This research work aims to present a robust deep learning framework by devising a deep learning-based ensemble method of YOLOv8 and EfficientNet. The suggested model is evaluated on the dataset collected from Kaggle, comprising 10,000 high-definition images of stems, leaves, and cut fruits of banana and papaya. These images are captured under different lighting conditions and thus expanded to 80,000 images. Authors have proposed an ensemble model comprising YoloV8 and EfficientNet as base deep learning models to enhance prediction and classification performance. Here, authors combine the merits of both models, i.e., speed of YoloV8 and the accuracy of EfficientNet, by putting a majority voting method in place. The final forecast is determined by majority voting, and EfficientNet is given higher significance in the situation of a tie owing to its enhanced accuracy. The proposed model presents a robust solution for agricultural disease management and demonstrates significant improvements in the detection of diseases in papaya and banana, opening avenues for its widespread employment in real life.

The appropriateness of the agricultural economy is very effective in sustainable food security. The appearance and shape of agricultural products change in different periods. The correct classification of the product in terms of quality after harvest affects the economy of farmers. Today, deep learning classifiers have greatly contributed to the correct classification of product quality. But the database challenges and the same conditions of the database in the training and testing phase affect the classification accuracy. The purpose of this article is to classify the quality of tomatoes in the challenging conditions of the database, including crowded backgrounds, noise in the image, leaves of the same color as the fruit in the image, and the similarity of growth stages. For this purpose, 3 databases with different challenges have been used in the stage of classification training and testing. In this article, the aim is to classify the quality of tomatoes into 3 classes ripe, unripe ,and semi-ripe using EfficientNet deep learning classifier. According to the conditions of the database, the first three processes of noise removal, image contrast improvement ,and image segmentation have been applied to the images. The results of the evaluation of the proposed method show the proper performance of EfficientNetB5.

Fire is a major hazard in sensitive environments and can cause irreparable financial and life losses. In addition, fire in the forest and residential areas is considered a threatening event for natural and human resources. Accordingly, detecting fires and smoke in a timely and accurate manner is crucial in preventing financial losses, injuries, and fatalities. Since smoke can be detected before visible flames, smoke detection is a critical component of many fire alarm systems. Sensors sensitive to smoke and fire have the ability to detect these two events, but implementing a huge network of sensors in an open space like a forest is not economical. There are various methods for detecting fire and smoke, and among these, the methods based on deep learning exhibit bigger advantages in terms of accuracy and speed in segmentation. In this paper, we proposed some deep neural networks for fire and smoke detection. These are based on UNet, UNet++, and UNet3+. A proposed FireNet and five other structures are tried as the encoder’s backbone to segment fire and smoke. To train the models, 1200 images gathered from Internet images and videos were prepared, with appropriate labels for smoke and fire applied to their pixels. Experiments show that the best IoU (88. 33%) is achieved by UNet++ with EfficientNet. B0 backbone. In small-scale fires, UNet with FireNet has the best performance, and when computational cost is important, UNet3+ with FireNet as the encoder’s backbone is the optimal choice.

Today, social networks have become a prominent source of news, significantly altering the way people obtain news from traditional media sources to social media. Alternatively, social media platforms have been plagued by unauthenticated and fake news in recent years. However, the rise of fake news on these platforms has become a challenging issue. Fake news dissemination, especially through visual content, poses a significant threat as people tend to share information in image format. Consequently, detecting and combating fake news has become crucial in the realm of social media. In this paper, we propose an approach to address the detection of fake image news. Our method incorporates the error level analysis (ELA) technique and the explicit convolutional neural network of the EfficientNet model. By converting the original image into an ELA image, it is possible to effectively highlight any manipulations or discrepancies within the image. The ELA image is further processed by the EfficientNet model, which captures distinctive features used to detect fake image news. Visual features extracted from the model are passed through a dense layer and a sigmoid function to predict the image type. To evaluate the efficacy of the proposed method, we conducted experiments using the CASIA 2. 0 dataset, a widely adopted benchmark dataset for fake image detection. The experimental results demonstrate an accuracy rate of 96. 11% for the CASIA dataset. The results outperform in terms of accuracy and computational efficiency, with a 6% increase in accuracy and a 5. 2% improvement in the F-score compared with other similar methods

