Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 20 de 40
Filter
1.
IEEE Trans Cybern ; PP2024 Mar 18.
Article in English | MEDLINE | ID: mdl-38498755

ABSTRACT

The problems of exponential stability and L1 -gain for positive impulsive Takagi-Sugeno (T-S) fuzzy systems are further studied in this article. Different from the Lyapunov function in the literature, where the Lyapunov matrices are time-invariant or only linearly dependent on the impulse interval, in this article, a novel polynomial impulse-dependent (ID) copositive Lyapunov function (CLF) is constructed by using the polynomial impulse time function. In addition, the binomial coefficients are applied to derive new finite linear programming conditions. Less conservative results are obtained since the polynomial ID CLF contains more impulse interval information. Three examples demonstrate the influence of the polynomial degree on the results and the effectiveness of the developed new results.

2.
IEEE Trans Cybern ; PP2024 Feb 19.
Article in English | MEDLINE | ID: mdl-38373120

ABSTRACT

This article is concerned with the integrated design of fault estimation (FE) and fault-tolerant control (FTC) for uncertain nonlinear systems suffering from actuator faults and external disturbance. The uncertain nonlinear systems are characterized as the interval type-2 (IT2) Takagi-Sugeno (T-S) fuzzy model, and IT2 membership functions are employed to effectively handle uncertainties. A fuzzy observer, utilizing only sampled-output measurements, is applied to simultaneously estimate actuator faults and system states. Based on the estimation, the fault-tolerant controller is designed to ensure the system stability under a predefined H∞ performance. The sampling behavior complicates the system dynamics and makes the integrated FTC design more challenging. To confront this issue, the discontinuous Lyapunov functional technique is exploited to enhance stability results by considering the sampling characteristic, upon which FE and FTC units are co-designed in the linear matrix inequality (LMI) framework. To further relax stability criteria, the analysis process incorporates the bound information of membership functions through the membership-function-dependent (MFD) method. Additionally, the relationship of mismatched premise variables resulting from the sampling scheme is also taken into account. Moreover, considering the imperfect premise matching (IPM) framework, the proposed fault-tolerant controller provides greater flexibility in selecting the shapes of membership functions and number of fuzzy rules that can vary from the counterpart of the fuzzy system. Finally, the efficacy of the proposed FTC technique is validated through a detailed numerical example.

3.
IEEE Trans Cybern ; PP2024 Feb 07.
Article in English | MEDLINE | ID: mdl-38324438

ABSTRACT

This article explores the observer-based feedback control problem for a nonlinear hyperbolic partial differential equations (PDEs) system. Initially, the polynomial fuzzy hyperbolic PDEs (PFHPDEs) model is established through the utilization of the fuzzy identification approach, derived from the nonlinear hyperbolic PDEs model. Various types of state estimation and controller design problems for the polynomial fuzzy PDEs system are discussed concerning the state estimation problem. To investigate the relaxed stability problem, Euler's homogeneous theorem, Lyapunov-Krasovskii functional with polynomial matrices (LKFPM), and the sum-of-squares (SOSs) approach are adopted. The exponential stabilization condition is formulated in terms of the spatial-derivative-SOSs (SD-SOSs). Additionally, a segmental algorithm is developed to find the feasible solution for the SD-SOS condition. Finally, a hyperbolic PDEs system and several numerical examples are provided to illustrate the validity and effectiveness of the proposed results.

