Showing papers by "Zheng Yan published in 2012"

Model Predictive Control for Tracking of Underactuated Vessels Based on Recurrent Neural Networks

Abstract: In this paper, a model predictive control (MPC) scheme is presented for tracking of underactuated vessels with only two available controls: namely, surge force and yaw moment. When no external disturbance is explicitly considered, the proposed MPC approach iteratively solves a formulated quadratic programming (QP) problem using a single-layer recurrent neural network called the general projection network over a finite receding horizon. When additive disturbances are taken into account, a reformulated minimax optimization problem is iteratively solved by using a two-layer recurrent neural network. The applied neural networks are both stable in the sense of Lyapunov and globally convergent to the exact optimal solutions of reformulated convex programming problems. Simulation results are provided to demonstrate the effectiveness and characteristics of the proposed neurodynamics-based MPC approaches to vessel tracking control.

Model Predictive Control of Nonlinear Systems With Unmodeled Dynamics Based on Feedforward and Recurrent Neural Networks

Abstract: This paper presents new results on a neural network approach to nonlinear model predictive control. At first, a nonlinear system with unmodeled dynamics is decomposed by means of Jacobian linearization to an affine part and a higher-order unknown term. The unknown higher-order term resulted from the decomposition, together with the unmodeled dynamics of the original plant, are modeled by using a feedforward neural network via supervised learning. The optimization problem for nonlinear model predictive control is then formulated as a quadratic programming problem based on successive Jacobian linearization about varying operating points and iteratively solved by using a recurrent neural network called the simplified dual network. Simulation results are included to substantiate the effectiveness and illustrate the performance of the proposed approach.

TruBeRepec: a trust-behavior-based reputation and recommender system for mobile applications

Abstract: Mobile applications are software packages that can be installed and executed in a mobile device. Which mobile application is trustworthy for a user to purchase, download, install, execute or recommend becomes a crucial issue that impacts its final success. This paper proposes TruBeRepec, a trust-behavior-based reputation and recommender system for mobile applications. We explore a model of trust behavior for mobile applications based on the result of a large-scale user survey. We further develop a number of algorithms that are used to evaluate individual user's trust in a mobile application through trust behavior observation, generate the application's reputation by aggregating individual trust and provide application recommendations based on the correlation of trust behaviors. We show the practical significance of TruBeRepec through simulations and analysis with regard to effectiveness, robustness, and usability, as well as privacy.

Methods, apparatuses, and computer-readable storage media for securely accessing social networking data

Abstract: An approach is provided for controlling access to social networking data for each of a plurality of members by issuing one or more first keys for at least one of data encryption or data decryption, based on a respective current trust level associated with a corresponding member and one or more context attributes corresponding to the social networking data. The one or more first keys expire at an expiration time determined with reference to a time clock. Based on a signal accepted from the time clock, one or more second keys for at least one of data encryption or data decryption are issued to one or more members of the plurality of members who are associated with a trust level above a predetermined threshold and/or who satisfy specified context attributes, prior to the expiration time of the first keys.

Unwanted Traffic Control via Hybrid Trust Management

Abstract: At the same time as the Internet provides a lot of social value, it is bogged down by unwanted traffic, which is malicious, harmful or unexpected for its receiver. This paper proposes an unwanted traffic control solution through hybrid trust management. It can control unwanted traffic from its source to destinations according to trust evaluation at a Global Trust Operator and traffic and behavior analysis at hosts. Thus, it can support unwanted traffic control in both a distributed and centralized manner and in both a defensive and offensive way. Simulation based evaluation shows that the solution is effective with regard to botnet intrusion, malicious attack of ISP and DDoS intrusion via reflectors.

A neurodynamic approach to bicriteria model predictive control of nonlinear affine systems based on a Goal Programming formulation

Abstract: This paper presents a neurodynamic approach to bicriteria model predictive control (MPC) of nonlinear affine systems based on a goal programming formulation. Bicriteria MPC refers to finding optimal control inputs that minimizes two performance indexes corresponding to tracking errors and control efforts. The bicriteria MPC is formulated as the solution to a nonlinear optimization problem via goal programming technique and is solved by using a two-layer recurrent neural network. Simulation results are included to illustrate the effectiveness of the proposed approach.

Model predictive control of autonomous underwater vehicles based on the simplified dual neural network

Abstract: Based on a recurrent neural network, a model predictive control (MPC) method for control of a class of autonomous underwater vehicles (AUVs) is presented. A coupled nonlinear kinematic model with constrains is considered. The model predictive control problem of AUVs is formulated as a time-varying quadratic programming problem, and a one-layer recurrent neural network called the simplified dual network is applied for real-time optimization. It is able to converge to the global optimal solution of the constrained optimization problem. Simulation results are discussed to demonstrate the effectiveness and characteristics of the proposed model predictive control method.

