Classification and statistical learning for detecting of switching time for switched linear systems

Sellami, Lamaa; Abderrahim, Kamel

doi:10.1016/j.jides.2015.10.002

Cited by 5 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used an SVM classifier to conduct supervised classification of the data in each scenario. SVM is a kind of machine learning based on statistical learning theory [42,43]. SVM has better performance than other classifiers such as the maximum-likelihood classifier for classifications based on high-dimensional data.…”

Section: Land Cover Classification and Accuracy Assessmentmentioning

confidence: 99%

Land Cover Classification Based on Fused Data from GF-1 and MODIS NDVI Time Series

Fanjie

Wang

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

Accurate regional and global information on land cover and its changes over time is crucial for environmental monitoring, land management, and planning. In this study, we selected Fengning County, in China's Hebei Province, as a case study area. Using satellite data, we generated fused normalized-difference vegetation index (NDVI) data with high spatial and temporal resolution by utilizing the STARFM algorithm to produce a fused GF-1 and MODIS NDVI dataset. We extracted seven phenological parameters (including the start, end, and length of the growing season, base value, mid-season date, maximum NDVI, seasonal NDVI amplitude) from a fused NDVI time-series after reconstruction using the TIMESAT software. We developed four classification scenarios based on different combinations of GF-1 spectral features, the fused NDVI time-series, and the phenological parameters. We then classified the land cover using a support vector machine and analyzed the classification accuracies. We found that the proposed method achieved satisfactory classification results, and that the combination of the fused NDVI data with the extracted phenological parameters significantly improved classification accuracy. The classification accuracy based on the composited GF-1 multi-spectral bands combined with the phenological parameters was the highest among the four scenarios, with an overall classification accuracy of 88.8% and a Kappa coefficient of 0.8714, which represent increases of 9.3 percentage points and 0.1073, respectively, compared with GF-1 spectral data alone. The producer's and user's accuracy for different land cover types improved, with a few exceptions, and cropland and broadleaf forest had the largest increase.

show abstract

Section: Land Cover Classification and Accuracy Assessmentmentioning

confidence: 99%

Land Cover Classification Based on Fused Data from GF-1 and MODIS NDVI Time Series

Fanjie

Wang

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Estimation switching time “off line”: In this part, we applied the approach proposed in Sellami and Abderrahim 47,48 to estimate the discrete dynamics of the system. Figure 7 describes the evolution of the discrete state and the table below summarizes the detected switching instants (Table 3).…”

Section: Simulation Resultsmentioning

confidence: 99%

“…Example 2: switched system with unknown switching mode. In this part, a simulation result is given in order to show the efficiency of the proposed FTC where the estimation switching time is provided using the technique proposed in Sellami and Abderrahim 47,48 . This allows us to avoid the confusion between switching system from one mode to another and the appearance of a fault.…”

Section: Simulation Resultsmentioning

confidence: 99%

“…In order to avoid this ambiguity and to apply the FTC correctly, it is necessary to develop an estimation approach to detect a mode switching and recognize the current mode in a switched system. In this section, the approach proposed in Sellami and Abderrahim, 47,48 is extended for mode detection because it showed quite encouraging. It used a data clustering approach combined with an online detection method of mode change.…”

Section: Switching Time Estimation “Off-line”mentioning

confidence: 99%

“… J j ( k ) can be chosen by various methods, since there is not a specific model which models the dynamics of the discrete state of the linear system. In Sellami and Abderrahim 47,48 J j ( k ) is the function of the square error between the output of the system y ( k ) and the first component of j eme center y j * …”

Section: Switching Time Estimation “Off-line”mentioning

confidence: 99%

See 2 more Smart Citations

Fault-tolerant control and sinusoidal disturbance attenuation for a class of hybrid dynamic systems

Yahia

Bedoui

Abderrahim

2022

Proceedings of the Institution of Mechanical Engineers, Part I:

Self Cite

View full text Add to dashboard Cite

The design of an accurate fault-tolerant control fault-tolerant control is still an active researches of switched hybrid system whose switching mechanism is unknown. In this paper, a new approach is proposed to deal with switching mode estimation and control problems for switched system subject to actuator faults and disturbances. First, the switching mode is estimated off-line using the Chiu clustering algorithm. Then, actuator fault estimation is proposed using data-based projection approach based on performance measures that allow fault estimation without relying on mathematical models and fault assumptions. Second, a novel switching control strategy is developed for actuator fault compensation and recovering the desired performances. These strategy integrate a set of controllers, corresponding to a set of partial modes to design a bank of switching control laws, compensating for the actuator fault effect and attenuating the sinusoidal disturbance. A new linear matrix inequality is proposed to compute control gains based on Lyapunov stability. This approach allows finding the optimal control gains matrices and ensure both actuator fault compensation and disturbance attenuation. Simulation results of two numerical examples shows the effectiveness of the proposed estimation and control strategies in spite of the presence of actuator faults and sinusoidal disturbance.

show abstract

Adaptive Sensor Fault Tolerant Control for Hybrid Systems with Unpredicted Switching Signals

Salwa,

Saida,

Kamel

2023

2023 IEEE 11th International Conference on Systems and Control (ICSC)

View full text Add to dashboard Cite

Classification and statistical learning for detecting of switching time for switched linear systems

Cited by 5 publications

References 20 publications

Land Cover Classification Based on Fused Data from GF-1 and MODIS NDVI Time Series

Land Cover Classification Based on Fused Data from GF-1 and MODIS NDVI Time Series

Fault-tolerant control and sinusoidal disturbance attenuation for a class of hybrid dynamic systems

Adaptive Sensor Fault Tolerant Control for Hybrid Systems with Unpredicted Switching Signals

Contact Info

Product

Resources

About