The identification of the characteristics of urban road traffic accidents is of great significance for reducing traffic accidents and the corresponding losses. In the context of big data, to accurately understand the characteristics of traffic accidents, the feature set of urban road traffic accidents is proposed, the XGBoost model is used to classify traffic accidents into minor accidents, general accidents, major accidents and serious accidents, and a GA-XGBoost feature recognition model is built. The GA-XGBoost feature recognition model is based on the genetic algorithm (GA) as a factor search algorithm and is verified by applying the big data of traffic accidents in a Chinese city from 2006 to 2016; in addition, the model is compared with the GA-RF, GA-GBDT and GA-LightGBM models. The results show that the GA-XGBoost model can accurately identify the features of the traffic accidents in 7 cities, including driving experience, illegal driving behavior, vehicle age, road intersection type, weather conditions, traffic flow and time interval. Compared with the GA-RF, GA-GBDT and GA-LightGBM models, the recognition features are more accurate, and the performance is better.

With more businesses are running online, the scale of data centers is increasing dramatically. The task-scheduling operation with traditional heuristic algorithms is facing the challenges of uncertainty and complexity of the data center environment. It is urgent to use new technology to optimize the task scheduling to ensure the efficient task execution. This study aimed at building a new scheduling model with deep reinforcement learning algorithm, which integrated the task scheduling with resource-utilization optimization. The proposed scheduling model was trained, tested, and compared with classical scheduling algorithms on real data center datasets in experiments to show the effectiveness and efficiency. The experiment report showed that the proposed algorithm worked better than the compared classical algorithms in the key performance metrics: average delay time of tasks, task distribution in different delay time levels, and task congestion degree.

Fruit tree diseases have a great influence on agricultural production. Artificial intelligence technologies have been used to help fruit growers identify fruit tree diseases in a timely and accurate way. In this study, a dataset of 10,000 images of pear black spot, pear rust, apple mosaic, and apple rust was used to develop the diagnosis model. To achieve better performance, we developed three kinds of ensemble learning classifiers and two kinds of deep learning classifiers, validated and tested these five models, and found that the stacking ensemble learning classifier outperformed the other classifiers with the accuracy of 98.05% on the validation dataset and 97.34% on the test dataset, which hinted that, with the small‐ and middle‐sized dataset, stacking ensemble learning classifiers may be used as cost‐effective alternatives to deep learning models under performance and cost constraints.

The sharing of electronic healthcare records (EHRs) is important to healthcare and medical research. However, institutions are faced with difficulties in privacy protection and efficiently secure data exchange. The main objective of this study is to propose a controllable secure blockchain-based EHRs sharing scheme. For this purpose, blockchain technologies are combined with interplanetary file systems (IPFS) to provide efficient secure EHRs sharing. Firstly, the IPFS-based EHR file system (IEFS) is designed to save and share large-size EHR files among medical institutions. With the high-throughput content-addressed block storage model and appropriate redundant backup of IPFS, IEFS is tamper-resistant and free of a single point of failure. Secondly, the blockchain is used to implement the blockchain-based EHR abstract system (BEAS) to manipulate EHR abstracts access. In BEAS, the EHR file addresses generated by IEFS are encrypted and saved in EHR abstracts for privacy protection. Since EHR abstracts are encrypted by patients’ public keys, the sharing of EHR files is under the control of patients. In our experiment, a prototype system is developed to validate the proposed scheme. The experimental results showed that (1) EHRs are securely shared under the control of patients and (2) EHR files are retrieved at an acceptable speed supported by IPFS technology. In this paper, solutions to some important practical issues such as incapacitated patients, encryption key forgetting/missing, and efficient interaction of doctors with EHRs sharing scheme are also seriously discussed.

E-Auction improves the efficiency of bid transaction. However, the protection of bidders’ privacy, transaction fairness and verifiability, transaction data security, high cost of third-party auction center, and other issues have attracted more attention. According to the transaction process and basic principles of the sealed auction, we explored the problems existing in the current sealed-bid e-auction schemes. Based on the blockchain technology, we proposed a sealed-bid e-auction scheme with smart contract technology, Bulletproofs zero-knowledge proof protocols, and Pedersen commitment algorithm. The proposed scheme constructed an auction mechanism without the third-party auctioneer so as to restrict the behaviors of auction parties for the sake of auction security, reliability, fairness, and privacy protection. Compared with the related sealed e-auction schemes based on blockchain technologies in six metrics, we conducted the experiment to show that the proposed scheme protected the bid information from leakage well and successfully verified the winning bid price and the related bidder by all transaction participants without the third-party auctioneer.

One of the major contradictions in China’s healthcare service is the serious imbalance between the supply and demand of medical resources and the uneven distribution of medical resources. Although the government intended to provide equal access for all, in the final evaluation, fairness of the distribution of services was usually dictated by location. Measuring and predicting access to social services can help to adjust and better accommodate underserved regions. 3SFCA modes based on the Gaussian function are proposed to delineate the service area of providers delivering social services and produce a probability metric that maps the equity of the medical services in multiple traffic modes. We identified the types of medical shortage areas and analyzed the distribution characteristics of medical accessibility in Guangzhou. The results showed that the accessibility of medical facilities in the multiple traffic modes varied greatly. The accessibility level of medical service resources was the highest in the driving mode, followed by the public traffic mode and bike-riding mode. The walking mode had the lowest accessibility. Finally, the paper provided advice for further improvement of the equal distribution of medical service resources in Guangzhou.