Deep Adaptive Chaos Synchronization Based on Optimization Algorithm

In this study, we address the problem of chaotic synchronization over a noisy channel by introducing a novel Deep Chaos Synchronization (DCS) system using a Convolutional Neural Network (CNN). Conventional Deep Learning (DL) based communication strategies are extremely powerful but training on large data sets is usually a difficult and time-consuming procedure. To tackle this challenge, DCS does not require prior information or large data sets. In addition, we provide a novel Recurrent Neural Network (RNN)-based chaotic synchronization system for comparative analysis. The results show that the proposed DCS architecture is competitive with RNN-based synchronization in terms of robustness against noise, convergence, and training. Hence, with these features, the DCS scheme will open the door for a new class of modulator schemes and meet the robustness against noise, convergence, and training requirements of the Ultra Reliable Low Latency Communications (URLLC) and Industrial Internet of Things (IIoT).

Convolutional Neural Network (CNN) tend to have better results on large data sets and poor performance on small data sets, so the data augmentation is crucial for a CNN to get better performance based on the dataset with limited size. In this paper, Deep Convolution Generative Adversarial Network (DCGAN) was used to augment data to make the AlexNet perform better on an image classification task with small data sets. AlexNet was trained on a small anime face training set with only 160 samples to determine whether the anime face was male or female, and then tested its accuracy on a test set with 240 sample. Then, a pre-trained DCGAN was transferred to train on the male and female training sets respectively. And 2 DCGANs were obtained, one could generate male cartoon faces and another could generate female cartoon faces. The images generated by DCGANs were put in train set, which was used to train AlexNet again and the result was recorded. Other data augmentation methods such as cutout, cutmix and Noise Injection were compared as well. Finally, it is found that AlexNet has the best performance when using the DCGAN augmentation method, which can significantly improve the verification accuracy of the model.

Urdu is a widely spoken language in East and South Asia, making Urdu digit recognition crucial for applications like cheque processing and number plate recognition. However, digit classification for Urdu numerals is challenging due to limited training data for deeper models. While large public datasets exist for languages like English, Chinese, and Arabic, Urdu lacks such resources. Data augmentation can mitigate this issue. This chapter explores using deep convolutional generative adversarial network (DCGAN) to generate artificial images, preserving the original data's features. DCGAN's performance is assessed with t-stochastic neighbour embedding (t-SNE) and Fréchet inception distance (FID), achieving an FID score of 25.32 on a dataset with 10 classes. This research enhances the dataset and paves the way for advanced Urdu numeral classifiers for future applications.

In this paper, a Lyapunov stability theorem is used to design a model system with adaptive control synchronization. The system uses the pseudo-randomness of chaotic signals to hide the signals that need to be transmitted in seemingly messy chaotic signals. The small input signals are superimposed on the chaotic signals, and the receiving end demodulates the useful information with a synchronized chaotic signal. The system can dynamically adjust the value of the controller according to the initial value of the neuron model so that the two coupling Hindmarsh-Rose neural system can be in a better synchronous state, with good stability and self-adaptability. In this paper, the controller is applied to chaotic secure communication. The simulation results verify the feasibility and effectiveness of the designed controller, and the capability of realizing the transmission of confidential information.

On the Performance of a Digital Chaos-Based Communication System in Noisy Channels

Network traffic classification serves as a building block for important tasks such as security and quality of service management. The field has been studied for a long time, with many techniques such as classical machine learning and deep learning methods currently available. However, the emergence of stronger encryption protocols has led to the rise of new challenges. One of the challenges is capturing and labeling a large amount of encrypted traffic data especially for training deep learning classifiers, as current techniques rely on deep packet inspection tools (DPI) which perform poorly on encrypted traffic. In this paper, we propose a semi-supervised learning approach using Deep Convolutional Generative Adversarial Network (DCGAN). The basic idea is to utilize the samples generated by DCGAN generators as well as unlabeled data to improve the performance of a classifier trained on a few labeled samples. Thus, alleviating the difficulties associated with large dataset collecting and labeling. To demonstrate the efficacy of our approach, we evaluated our model using a self-collected dataset of the recently established QUIC protocol as well as publicly available ISCX VPN-NonVPN dataset. Our approach is able to achieve 89% and 78% accuracy with a very small number of labeled samples (just 10% of the dataset) on both QUIC and ISCX VPN-NonVPN datasets respectively.

This paper investigates the asymptotical synchronization problem of a class of novel uncertain chaotic systems with channel delay. Furthermore, the parameters of the chaotic system in the synchronization systems are assumed to be fully unknown. It is reasonable since the sending end usually is located on the remote site. By virtue of the definition of lag synchronization and adaptive control idea, the asymptotical synchronization for a novel type chaotic systems is implemented. The above results will provide theoretical foundation for the secure communication applications based on chaotic synchronization. Simulation results are given to verify the effectiveness of the proposed adaptive synchronization method.

A chaos-based multi-user time division multiplexing (TDM) communication system has been proposed and its benchmark performance compared to that of the chaos-based direct sequence code division multiple access (DS-CDMA) system in the noisy and Rayleigh fading channels. The benchmark performance of the systems is investigated in terms of the bit error rate (BER) under the assumption of perfect synchronisation. The chaotic spreading signals, used to encrypt the binary messages, are generated using the logistic map. The degradation in performance of the systems in the Rayleigh fading channel when compared with the noisy channel is demonstrated. Furthermore, it is shown that in both noisy and Rayleigh fading channels, the chaos-based multi-user TDM system outperforms the chaos-based DS-CDMA system for a large number of users in the system, whereas the chaos-based DS-CDMA system yields better performance for low user numbers. The overall BER performance degradation for the chaos-based DS-CDMA multi-user system in noisy and Rayleigh fading channels is characterised by the flattening of the BER curves at low levels of noise due to the prevailing effects of the interuser interferences.

