Feng Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Feng Gao has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Chao-Bo Yan
State Key Laboratory for Manufacturing Systems Engineering and the School of Automation Science and Engineering, Faculty of Electronic and Information Engineering, Xian Jiaotong University, Xian, Shaanxi, China
2 shared publications Jiang Wu
System Engineering Institute Xi'an Jiaotong University Xi'an China
2 shared publications- Jiang Wu
MOE KLINNS Lab, Xian Jiaotong University, Xian, China
2 shared publications - Kun Liu
School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an 710049, China
2 shared publications - Xingbo Fu
System Engineering Institute Xi'an Jiaotong University Xi'an China
2 shared publications - Zelin Nie
School of Mechanical Engineering, Xian Jiaotong University, Xian, China
2 shared publications
Latest Publications
- 26 April 2024
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 22 (6) , 1856-1868
Balance Between User Comfort and Energy Consumption of Two-timescale Optimization and Control in Majorization Order
- 26 April 2024
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 22 (6) , 1856-1868
Balance Between User Comfort and Energy Consumption of Two-timescale Optimization and Control in Majorization Order
- 13 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (4) , 6928-6942
AttAuth: An Implicit Authentication Framework for Smartphone Users Using Multimodality Data
Smartphones have become the most important devices for users to communicate and interact with different forms of media, and at the same time stored a large amount of sensitive and private data. The security and protection of such data has become increasingly critical. As the sensor technology rapid developed, the diversity of sensors on smartphones has greatly increased (e.g., motion sensor, touchscreen sensor), empowering the smartphones to provide continuous and implicit user authentication by capturing behavioral biometrics. Unfortunately, it remains a challenge to make full use of the data from the multi-modality sensors to provide accurate authentication. Towards this end, in this paper, we develop an implicit authentication framework AttAuth which explores organic integration of such multi-modality data to authenticate smartphone users through the usage session. Specifically, AttAuth first develops a series of data processing techniques to process the multi-channel motion sensor data and the discrete touchscreen data. Then, a temporal and channel-wise attention based recurrent neural network (TCA-RNN) is developed to build authentication model, which allows to jointly model continuously-monitored motion sensor data and irregularly-recorded discrete touchscreen data effectively. By generating a guidance vector based on touch events, TCA-RNN guides the temporal-wise attention mechanism on the processed multi-channel motion sensor data and outputs authentication results. We evaluate AttAuth on a real-world multi-modality smartphone usage dataset of 100 users. Extensive experiments demonstrate that AttAuth achieves the state-of-the-art authentication accuracy. Additional experiments are provided to examine the applicability of AttAuth in terms of running overheads and sensitivity to various application scenarios.
- 13 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (4) , 6928-6942
AttAuth: An Implicit Authentication Framework for Smartphone Users Using Multimodality Data
Smartphones have become the most important devices for users to communicate and interact with different forms of media, and at the same time stored a large amount of sensitive and private data. The security and protection of such data has become increasingly critical. As the sensor technology rapid developed, the diversity of sensors on smartphones has greatly increased (e.g., motion sensor, touchscreen sensor), empowering the smartphones to provide continuous and implicit user authentication by capturing behavioral biometrics. Unfortunately, it remains a challenge to make full use of the data from the multi-modality sensors to provide accurate authentication. Towards this end, in this paper, we develop an implicit authentication framework AttAuth which explores organic integration of such multi-modality data to authenticate smartphone users through the usage session. Specifically, AttAuth first develops a series of data processing techniques to process the multi-channel motion sensor data and the discrete touchscreen data. Then, a temporal and channel-wise attention based recurrent neural network (TCA-RNN) is developed to build authentication model, which allows to jointly model continuously-monitored motion sensor data and irregularly-recorded discrete touchscreen data effectively. By generating a guidance vector based on touch events, TCA-RNN guides the temporal-wise attention mechanism on the processed multi-channel motion sensor data and outputs authentication results. We evaluate AttAuth on a real-world multi-modality smartphone usage dataset of 100 users. Extensive experiments demonstrate that AttAuth achieves the state-of-the-art authentication accuracy. Additional experiments are provided to examine the applicability of AttAuth in terms of running overheads and sensitivity to various application scenarios.
