References of "Huang, Hui 50040408"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailData Augmentation and Dense-LSTM for Human Activity Recognition using WiFi Signal
Zhang, Jin; Wu, Fuxiang Wu; Wei, Bo et al

in IEEE Internet of Things Journal (2020)

Recent research has devoted significant efforts on the utilization of WiFi signals to recognize various human activities. An individual’s limb motions in the WiFi coverage area could interfere wireless ... [more ▼]

Recent research has devoted significant efforts on the utilization of WiFi signals to recognize various human activities. An individual’s limb motions in the WiFi coverage area could interfere wireless signal propagation, that manifested as unique patterns for activities recognition. Existing approaches though yielding reasonable performance in certain cases, are ignorant of two major challenges. The performed activities of the individual normally have inconsistent speed in different situations and time. Besides that the wireless signal reflected by human bodies normally carry substantial information that is specific to that subject. The activity recognition model trained on a certain individual may not work well when being applied to predict another individual’s activities. Since only recording activities of limited subjects in certain speed and scale, recent works commonly have moderate amount of activity data for training the recognition model. The small-size data could often incur the overfitting issue that negative affect the traditional classification model. To address these challenges, we propose a WiFi based human activity recognition system that synthesize variant activities data through 8 CSI transformation methods to mitigate the impact of activity inconsistency and subject-specific issues, and also design a novel deep learning model that cater to the small-size WiFi activity data. We conduct extensive experiments and show synthetic data improve performance by up to 34.6% and our system achieves around 90% of accuracy with well robustness in adapting to small-size CSI data. [less ▲]

Detailed reference viewed: 30 (2 UL)
Full Text
Peer Reviewed
See detailLearn to Make Decision with Small Data for Autonomous Driving : Deep Gaussian Process and Feedback Control
Fang, Wenqi; Zhang, Shitian; Huang, Hui UL et al

in Journal of Advanced Transportation (2020), 2020

Autonomous driving is a popular and promising field in artificial intelligence. Rapid decision of the next action according to the latest few actions and status, such as acceleration, brake, and steering ... [more ▼]

Autonomous driving is a popular and promising field in artificial intelligence. Rapid decision of the next action according to the latest few actions and status, such as acceleration, brake, and steering angle, is a major concern for autonomous driving. There are some learning methods, such as reinforcement learning which automatically learns the decision. However, it usually requires large volume of samples. In this paper, to reduce the sample size, we exploit the deep Gaussian process, where a regression model is trained on small sample datasets and captures the most significant features correctly. Besides, to realize the real-time and close-loop control, we combine the feedback control into the process. Experimental results on the Torcs simulation engine illustrate smooth driving on virtual road which can be achieved. Compared with the amount of training data in deep reinforcement learning, our method uses only 0.34\% of its size and obtains similar simulation results. It may be useful for real road tests in the future. [less ▲]

Detailed reference viewed: 63 (1 UL)
Full Text
Peer Reviewed
See detailSparse Gaussian Process Based On Hat Basis Functions
Fang, W.; Li, H.; Huang, Hui UL et al

in 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE) (2020, August 28)

Gaussian process is a popular non-parametric Bayesian methodology for modeling the regression problem, which is completely determined by its mean and covariance function. Nevertheless, this method still ... [more ▼]

Gaussian process is a popular non-parametric Bayesian methodology for modeling the regression problem, which is completely determined by its mean and covariance function. Nevertheless, this method still has two major disadvantages: it is difficult to handle large datasets and may not meet inequality constraints in specific problems. These two issues have been addressed by the so-called sparse Gaussian process and constrained Gaussian process in recent years. In this paper, to reduce the overall computational complexity in the exact Gaussian process, we propose a new sparse Gaussian process method to solve the unconstrained regression problem. The idea is inspired by the constrained Gaussian process method. The critical point of our method is that we introduce the hat basis function, which is mentioned in the constrained Gaussian process, and modify its definition according to the range of training or test data. It turns out that this method belongs to the spectral approximation methods. Similar to the exact Gaussian process and Gaussian process with Fully Independent Training Conditional approximation, our method obtains satisfactory approximate results on analytical functions or open-source datasets. [less ▲]

