Citrus fruit diseases have an egregious impact on both the quality and quantity of the citrus fruit production and market. Automatic detection of severity is essential for the high-quality production of fruit. In the current work, a citrus fruit dataset is preprocessed by rescaling and establishing bounding boxes with labeled image software. Then, a selective search, which combines the capabilities of both an extensive search and graph-based segmentation, is applied. The proposed deep neural network (DNN) model is trained to detect targeted areas of the disease with its severity level using citrus fruits that have been labeled with the help of a domain expert with four severity levels (high, medium, low and healthy) as ground truth. Transfer learning using VGGNet is applied to implement a multi-classification framework for each class of severity. The model predicts the low severity level with 99% accuracy, and the high severity level with 98% accuracy. The model demonstrates 96% accuracy in detecting healthy conditions and 97% accuracy in detecting medium severity levels. The result of the work shows that the proposed approach is valid, and it is efficient for detecting citrus fruit disease at four levels of severity.

As a result of the widespread adoption of the Internet of Things, there are now hundreds of millions of connected devices, increasing the likelihood that they may be vulnerable to various types of cyberattacks. In recent years, distributed denial of service (DDoS) has emerged as one of the most destructive tools utilized by attackers. Traditional machine learning approaches are typically ineffective and unable to cope with actual traffic properties when used to identify DDoS attacks. This paper introduces a novel deep learning-based intrusion detection system, specifically designed for deployment at either the Cloud or Fog level in the IoT environment. The proposed model aims to detect all types of DDoS attacks with their specific subcategory. Our hybrid model combines different types of deep learning models, including Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Deep Autoencoder, and Deep Neural Networks (DNNs). Our proposed model is made up of two main levels. The first one contains different parallel sub-neural networks trained with specific algorithms. The second level uses the output of the frozen first level combined with the initial data as input. The idea behind the combination of these various types of deep neural networks is to exploit their different properties to achieve very high performance. To evaluate our model, we used the CIC-DDoS2019 dataset, which satisfies all the constraints of an intrusion detection dataset. The results obtained demonstrate that our proposed model outperformed various well-known machine learning and deep learning models in terms of the true positive rate, accuracy, false alarm rate, average accuracy, and average detection rate.

An expert performs bone fracture diagnosis using an X-ray image manually, which is a time-consuming process. The development of machine learning (ML), as well as deep learning (DL), has set a new path in medical image diagnosis. In this study, we proposed a novel multi-scale feature fusion of a convolution neural network (CNN) and an improved canny edge algorithm that segregate fracture and healthy bone image. The hybrid scale fracture network (SFNet) is a novel two-scale sequential DL model. This model is highly efficient for bone fracture diagnosis and takes less computation time compared to other state-of-the-art deep CNN models. The innovation behind this research is that it works with an improved canny edge algorithm to obtain edges in the images that localize the fracture region. After that, grey images and their corresponding canny edge images are fed to the proposed hybrid SFNet for training and evaluation. Furthermore, the performance is also compared with the state-of-the-art deep CNN models on a bone image dataset. Our results showed that SFNet with canny (SFNet + canny) achieved the highest accuracy, F1-score and recall of 99.12%, 99% and 100%, respectively, for bone fracture diagnosis. It showed that using a canny edge algorithm improves the performance of CNN.

Earthquake early warning systems (EEWS) are crucial for saving lives in earthquake-prone areas. In this study, we explore the potential of IoT and cloud infrastructure in realizing a sustainable EEWS that is capable of providing early warning to people and coordinating disaster response efforts. To achieve this goal, we provide an overview of the fundamental concepts of seismic waves and associated signal processing. We then present a detailed discussion of the IoT-enabled EEWS, including the use of IoT networks to track the actions taken by various EEWS organizations and the cloud infrastructure to gather data, analyze it, and send alarms when necessary. Furthermore, we present a taxonomy of emerging EEWS approaches using IoT and cloud facilities, which includes the integration of advanced technologies such as machine learning (ML) algorithms, distributed computing, and edge computing. We also elaborate on a generic EEWS architecture that is sustainable and efficient and highlight the importance of considering sustainability in the design of such systems. Additionally, we discuss the role of drones in disaster management and their potential to enhance the effectiveness of EEWS. Furthermore, we provide a summary of the primary verification and validation methods required for the systems under consideration. In addition to the contributions mentioned above, this study also highlights the implications of using IoT and cloud infrastructure in early earthquake detection and disaster management. Our research design involved a comprehensive survey of the existing literature on early earthquake warning systems and the use of IoT and cloud infrastructure. We also conducted a thorough analysis of the taxonomy of emerging EEWS approaches using IoT and cloud facilities and the verification and validation methods required for such systems. Our findings suggest that the use of IoT and cloud infrastructure in early earthquake detection can significantly improve the speed and effectiveness of disaster response efforts, thereby saving lives and reducing the economic impact of earthquakes. Finally, we identify research gaps in this domain and suggest future directions toward achieving a sustainable EEWS. Overall, this study provides valuable insights into the use of IoT and cloud infrastructure in earthquake disaster early detection and emphasizes the importance of sustainability in designing such systems.