- 18 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 7545-7558
DETA: A Point-Based Tracker With Deformable Transformer and Task-Aligned Learning
Current point-based trackers are usually implemented by the following two branches: a classification branch for predicting the target candidate locations and a regression branch for regressing the tracking box, which may lead to a spatial misalignment between the two tasks. Meanwhile, they ignore a meaningful exploration on how to define positive and negative samples during training and explicit border information for accurate box prediction. In this research, we investigate the key issues of point-based trackers and unlock their key limitations. First, we design a novel task-aligned component and a new loss function, named task-aligned loss, to learn the alignment of the classification and regression tasks. Second, we introduce a border alignment (BorderAlign) component in both the classification and regression branches to effectively exploit the border features of a tracking target. Third, we develop an adaptive training sample assignment (ATSA) to adaptively divide the positive and negative samples based on the statistical characteristics of the tracking object. Finally, a deformable transformer is developed to enhance the representations of search features and explore rich temporal contexts among video frames. Extensive experimental results demonstrate that the proposed tracker achieves state-of-the-art performance on six tracking benchmark datasets.
- 18 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 7545-7558
DETA: A Point-Based Tracker With Deformable Transformer and Task-Aligned Learning
Current point-based trackers are usually implemented by the following two branches: a classification branch for predicting the target candidate locations and a regression branch for regressing the tracking box, which may lead to a spatial misalignment between the two tasks. Meanwhile, they ignore a meaningful exploration on how to define positive and negative samples during training and explicit border information for accurate box prediction. In this research, we investigate the key issues of point-based trackers and unlock their key limitations. First, we design a novel task-aligned component and a new loss function, named task-aligned loss, to learn the alignment of the classification and regression tasks. Second, we introduce a border alignment (BorderAlign) component in both the classification and regression branches to effectively exploit the border features of a tracking target. Third, we develop an adaptive training sample assignment (ATSA) to adaptively divide the positive and negative samples based on the statistical characteristics of the tracking object. Finally, a deformable transformer is developed to enhance the representations of search features and explore rich temporal contexts among video frames. Extensive experimental results demonstrate that the proposed tracker achieves state-of-the-art performance on six tracking benchmark datasets.
- Open Access
A Multi-Timescale Bilinear Model for Optimization and Control of HVAC Systems with Consistency
Reducing the energy consumption of the heating, ventilation, and air conditioning (HVAC) systems while ensuring users’ comfort is of both academic and practical significance. However, the-state-of-the-art of the optimization model of the HVAC system is that either the thermal dynamic model is simplified as a linear model, or the optimization model of the HVAC system is single-timescale, which leads to heavy computation burden. To balance the practicality and the overhead of computation, in this paper, a multi-timescale bilinear model of HVAC systems is proposed. To guarantee the consistency of models in different timescales, the fast timescale model is built first with a bilinear form, and then the slow timescale model is induced from the fast one, specifically, with a bilinear-like form. After a simplified replacement made for the bilinear-like part, this problem can be solved by a convexification method. Extensive numerical experiments have been conducted to validate the effectiveness of this model.
Open AccessA Multi-Timescale Bilinear Model for Optimization and Control of HVAC Systems with Consistency
Reducing the energy consumption of the heating, ventilation, and air conditioning (HVAC) systems while ensuring users’ comfort is of both academic and practical significance. However, the-state-of-the-art of the optimization model of the HVAC system is that either the thermal dynamic model is simplified as a linear model, or the optimization model of the HVAC system is single-timescale, which leads to heavy computation burden. To balance the practicality and the overhead of computation, in this paper, a multi-timescale bilinear model of HVAC systems is proposed. To guarantee the consistency of models in different timescales, the fast timescale model is built first with a bilinear form, and then the slow timescale model is induced from the fast one, specifically, with a bilinear-like form. After a simplified replacement made for the bilinear-like part, this problem can be solved by a convexification method. Extensive numerical experiments have been conducted to validate the effectiveness of this model.
- Open Access
When Do Drivers Concentrate? Attention-based Driver Behavior Modeling With Deep Reinforcement Learning
Driver distraction a significant risk to driving safety. Apart from spatial domain, research on temporal inattention is also necessary. This paper aims to figure out the pattern of drivers' temporal attention allocation. In this paper, we propose an actor-critic method - Attention-based Twin Delayed Deep Deterministic policy gradient (ATD3) algorithm to approximate a driver' s action according to observations and measure the driver' s attention allocation for consecutive time steps in car-following model. Considering reaction time, we construct the attention mechanism in the actor network to capture temporal dependencies of consecutive observations. In the critic network, we employ Twin Delayed Deep Deterministic policy gradient algorithm (TD3) to address overestimated value estimates persisting in the actor-critic algorithm. We conduct experiments on real-world vehicle trajectory datasets and show that the accuracy of our proposed approach outperforms seven baseline algorithms. Moreover, the results reveal that the attention of the drivers in smooth vehicles is uniformly distributed in previous observations while they keep their attention to recent observations when sudden decreases of relative speeds occur. This study is the first contribution to drivers' temporal attention and provides scientific support for safety measures in transportation systems from the perspective of data mining.