4.
Artif Intell Med ; 146: 102721, 2023 12.
Article in English | MEDLINE | ID: mdl-38042594

ABSTRACT

Hospital patients can have catheters and lines inserted during the course of their admission to give medicines for the treatment of medical issues, especially the central venous catheter (CVC). However, malposition of CVC will lead to many complications, even death. Clinicians always detect the status of the catheter to avoid the above issues via X-ray images. To reduce the workload of clinicians and improve the efficiency of CVC status detection, a multi-task learning framework for catheter status classification based on the convolutional neural network (CNN) is proposed. The proposed framework contains three significant components which are modified HRNet, multi-task supervision including segmentation supervision and heatmap regression supervision as well as classification branch. The modified HRNet maintaining high-resolution features from the start to the end can ensure to generation of high-quality assisted information for classification. The multi-task supervision can assist in alleviating the presence of other line-like structures such as other tubes and anatomical structures shown in the X-ray image. Furthermore, during the inference, this module is also considered as an interpretation interface to show where the framework pays attention to. Eventually, the classification branch is proposed to predict the class of the status of the catheter. A public CVC dataset is utilized to evaluate the performance of the proposed method, which gains 0.823 AUC (Area under the ROC curve) and 82.6% accuracy in the test dataset. Compared with two state-of-the-art methods (ATCM method and EDMC method), the proposed method can perform best.


Subject(s)
Central Venous Catheters , Humans , Neural Networks, Computer
5.
Med Image Anal ; 88: 102876, 2023 08.
Article in English | MEDLINE | ID: mdl-37423057

ABSTRACT

Hospital patients can have catheters and lines inserted during the course of their admission to give medicines for the treatment of medical issues, especially the central venous catheter (CVC). However, malposition of CVC will lead to many complications, even death. Clinicians always detect the malposition based on position detection of CVC tip via X-ray images. To reduce the workload of the clinicians and the percentage of malposition occurrence, we propose an automatic catheter tip detection framework based on a convolutional neural network (CNN). The proposed framework contains three essential components which are modified HRNet, segmentation supervision module, and deconvolution module. The modified HRNet can retain high-resolution features from start to end, ensuring the maintenance of precise information from the X-ray images. The segmentation supervision module can alleviate the presence of other line-like structures such as the skeleton as well as other tubes and catheters used for treatment. In addition, the deconvolution module can further increase the feature resolution on the top of the highest-resolution feature maps in the modified HRNet to get a higher-resolution heatmap of the catheter tip. A public CVC Dataset is utilized to evaluate the performance of the proposed framework. The results show that the proposed algorithm offering a mean Pixel Error of 4.11 outperforms three comparative methods (Ma's method, SRPE method, and LCM method). It is demonstrated to be a promising solution to precisely detect the tip position of the catheter in X-ray images.


Subject(s)
Catheterization, Central Venous , Central Venous Catheters , Humans , Catheterization, Central Venous/methods , X-Rays
6.
IEEE Trans Cybern ; 53(2): 979-987, 2023 Feb.
Article in English | MEDLINE | ID: mdl-34406956

ABSTRACT

This work investigates the issue of output-feedback sliding-mode control (SMC) for nonlinear 2-D systems by Takagi-Sugeno fuzzy-affine models. Via combining with the sliding surface, the sliding-mode dynamical properties are depicted by a singular piecewise-affine system. Through piecewise quadratic Lyapunov functions, new stability and robust performance analysis of the sliding motion are carried out. An output-feedback dynamic SMC design approach is developed to guarantee that the system states can converge to a neighborhood of the sliding surface. Simulation studies are given to verify the validity of the proposed scheme.

7.
IEEE Trans Cybern ; 53(11): 7085-7094, 2023 Nov.
Article in English | MEDLINE | ID: mdl-35503816

ABSTRACT

In this work, the problem of tracking control for discrete-time nonlinear actuator-saturated systems via interval type-2 (IT2) T-S fuzzy framework is investigated. Improved on the (type-1) T-S fuzzy system, the IT2 T-S fuzzy system has a better capability for the expression of system uncertainty, and correspondingly, it will increase the difficulty of analysis, especially for the membership-functions-dependent (MFD) method. In addition, in this case, the control input nonlinearity caused by actuator saturation will complicate the stability analysis of the systems. We make an attempt to address the challenges that the information of membership functions (MFs) is underutilized or not utilized, by developing an MFD analysis approach, which allows the enhancement of design flexibility of IT2 fuzzy controller and effectiveness of lessening the conservativeness of the analysis result. The piecewise MFs which are formed by connecting the sample point on or close to the original IT2 MFs are utilized to approximate the original IT2 MFs, and the error between the piecewise MFs and the original upper and lower MFs is taken into account in the stability analysis. To acquire the linear matrix inequality-based (LMI-based) constraint, the actuator saturation is converted to a sector nonlinear issue. H∞ performance is considered to limit the difference between the reference system and the control saturated system. Examples are presented to illustrate the validity of the results.