Gemini: A Handbag for Pervasive Social Communications

Abstract: Fashionable technology is becoming a trend in HCI design. It extends the traditional understanding of HCI by emphasizing on the aesthetic element. Pervasive social communications are instant social activities through communications based on mobile elements. This paper investigates how to use the fashionable technology in pervasive social communications. It presents the design and preliminary prototype of Gemini, a fashionable bag for pervasive social communications. The social acceptance of Gemini design is also explored through a small-scale user study.

An approach of secure and fashionable recognition for pervasive face-to-face social communications

Abstract: Pervasive social communications are instant social activities through communications based on mobile elements, e.g., via mobile ad hoc networks. Meanwhile, fashionable technology is becoming a trend in Human-Computer Interaction (HCI) design. It extends the traditional understanding of HCI by emphasizing aesthetic element. This paper investigates how to use fashionable technology in pervasive social communications. It presents a novel approach to realize secure recognition for pervasive face-to-face social communications based on MANET, local connectivity and fashionable technology. The social acceptance of this inter-disciplinary approach is explored through a small-scale user study.

Implementation of an Evaluation Platform for Unwanted Traffic Control via Trust Management

Abstract: People's life has been totally changed by the fast growth of the Internet, which provides opportunities to get access to huge amount of information resources, killer services and applications, offering users great convenience. However, various unwanted or unexpected contents could be distributed over the Internet, which greatly burden both users and internet service providers. People have conducted much research on unwanted traffic control via trust and reputation mechanisms, but literature still lacks a good evaluation platform that could simulate various kinds of attacks on the trust management systems and evaluate their performance. This paper reports the design and implementation of a MATLAB-based evaluation platform, which can simulate a network environment and evaluate trust management performance under various intrusion and attack models for unwanted traffic control. We investigate the effectiveness of the evaluation platform through case studies on two trust management systems: global trust management system and hybrid trust management system. Our evaluation results show the applicability of our platform.

Compact Triple-Band Printed Antenna with a via Hole Connecting to a Parasitic Patch for Wlan and Wimax Applications

Abstract: A compact triple-band printed antenna for wireless local area network and worldwide interoperability for microwave access (WLAN and WiMAX) applications is proposed. The antenna occupies only a small area of 34 × 11 mm2 and consists of branch strips, a parasitic patch and a modified ground plane. With the use of a plated-through via connecting the parasitic patch with the branch strips on the both sides, multiple impedance bandwidths covering WLAN/2.4/5.2/5.8 and WiMAX/3.5 are obtained. In addition, the proposed antenna has good radiation characteristic and peek gains to be 3.92, 2.8 and 3.8 dBi at 2.45, 3.5 and 5.5 GHz, respectively.

Control method of 4WS based on neural network

Abstract: This paper introduces an active 4WS control method based on neural network. The method takes nonlinear dynamic characteristic of vehicle and tire into account. And discerns them by neural network method according to those actual survey data come from real vehicle. It shows that it has a good control property and can improve the safety and handling stability of vehicle effectively.

A neurodynamic approach to model predictive control of piecewise linear systems

Abstract: This paper presents a neurodynamic approach to model predictive control (MPC) of constrained piecewise linear systems. A novel procedure for estimating uncertain system parameters of piecewise linear systems is proposed. The model predictive control problem is then formulated as a quadratic optimization problem. To realize the real-time optimization in MPC, a one-layer recurrent neural network is employed for solving the quadratic optimization problem during each sampling interval. The overall MPC approach is of low computational complexity. Simulation results are included to substantiate the effectiveness and usefulness of the proposed approach.

Mechanism for Security Enhancement in Mobile Application Installation

Abstract: Mobile operating systems (e.g., iOS, Android, Windows Mobile, etc) are becoming powerful platforms on which various applications can be installed and run. Each mobile OS offers application store (e.g., Apple App Store, Android Play, etc) for developers to easily publish applications and earn profits. However, existing mobile platforms provide little means for mobile users to evaluate risks on allowing certain security permissions when installing mobile applications. Since mobile users may not be able to justify the risks on allowing certain permissions required by an application, mobile users may install malware with extra permissions, which leads to security risk for mobile users, e.g., private information leaked, etc. In this paper, we present process and visual User Interface for mobile users to understand and justify the risks on permissions required by mobile applications during installation. We also present two algorithms for calculating the risks.