algorithm (EGOA)-based deep belief network (DBN) model is employed for oral cancer detection and classification. The hyperparameter tuning of the DBN model is performed using the EGOA algorithm which in turn boosts the classification outcomes. The experimentation outcomes of the IDL-OSCDC model using a benchmark biomedical imaging dataset highlighted its promising performance over the other methods with maximum accu y , prec n , reca l , and F score of 95%, 96.15%, 93.75%, and 94.67% correspondingly.

Advanced Deep Learning for Resource Allocation and Security Aware Data Offloading in Industrial Mobile Edge Computing.

The Internet of Things (IoT) is permeating our daily lives through continuous environmental monitoring and data collection. The promise of low latency communication, enhanced security, and efficient bandwidth utilization lead to the shift from mobile cloud computing to mobile edge computing. In this study, we propose an advanced deep reinforcement resource allocation and security-aware data offloading model that considers the constrained computation and radio resources of industrial IoT devices to guarantee efficient sharing of resources between multiple users. This model is formulated as an optimization problem with the goal of decreasing energy consumption and computation delay. This type of problem is non-deterministic polynomial time-hard due to the curse-of-dimensionality challenge, thus, a deep learning optimization approach is presented to find an optimal solution. In addition, a 128-bit Advanced Encryption Standard-based cryptographic approach is proposed to satisfy the data security requirements. Experimental evaluation results show that the proposed model can reduce offloading overhead in terms of energy and time by up to 64.7% in comparison with the local execution approach. It also outperforms the full offloading scenario by up to 13.2%, where it can select some computation tasks to be offloaded while optimally rejecting others. Finally, it is adaptable and scalable for a large number of mobile devices.