Detailed reference viewed: 113 (6 UL)
Full Text
Peer Reviewed
See detailData Redundancy Mitigation in V2X based Collective Perceptions
Huang, Hui UL; Li, Huiyun; Shao, Cuiping et al

in IEEE Access (2020), 8

Collective perception is a new paradigm to extend the limited horizon of individual vehicles. Incorporating with the recent vehicle-2-x (V2X) technology, connected and autonomous vehicles (CAVs) can ... [more ▼]

Collective perception is a new paradigm to extend the limited horizon of individual vehicles. Incorporating with the recent vehicle-2-x (V2X) technology, connected and autonomous vehicles (CAVs) can periodically share their sensory information, given that traffic management authorities and other road participants can benefit from these information enormously. Apart from the benefits, employing collective perception could result in a certain level of transmission redundancy, because the same object might fall in the visible region of multiple CAVs, hence wasting the already scarce network resources. In this paper, we analytically study the data redundancy issue in highway scenarios, showing that the redundant transmissions could result in heavy loads on the network under medium to dense traffic. We then propose a probabilistic data selection scheme to suppress redundant transmissions. The scheme allows CAVs adaptively adjust the transmission probability of each tracked objects based on the position, vehicular density and road geometry information. Simulation results confirm that our approach can reduce at most 60% communication overhead in the meanwhile maintain the system reliability at desired levels. [less ▲]

Detailed reference viewed: 56 (4 UL)
Full Text
Peer Reviewed
See detailPerformance Modelling of V2V based Collective Perceptions in Connected and Autonomous Vehicles
Huang, Hui UL; Fang, Wenqi; Li, Huiyun

in 2019 IEEE 44th Conference on Local Computer Networks (LCN) (2019, October 14)

With the introduction of Connected and Autonomous Vehicles (CAVs), it is possible to extend the limited horizon of vehicles on the road by collective perceptions, where vehicles periodically share their ... [more ▼]

With the introduction of Connected and Autonomous Vehicles (CAVs), it is possible to extend the limited horizon of vehicles on the road by collective perceptions, where vehicles periodically share their sensory information with others using Vehide-2-Vehicle (V2V) communications. This technique relies on a certain number of participants to have a measurable advantage. Nevertheless, the spread of CAVs will take a considerable period of time, it is critical to understand the benefits and limits of V2V based collective perceptions in different market stages. In this work, we characterise the effective Field of View (eFoV) of a vehicle as the perception range using local sensors only, and the collective Field of View (cFoV) as the region learn from the network. Applying analytic and simulation studies in highway scenarios, we show that the eFoV drops quickly with the increase in traffic density due to blockage effects of surrounding vehicles, and it is insufficient to overcome this problem by increasing the sensing range of local sensors. On the other hand, vehicles can gain around 16 folds more information about the road environment by leveraging collective perceptions with only 10\% CAV penetration rate. When the penetration rate reaches to around 30\%, collective perceptions can provide 95\% coverage over the road environments. Our analyses also show that apart from the benefits, employing collective perceptions could result in heavy broadcast redundancy, hence wasting the already scarce network resources. This observation suggests that the sharing of sensory information should be controlled appropriately to avoid overloading the communication networks. [less ▲]

Detailed reference viewed: 28 (2 UL)
Full Text
Peer Reviewed
See detailCombining Deep Gaussian Process and Rule-Based Method for Decision-Making in Self-Driving Simulation with Small Data
Fang, W.; Li, H.; Dang, S. et al

in 2019 15th International Conference on Computational Intelligence and Security (CIS) (2019, March 05)

Self-driving vehicle is a popular and promising field in artificial intelligence. Conventional architecture consists of multiple sensors, which work collaboratively to sense the units on road to yield a ... [more ▼]

