Tomato diseases, including Leaf blight, Leaf curl, Septoria leaf spot, and Verticillium wilt, are responsible for up to 50% of annual yield loss, significantly impacting global tomato production, valued at approximately USD 87 billion. In Ghana, there is a yield gap of about 50% in tomato production, which requires drastic measures to increase the yield of tomatoes. Conventional diagnostic methods are labor-intensive and impractical for real-time application, highlighting the need for innovative solutions. This study addresses these issues in Ghana by utilizing Edge Impulse to deploy multiple deep-learning models on a single mobile device, facilitating the rapid and precise detection of tomato leaf diseases in the field. This work compiled and rigorously prepared a comprehensive Ghanaian dataset of tomato leaf images, applying advanced preprocessing and augmentation techniques to enhance robustness. Using TensorFlow, we designed and optimized efficient convolutional neural network (CNN) architectures, including MobileNet, Inception, ShuffleNet, Squeezenet, EfficientNet, and a custom Deep Neural Network (DNN). The models were converted to TensorFlow Lite format and quantized to int8, substantially reducing the model size and improving inference speed. Deployment files were generated, and the Edge Impulse platform was configured to enable multiple model deployments on a mobile device. Performance evaluations across edge hardware provided metrics such as inference speed, accuracy, and resource utilization, demonstrating reliable real-time detection. EfficientNet achieved a high training accuracy of 97.12% with a compact 4.60 MB model size, proving its efficacy for mobile device deployment. In contrast, the custom DNN model is optimized for microcontroller unit (MCU) deployment. This edge artificial intelligence (AI) technology integration into agricultural practices offers scalable, cost-effective, and accessible solutions for disease classification, enhancing crop management, and supporting sustainable farming practices.

As a harmless detection method, terahertz has become a new trend in security detection. However, there are inherent problems such as the low quality of the images collected by terahertz equipment and the insufficient detection accuracy of dangerous goods. This work advances BiFPN at the neck of YOLOv5 of the deep learning model as a mechanism to improve low resolution. We also perform transfer learning, thereby fine-tuning the pre-training weight of the backbone for migration learning in our model. Results from experimental analysis reveal that mAP@0.5 and mAP@0.5:0.95 values witness a percentage increase of 0.2% and 1.7%, respectively, attesting to the superiority of the proposed model to YOLOv5, which is the state-of-the-art model in object detection.

Recently, blockchain technology has garnered support. However, an attenuating factor to its global adoption in certain use cases is privacy-preservation owing to its inherent transparency. A widely explored cryptographic option to address this challenge has been ring signature which aside its privacy guarantee must be double spending resistant. In this paper, we identify and prove a catastrophic flaw for double-spending attack in a Lightweight Ring Signature scheme and proceed to construct a new, fortified commitment scheme using the signer’s entire private key. Subsequently, we compute a stronger key image to yield a double-spending-resistant signature scheme solidly backed by formal proof. Inherent in our solution is a novel, zero-knowledge-based, secured and cost-effective smart contract for public key aggregation. We test our solution on a private blockchain as well as Kovan testnet along with performance analysis attesting to efficiency and usability and make the code publicly available on GitHub.