8.
IEEE Trans Cybern ; 53(6): 3771-3781, 2023 Jun.
Article in English | MEDLINE | ID: mdl-35412998

ABSTRACT

This article investigates the sliding-mode control issue for interval type-2 (IT2) T-S fuzzy systems under limited communication resources. An event-triggering weight try-once-discard (ET-WTOD) protocol is formulated via two thresholds to determine the transmission of the state signal. The proposed ET-WTOD protocol can dynamically adjust the transmitted nodes and permits only partial components with larger error to be sent at each triggering instant, which is just the key distinction from the existing protocols. Under the imperfect premise matching framework, the controller's membership functions are reconstructed via the received state and the known upper and lower bounds, and then, a new scheduling signal set is established to design the scheduling-signal-dependent fuzzy sliding-mode controller. With the aid of the membership-function-dependent approach, the mismatching premise variables of the fuzzy model and the controller are effectively handled by introducing some slack matrices, while the relaxed stability conditions are derived to ensure the stability of the closed-loop system and the reachability of the specified sliding surface. Moreover, an optimized sliding domain is further obtained via the genetic algorithm (GA). Finally, the proposed control strategy is verified via the mass-spring-damper system.

9.
IEEE Trans Cybern ; 53(5): 3220-3230, 2023 May.
Article in English | MEDLINE | ID: mdl-35442897

ABSTRACT

This article tackles the problem of filtering design for continuous-time Roesser-type 2-D nonlinear systems via Takagi-Sugeno (T-S) fuzzy affine models. The aim is to design an admissible piecewise affine (PWA) filter such that the filtering error system is asymptotically stable with a prescribed disturbance attenuation level. First, 2-D Roesser nonlinear systems are approximated by a kind of 2-D fuzzy affine models with norm-bounded uncertainties. Then, the premise variable space of the 2-D fuzzy affine systems is partitioned into two classes of subspaces, that is: 1) crisp regions and 2) fuzzy regions. For each region, boundary continuity matrices and characterizing matrices are constructed by utilizing the space partition information and 2-D structure. After that, novel piecewise Lyapunov functions are constructed, based on which together with S -procedure, the asymptotic stability with H∞ performance is guaranteed for the filtering error system. By the projection lemma and some elegant convexification techniques, the PWA H∞ filtering design conditions are obtained. Finally, the less conservativeness and effectiveness of the proposed approach over a common Lyapunov function-based one are illustrated by simulation studies.

10.
Inf Fusion ; 90: 364-381, 2023 Feb.
Article in English | MEDLINE | ID: mdl-36217534

ABSTRACT

The COVID-19 (Coronavirus disease 2019) pandemic has become a major global threat to human health and well-being. Thus, the development of computer-aided detection (CAD) systems that are capable of accurately distinguishing COVID-19 from other diseases using chest computed tomography (CT) and X-ray data is of immediate priority. Such automatic systems are usually based on traditional machine learning or deep learning methods. Differently from most of the existing studies, which used either CT scan or X-ray images in COVID-19-case classification, we present a new, simple but efficient deep learning feature fusion model, called U n c e r t a i n t y F u s e N e t , which is able to classify accurately large datasets of both of these types of images. We argue that the uncertainty of the model's predictions should be taken into account in the learning process, even though most of the existing studies have overlooked it. We quantify the prediction uncertainty in our feature fusion model using effective Ensemble Monte Carlo Dropout (EMCD) technique. A comprehensive simulation study has been conducted to compare the results of our new model to the existing approaches, evaluating the performance of competing models in terms of Precision, Recall, F-Measure, Accuracy and ROC curves. The obtained results prove the efficiency of our model which provided the prediction accuracy of 99.08% and 96.35% for the considered CT scan and X-ray datasets, respectively. Moreover, our U n c e r t a i n t y F u s e N e t model was generally robust to noise and performed well with previously unseen data. The source code of our implementation is freely available at: https://github.com/moloud1987/UncertaintyFuseNet-for-COVID-19-Classification.