Self-driving vehicle is a popular and promising field in artificial intelligence. Conventional architecture consists of multiple sensors, which work collaboratively to sense the units on road to yield a precise and safe driving strategy. Besides the precision and safety, the quickness of decision is also a major concern. In order to react quickly, the vehicle need to predict its next possible action, such as acceleration, brake and steering angle, according to its latest few actions and status. In this paper, we treat this decision-making problem as a regression problem and use deep gaussian process to predict its next action. The regression model is trained using simulation data sets and accurately captures the most significant features. Combined with rule-based method, it can be used in Torcs simulation engine to realize successful loop trip on virtual roads. The proposed method outperforms the existing reinforcement learning methods on the performance indicators of time consumption and the size of data volume. It may be useful for real road tests in the future. [less ▲]

Detailed reference viewed: 77 (3 UL)
Full Text
Peer Reviewed
See detailCarAgent: Collecting and disseminating floating car data in vehicular networks
Huang, Hui UL; Hassan, Mahbub; Geers, Glenn et al

in Vehicular Communications (2018), 13

Floating car data (FCD) refers to the motion and sensor data produced by moving vehicles on the road. Given that traffic management authorities and drivers can benefit from FCD enormously, there is an ... [more ▼]

Floating car data (FCD) refers to the motion and sensor data produced by moving vehicles on the road. Given that traffic management authorities and drivers can benefit from FCD enormously, there is an urgency to develop efficient FCD collection and dissemination techniques that scale with peak road traffic. In this paper, we present CarAgent, a message exchange protocol that periodically collects and uploads FCD to data centres with the minimal utilisation of existing mobile network resources. We also show how CarAgent can be easily extended to efficiently disseminate FCD to all vehicles in a target area using Dedicated Short Range Communication (DSRC), a recently released wireless communication standard for vehicles. We analytically derive the key performance metrics of CarAgent and validate them with simulations. We evaluate CarAgent using microscopic simulation of road traffic in real street maps while incorporating wireless protocol details of Long Term Evolution (LTE) and DSRC. Simulation results confirm that, compared to the state-of-the-art, CarAgent consumes 50% less LTE resources for FCD collection. For FCD dissemination, CarAgent consumes 45% less DSRC resources while improving the speed of dissemination significantly. [less ▲]

Detailed reference viewed: 37 (1 UL)
Full Text
Peer Reviewed
See detailAn agent based data collection scheme for vehicular sensor networks
Huang, Hui UL; Libman, L.; Geers, G.

in 24th International Conference on Computer Communications and Networks, ICCCN 2015 (2015, October 05)

A Vehicular Sensor Network (VSN) is a sensing platform composed of smart onboard sensor nodes (vehicles) and roadside units, in which vehicles continuously collect sensor data from the road network to ... [more ▼]

A Vehicular Sensor Network (VSN) is a sensing platform composed of smart onboard sensor nodes (vehicles) and roadside units, in which vehicles continuously collect sensor data from the road network to enable a range of real-time data-intensive applications, such as traffic pattern/congestion analysis, road surface diagnosis, and urban pollution monitoring. However, due to lossy links, limited bandwidth and highly dynamic network topology, it is very challenging to efficiently collect the data generated by vehicles on the road, especially under dense traffic situations. In this paper, we propose to deploy mobile agents for collecting sensor readings from a given road segment of interest. The mobile agent migrates among vehicles within the segment via wireless broadcast and uses local on-board computational resources to process and collect data as required. Since the wireless links are generally lossy, a broadcast may not reach all the vehicles within the segment; thus, to improve the reliability of the scheme, we further propose a termination decision algorithm based on recursive Bayesian estimation by which the agent decides whether all vehicles within the segment have been visited. Extensive simulation results show that the proposed agent-based data collection scheme achieves close to 100\% data collection coverage under a wide range of vehicular traffic densities, while retaining a small communication overhead. \textcopyright 2015 IEEE. [less ▲]

Detailed reference viewed: 43 (2 UL)