A comprehensive comparison of handcrafted features and convolutional autoencoders for epileptic seizures detection in EEG signals

Self Cite

In this paper, a novel medical image encryption method based on multi-mode synchronization of hyper-chaotic systems is presented. The synchronization of hyper-chaotic systems is of great significance in secure communication tasks such as encryption of images. Multi-mode synchronization is a novel and highly complex issue, especially if there is uncertainty and disturbance. In this work, an adaptive-robust controller is designed for multimode synchronized chaotic systems with variable and unknown parameters, despite the bounded disturbance and uncertainty with a known function in two modes. In the first case, it is a main system with some response systems, and in the second case, it is a circular synchronization. Using theorems it is proved that the two synchronization methods are equivalent. Our results show that, we are able to obtain the convergence of synchronization error and parameter estimation error to zero using Lyapunov’s method. The new laws to update time-varying parameters, estimating disturbance and uncertainty bounds are proposed such that stability of system is guaranteed. To assess the performance of the proposed synchronization method, various statistical analyzes were carried out on the encrypted medical images and standard benchmark images. The results show effective performance of the proposed synchronization technique in the medical images encryption for telemedicine application.

Section: Resultsmentioning

confidence: 99%

Medical Images Encryption Based on Adaptive-Robust Multi-Mode Synchronization of Chen Hyper-Chaotic Systems

Javan

Jafari

Shoeibi

et al. 2021

Self Cite

“…HAR classification research involving IMU sensors embedded in wearables is fairly common given the ubiquity of these devices, including those using smartphones [ 2 , 10 , 22 , 69 , 70 ] and smartwatches [ 5 , 6 , 12 , 71 ]. Studies examining feature extraction techniques have previously been performed for time series [ 72 , 73 , 74 ]. However, in this paper, we are interested in the impact of engineered versus deep learning-generated features on HAR inertial data for OOD detection in particular.…”

Section: Discussionmentioning

confidence: 99%

Out-of-Distribution Detection of Human Activity Recognition with Smartwatch Inertial Sensors

Boyer

Burns

Whyne

2021

Out-of-distribution (OOD) in the context of Human Activity Recognition (HAR) refers to data from activity classes that are not represented in the training data of a Machine Learning (ML) algorithm. OOD data are a challenge to classify accurately for most ML algorithms, especially deep learning models that are prone to overconfident predictions based on in-distribution (IIN) classes. To simulate the OOD problem in physiotherapy, our team collected a new dataset (SPARS9x) consisting of inertial data captured by smartwatches worn by 20 healthy subjects as they performed supervised physiotherapy exercises (IIN), followed by a minimum 3 h of data captured for each subject as they engaged in unrelated and unstructured activities (OOD). In this paper, we experiment with three traditional algorithms for OOD-detection using engineered statistical features, deep learning-generated features, and several popular deep learning approaches on SPARS9x and two other publicly-available human activity datasets (MHEALTH and SPARS). We demonstrate that, while deep learning algorithms perform better than simple traditional algorithms such as KNN with engineered features for in-distribution classification, traditional algorithms outperform deep learning approaches for OOD detection for these HAR time series datasets.

“…Medical data stored in hospitals contain significant information about the patients. In future work, the proposed method for secure communication can be used for medical applications [ 42 , 43 , 44 , 45 , 46 , 47 ]. Synchronization of chaotic systems is also used in some other applications such as electromagnetism [ 48 ] and mechanics [ 49 , 50 ].…”

Section: Discussionmentioning

confidence: 99%

Design of Adaptive-Robust Controller for Multi-State Synchronization of Chaotic Systems with Unknown and Time-Varying Delays and Its Application in Secure Communication

Javan

Shoeibi

Zare

et al. 2021

Self Cite

In this paper, the multi-state synchronization of chaotic systems with non-identical, unknown, and time-varying delay in the presence of external perturbations and parametric uncertainties was studied. The presence of unknown delays, unknown bounds of disturbance and uncertainty, as well as changes in system parameters complicate the determination of control function and synchronization. During a synchronization scheme using a robust-adaptive control procedure with the help of the Lyapunov stability theorem, the errors converged to zero, and the updating rules were set to estimate the system parameters and delays. To investigate the performance of the proposed design, simulations have been carried out on two Chen hyper-chaotic systems as the slave and one Chua hyper-chaotic system as the master. Our results showed that the proposed controller outperformed the state-of-the-art techniques in terms of convergence speed of synchronization, parameter estimation, and delay estimation processes. The parameters and time delays were achieved with appropriate approximation. Finally, secure communication was realized with a chaotic masking method, and our results revealed the effectiveness of the proposed method in secure telecommunications.