11.
Comput Biol Med ; 152: 106417, 2023 01.
Article in English | MEDLINE | ID: mdl-36543003

ABSTRACT

The COVID-19 pandemic continues to spread rapidly over the world and causes a tremendous crisis in global human health and the economy. Its early detection and diagnosis are crucial for controlling the further spread. Many deep learning-based methods have been proposed to assist clinicians in automatic COVID-19 diagnosis based on computed tomography imaging. However, challenges still remain, including low data diversity in existing datasets, and unsatisfied detection resulting from insufficient accuracy and sensitivity of deep learning models. To enhance the data diversity, we design augmentation techniques of incremental levels and apply them to the largest open-access benchmark dataset, COVIDx CT-2A. Meanwhile, similarity regularization (SR) derived from contrastive learning is proposed in this study to enable CNNs to learn more parameter-efficient representations, thus improve the accuracy and sensitivity of CNNs. The results on seven commonly used CNNs demonstrate that CNN performance can be improved stably through applying the designed augmentation and SR techniques. In particular, DenseNet121 with SR achieves an average test accuracy of 99.44% in three trials for three-category classification, including normal, non-COVID-19 pneumonia, and COVID-19 pneumonia. The achieved precision, sensitivity, and specificity for the COVID-19 pneumonia category are 98.40%, 99.59%, and 99.50%, respectively. These statistics suggest that our method has surpassed the existing state-of-the-art methods on the COVIDx CT-2A dataset. Source code is available at https://github.com/YujiaKCL/COVID-CT-Similarity-Regularization.


Subject(s)
COVID-19 , Humans , COVID-19/diagnostic imaging , COVID-19 Testing , Pandemics , Benchmarking , Tomography, X-Ray Computed
12.
Annu Int Conf IEEE Eng Med Biol Soc ; 2022: 1927-1930, 2022 07.
Article in English | MEDLINE | ID: mdl-36086299

ABSTRACT

Ventricular arrhythmias are the primary arrhythmias that cause sudden cardiac death. In current clinical and preclinical research, the discovery of new therapies and their translation is hampered by the lack of consistency in diagnostic criteria for distinguishing between ventricular tachycardia (VT) and ventricular fibrillation (VF). This study develops a new set of features, similarity maps, for discrimination between VT and VF using deep neural network architectures. The similarity maps are designed to capture the similarity and the regularity within an ECG trace. Our experiments show that the similarity maps lead to a substantial improvement in distinguishing VT and VF.


Subject(s)
Electrocardiography , Tachycardia, Ventricular , Arrhythmias, Cardiac/diagnosis , Death, Sudden, Cardiac/prevention & control , Humans , Ventricular Fibrillation/diagnosis
13.
IEEE Trans Cybern ; PP2022 Jun 20.
Article in English | MEDLINE | ID: mdl-35724293

ABSTRACT

The path-tracking control of an intelligent vehicle always suffers from the high-frequency measurement noises. To confront this issue, this work puts forward a novel delayed output-feedback implementation of proportional-integral-derivation (PID) control, which is called multidelay proportional-integral-retarded (PIR) control. The mathematical model of the vehicle system is represented in the form of a linear parameter-varying (LPV) system, which uses the car position as the scheduling variable for regulation. On this basis, the multidelay PIR controller is designed such that the tracking errors gradually converge to zero with the aid of the proportional and integral actions, and the harmful high-frequency measurement noises are attenuated by the retarded term consisting of a few delayed proportional actions. To tune the PIR controller parameters, linear matrix inequalities (LMIs), derived by applying Taylor's expansion to the retarded term, are used to compute the convex subcontroller gains. Then, the self-scheduled tracking controller is formulated as the weighted sum of convex subcontrollers, and the weight functions scheduled by the current position are adaptive to the different operational conditions. Experiments in real time using a laboratory car-like vehicle are employed to assess the performance of the proposed controller.

