Search

Wheat serves as a crucial agricultural commodity and a primary dietary staple for numerous global populations. However, it faces persistent threats from various diseases targeting wheat leaves, ultimately impacting its production. Accurate and prompt automated disease diagnosis through advanced computer vision is crucial for safeguarding wheat quality. However, the literature relied on inadequate feature selection acquired from computationally expensive backbones followed by shallow layered networks. It is resultantly limiting their capacity to recognize and prioritize diseased areas effectively. Therefore, this paper introduces an optimal features-assisted lightweight framework that integrates EfficientNet-B3 with a spatial attention (SA) mechanism to capture healthy and unhealthy patterns effectively. The proposed framework harnesses this capability to address the vital regions affected by wheat diseases via an optimized, lightweight, and attentive network. Subsequently, we thoroughly analyzed several backbone features to identify robust hyperparameters conducive to achieving our lightweight objective. Furthermore, we employed SA blocks to fortify the network, directing attention efficiently towards diseased regions. The efficacy of the proposed network is validated through comprehensive evaluations conducted on both our proposed and LWDCD2020 benchmarks. Comparative analyses with existing methods consistently showcase superiority, firmly establishing our proposed approach as a viable network for wheat disease recognition. additionally, we also collected our own dataset, namely the Wheat Disease Five Classes Classification Dataset (WD5CC), and included diverse images.

The demand for electrical energy is increasing every day, which is one of the critical challenges facing the world today. Hence, the necessity of turning to clean renewable energy sources that are not harmful to the environment as an alternative to the traditional generation based on fossil fuels has become more important than ever before. Wind power is one of the renewable sources that provides a clean solution to generate electricity. In this context, the Kingdom of Saudi Arabia announces renewable energy projects to generate 9 GW from wind in 2032. Hence, the aim of this paper is to investigate the most suitable method of Weibull parameter estimation in order to predict wind characteristics and employ it for wind energy assessment in the Qassim region located in the center of the country. In this study, wind data is collected from NASA's forecasts of global energy resources for 2010–2015 based on their availability at altitudes of 10m and 50m and analyzed by using six different methods for Weibull parameter estimation: the graphical method (GM), standard deviation method (SDM), energy pattern factor method (EPF), moment method (MM), alternative maximum likelihood method (AMLM), and novel energy pattern factor method (NEPF). The efficiency of each method is tested by calculating the root mean square error (RMSE) and the relative wind power density error (RPDE). The comparison shows that the most appropriate method for estimating wind power density in the country is the Moment Method (MM), with the lowest RPDE ratio equal to 0.2018%. It has been found that the wind power density in the Qassim region falls into the class 1 category, as it is less than 100 W/m2 at a height of 10m and less than 200 W/m2at an altitude of 50m. The results show the region is only suitable for small off-grid projects. Doi: 10.28991/ESJ-2023-07-06-024 Full Text: PDF

Sign language recognition, an essential interface between the hearing and deaf-mute communities, faces challenges with high false positive rates and computational costs, even with the use of advanced deep learning techniques. Our proposed solution is a stacked encoded model, combining artificial intelligence (AI) with the Internet of Things (IoT), which refines feature extraction and classification to overcome these challenges. We leverage a lightweight backbone model for preliminary feature extraction and use stacked autoencoders to further refine these features. Our approach harnesses the scalability of big data, showing notable improvement in accuracy, precision, recall, F1-score, and complexity analysis. Our model’s effectiveness is demonstrated through testing on the ArSL2018 benchmark dataset, showcasing superior performance compared to state-of-the-art approaches. Additional validation through an ablation study with pre-trained convolutional neural network (CNN) models affirms our model’s efficacy across all evaluation metrics. Our work paves the way for the sustainable development of high-performing, IoT-based sign-language-recognition applications.

Currently, algorithms for compressed image steganography mainly embed hidden message by minimizing the resulting distortion or statistical detectability. However, as a result of purely heuristic distortion definitions and numerically solvable equations in statistical models, there are no closed-form solutions for JPEG steganography. The absence of closed-form expression to model JPEG steganography is the main limitation on understanding single image and pool steganalysis behavior. In this study, building upon our previously proposed framework for spatial steganography, we develop a statistical framework for JPEG steganography in which the cover and the hidden message are modeled by multivariate Gaussian distribution. Based on this statistical model, we propose a novel quantized Gaussian JPEG steganography that is able to accomplish embedding using any costs defined in spatial or discrete cosine transform (DCT) domain as well as residual variances. We conduct our experiments using a popular database with different compression qualities to determine the effectiveness of the proposed model. The experimental results show that the proposed model improves the security of previous works and outperforms the state-of-the-art JPEG steganography algorithms. Furthermore, we extend the closed-form expression of single image steganalysis error to pool steganalysis for an omniscience optimal detector. We employ the derived expression to approximate the empirical results of pool steganalysis based on the empirical detection error of single image steganalysis. The practical advantage of the approximation is that even though it is derived based on the adopted statistical model, it is accurate regardless of payload, embedding domain, embedding method, and steganalysis feature as long as the pooling strategy is optimal. In addition to approximation of the error, we employ the proposed model to make predictions about the variance behavior of pool steganalysis error. We mathematically show that the variance increases as the pool size increases in small payloads. The same behavior is observed in experimental results which re-validates our analytical model. We conclude that although pooling improves detector’s performance, it makes the detector less stable in low payloads and high pool sizes.

