The organization and management of electricity markets worldwide are rapidly evolving, moving towards decentralized, distributed, and renewable energy-based generation with solutions based on real-time data exchange. A Vehicle-to-Vehicle (V2V) energy trading has emerged as one of the most promising alternatives for relieving the load imposed on the traditional grid enabling two individuals to buy and sell energy directly without intermediaries. However, the Internet of Electric Vehicles (IoEV) environment is trustless, and such P2P energy trading is prone to different kinds of cyber attacks. Blockchain technology has lately been proposed to implement V2V energy trading to securely and fairly share energy. The consensus mechanism is one of the most important modules of blockchain applied to the V2V network. It determines the efficiency and security among untrustworthy EVs of the energy trading blockchain (ETB). Nevertheless, most works on ETB have currently adopted traditional consensus mechanisms. Due to high computing power and communication overhead, these consensus algorithms are unsuitable for applications requiring real-time services such as energy trading. The efficient and secured Hashgraph is the revolutionary technology of consensus in blockchain and a promising technology suitable for V2V energy trading with frequent transactions. However, Hashgraph does not support the dynamic addition and deletion of nodes and is completely decentralized and vulnerable to Sybil Attack in a large-scale blockchain. Furthermore, this “complete decentralization” model may result in states losing the ability to macro-control the energy industry and even systemic energy security issues. Therefore, we propose a Block Alliance Consensus (BAC) mechanism to solve these problems. BAC can maintain the throughput of Hashgraph and resist Sybil Attack in a large-scale P2P energy trading network. We design a cryptography-based leader election mechanism and adopt a reputation incentive mechanism to motivate honest and cooperative electric vehicles (EVs). Finally, we implement ETB and the BAC consensus mechanism on the Hyperledger Fabric platform. The high efficiency and security of BAC and the blockchain-based V2V energy trading platform are verified through experiments.

Computed tomography (CT) is increasingly essential for clinical diagnosis nowadays while X-ray ionizing radiation is harmful and may increase the risk of cancers. Researchers have thus proposed to obtain the sparse sinograms by reducing the number of detectors to reduce the radioactive impact on human body. However, the sparse-view sinograms have some problems including blurring and streak artifacts, which may adversely confuse the diagnostic assessment to some extent. In this paper, we propose a Transformer-based module named DDPTransformer Block to capture the long-term dependencies within the images and reconstruct high-quality CT images from sparsely sampled sinograms. More specifically, we replace the traditional convolution operation with the Parallel Transformers, and augment the edge information of patch blocks by different splits. In addition, considering that the images to be processed are two-dimensioned, we propose the Layer-Conv-Layer (LCL) module to replace the multilayer perceptron (MLP) in Transformer for feature extraction. Finally, with DDPTransformer Block as the backbone, we propose a deep learning model with four stages including Interpolation, Sinogram Domain Subnet, Filtered BackProjection (FBP) and Image Domain SubNet. For training the model, we use the dataset from the “ Low Dose CT Image and Projection Data (LDCT-and-Projection data)”. Experimental results show that the proposed model outperforms the state-of-the-art algorithms for various sparsely sampled sinograms and its robustness has been further verified through other datasets. The code and model are publicly available at: https://github.com/MikasaLee/DDPTransformer .

There has been a growing penetration of renewable energy sources (RES) into power grids in recent years. As extreme weather events and cyber-attacks frequently occur, grid resilience has been an important issue. Vehicle-to-Vehicle (V2V) energy trading has great potential to improve the stability and reliability of resilient power grids integrated with high-penetrated RES. V2V energy trading is a distributed peer-to-peer (P2P) application. As a decentralized distributed ledger technology, blockchain is an ideal platform for V2V energy trading. The consensus mechanism of blockchain determines whether the V2V energy trading blockchain (ETB) can improve grid resilience. However, most studies in the ETB currently utilize conventional consensus mechanisms. Due to their substantial computational requirements and communication overhead, these consensus algorithms are not well-suited for real-time service applications like energy trading. We propose a novel BAC-SDS consensus specifically for V2V ETB, thus enabling resilient grids to maximise the use of renewable energy. We propose an Electric Vehicle (EV) leader election based on cryptography and adopt the sharding technique to enhance the system's scalability. Furthermore, our approach ensures the secure transfer of energy and value, contingent upon the condition that all EVs exhibit reasonable behavior and retain the proofs they possess. We implement the V2V ETB on Hyperledger Fabric. The experiments demonstrate (1) that V2V ETB significantly enhances the resilience of the power grid compared to traditional centralized trading models and (2) the consensus mechanism proposed in this paper is better suited for V2V energy trading than existing mechanisms, exhibiting superior performance in terms of security, throughput, and scalability, thus further enhancing the resilience of the power grid.

Background: Predicting the mutation statuses of 2 essential pathogenic genes [epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma (KRAS)] in non-small cell lung cancer (NSCLC) based on CT is valuable for targeted therapy because it is a non-invasive and less costly method. Although deep learning technology has realized substantial computer vision achievements, CT imaging being used to predict gene mutations remains challenging due to small dataset limitations. Methods: We propose a multi-channel and multi-task deep learning (MMDL) model for the simultaneous prediction of EGFR and KRAS mutation statuses based on CT images. First, we decomposed each 3D lung nodule into 9 views. Then, we used the pre-trained inception-attention-resnet model for each view to learn the features of the nodules. By combining 9 inception-attention-resnet models to predict the types of gene mutations in lung nodules, the models were adaptively weighted, and the proposed MMDL model could be trained end-to-end. The MMDL model utilized multiple channels to characterize the nodule more comprehensively and integrate patient personal information into our learning process. Results: We trained the proposed MMDL model using a dataset of 363 patients collected by our partner hospital and conducted a multi-center validation on 162 patients in The Cancer Imaging Archive (TCIA) public dataset. The accuracies for the prediction of EGFR and KRAS mutations were, respectively, 79.43% and 72.25% in the training dataset and 75.06% and 69.64% in the validation dataset. Conclusions: The experimental results demonstrated that the proposed MMDL model outperformed the latest methods in predicting EGFR and KRAS mutations in NSCLC.