14.
IEEE Trans Cybern ; 52(7): 6504-6517, 2022 Jul.
Article in English | MEDLINE | ID: mdl-35468077

ABSTRACT

Biomarkers, such as magnetic resonance imaging (MRI) and electroencephalogram have been used to help diagnose autism spectrum disorder (ASD). However, the diagnosis needs the assist of specialized medical equipment in the hospital or laboratory. To diagnose ASD in a more effective and convenient way, in this article, we propose an appearance-based gaze estimation algorithm-AttentionGazeNet, to accurately estimate the subject's 3-D gaze from a raw video. The experimental results show its competitive performance on the MPIIGaze dataset and the improvement of 14.7% for static head pose and 46.7% for moving head pose on the EYEDIAP dataset compared with the state-of-the-art gaze estimation algorithms. After projecting the obtained gaze vector onto the screen coordinate, we apply accumulated histogram to taking into account both spatial and temporal information of estimated gaze-point and head-pose sequences. Finally, classification is conducted on our self-collected autistic children video dataset (ACVD), which contains 405 videos from 135 different ASD children, 135 typically developing (TD) children in a primary school, and 135 TD children in a kindergarten. The classification results on ACVD shows the effectiveness and efficiency of our proposed method, with the accuracy 94.8%, the sensitivity 91.1% and the specificity 96.7% for ASD.


Subject(s)
Autism Spectrum Disorder , Algorithms , Autism Spectrum Disorder/diagnostic imaging , Child , Fixation, Ocular , Humans
15.
Sensors (Basel) ; 22(5)2022 Feb 23.
Article in English | MEDLINE | ID: mdl-35270895

ABSTRACT

The brain-computer interface (BCI) has many applications in various fields. In EEG-based research, an essential step is signal denoising. In this paper, a generative adversarial network (GAN)-based denoising method is proposed to denoise the multichannel EEG signal automatically. A new loss function is defined to ensure that the filtered signal can retain as much effective original information and energy as possible. This model can imitate and integrate artificial denoising methods, which reduces processing time; hence it can be used for a large amount of data processing. Compared to other neural network denoising models, the proposed model has one more discriminator, which always judges whether the noise is filtered out. The generator is constantly changing the denoising way. To ensure the GAN model generates EEG signals stably, a new normalization method called sample entropy threshold and energy threshold-based (SETET) normalization is proposed to check the abnormal signals and limit the range of EEG signals. After the denoising system is established, although the denoising model uses the different subjects' data for training, it can still apply to the new subjects' data denoising. The experiments discussed in this paper employ the HaLT public dataset. Correlation and root mean square error (RMSE) are used as evaluation criteria. Results reveal that the proposed automatic GAN denoising network achieves the same performance as the manual hybrid artificial denoising method. Moreover, the GAN network makes the denoising process automatic, representing a significant reduction in time.


Subject(s)
Brain-Computer Interfaces , Signal Processing, Computer-Assisted , Algorithms , Electroencephalography , Humans , Neural Networks, Computer
16.
Front Robot AI ; 9: 834177, 2022.
Article in English | MEDLINE | ID: mdl-35252366

ABSTRACT

Over the course of the past decade, we have witnessed a huge expansion in robotic applications, most notably from well-defined industrial environments into considerably more complex environments. The obstacles that these environments often contain present robotics with a new challenge - to equip robots with a real-time capability of avoiding them. In this paper, we propose a magnetic-field-inspired navigation method that significantly has several advantages over alternative systems. Most importantly, 1) it guarantees obstacle avoidance for both convex and non-convex obstacles, 2) goal convergence is still guaranteed for point-like robots in environments with convex obstacles and non-maze concave obstacles, 3) no prior knowledge of the environment, such as the position and geometry of the obstacles, is needed, 4) it only requires temporally and spatially local environmental sensor information, and 5) it can be implemented on a wide range of robotic platforms in both 2D and 3D environments. The proposed navigation algorithm is validated in simulation scenarios as well as through experimentation. The results demonstrate that robotic platforms, ranging from planar point-like robots to robot arm structures such as the Baxter robot, can successfully navigate toward desired targets within an obstacle-laden environment.