Open AccessWhen Do Drivers Concentrate? Attention-based Driver Behavior Modeling With Deep Reinforcement Learning
Driver distraction a significant risk to driving safety. Apart from spatial domain, research on temporal inattention is also necessary. This paper aims to figure out the pattern of drivers' temporal attention allocation. In this paper, we propose an actor-critic method - Attention-based Twin Delayed Deep Deterministic policy gradient (ATD3) algorithm to approximate a driver' s action according to observations and measure the driver' s attention allocation for consecutive time steps in car-following model. Considering reaction time, we construct the attention mechanism in the actor network to capture temporal dependencies of consecutive observations. In the critic network, we employ Twin Delayed Deep Deterministic policy gradient algorithm (TD3) to address overestimated value estimates persisting in the actor-critic algorithm. We conduct experiments on real-world vehicle trajectory datasets and show that the accuracy of our proposed approach outperforms seven baseline algorithms. Moreover, the results reveal that the attention of the drivers in smooth vehicles is uniformly distributed in previous observations while they keep their attention to recent observations when sudden decreases of relative speeds occur. This study is the first contribution to drivers' temporal attention and provides scientific support for safety measures in transportation systems from the perspective of data mining.
- Open Access
Spatiotemporal Attention Networks for Wind Power Forecasting
Wind power is one of the most important renewable energy sources and accurate wind power forecasting is very significant for reliable and economic power system operation and control strategies. This paper proposes a novel framework with spatiotemporal attention networks (STAN) for wind power forecasting. This model captures spatial correlations among wind farms and temporal dependencies of wind power time series. First of all, we employ a multi-head self-attention mechanism to extract spatial correlations among wind farms. Then, temporal dependencies are captured by the Sequence-to-Sequence (Seq2Seq) model with a global attention mechanism. Finally, experimental results demonstrate that our model achieves better performance than other baseline approaches. Our work provides useful insights to capture non-Euclidean spatial correlations.
Open AccessSpatiotemporal Attention Networks for Wind Power Forecasting
Wind power is one of the most important renewable energy sources and accurate wind power forecasting is very significant for reliable and economic power system operation and control strategies. This paper proposes a novel framework with spatiotemporal attention networks (STAN) for wind power forecasting. This model captures spatial correlations among wind farms and temporal dependencies of wind power time series. First of all, we employ a multi-head self-attention mechanism to extract spatial correlations among wind farms. Then, temporal dependencies are captured by the Sequence-to-Sequence (Seq2Seq) model with a global attention mechanism. Finally, experimental results demonstrate that our model achieves better performance than other baseline approaches. Our work provides useful insights to capture non-Euclidean spatial correlations.
- Open Access
A Simulation Approach to Multi-station Solar Irradiance Data Considering Temporal Correlations
Solar energy is one of important renewable energy sources and simulation of solar irradiance can be used as input for simulation of photovoltaic (PV) generation. This paper proposes a simulation algorithm of multi-station solar irradiance data considering temporal correlations. First of all, we group all the days of the observed data to k clusters for each station based on their daily features of solar irradiance and the daily states constitute Markov chain of days. Then, we reduce state permutations of different stations before getting Markov Transition Probability Matrix (MTPM). In terms of the observed data and MTPM, the simulation approach is proposed. Finally, we test our approach by applying to solar irradiance data of three stations and show that the properties of simulated data match those of the observed data.
Open AccessA Simulation Approach to Multi-station Solar Irradiance Data Considering Temporal Correlations
Solar energy is one of important renewable energy sources and simulation of solar irradiance can be used as input for simulation of photovoltaic (PV) generation. This paper proposes a simulation algorithm of multi-station solar irradiance data considering temporal correlations. First of all, we group all the days of the observed data to k clusters for each station based on their daily features of solar irradiance and the daily states constitute Markov chain of days. Then, we reduce state permutations of different stations before getting Markov Transition Probability Matrix (MTPM). In terms of the observed data and MTPM, the simulation approach is proposed. Finally, we test our approach by applying to solar irradiance data of three stations and show that the properties of simulated data match those of the observed data.
