Qingdao Academy of Intelligent Industries

Qingdao, China

Qingdao Academy of Intelligent Industries

Qingdao, China
SEARCH FILTERS
Time filter
Source Type

Wei Q.,CAS Institute of Automation | Wei Q.,University of Chinese Academy of Sciences | Liu D.,University of Science and Technology Beijing | Lewis F.L.,University of Texas at Arlington | And 4 more authors.
IEEE Transactions on Industrial Electronics | Year: 2017

In this paper, a novel mixed iterative adaptive dynamic programming (ADP) algorithm is developed to solve the optimal battery energy management and control problem in smart residential microgrid systems. Based on the data of the load and electricity rate, two iterations are constructed, which are P-iteration and V-iteration, respectively. The V-iteration is implemented based on value iteration, which aims to obtain the iterative control law sequence in each period. The P-iteration is implemented based on policy iteration, which updates the iterative value function according to the iterative control law sequence. Properties of the developed mixed iterative ADP algorithm are analyzed. It is shown that the iterative value function is monotonically nonincreasing and converges to the solution of the Bellman equation. In each iteration, it is proven that the performance index function is finite under the iterative control law sequence. Finally, numerical results and comparisons are given to illustrate the performance of the developed algorithm. © 2017 IEEE.


Sheng L.,CAS Institute of Automation | Xiuqin S.,CAS Institute of Automation | Changjian C.,CAS Institute of Process Engineering | Hongxia Z.,CAS Institute of Automation | And 2 more authors.
Computers and Industrial Engineering | Year: 2017

This paper addresses the container loading problem with multiple constraints that occur at many manufacturing sites, such as furniture factories, appliances factories, and kitchenware factories. These factories receive daily orders with expiration dates, and each order consists of one or more items. On a particular day, certain orders expire, and the expiring orders must be handled (shipped) prior to the non-expiring ones. All of the items in an order must be placed in one container, and the volume of the container should be maximally utilized. A heuristic algorithm is proposed to standardize the packing of (order) items into a container. The algorithm chooses the expiring orders first before handling the non-expiring orders. In both steps, the algorithm first selects a collection of orders by considering a simulated annealing strategy and subsequently packs the collection of orders into the container via a tree-graph search procedure. The validity of the algorithm is examined through experimental results using BR instances. © 2017 Elsevier Ltd


Gou C.,CAS Institute of Automation | Gou C.,Qingdao Academy of Intelligent Industries | Wu Y.,Rensselaer Polytechnic Institute | Wang K.,Rensselaer Polytechnic Institute | And 3 more authors.
Proceedings - International Conference on Pattern Recognition | Year: 2017

Cascade regression framework has been successfully applied to facial landmark detection and achieves state-of-the-art performance recently. It requires large number of facial images with labeled landmarks for training regression models. We propose to use cascade regression framework to detect eye center by capturing its contextual and shape information of other related eye landmarks. While for eye detection, it is time-consuming to collect large scale training data and it also can be unreliable for accurate manual annotation of eye related landmarks. In addition, it is difficult to collect enough training data to cover various illuminations, subjects with different head poses and gaze directions. To tackle this problem, we propose to learn cascade regression models from synthetic photorealistic data. In our proposed approach, eye region is coarsely localized by a facial landmark detection method first. Then we learn the cascade regression models iteratively to predict the eye shape updates based on local appearance and shape features. Experimental results on benchmark databases such as BioID and GI4E show that our proposed cascade regression models learned from synthetic data can accurately localize the eye center. Comparisons with existing methods also demonstrates our proposed framework can achieve preferable performance against state-of-the-art methods. © 2016 IEEE.


Dong X.,CAS Institute of Automation | Dong X.,Qingdao Academy of Intelligent Industries
Proceedings - 2016 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2016 | Year: 2016

Virtual Reality (VR) is a three-dimensional computer-generated virtual world. It is essential to introduced VR technology to education area to develop new teaching mode to improve the efficiency and quality of teaching and learning. Among them, VR classroom has quickly become most dazzling star with its subversive advantage. This paper proposes an overall integration solution of VR classroom, including its composition, its scene design of various disciplines and its main advantage. Finally, a case study of a geography lesson is provided to show its advantages and strong potentiality. © 2016 IEEE.


Gong X.,CAS Institute of Automation | Gong X.,Qingdao Academy of Intelligent Industries
Proceedings - 2016 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2016 | Year: 2016

In this article, I would like to share my daughter's experience on self-STEAM education. In our daily life, she can always find problems and then dream them with her imagination, finally narrows down her solutions to solve problems in her own way. During these problem-solving processes, I noticed that she went through sciences, technology, engineering, arts and mathematics in a very natural way. So I would like to say, STEAM is the way we learn and grow ever since we were born. But later at school, we are trained in a way that subjects are completely disconnected. It might take time to change this situation at school, but at home, as parents, we need to realize that children can discover new things by themselves even from young ages, and provide rich learning environment for them and let them 'STEAM' themselves in their own way. © 2016 IEEE.


