Showing papers by "Yongrui Qin published in 2019"

Enabling Distributed Intelligence in the Internet of Things using the IOTA Tangle Architecture

Abstract: It is estimated that there will be approximately 26 to 30 billion Internet of Things (IoT) devices connected to the Internet by 2020. This presents research challenges in areas such as data processing, infrastructure scalability, and privacy. Several studies have demonstrated the benefits of using distributed intelligence to overcome these challenges. This article reviews existing state-of-the-art distributed intelligence approaches in IoT and focuses on the motivations and challenges for distributed intelligence in IoT. We propose a potential solution based on IOTA (Tangle), a platform that enables highly scalable transaction-based data exchange amongst large quantities of smart things in a peer-to-peer manner, together with mobile agents to support distributed intelligence. Challenges and future research directions are also discussed.

3D Object Detection Algorithm for Panoramic Images With Multi-Scale Convolutional Neural Network

Abstract: This paper addresses the challenge of 3D object detection from a single panoramic image under severe deformation. The advent of the two-stage approach has impelled significant progress in 3D object detection. However, most available methods only can localize region proposals by a single-scale architecture network, which are sensitive to deformation and distortion. To address this issue, we propose a multi-scale convolutional neural network (MSCNN) to estimate the 3D pose of an object. To be specific, the proposed MSCNN consists of three steps for effectively detecting the distorted object on the panoramic images. The MSCNN contains the CycleGAN network that converts rectilinear images into panoramas, a fused framework that improves both accuracy and speed for object detection, and an adversarial spatial transformer network (ASTN) that extracts the deformation features of the object on panoramic images. Additionally, we recover the 3D pose of the object using a coordinate projection and a 3D bounding box. Extensive experiments demonstrate that the proposed method can achieve a 3D detection accuracy of 38.7% in high-resolution panoramic images, which is higher than the current state-of-the-art algorithm of 5.2%. Moreover, the speed of detection is only about 0.6 seconds per image, which is six times faster than Faster R-CNN (COCO). The code will be available at https://github.com/Yanhui-He.

Guidance Systematic Error Separation for Mobile Launch Vehicles Using Artificial Fish Swarm Algorithm

Abstract: For missile’s accuracy assessment, an accurate separation about the guidance of systematic errors is a critical part. Based on the vehicles from a mobile launcher platform, this paper proposes a nonlinear error separation model and a corresponding method in consideration of the ill-conditioning of the environmental function matrix, and the coupling of the guidance instrumental errors and the initial errors. The nonlinear model is built in combination with the tracking data. For the error separation problem with ill-conditioning, the traditional nonlinear methods can only slightly weaken the degree of ill-conditioning rather than solve it. To address this issue, this paper puts forward a novel guidance systematic error separation method based on the artificial fish swarm algorithm (AFSA). We first provide a brief introduction to AFSA and then analyze the convergence and the optimality of parameter estimation. Furthermore, we present the details of our novel algorithm that can address the guidance systematic error separation problem. We conduct a set of simulations to verify our approach. The simulation results confirm that our approach, which is based on AFSA, can improve the error separation accuracy effectively and perform better than the Bayesian estimation based on the traditional linear model and the Bayesian maximum a posteriori estimation based on the nonlinear model.

Fault Detection for Closed-Loop Control Systems Based on Parity Space Transformation

Abstract: Fault detection for closed-loop control systems is the future development in the field of the fault diagnosis. Since a closed-loop control system is generally very robust to the external disturbances, fault detection has been challenging a hot research area. Traditional data-driven detection methods are not particularly designed for closed-loop control systems and thus can be improved. In this paper, a new fault detection method is proposed, which is based on the parity space for the closed-loop control system. The main principle of our method is to transform the detection residual into the parity space of the original space to restrict false detection or leak detection caused by the estimation of uncertain states. More specifically, the construction of the stable kernel matrix in the parity space is given, and the residual sequence is accumulated to improve the fault-to-noise ratio and thus increase the detection performance. To verify our method, we have conducted a simulation which is based on a numerical simulation model and the Tennessee industrial system respectively. The results show that the proposed method is more feasible and more effective in fault detection for closed-loop control systems compared with the traditional data-driven detection methods, including the time series modeling method and the partial least squares method.

Research Directions on Big IoT Data Processing Using Distributed Ledger Technology: A Position Paper

Abstract: The significant growth and adoption of Internet of Things (IoT) solutions has led to tremendous increase in the generation of data. The need for high speed data processing has become very important to meet with the ever increasing volume and velocity of IoT data, due to the large scale and distributed nature of IoT infrastructure and networks. Present cloud based technologies are struggling to meet up with these needs for real time data processing in the midst of enormous amounts of data. The success of bitcoin has inspired more research in the application of Distributed ledger technologies in various domains. The decentralized nature of these platforms have enabled security and privacy of data in previous research and their architecture has a potential for enabling large scale decentralized data processing. In this paper, we identify some open areas of research in the use of distributed ledger technology and propose a framework for storing, analyzing and ensuring the security of large volumes of IoT data.