7 July 2022 in IEEE Internet of Things Journal
Blockchain is an innovative application of distributed storage, consensus algorithm, encryption algorithm, and other computer technologies. The consensus algorithm is the key to keep consistent among blockchain nodes. In most existing consensus algorithms, the leader node is responsible for proposing new block and communicating with other nodes. The leader node is easy to be the target of malicious attackers. With the increase of the number of nodes, the throughput and scalability of the blockchain system are also unsatisfactory. To address such issues, we propose the AnonymousFox consensus algorithm, which is suitable for the consortium blockchain and private blockchain. First, we design an anonymous leader node sorting algorithm, which hides the identity of the leader node through a variety of encryption algorithms. It periodically changes the ordered leader list to hide the target of malicious attackers. In addition, we design a consensus algorithm based on the anonymous identity of the leader node. Through one-to-many message communication, the amount of messages is greatly reduced. The complexity of the algorithm is $O(n)$ . It solves the problem of ordered replication of state machines when the leader node is anonymous. We analyze the algorithm, it ensures safety and liveness when the fault nodes are less than one-third of the total. We evaluate the throughput, latency, scalability, resource consumption, exception processing, smart contract, and blockchain network through experiments. The throughput of the proposed algorithm is 49.3% higher than that of the practical Byzantine fault tolerance (PBFT) algorithm. The experimental results show that the proposed algorithm has high performance and scalability.
29 August 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Manga is a fashionable Japanese-style comic form that is composed of black-and-white strokes and is generally displayed as raster images on digital devices. Typical mangas have simple textures, wide lines, and few color gradients, which are vectorizable natures to enjoy the merits of vector graphics, e.g., adaptive resolutions and small file sizes. In this paper, we propose MARVEL (MAnga’s Raster to VEctor Learning), a primitive-wise approach for vectorizing raster gray-level mangas by Deep Reinforcement Learning (DRL). Unlike previous learning-based methods which predict vector parameters for an entire image, MARVEL introduces a new perspective that regards an entire manga as a collection of basic primitives—stroke lines, and designs a DRL model to decompose the target image into a primitive sequence for achieving accurate vectorization. To improve vectorization accuracies and decrease file sizes, we further propose a stroke accuracy reward to predict accurate stroke lines, and a pruning mechanism to avoid generating erroneous and repeated strokes. Extensive subjective and objective experiments show that our MARVEL can generate impressive results and reaches the state-of-the-art level.
14 June 2023 in Peer-to-Peer Networking and Applications
20 August 2024 in Journal of Network and Computer Applications
1 February 2021 in Software Testing, Verification and Reliability
25 August 2025 in IEEE Transactions on Services Computing
Social images shared on social media are often associated with geo-tagged information and text descriptions. Given a set of keywords and a spatial location, geo-tagged social image search can retrieve top-k image objects that best match query parameters in terms of spatial distance and tag similarity of social images. However, due to improper parameter settings, users may notice that some expected images are missing and wonder why these objects do not appear in the query results. This paper studies the why-not top-k social image search question and proposes efficient query refinement algorithms, aiming to minimally modify users' initial queries to reintroduce missing objects. We first develop a baseline algorithm that traverses each possible query parameter sequentially to find the best refinement parameters. Then, we propose a fast search algorithm with two optimization strategies named lower ranking nodes pruning and early stop pruning, which can improve performance by quickly removing low-ranking social images. In addition, we propose an efficient boundary search algorithm that can determine the ranking of missing images at a low time cost. We also extend the proposed techniques to handle multiple missing images. Extensive experimental results demonstrate that the proposed solution is two orders of magnitude faster than baseline and is effective in a wide range of settings.