Yuan Y.,CAS Institute of Automation | Yuan Y.,Qingdao Academy of Intelligent Industries | Wang F.-Y.,CAS Institute of Automation | Wang F.-Y.,National University of Defense Technology | Zeng D.,CAS Institute of Automation
Information Sciences | Year: 2016

Sponsored search advertising (SSA) markets have witnessed soaring bid prices from advertisers, which have been considered to be a potential challenge to the long-term stability, profitability and effectiveness of the SSA ecosystem. One approach to addressing this challenge is identifying cooperative and stable bidding strategies for competing advertisers with the objective of reaching socially optimal outcomes in repeated SSA auctions. Although useful in analyzing advertisers’ bidding behavior in single auction sessions, static game-theoretic analysis and simulation studies in the extant SSA literature offer only limited insights for characterizing the long-term evolutionary dynamics and stability of advertisers’ bidding behavior. In this paper, we address this problem by applying evolutionary game theory and coevolutionary simulation. Our key finding is that a group of “nice” and retaliatory (NR) strategies can promote stable cooperation among competing advertisers. Advertisers using NR strategies will never deviate from cooperation first (nice) and always punish their rivals’ deviations using competitive bids (retaliatory). The NR strategies are shown to be able to encourage advertisers to decrease their bids to obtain revenue that is equal to that awarded under the Vickrey-Clarke-Groves (VCG) auction mechanism and are further shown to alleviate bid inflation effectively at the system level. © 2016 Elsevier Inc.


Liu Y.,Qingdao Academy of Intelligent Industries | Wang K.,Intelligent Systems Technology, Inc.
Proceedings of 2014 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2014 | Year: 2014

Vehicle classification system is an important part of intelligent transportation system (ITS), which can provide us the necessary information for autonomous navigation, toll systems, surveillance and security systems, and transport planning. In this paper, we introduce a vehicle classification system based on dynamic Bayesian network (DBN). Three main types of features are employed in our system: the geometrical characteristic of the vehicle, the location and shape of license plate, and the vehicle pose. Firstly, vehicle detection and tracking method are used to locate the vehicle. Then, we extract the features from video sequences. Gaussian Mixture Model (GMM) is used to construct the probability distribution of the feature. Finally, we classify a vehicle into one of four classes: sedan, bus, microbus, and unknown. The experiment shows the proposed method can achieve classification exactly and credibly. © 2014 IEEE.


Wang F.-Y.,Chinese Academy of Sciences | Wang F.-Y.,National University of Defense Technology | Wang F.-Y.,Qingdao Academy of Intelligent Industries
IEEE Transactions on Intelligent Transportation Systems | Year: 2015

Provides an overview of the technical articles and features presented in this issue. © 2000-2011 IEEE.


Wang F.-Y.,Chinese Academy of Sciences | Wang F.-Y.,National University of Defense Technology | Wang F.-Y.,Qingdao Academy of Intelligent Industries
IEEE Transactions on Intelligent Transportation Systems | Year: 2015

The first issue of IEEE Intelligent Transportation Systems Society (ITSS) starts with survey papers on technology and security for intelligent vehicles. The first paper titled 'Intra-Vehicle Networks: A Review' by S. Tuohy, M. Glavin, C. Hughes, E. Jones, M. Trivedi, and L. Kilmartin presents a comprehensive overview of current research on advanced intra-vehicle networks and identifies outstanding research questions for the future. J. Petit and S. E. Shladover's paper, 'Potential Cyberattacks on Automated Vehicles' analyzes the threats on autonomous automated vehicle and cooperative automated vehicle. 'A Video-Analysis-Based Railway-Road System for Detecting Hazard Situations at Level Crossings' by H. Salmane, L. Khoudour, and Y. Ruichek explores the possibility of implementing a smart video surveillance security system that is tuned toward detecting and evaluating abnormal situations induced by users in level crossing. 'Traffic Flow Prediction for Road Transportation Networks with Limited Traffic Data' by A. Abadi, T. Rajabioun, and P. A. Ioannou, uses a dynamic traffic simulator to generate flows in all links using available traffic information, estimated demand, and historical traffic data available from links equipped with sensors. The paper titled 'GNSS Multipath and Jamming Mitigation Using High-Mask-Angle Antennas and Multiple Constellations' studies the optimal antenna mask angle that maximizes the suppression of interference but still maintains the performance of a single constellation with a low-mask-angle antenna.


Zhao Y.-F.,Qingdao Academy of Intelligent Industries | Kong Q.-J.,Qingdao Academy of Intelligent Industries | Gao H.,Qingdao Academy of Intelligent Industries | Zhu F.-H.,Qingdao Academy of Intelligent Industries | Wang F.-Y.,Qingdao Academy of Intelligent Industries
2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014 | Year: 2014

With the rapid growth of the number of urban vehicles, it will be not advisable to alleviate traffic congestion by changing the traffic facilities only. And the traditional control strategies for single intersection or regional multiple intersections have been confirmed to have some effect in the past few decades, but still need to be improved. Based on ACP (Artificial societies, Computational experiments, Parallel execution) idea, we firstly proposed the concept of 'event agent' in this paper, which refers to the ratings that traffic states give corresponding timing plans. Based on event agent, we used computational methods to establish a Parallel transportation Management Systems (PtMS), which was a self-completing system. In the system plenty of artificial events were generated, and some of them can not only simulate the actual traffic events, but also be substitutes for the actual events. Then through the parallel execution between actual and artificial events, the system recommends the most suitable timing plans to the current traffic state. Different from traditional control strategies, event agent based PtMS takes results as an orientation according to the idea of data-driven, which is more adaptive to the characteristics of transportation systems. For ensuring the validity and accuracy of experiments, our related data are all based on the famous traffic micro-simulation software Paramics. Furthermore, we compared our method with the classic Webster method, and experiments achieved good results. © 2014 IEEE.

Loading Qingdao Academy of Intelligent Industries collaborators
Loading Qingdao Academy of Intelligent Industries collaborators