Hengtao Wang

An RFID indoor positioning system by using weighted path loss and extreme learning machine

Radio Frequency Identification (RFID) technology has been widely used in many application domains. How to apply RFID technology to develop an Indoor Positioning System (IPS) has become a hot research topic in recent years. LANDMARC approach is one of the first IPSs by using active RFID tags and readers to provide location based service in indoor environment. However, major drawbacks of the LANDMARC approach are that its localization accuracy largely depends on the density of reference tags and the high cost of RFID readers. In order to overcome these drawbacks, two localization algorithms, namely weighted path loss (WPL) and extreme learning machine (ELM), are proposed in this paper. These two approaches are tested on a novel cost-efficient active RFID IPS. Based on our experimental results, both WPL and ELM can provide higher localization accuracy and robustness than existing ones.

Estimation of occupancy level in indoor environment based on heterogeneous information fusion

Monitoring the number of occupants in each zone of a building is important for energy-efficient control of the HVAC system and the lighting system under normal conditions and for fast evacuation under emergency conditions. There usually exist multiple systems for localizing and monitoring the occupants in a building such as the active RFID system and the video cameras. The accuracy of each system is affected by different factors. Further hardware investment is usually required to improve the accuracy of each system. It is thus of practical interest to combine multiple systems to achieve higher counting accuracy without further hardware investment. In this paper, this problem is formulated as an information fusion problem under the criterion of minimum mean square error. However, it is usually difficult to solve the problem optimally due to the lack of data on the joint distribution of the observation noises of multiple systems. Two approximation methods are developed following the independence assumption and heuristics, respectively. Experimental results show that the two methods improve the accuracy of the active RFID system and the video cameras by around 43% and 73%, respectively.

Platform and Algorithm Development for a RFID-Based Indoor Positioning System

In recent years, developing Indoor Positioning System (IPS) has become an attractive research topic due to the increasing demands on Location-Based Service (LBS) in indoor environment. Several advantages of Radio Frequency Identification (RFID) Technology, such as anti-interference, small, light and portable size of RFID tags, and its unique identification of different objects, make it superior to other wireless communication technologies for indoor positioning. However, certain drawbacks of existing RFID-based IPSs, such as high cost of RFID readers and active tags, as well as heavy dependence on the density of reference tags to provide the LBS, largely limit the application of RFID-based IPS. In order to overcome these drawbacks, we develop a cost-efficient RFID-based IPS by using cheaper active RFID tags and sensors. Furthermore, we also proposed three localization algorithms: Weighted Path Loss (WPL), Extreme Learning Machine (ELM) and integrated WPL-ELM. WPL is a centralized model-based approach which does not require any reference tags and provides accurate location estimation of the target effectively. ELM is a machine learning fingerprinting-based localization algorithm which can provide higher localization accuracy than other existing fingerprinting-based approaches. The integrated WPL-ELM approach combines the fast estimation of WPL and the high localization accuracy of ELM. Based on the experimental results, this integrated approach provides a higher localization efficiency and accuracy than existing approaches, e.g., the LANDMARC approach and the support vector machine for regression (SVR) approach.

An integrative Weighted Path Loss and Extreme Learning Machine approach to Rfid based Indoor Positioning

In recent years, applying RFID technology to develop an Indoor Positioning System (IPS) has become a hot research topic. The most prominent advantage of active RFID IPS comes from its unique identification of different objects in indoor environment. However, certain drawbacks of existing RFID IPSs, such as high cost of RFID readers and active tags, as well as heavy dependence on the density of reference tags to provide the location based service, largely limit the applications of active RFID IPS. In order to overcome these drawbacks, we develop a cost-efficient RFID IPS by using cheaper active RFID tags, sensors and reader. In addition, one localization algorithm: integrated Weighted Path Loss (WPL) - Extreme Learning Machine (ELM) which combines the fast estimation of WPL and the high localization accuracy of ELM is proposed. According to the algorithm, an indoor environment is divided into small zones firstly and an ELM model is developed for each zone during the offline phase. During the online phase, the WPL approach is used to determine the zone of the target primarily, then the ELM model of that zone is deployed to provide the final estimated location of the target. Based on our experimental result, this integrated algorithm provides a higher localization efficiency and accuracy than existing approaches.