In the world, brain tumor (BT) is considered the major cause of death related to cancer, which requires early and accurate detection for patient survival. In the early detection of BT, computer-aided diagnosis (CAD) plays a significant role, the medical experts receive a second opinion through CAD during image examination. Several researchers proposed different methods based on traditional machine learning (TML) and deep learning (DL). The TML requires hand-crafted features engineering, which is a time-consuming process to select an optimal features extractor and requires domain experts to have enough knowledge of optimal features selection. The DL methods outperform the TML due to the end-to-end automatic, high-level, and robust feature extraction mechanism. In BT classification, the deep learning methods have a great potential to capture local features by convolution operation, but the ability of global features extraction to keep Long-range dependencies is relatively weak. A self-attention mechanism in Vision Transformer (ViT) has the ability to model long-range dependencies which is very important for precise BT classification. Therefore, we employ a hybrid transformer-enhanced convolutional neural network (TECNN)-based model for BT classification, where the CNN is used for local feature extraction and the transformer employs an attention mechanism to extract global features. Experiments are performed on two public datasets that are BraTS 2018 and Figshare. The experimental results of our model using BraTS 2018 and Figshare datasets achieves an average accuracy of 96.75% and 99.10%, respectively. In the experiments, the proposed model outperforms several state-of-the-art methods using BraTS 2018 and Figshare datasets by achieving 3.06% and 1.06% accuracy, respectively.

Insect pests and crop diseases are considered the major problems for agricultural production, due to the severity and extent of their occurrence causing significant crop losses. To increase agricultural production, it is significant to protect the crop from harmful pests which is possible via soft computing techniques. The soft computing techniques are based on traditional machine and deep learning-based approaches. However, in the traditional methods, the selection of manual feature extraction mechanisms is ineffective, inefficient, and time-consuming, while deep learning techniques are computationally expensive and require a large amount of training data. In this paper, we propose an efficient pest detection method that accurately localized the pests and classify them according to their desired class label. In the proposed work, we modify the YOLOv5s model in several ways such as extending the cross stage partial network (CSP) module, improving the select kernel (SK) in the attention module, and modifying the multiscale feature extraction mechanism, which plays a significant role in the detection and classification of small and large sizes of pest in an image. To validate the model performance, we develop a medium-scale pest detection dataset that includes the five most harmful pests for agriculture products that are ants, grasshopper, palm weevils, shield bugs, and wasps. To check the model’s effectiveness, we compare the results of the proposed model with several variations of the YOLOv5 model, where the proposed model achieved the best results in the experiments. Thus, the proposed model has the potential to be applied in real-world applications and further motivate research on pest detection to increase agriculture production.

Skin Cancer (SC) is considered the deadliest disease in the world, killing thousands of people every year. Early SC detection can increase the survival rate for patients up to 70%, hence it is highly recommended that regular head-to-toe skin examinations are conducted to determine whether there are any signs or symptoms of SC. The use of Machine Learning (ML)-based methods is having a significant impact on the classification and detection of SC diseases. However, there are certain challenges associated with the accurate classification of these diseases such as a lower detection accuracy, poor generalization of the models, and an insufficient amount of labeled data for training. To address these challenges, in this work we developed a two-tier framework for the accurate classification of SC. During the first stage of the framework, we applied different methods for data augmentation to increase the number of image samples for effective training. As part of the second tier of the framework, taking into consideration the promising performance of the Medical Vision Transformer (MVT) in the analysis of medical images, we developed an MVT-based classification model for SC. This MVT splits the input image into image patches and then feeds these patches to the transformer in a sequence structure, like word embedding. Finally, Multi-Layer Perceptron (MLP) is used to classify the input image into the corresponding class. Based on the experimental results achieved on the Human Against Machine (HAM10000) datasets, we concluded that the proposed MVT-based model achieves better results than current state-of-the-art techniques for SC classification.

Since December 2019, the COVID-19 pandemic has led to a dramatic loss of human lives and caused severe economic crises worldwide. COVID-19 virus transmission generally occurs through a small respiratory droplet ejected from the mouth or nose of an infected person to another person. To reduce and prevent the spread of COVID-19 transmission, the World Health Organization (WHO) advises the public to wear face masks as one of the most practical and effective prevention methods. Early face mask detection is very important to prevent the spread of COVID-19. For this purpose, we investigate several deep learning-based architectures such as VGG16, VGG19, InceptionV3, ResNet-101, ResNet-50, EfficientNet, MobileNetV1, and MobileNetV2. After these experiments, we propose an efficient and effective model for face mask detection with the potential to be deployable over edge devices. Our proposed model is based on MobileNetV2 architecture that extracts salient features from the input data that are then passed to an autoencoder to form more abstract representations prior to the classification layer. The proposed model also adopts extensive data augmentation techniques (e.g., rotation, flip, Gaussian blur, sharping, emboss, skew, and shear) to increase the number of samples for effective training. The performance of our proposed model is evaluated on three publicly available datasets and achieved the highest performance as compared to other state-of-the-art models.