An Electrocardiogram (ECG) is a test that is done with the objective of monitoring the heart’, s rhythm and electrical activity. It is conducted by attaching a specific type of sensor to the subject’, s skin to detect the signals generated by the heartbeats. These signals can reveal significant information about the wellness of the subjects’,heart state, and cardiologists use them to detect abnormalities. Due to the prevalence of heart diseases amongst individuals around the globe, there is an urgent need to design computer-aided approaches to automatically analyze ECG signals. Recently, computer vision-based techniques have demonstrated remarkable performance in medical image analysis in a variety of applications and use cases. This paper proposes an approach based on Convolutional Autoencoders (CAEs) and Transfer Learning (TL). Our approach is an ensemble way of learning, the most useful features from both the signal itself, which is the input of the CAE, and the spectrogram version of the same signal, which is fed to a convolutional feature extractor named MobileNetV1. Based on the experiments conducted on a dataset collected from 3 well-known hospitals in Baghdad, Iraq, the proposed method claims good performance in classifying four types of problems in the ECG signals. Achieving an accuracy of 97. 3% proves that our approach can be remarkably fruitful in situations where access to expert human resources is scarce.

One method to diagnose retinal diseases is by using the Optical Coherence Tomography (OCT) scans. Annually, it is estimated that around 30 million OCT scans are performed worldwide. However, the process of analyzing and diagnosing OCT scan results by an ophthalmologist requires a long time so machine learning, especially deep learning, can be utilized to shorten the diagnosis process and speed up the treatment process. In this study, several pre-trained deep learning models are compared, including EfficientNet-B0, ResNet-50V2, Inception-V3, and DenseNet-169. These models will be fine-tuned and trained with a dataset containing OCT scanned images to classify four retinal conditions, namely Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), Drusen, and Normal. The models that have been trained are then tested to classify the test set and the results are evaluated using a confusion matrix in terms of accuracy, recall, precision, and F1-score. The results show that the model with the best classification results in the batch size of 32 scenario is the ResNet-50V2 model with an accuracy value of 98.24%, precision of 98.25%, recall of 98.24%, and F1-score of 98.24%. While for the batch size of 64, the EfficientNet-B0 model is the model with the best classification results with an accuracy value of 96.59%, precision of 96.84%, recall of 96.59%, and F1-score of 96.59%.

Background: One of the best ways to reduce the spread of tuberculosis (TB) is to diagnose the disease using chest X-ray (CXR) images as a low-cost and affordable method. However, there are two problems: the lack of adequate radiologists and the possibility of misdiagnosis. This is why it is necessary to use an accessible and accurate diagnostic system. This research aimed to design an accurate and accessible automatic diagnosis system that can solve diagnosis problems using deep learning.Methods: Six convolutional neural networks (CNNs), InceptionV3, ResNet50, DenseNet201, MnasNet, MobileNetV3, and EfficientNet-B4, were trained by transfer learning, the Adam optimizer, and 20 training epochs using the new, large, and accurate TBX11K dataset. The network was designed to categorize images into three groups: patients diagnosed with TB, patients exhibiting lung abnormalities unrelated to TB, and healthy individuals with no evidence of TB or other pulmonary anomalies within the lung imagery.Results: In the testing step, the networks achieved very high performance. The EfficientNet-B4 network outperformed the other networks with a sensitivity of 97.1%, specificity of 99.9%, and accuracy of 99.5%. It also performed better than previous studies in TB diagnosis using CXR images by CNNs.Conclusion: This research showed that with access to large high-quality datasets and standard training, it is possible to entrust the diagnosis of TB using medical images to computers and artificial neural networks with high confidence as they achieved accuracies higher than 99%.