Yingying Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yingying Liu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Jin Hu
College of Information Engineering, Northwest AF University, Yangling, China
2 shared publications - Jan Komenda
Institute of Mathematics, Czech Academy of Sciences, Prague, Czechia
1 shared publication - Shaoyuan Li
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Shizhuo Zhang
College of Information Engineering, Northwest AF University, Xianyang, China
1 shared publication - Xiang Yin
Shanghai Jiao Tong University
1 shared publication - Xuannan Li
College of Information Engineering, Northwest AF University, Xianyang, China
1 shared publication
Latest Publications
- 3 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 71 (5) , 3432-3439
Distributed Sensing and Information Transmission of Discrete-Event Systems With Edge Sensors
This article studies distributed sensing and information transmission in partially observed discrete-event systems with edge sensors. We assume that each edge sensor selectively transmits its observable events, according to information transmission policies, to a central site for the purpose of decision making. A general class of decision-making requirement at the central site called distinguishability is considered. We consider both the verification problem and the synthesis problem in this setting. For the verification problem, two different approaches, one based on the observer and the other based on the verifier, are proposed to check whether or not a given set of sensor transmission policies fulfills the distinguishability requirement. For the synthesis problem, we also develop an effective algorithm to design an observer-based optimal information transmission policy for each edge sensor. Moreover, we show that finding an information transmission policy with minimal number of transmitted events is NP-hard.
- 3 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 71 (5) , 3432-3439
Distributed Sensing and Information Transmission of Discrete-Event Systems With Edge Sensors
This article studies distributed sensing and information transmission in partially observed discrete-event systems with edge sensors. We assume that each edge sensor selectively transmits its observable events, according to information transmission policies, to a central site for the purpose of decision making. A general class of decision-making requirement at the central site called distinguishability is considered. We consider both the verification problem and the synthesis problem in this setting. For the verification problem, two different approaches, one based on the observer and the other based on the verifier, are proposed to check whether or not a given set of sensor transmission policies fulfills the distinguishability requirement. For the synthesis problem, we also develop an effective algorithm to design an observer-based optimal information transmission policy for each edge sensor. Moreover, we show that finding an information transmission policy with minimal number of transmitted events is NP-hard.
- 2 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (18) , 38004-38016
Multivariable Environmental Prediction for Chinese Solar Greenhouse IoT System Based on FB-LSTM Model
Accurate prediction with limited data is crucial for solar greenhouse Internet of Things (IoT) systems, as it enables efficient resource utilization and timely decision-making while minimizing energy consumption and communication overhead. This capability is particularly vital for applications requiring long-term monitoring, such as precision agriculture and environmental sensing, where frequent data transmission is often impractical. This article introduces a feedback long short-term memory (FB-LSTM) neural network architecture for multistep environmental forecasting in solar greenhouse IoT systems, including the prediction of indoor air temperature and relative humidity. The FB-LSTM architecture features a feedback mechanism that recursively feeds predicted values into the model for subsequent forecasts, thereby reducing reliance on real-time sensor inputs. Through systematic multistep prediction experiments across 12–48 h horizons, the proposed model demonstrated superior predictive capability in terms of root mean square error and mean absolute error when compared with conventional baseline models such as recurrent neural network, GRU, and long short-term memory (LSTM). The experiments show that the FB-LSTM architecture achieves superior prediction performance by transmitting only 2.78% of data in the best case, significantly reducing transmission burden—especially in large-scale multigreenhouse IoT. This research establishes a robust computational framework for greenhouse climate modeling, providing actionable insights for environmental regulation systems and early warning mechanisms. The methodology demonstrates practical implementation potential for optimizing microclimate management in protected agricultural systems.
- 2 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (18) , 38004-38016
Multivariable Environmental Prediction for Chinese Solar Greenhouse IoT System Based on FB-LSTM Model
Accurate prediction with limited data is crucial for solar greenhouse Internet of Things (IoT) systems, as it enables efficient resource utilization and timely decision-making while minimizing energy consumption and communication overhead. This capability is particularly vital for applications requiring long-term monitoring, such as precision agriculture and environmental sensing, where frequent data transmission is often impractical. This article introduces a feedback long short-term memory (FB-LSTM) neural network architecture for multistep environmental forecasting in solar greenhouse IoT systems, including the prediction of indoor air temperature and relative humidity. The FB-LSTM architecture features a feedback mechanism that recursively feeds predicted values into the model for subsequent forecasts, thereby reducing reliance on real-time sensor inputs. Through systematic multistep prediction experiments across 12–48 h horizons, the proposed model demonstrated superior predictive capability in terms of root mean square error and mean absolute error when compared with conventional baseline models such as recurrent neural network, GRU, and long short-term memory (LSTM). The experiments show that the FB-LSTM architecture achieves superior prediction performance by transmitting only 2.78% of data in the best case, significantly reducing transmission burden—especially in large-scale multigreenhouse IoT. This research establishes a robust computational framework for greenhouse climate modeling, providing actionable insights for environmental regulation systems and early warning mechanisms. The methodology demonstrates practical implementation potential for optimizing microclimate management in protected agricultural systems.
- 10 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 6, 1867-1872
Supervisory Control of Multiagent Discrete-Event Systems With Partial Observation
In this letter, we investigate multi-agent discrete-event systems with partial observation. The agents can be divided into several groups in each of which the agents have identical (isomorphic) state transition structures, and can thus be relabeled into the same template. Based on the template a scalable supervisor whose state size and computational cost are independent of the number of agents is designed for the case of partial observation. The scalable supervisor under partial observation does not need to be recomputed regardless of how many agents are added to or removed from the system. We generalize our earlier results from complete to partial observation by proposing sufficient conditions for safety and maximal permissiveness of the scalable least restrictive supervisor on the template level. An example is provided to illustrate the proposed scalable supervisory synthesis.
- 10 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 6, 1867-1872
Supervisory Control of Multiagent Discrete-Event Systems With Partial Observation
In this letter, we investigate multi-agent discrete-event systems with partial observation. The agents can be divided into several groups in each of which the agents have identical (isomorphic) state transition structures, and can thus be relabeled into the same template. Based on the template a scalable supervisor whose state size and computational cost are independent of the number of agents is designed for the case of partial observation. The scalable supervisor under partial observation does not need to be recomputed regardless of how many agents are added to or removed from the system. We generalize our earlier results from complete to partial observation by proposing sufficient conditions for safety and maximal permissiveness of the scalable least restrictive supervisor on the template level. An example is provided to illustrate the proposed scalable supervisory synthesis.