Building occupant level estimation based on heterogeneous information fusion

It is of great practical interest to estimate the number of occupants at a zonal level in buildings, which is useful for energy-efficient control of air conditioning and lighting systems. We consider this important problem in this paper. First, the occupant level estimation problem is formulated as an information fusion problem with heterogeneous information sources with the criterion of the minimum mean square error (MMSE). Two fusion methods are developed. The first method assumes independent observation noises and the second method exploits the correlation among the multiple information sources to improve the estimation accuracy. The experimental results show that in comparison with individual RFID or video cameras, the two fusion methods improve the accuracy of occupant level estimation by 43% and 73%, respectively, and outperform the linear least mean square error (LLMSE) method 3]. Simulations and theoretical analysis are also conducted to analyze the performance of the two methods under different occupant levels and different correlated observations. It is shown that the second method is more effective for the cases where the multi-sensor measurements are highly correlated.

Estimation of occupant distribution by detecting the entrance and leaving events of zones in building

For energy saving and security in building, the information of occupant number of each zone is very important. This paper works on the estimation of the occupant number of zones in building by detecting the entrance and leaving events. In this paper, we first formulate the problem under an assumption of Markov Chain, and basing on the theoretical analysis of the model, we propose a method of occupant distribution estimation, which can be implemented distributively. The method counts occupant by detecting the entrance and leaving events of zones in real time and uses the prior information of the occupants entrance and leaving events in each zone to reduce the estimation error, which increases the accuracy of the estimation of occupant distribution in building. Numerical experiments including simulation and field test demonstrate the performance of the method.

Enhancing the Robustness and Efficiency of Scale-free Network with Limited Link Addition

The robustness of a network is usually measured by error tolerance and attack vulnerability. Significant research effort has been devoted to determining the network design with optimal robustness. However, little attention has been paid to the problem of how to improve the robustness of existing networks. In this paper, we investigate how to optimize attack tolerance and communication efficiency of an existing network under the limited link addition. A survival fitness metric is defined to measure both the attack tolerance and the communication efficiency of the network. We show that network topology reconfiguration optimization with limited link addition (NTRLA) problem is NP-hard. Two approximate solution methods are developed. First, we present a degree-fitness parameter to guide degree-based link addition method. Second, a preferential configuration node-protecting cycle (PCNC) method is developed to do trade-off between network robustness and efficiency. The performance of PCNC method is demonstrated by numerical experiments.

A Decentralized Stay-Time Based Occupant Distribution Estimation Method for Buildings

Zonal occupant level is of great practical interest for building energy saving under normal operations and for fast evacuation under emergency. Though there are many existing sensing systems to estimate this information, the problem is still challenging due to the privacy concerns, the random human movement, and the accumulative error. In this paper, we consider this important problem and focus on infrared beam systems that monitor the zonal arrival and departure events. We make the following contributions. First, a rule (i.e., Rule 1) based on the stay time is developed to reduce the accumulated estimation error in each zone. Second, a rule (i.e., Rule 2) is designed to coordinate the estimation among neighboring zones. A decentralized estimation method is then developed using these two rules. Third, the advantage of this method is demonstrated through simulation results and field tests. We hope this work brings insight to zonal occupant level estimation in buildings in more general situations.

Efficient topology optimization for a wired networked system by adding wireless communication

Adding wireless communication capabilities to networked systems can effectively improve its connectivity, which in turn improves the robustness of the system under emergency. When the resource is limited, only finite wireless communication capacities can be installed to the existing nodes. It is in general difficult to determine which nodes to install in order to achieve the required connectivity, leaving alone the further task to find the installation with efficiency requirement. We consider this important problem in this paper and make the following major contributions. First, we develop an algorithm to configure the network to achieve biconnectivity through installing the minimal number of wireless communication devices. Second, when there are multiple such installations, we further develop an algorithm to pick the installation that maximizes the efficiency of the network. Both algorithms are polynomial w.r.t. the network size. The performances of both algorithms are demonstrated through numerical examples. We hope this work brings insight to topology optimization in more general situations.

A systematic method for network topology reconfiguration with limited link additions

As a promising approach to improve network survivability, reliability and flexibility, topology reconfiguration is extremely important for modern networked infrastructures. In particular, for an existing network and the limited link addition resources, it is valuable to determine how to optimally allocate the new link resources, such that the resulting network is the most robust and efficient. In this paper, we investigate the problem of network topology reconfiguration (NTR) optimization with limited link additions. A dynamic robustness metric is developed to quantitatively characterize the robust connectivity and the efficiency under either random or targeted attack. We show that the NTR optimization with limited link additions is NP-hard. Therefore, to approximately solve the problem, we develop a preferential configuration node-protecting cycle (PCNC) method for sequential link additions. Analysis showed that PCNC method provides an approximate optimal solution under the dynamic robustness metric when compared with the optimal solution found by exhaustive search. Simulation results also showed that PCNC method effectively improves the network robustness and communication efficiency at the cost of least added link resources.