Supply chains are evolving into automated and highly complex networks and are becoming an important source of potential benefits in the modern world. At the same time, consumers are now more interested in food product quality. However, it is challenging to track the provenance of data and maintain its traceability throughout the supply chain network. The traditional supply chains are centralized and they depend on a third party for trading. These centralized systems lack transparency, accountability and auditability. In our proposed solution, we have presented a complete solution for blockchain-based Agriculture and Food (Agri-Food) supply chain. It leverages the key features of blockchain and smart contracts, deployed over ethereum blockchain network. Although blockchain provides immutability of data and records in the network, it still fails to solve some major problems in supply chain management like credibility of the involved entities, accountability of the trading process and traceability of the products. Therefore, there is a need of a reliable system that ensures traceability, trust and delivery mechanism in Agri-Food supply chain. In the proposed system, all transactions are written to blockchain which ultimately uploads the data to Interplanetary File Storage System (IPFS). The storage system returns a hash of the data which is stored on blockchain and ensures efficient, secure and reliable solution. Our system provides smart contracts along with their algorithms to show interaction of entities in the system. Furthermore, simulations and evaluation of smart contracts along with the security and vulnerability analyses are also presented in this work.

This paper presents an automatic solution to the problem of detecting and counting cars in unmanned aerial vehicle (UAV) images. This is a challenging task given the very high spatial resolution of UAV images (on the order of a few centimetres) and the extremely high level of detail, which require suitable automatic analysis methods. Our proposed method begins by segmenting the input image into small homogeneous regions, which can be used as candidate locations for car detection. Next, a window is extracted around each region, and deep learning is used to mine highly descriptive features from these windows. We use a deep convolutional neural network (CNN) system that is already pre-trained on huge auxiliary data as a feature extraction tool, combined with a linear support vector machine (SVM) classifier to classify regions into “car” and “no-car” classes. The final step is devoted to a fine-tuning procedure which performs morphological dilation to smooth the detected regions and fill any holes. In addition, small isolated regions are analysed further using a few sliding rectangular windows to locate cars more accurately and remove false positives. To evaluate our method, experiments were conducted on a challenging set of real UAV images acquired over an urban area. The experimental results have proven that the proposed method outperforms the state-of-the-art methods, both in terms of accuracy and computational time.

Local energy generation and peer to peer (P2P) energy trading in the local market can reduce the energy consumption cost, emission of harmful gases (as renewable energy sources are used to generate energy at user's premises) and increase the smart grid resilience. However, local energy trading with peers can have trust and privacy issues. A centralized system can be used to manage this energy trading but it increases the overall cost of the system and also faces several issues. In this paper, to implement a hybrid P2P energy trading market, a blockchain-based system is proposed. It is fully decentralized and allows the market members to interact with each other and trade energy without involving a third party. Smart contracts play a very important role in the blockchain-based energy trading market. They contain all the necessary rules for energy trading. We have proposed three smart contracts to implement the hybrid electricity trading market. The market members interact with the main smart contract, which requests P2P and prosumer to grid smart contracts for further processing. The main objectives of this paper are to propose a model to implement an efficient hybrid energy trading market while reducing cost and peak to average ratio of electricity.

In this paper, a blockchain-based data sharing and access control system is proposed, for communication between the Internet of Things (IoT) devices. The proposed system is intended to overcome the issues related to trust and authentication for access control in IoT networks. Moreover, the objectives of the system are to achieve trustfulness, authorization, and authentication for data sharing in IoT networks. Multiple smart contracts such as Access Control Contract (ACC), Register Contract (RC), and Judge Contract (JC) are used to provide efficient access control management. Where ACC manages overall access control of the system, and RC is used to authenticate users in the system, JC implements the behavior judging method for detecting misbehavior of a subject (i.e., user). After the misbehavior detection, a penalty is defined for that subject. Several permission levels are set for IoT devices’ users to share services with others. In the end, performance of the proposed system is analyzed by calculating cost consumption rate of smart contracts and their functions. A comparison is made between existing and proposed systems. Results show that the proposed system is efficient in terms of cost. The overall execution cost of the system is 6,900,000 gas units and the transaction cost is 5,200,000 gas units.

In the clinical and healthcare domains, medical images play a critical role. A mature medical visual question answering system (VQA) can improve diagnosis by answering clinical questions presented with a medical image. Despite its enormous potential in the healthcare industry and services, this technology is still in its infancy and is far from practical use. This paper introduces an approach based on a transformer encoder–decoder architecture. Specifically, we extract image features using the vision transformer (ViT) model, and we embed the question using a textual encoder transformer. Then, we concatenate the resulting visual and textual representations and feed them into a multi-modal decoder for generating the answer in an autoregressive way. In the experiments, we validate the proposed model on two VQA datasets for radiology images termed VQA-RAD and PathVQA. The model shows promising results compared to existing solutions. It yields closed and open accuracies of 84.99% and 72.97%, respectively, for VQA-RAD, and 83.86% and 62.37%, respectively, for PathVQA. Other metrics such as the BLUE score showing the alignment between the predicted and true answer sentences are also reported.

Exploring the relevance between images and their respective natural language descriptions, due to its paramount importance, is regarded as the next frontier in the general computer vision literature. Thus, recently several works have attempted to map visual attributes onto their corresponding textual tenor with certain success. However, this line of research has not been widespread in the remote sensing community. On this point, our contribution is three-pronged. First, we construct a new dataset for text-image matching tasks, termed TextRS, by collecting images from four well-known different scene datasets, namely AID, Merced, PatternNet, and NWPU datasets. Each image is annotated by five different sentences. All the five sentences were allocated by five people to evidence the diversity. Second, we put forth a novel Deep Bidirectional Triplet Network (DBTN) for text to image matching. Unlike traditional remote sensing image-to-image retrieval, our paradigm seeks to carry out the retrieval by matching text to image representations. To achieve that, we propose to learn a bidirectional triplet network, which is composed of Long Short Term Memory network (LSTM) and pre-trained Convolutional Neural Networks (CNNs) based on (EfficientNet-B2, ResNet-50, Inception-v3, and VGG16). Third, we top the proposed architecture with an average fusion strategy to fuse the features pertaining to the five image sentences, which enables learning of more robust embedding. The performances of the method expressed in terms Recall@K representing the presence of the relevant image among the top K retrieved images to the query text shows promising results as it yields 17.20%, 51.39%, and 73.02% for K = 1, 5, and 10, respectively.