17.
IEEE Trans Cybern ; 52(11): 11604-11613, 2022 Nov.
Article in English | MEDLINE | ID: mdl-34982708

ABSTRACT

Recently, a switching method is applied to deal with the membership function-dependent Lyapunov-Krasovskii functional (LKF) for fuzzy systems with time delay; however, the Lyapunov matrices are only linear dependent on the grades of membership which leads to linear switching (Wang and Lam, 2019). In this article, the linear dependence on the grades of membership is extended to homogenous polynomially membership function dependent (HPMFD) and the linear switching is extended to polynomial matrix switching, based on which the obtained result contains the previous one as a special case. Furthermore, in order to fully use the introduced variables without speial structure, an iteration algorithm is designed to construct the switching controller and the initial condition of the algorithm is also discussed. The final simulation demonstrates the effectiveness of the developed new results.

18.
IEEE Trans Cybern ; 52(6): 4198-4208, 2022 Jun.
Article in English | MEDLINE | ID: mdl-33175685

ABSTRACT

This article investigates the design of the l2-l∞ dynamic output-feedback (DOF) controller for interval type-2 (IT2) T-S fuzzy systems with state delay. For nonlinear systems, the IT2 fuzzy model is an efficient modeling method which can better express uncertainties than the (type-1) fuzzy model. In addition, state delay is also a general factor that affects system performance. After analyzing the stability of the system, based on convex linearization and the projection theorem, this article proposes a delay-dependent output-feedback controller design method. The IT2 membership functions (MFs) of the fuzzy controller are chosen to be different from those of the model so as to increase the freedom of controller selection. A membership-function-dependent (MFD) method based on the staircase MFs is applied to relax the stability analysis results. Finally, a numerical simulation example is given to illustrate the effectiveness of the results.


Subject(s)
Algorithms , Fuzzy Logic , Computer Simulation , Feedback
19.
IEEE Trans Cybern ; 52(3): 1681-1690, 2022 Mar.
Article in English | MEDLINE | ID: mdl-32396117

ABSTRACT

This article focuses on the sampled-data output-feedback control problem for nonlinear systems represented by Takagi-Sugeno fuzzy affine models. An input delay approach is adopted to describe the sample-and-hold behavior of the measurement output. Via augmenting the system states with the control input, the resulting closed-loop system is converted into a singular system first. Based on the piecewise quadratic Lyapunov-Krasovskii functionals, some novel results on the sampled-data piecewise affine output-feedback controller design are attained by employing some convexification techniques. The simulation studies are presented to illustrate the effectiveness of the proposed scheme.

20.
IEEE Trans Cybern ; 52(8): 7906-7912, 2022 Aug.
Article in English | MEDLINE | ID: mdl-33417579

ABSTRACT

In this text, a membership function derivatives (MFDs) extrema-based method is proposed to relax the conservatism both in stability analysis and synthesis problems of Takagi-Sugeno fuzzy systems. By the designed algorithm, the nonpositiveness of the MFDs extrema is conquered. For an open-loop system, based on certain information of the MFs and derivatives, a series of convex stability conditions is derived. Then, an extremum-based construction method is adopted to involve the MF information. For the shape of MFDs, a coordinate transformation algorithm is proposed to involve it in the stability conditions to achieve local stable effects. For a state-feedback control system, conditions guaranteeing the stability and robustness are listed. Finally, simulation examples and comparisons are carried out to clarify the conservatism reduction results of the raised method.

SELECTION OF CITATIONS
SEARCH DETAIL
...