Hossein Hassani

Dr. Hossein Hassani

Electrical and Computer Engineering, Western University, London, Ontario, Canada
orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 September 2016 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
Hossein HassaniHossein Hassani
Hossein Hassani
JZJafar Zarei
Jafar Zarei
Mohammed ChadliMohammed Chadli
Mohammed Chadli
JQJianbin Qiu
Jianbin Qiu
This paper deals with the problem of robust unknown input fault detection observers (UIFDOs) design for interval type-2 Takagi-Sugeno (T-S) fuzzy systems with immeasurable premise variables. It has been shown that choosing the system states, which may be immeasurable, as premise variables, will able us to model a larger class of nonlinear systems. Accordingly, the premise variables of underlying system are considered to be immeasurable. However, the design procedure of a stable observer for such systems are more challenging. Furthermore, the system is supposed be affected by time-varying delays and unknown inputs. The UIFDO is exploited so as to generate a residual signal with the most possible sensitivity to fault and the least sensitivity to exogenous signals. In this paper, this issue is investigated thoroughly, in this respect the design procedure consists of two sections: 1) measurable and 2) immeasurable premise variables. Sufficient design conditions are provided in terms of linear matrix inequalities for both cases. The effectiveness of the proposed UIFDO in detection of two different kinds of faults is illustrated during the simulation of a numerical example. Moreover, a fair comparison has been drawn between the proposed UIFDO and an existent reference to indicate that interval type-2 T-S fuzzy model is more superior than type-1. Finally, the faulty behavior of a one-link manipulator is investigated to express the applicability of the proposed method.

13 July 2022 in Information Fusion
Verified
Journal Article
Closed access
Hossein HassaniHossein Hassani
Hossein Hassani
Roozbeh Razavi-FarRoozbeh Razavi-Far
Roozbeh Razavi-Far
MSMehrdad Saif
Mehrdad Saif
FCFrancisco Chiclana
Francisco Chiclana
Ondrej KrejcarOndrej Krejcar
Ondrej Krejcar
EHEnrique Herrera-Viedma
Enrique Herrera-Viedma

29 March 2017 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
Hossein HassaniHossein Hassani
Hossein Hassani
JZJafar Zarei
Jafar Zarei
MAMohammad Mehdi Arefi
Mohammad Mehdi Arefi
RRRoozbeh Razavi-Far
Roozbeh Razavi-Far
This paper proposes a fusion model to enhance classification accuracy of support vector machines (SVMs) for fault detection. The proposed method consists of two different phases, where in the first phase, different SVMs are constructed based on training datasets, and these trained SVMs are evaluated with respect to test datasets by calculating distances between test samples and trained hyperplanes. In order to achieve better results, an optimization scheme based on particle swarm optimization (PSO) is employed to adjust the SVMs parameters. In the next phase, a fusion model, in which the attained accuracies and distances are considered as inputs, is constructed. The fusion model utilizes zSlices-based representation of general type-2 fuzzy logic systems to combine different SVMs. The proposed approach is then applied for bearing fault detection of an induction motor with inner and outer race defects. To investigate the effectiveness of the proposed method, the general type-2 and type-1 fuzzy sets are compared with other two state-of-the-art techniques. The obtained results confirm the superiority of the proposed approach.

25 October 2022 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
Hossein HassaniHossein Hassani
Hossein Hassani
Roozbeh Razavi-FarRoozbeh Razavi-Far
Roozbeh Razavi-Far
Mehrdad SaifMehrdad Saif
Mehrdad Saif
Enrique Herrera-ViedmaEnrique Herrera-Viedma
Enrique Herrera-Viedma
The number of discussion rounds and harmony degree of decision makers are two crucial efficiency measures to be considered in the design of the consensus-reaching process for the group decision-making problems. Adjusting the feedback parameter and importance weights of the decision makers in the recommendation mechanism has a great impact on these efficiency measures. This work aims to propose novel and efficient reinforcement learning-based adjustment mechanisms to address the tradeoff between the aforementioned measures. To employ these adjustment mechanisms, we propose to extract the dynamics of state transition from consensus models based on the distributed trust functions and $Z$ -Numbers in order to convert the decision environment into a Markov decision process. Two independent reinforcement learning agents are then trained via a deep deterministic policy gradient algorithm to adjust the feedback parameter and importance weights of decision makers. The first agent is trained toward reducing the number of discussion rounds while ensuring the highest possible level of harmony degree among the decision makers. The second agent merely speeds up the consensus reaching process by adjusting the importance weights of the decision makers. Various experiments are designed to verify the applicability and scalability of the proposed feedback and weight-adjustment mechanisms in different decision environments.

11 February 2021 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
Hossein HassaniHossein Hassani
Hossein Hassani
EHEhsan Hallaji
Ehsan Hallaji
Roozbeh Razavi-FarRoozbeh Razavi-Far
Roozbeh Razavi-Far
MSMehrdad Saif
Mehrdad Saif

9 January 2019 in IEEE Systems Journal
Verified
Journal Article
Closed access
Hossein HassaniHossein Hassani
Hossein Hassani
JZJafar Zarei
Jafar Zarei
Roozbeh Razavi-FarRoozbeh Razavi-Far
Roozbeh Razavi-Far
Mehrdad SaifMehrdad Saif
Mehrdad Saif
In this paper, a novel observer design has been suggested for fault detection of networked control systems under random measurement delays. A randomly varying communication delay structure has been assumed in data transmission between the physical system and the observer. In order to increase the applicability of the proposed Takagi—Sugeno fuzzy observer, it has been contemplated to be under immeasurable premise variables. In addition, time-varying parameter uncertainties are added to the system, which contribute to the system uncertainties. Theoretical materials related to the system and the observer design with a predetermined $H_{\infty }$ index are provided resulting in less conservative constraints in the proof of asymptotical mean-square stability of the closed-loop system. Simulation results, which have been applied to a real-world system of tunnel diode circuit, have shown how the proposed observer would benefit from the use of interval type-2 fuzzy sets in dealing with uncertainties of the system.