Simulations are commonly used to develop and evaluate video encryption algorithms. Although these approaches are useful for demonstrating theoretical feasibility and algorithm performance, they neglect practical chall...
详细信息
Memristors have proven since their discovery to play a very important role as artificial synapses in the implementation of artificial neural networks. Just as biological synapses, memristors can significantly influenc...
Memristors have proven since their discovery to play a very important role as artificial synapses in the implementation of artificial neural networks. Just as biological synapses, memristors can significantly influence the behaviors of the neural network. A non-polynomial memristor is used in this work to investigate the memristive synaptic weight effect on the dynamics of a simplified Rulkov neuron. The model is first introduced from where theoretical analyses show the system’s ability to develop regular and irregular behaviors. Analysis methods such as two parameter charts, bifurcation diagrams and maximum Lyapunov exponents (MLE) are then used to study the dynamics of the proposed Rulkov model. The numerical results show that the memristive synaptic weight Rulkov neuron model can exhibit self-excited and hidden firings. Furthermore, the system can undergo interesting offset boosting dynamics and antimonotonicity features (i.e., bubble bifurcations) for some system parameters. To corroborate the computational findings, the proposed model is implemented on an Arduino Due microcontroller board, from where the experimental results are seen to be in agreement with the obtained numerical results.
Breast cancer is a leading cause of mortality worldwide. Screening therefore remains the best defense against this disease, highlighting the need for accurate and efficient diagnostic methods. Previous authors address...
详细信息
Background Ophthalmological consultations are essential for the early detection of retinal pathologies. The development of advanced diagnostic devices that combine portability, ease of access, and energy efficiency of...
详细信息
Background Ophthalmological consultations are essential for the early detection of retinal pathologies. The development of advanced diagnostic devices that combine portability, ease of access, and energy efficiency offers significant benefits, especially in rural or peri-urban areas, which often struggle with limited medical resources and time constraints. Method In this study, we develop a classification platform for various retinal diseases using a Raspberry Pi 4 board. The system relies on a lightweight deep learning model based on convolutional neural networks (CNNs). To enhance the model's efficiency, we integrate biorthogonal wavelet transforms, which facilitate the effective extraction of relevant features from the input images. This approach reduces computational complexity while maintaining the quality of the extracted information. The model, optimized for real-time deployment, was trained on a dataset containing 4303 retinal images, representing four classes of pathologies. Results The proposed embedded model achieves an accuracy of 0.9806 across the four classes of pathologies collected from the two public databases ODIR (Ocular Disease Intelligence Recognition) and RFMiD (Retinal Fundus Multi-Disease Image Dataset). Conclusions Compared to several state-of-the-art methods published to date, the outstanding performance of the proposed embedded system demonstrates its potential as a valuable tool for clinicians to diagnose various ocular diseases in underprivileged healthcare settings.
In this contribution, we improve of the performance of the Rectified Linear unit Memristor Like Activation Function with the implication to help training process of CNN without a lot of epochs by computing the best va...
详细信息
Nonlinear systems with high dimension have received considerable attention recently due to their possibility to exhibit complex dynamics including chaos, hyperchaos, pattern formation, self-organization, and other rel...
Nonlinear systems with high dimension have received considerable attention recently due to their possibility to exhibit complex dynamics including chaos, hyperchaos, pattern formation, self-organization, and other related dynamics. In this work, a novel four dimensional autonomous hyperchaotic hyperjerk circuit with hyperbolic sine and quintic nonlinearities is proposed and its corresponding dynamics is analyzed theoretically, numerically and experimentally. Using Kirchhoff’s laws, the state equations of the proposed hyperchaotic hyperjerk circuit are described. Some fundamental properties of the model including symmetry, dissipation, equilibrium points and their stability are examined. Bifurcation diagrams, Lyapunov exponent spectrum and phase portraits are plotted to point out the complex dynamical behaviors exhibited by the system. The numerical results are validated using PSpice-based circuit simulations and Field-Programmable Gate Array (FPGA) implementations. In addition, to use the proposed hyperchaotic hyperjerk circuit for medical images encryption, a random number generator (RNG) is designed. The resulting random number generator (RNG) successfully passes the National Institute of Standards and Technology (NIST-800-22) statistical tests. This confirms that the proposed hyperchaotic hyperjerk circuit is effective in showing randomness. Finally, a medical images encryption algorithm is developed based on the generated random bits. The security performances analyses are performed and the results show that the proposed algorithm can effectively encrypt and decrypt medical images with better security performances.
The evolution of embedded systems has demonstrated their reliability as a solution for monitoring and controlling industrial systems, particularly in renewable energy conversion systems like photovoltaic (PV) energy. ...
详细信息
ISBN:
(数字)9798350373974
ISBN:
(纸本)9798350373981
The evolution of embedded systems has demonstrated their reliability as a solution for monitoring and controlling industrial systems, particularly in renewable energy conversion systems like photovoltaic (PV) energy. The increasing adoption of PV systems highlights the critical need for effective fault diagnosis to ensure their reliable operation. In this paper, we present a novel fault diagnosis approach utilizing Long Short-Term Memory (LSTM) networks optimized through Bayesian optimization techniques. Our methodology is implemented on a Raspberry Pi platform, demonstrating the feasibility of deploying sophisticated fault diagnosis algorithms in resource-constrained environments. Through extensive experiments, we demonstrate the effectiveness of our approach to accurately diagnose faults in grid-connected photovoltaic systems, thereby improving the reliability and efficiency of integrated environmental monitoring *** obtained results highlight the potential of combining advanced deep learning techniques with embedded systems to address complex diagnostic challenges, as demonstrated by achieving a 100% accuracy rate.
Current in vivo microscopy allows us detailed spatiotemporal imaging (3D+t) of complete organisms and offers insights into their development on the cellular level. Even though the imaging speed and quality is steadily...
详细信息
ISBN:
(数字)9781728163956
ISBN:
(纸本)9781728163963
Current in vivo microscopy allows us detailed spatiotemporal imaging (3D+t) of complete organisms and offers insights into their development on the cellular level. Even though the imaging speed and quality is steadily improving, fullyautomated segmentation is often not accurate enough in lowsignal image regions. This is particularly true while imaging large samples (100 μm -1 mm) and deep inside the specimen. Drosophila embryogenesis, widely used as a developmental paradigm, presents an example for such a challenge, especially where cell outlines need to imaged - a general challenge in other systems as well. To deal with the current bottleneck in analyzing quantitatively the 3D+t light-sheet microscopy images of Drosophila embryos, we developed a collection of semi-automatic open-source tools. The presented methods include a semi-automatic masking procedure, automatic projection of non-convex 3D isosurfaces to 2D representations as well as cell segmentation and tracking.
Diagnosis of most ophthalmic conditions, such as diabetic retinopathy, generally relies on an effective analysis of retinal blood vessels. Techniques that depend solely on the visual observation of clinicians can be t...
详细信息
This paper proposes an Intrusion Detection System (IDS) employing the Harris Hawks Optimization algorithm (HHO) to optimize Multilayer Perceptron learning by optimizing bias and weight parameters. HHO-MLP aims to sele...
详细信息
暂无评论