Accurate and timely detection of plant diseases is crucial for protecting crop yields and promoting sustainable agriculture. This study introduces a deep learning-based approach for plant health detection by integrati...
详细信息
ISBN:
(数字)9798350367775
ISBN:
(纸本)9798350367782
Accurate and timely detection of plant diseases is crucial for protecting crop yields and promoting sustainable agriculture. This study introduces a deep learning-based approach for plant health detection by integrating a Convolutional Neural Network (CNN) with a Humanoid robot for real-time monitoring. The approach leverages advanced tools such as TensorFlow for model development, OpenCV for image processing, and YOLOv5 for object detection. A dataset comprising 1,530 images, labeled as “Healthy,” “Powdery,” and “Rust,” was used to train, validate, and test the model. Through pre-processing techniques like rescaling, data augmentation, and feature extraction, the model achieved impressive results, with a training accuracy of 98.4%, validation accuracy of 98.2%, and testing accuracy of 99.3%. This approach marks a significant improvement in precision agriculture, offering a scalable and highly accurate solution for early plant health detection.
Composed Image Retrieval (CIR) is a challenging task that aims to retrieve the target image with a multimodal query, i.e., a reference image, and its complementary modification text. As previous supervised or zero-sho...
详细信息
Increasing popularity of trading digital assets can lead to significant delays in Blockchain networks when processing transactions. When transaction fees become miners’ primary revenue, an imbalance in reward may lea...
详细信息
A transaction fee mechanism (TFM) is an essential component of a blockchain protocol. However, a systematic evaluation of the real-world impact of TFMs is still absent. Using rich data from the Ethereum blockchain, th...
详细信息
An innovative method for early warnings in the area of financial risk management is the Flying Neural Network-based Optimistic Financial Early Alert System (FNN-OFEAS). The FNN-OFEAS outperforms conventional models an...
详细信息
Federated learning (FL) enables data sharing in healthcare contexts where it might otherwise be difficult due to data-use-ordinances or security and communication constraints. Distributed and shared data models allow ...
详细信息
Gradient regularization, as described in Barrett and Dherin (2021), is a highly effective technique for promoting flat minima during gradient descent. Empirical evidence suggests that this regularization technique can...
详细信息
Since 2019, the world has suffered from the outbreak of the "Coronavirus Disease (COVID)-19 pandemic. This study used the principle of Ultraviolet (UV)-C disinfection to produce a mobile high-power UV-C sterilize...
详细信息
The outburst of COVID-19 in late 2019 was the start of a health crisis that shook the world and took millions of lives in the ensuing years. Many governments and health officials failed to arrest the rapid circulation...
The outburst of COVID-19 in late 2019 was the start of a health crisis that shook the world and took millions of lives in the ensuing years. Many governments and health officials failed to arrest the rapid circulation of infection in their communities. The long incubation period and the large proportion of asymptomatic cases made COVID-19 particularly elusive to track. However, wastewater surveillance soon became a promising data source in addition to conventional indicators such as confirmed daily cases, hospitalizations, and deaths. Despite the consensus on the effectiveness of wastewater viral load, there is a lack of methodological approaches that leverage viral load to improve COVID-19 forecasting. This paper proposes a deep learning framework to automatically discover the relationship between daily cases and viral load data. We trained a Deep Temporal Convolutional Network (DeepTCN) and a Temporal Fusion Transformer (TFT) model to obtain a global forecasting model. We supplement the daily confirmed cases with viral loads and other socio-economic factors as covariates to the models. Our results suggest that TFT outperforms DeepTCN and learns a better association between viral load and daily cases. We demonstrate that equipping the models with the viral load improves forecasting accuracy and reduces uncertainty. Moreover, viral load is shown to be the second most predictive input, following the containment and health index. Our results reveal the feasibility of training a location-agnostic deep-learning model to capture the dynamics of infection diffusion when wastewater viral load data is available.
In the fast changing world of cloud based internet of things (IoT) eco-systems, secure connectivity between devices and cloud services is vital. On the other hand, the rising Man-in-the- Middle (MitM) attacks present ...
详细信息
ISBN:
(数字)9798350366846
ISBN:
(纸本)9798350366853
In the fast changing world of cloud based internet of things (IoT) eco-systems, secure connectivity between devices and cloud services is vital. On the other hand, the rising Man-in-the- Middle (MitM) attacks present serious threats to data integrity and confidentiality. In this regard, through a combination of Software Defined Networking (SDN) and Blockchain technology, this study proposes an innovative technique for improving security architecture in cloud IoT settings against MitM attacks. The solution put forward relies on blockchain to provide immutable transactions that are used as tamper-proof ledgers for device authentication and secure data sharing. Smart contracts create unchangeable transactions that also maintain the anonymity of devices and their communication processes. Additionally, SDN technology segments traffic, implements dynamic network policies, and therefore reduces MitM attack vectors through traffic inspection and access control. The testing process has shown that the approach effectively prevents MitM attacks while ensuring safe communication channels in cloud-based IoT systems. This implementation demonstrates improved data integrity, confidentiality, and security against unwanted intrusion attempts. This research paper contributes to the development of the cloud-based IoT security paradigm and highlights the synergistic potential of Blockchain and SDN in dealing with common security issues and improving the trustworthiness of networked devices for the Internet of Things.
暂无评论