- 25 November 2016
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 31 (3) , 573-605
Detecting cooperative and organized spammer groups in micro-blogging community
- 25 November 2016
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 31 (3) , 573-605
Detecting cooperative and organized spammer groups in micro-blogging community
- Open Access
Optimal Real-Time Scheduling for Hybrid Energy Storage Systems and Wind Farms Based on Model Predictive Control
Energy storage devices are expected to be more frequently implemented in wind farms in near future. In this paper, both pumped hydro and fly wheel storage systems are used to assist a wind farm to smooth the power fluctuations. Due to the significant difference in the response speeds of the two storages types, the wind farm coordination with two types of energy storage is a problem. This paper presents two methods for the coordination problem: a two-level hierarchical model predictive control (MPC) method and a single-level MPC method. In the single-level MPC method, only one MPC controller coordinates the wind farm and the two storage systems to follow the grid scheduling. Alternatively, in the two-level MPC method, two MPC controllers are used to coordinate the wind farm and the two storage systems. The structure of two level MPC consists of outer level and inner level MPC. They run alternatively to perform real-time scheduling and then stop, thus obtaining long-term scheduling results and sending some results to the inner level as input. The single-level MPC method performs both long- and short-term scheduling tasks in each interval. The simulation results show that the methods proposed can improve the utilization of wind power and reduce wind power spillage. In addition, the single-level MPC and the two-level MPC are not interchangeable. The single-level MPC has the advantage of following the grid schedule while the two-level MPC can reduce the optimization time by 60%.
Open AccessOptimal Real-Time Scheduling for Hybrid Energy Storage Systems and Wind Farms Based on Model Predictive Control
Energy storage devices are expected to be more frequently implemented in wind farms in near future. In this paper, both pumped hydro and fly wheel storage systems are used to assist a wind farm to smooth the power fluctuations. Due to the significant difference in the response speeds of the two storages types, the wind farm coordination with two types of energy storage is a problem. This paper presents two methods for the coordination problem: a two-level hierarchical model predictive control (MPC) method and a single-level MPC method. In the single-level MPC method, only one MPC controller coordinates the wind farm and the two storage systems to follow the grid scheduling. Alternatively, in the two-level MPC method, two MPC controllers are used to coordinate the wind farm and the two storage systems. The structure of two level MPC consists of outer level and inner level MPC. They run alternatively to perform real-time scheduling and then stop, thus obtaining long-term scheduling results and sending some results to the inner level as input. The single-level MPC method performs both long- and short-term scheduling tasks in each interval. The simulation results show that the methods proposed can improve the utilization of wind power and reduce wind power spillage. In addition, the single-level MPC and the two-level MPC are not interchangeable. The single-level MPC has the advantage of following the grid schedule while the two-level MPC can reduce the optimization time by 60%.
- Open Access
Optimal Bidding Strategies for Wind Power Producers in the Day-ahead Electricity Market
Wind Power Producers (WPPs) seek to maximize profit and minimize the imbalance costs when bidding into the day-ahead market, but uncertainties in the hourly available wind and forecasting errors make the bidding risky. This paper assumes that hourly wind power output given by the forecast follows a normal distribution, and proposes three different bidding strategies, i.e., the expected profit-maximization strategy (EPS), the chance-constrained programming-based strategy (CPS) and the multi-objective bidding strategy (ECPS). Analytical solutions under the three strategies are obtained. Comparisons among the three strategies are conducted on a hypothetical wind farm which follows the Spanish market rules. Results show that bid under the EPS is highly dependent on market clearing price, imbalance prices, and also the mean value and standard deviation of wind forecast, and that bid under the CPS is largely driven by risk parameters and the mean value and standard deviation of the wind forecast. The ECPS combining both EPS and CPS tends to choose a compromise bid. Furthermore, the ECPS can effectively control the tradeoff between expected profit and target profit for WPPs operating in volatile electricity markets.
Open AccessOptimal Bidding Strategies for Wind Power Producers in the Day-ahead Electricity Market
Wind Power Producers (WPPs) seek to maximize profit and minimize the imbalance costs when bidding into the day-ahead market, but uncertainties in the hourly available wind and forecasting errors make the bidding risky. This paper assumes that hourly wind power output given by the forecast follows a normal distribution, and proposes three different bidding strategies, i.e., the expected profit-maximization strategy (EPS), the chance-constrained programming-based strategy (CPS) and the multi-objective bidding strategy (ECPS). Analytical solutions under the three strategies are obtained. Comparisons among the three strategies are conducted on a hypothetical wind farm which follows the Spanish market rules. Results show that bid under the EPS is highly dependent on market clearing price, imbalance prices, and also the mean value and standard deviation of wind forecast, and that bid under the CPS is largely driven by risk parameters and the mean value and standard deviation of the wind forecast. The ECPS combining both EPS and CPS tends to choose a compromise bid. Furthermore, the ECPS can effectively control the tradeoff between expected profit and target profit for WPPs operating in volatile electricity markets.