The purpose of this study is to develop a novel computer-aided diagnosis (CAD) scheme to facilitate breast mass classification, which is based on the latest transferring generative adversarial networks (GAN) technology. Although GAN is one of the most popular techniques for image augmentation, it requires a relatively large original dataset to achieve satisfactory results, which may not be available for most of the medical imaging tasks. To address this challenge, we developed a novel transferring GAN, which was built based on the deep convolutional generative adversarial networks (DCGAN). This novel model was first pre-trained on a dataset of non-mass mammogram patches. Then the generator and the discriminator were fine-tuned on the mass dataset. A supervised loss was integrated with the discriminator, such that it can be used to directly classify the benign/malignant masses. We retrospectively assembled a total of 25,000 non-mass patches and 1024 mass images to assess this model, using classification accuracy and receiver operating characteristic (ROC) curve. The results demonstrated that our proposed approach improved the accuracy and area under the ROC curve (AUC) by 6.0% and 3.5% respectively, when compared with the classifiers trained without conventional data augmentation. This investigation may provide a new perspective for researchers to effectively train the GAN models on medical imaging tasks with limited datasets.

본 논문에서는 카오스 신호를 이용하여 음성신호의 보안전송을 위한 아날로그 비화통신 시스템을 제안하고 통신성능을 분석하였다. 기존의 카오스 동기화 및 카오스 변조통신 알고리즘을 개선하여 통신환경에서 발생하는 다양한 조건들을 적용하여 음성신호의 복원능력을 모의실험 하였다. 일반적인 PC(Pecora ＆ Carroll) 제어기법과 제안한 SFB(Self-FeedBack) 마스킹 기법을 사용하여 송신단에서 음성신호를 카오스 신호로 마스킹하여 변조하고, 통신채널에 잡음신호를 추가하여 전송하였다. 수신단에서는 카오스 응답시스템을 이용하여 음성신호를 복조하고, 복원성능을 계산하기 위하여 아날로그 복원 에러 신호의 평균전력을 제안하여 계산하였다. 실험결과 마스킹 정도, 파라미터들의 민감성, 채널잡음 등에 대하여 PC 제어기법보다 피드백 제어기법의 복원성능이 우수함을 정량적인 데이터로 확인할 수 있었다. 또한 로렌쯔 카오스 비화통신시스템에 사용할 경우 파라미터들의 조합으로 암호키를 구성해야 하므로 파라미터 변화율에 대응하는 복원에러율의 관계를 모의실험 값으로 구하였다. This paper presents analog secure communication system about safe speech transmission using chaotic signals. We applied various conditions that happen in actuality communication environment modifying chaotic synchronization and chaotic communication schemes and analyzed restoration performance of speech signal to computer simulation. In transmitter, we made the chaotic masking signal which is added voice signal to chaotic signal using PC(Pecora ＆ Carroll) and SFB(self-feedback) control techniques and transmitted encryption signal to noisy communication channel And in order to calculate the degree of restoration performance, we proposed the definition of analog average power of recovered error signals in receiver chaotic system. The simulation results show that feedback control techniques can certify that restoration performance is superior to quantitative data than PC method about masking degree, susceptibility of parameters and channel noise. We experimentally computed the table of relation of parameter fluxion to restoration error rate which is applied the encryption key values to the chaotic secure communication.

In this paper, we consider the adaptive synchronization problem for multi-agents systems with unknown nonlinear dynamics. The topologies of the networks are switching. A novel adaptive synchronization algorithm is proposed by using linear parameterizations of unknown nonlinear dynamics of all agents. By stability analysis and parameter convergence analysis of the proposed algorithm, adaptive synchronization can be realized based on neighboring graphs. The stability analysis is based on algebraic graph theory and Lyapunov theory, the PE condition plays a key role in parameter convergence analysis. Example is given to validate the theoretical results.

In recent years, with the development of the Internet of Things (IoT) technology, a large amount of data can be captured from sensors for real-time analysis. By monitoring the traffic video data from the IoT, we can detect the anomalies that may occur and evaluate the security. However, the number of traffic anomalies is extremely limited, so there is a severe over-fitting problem when using traditional deep learning methods. In order to solve the problem above, we propose a similarity metric Convolutional Neural Network (CNN) based on a channel attention model for traffic anomaly detection task. The method mainly includes (1) A Siamese network with a hierarchical attention model by word embedding so that it can selectively measure similarities between anomalies and the templates. (2) A deep transfer learning method can automatically annotate an unlabeled set while fine-tuning the network. (3) A background modeling method combining spatial and temporal information for anomaly extraction. Experiments show that the proposed method is three percentage points higher than deep convolutional generative adversarial network (DCGAN) and five percentage points higher than AutoEncoder on the accuracy. No more time consumption is needed for the annotation process. The extracted candidates can be classified correctly through the proposed method.

Learning the underlying dynamics of periodic and aperiodic systems evolving over space and time provides substantial challenges across scientific fields. Despite recent advances in machine learning (ML), our understanding of its limits to learning, identifying, and emulating real physical systems remains incomplete. With the increasing complexity of dynamical systems and higher power consumption, ML systems take inspiration from the complex learning mechanisms of the mammalian brain, for biologically plausible learning. As we delve into the designing of brain- inspired ML systems, we deal with the challenges of the learning procedures, network sizes, energy efficiency and training complexities involved with it. It's crucial to characterize their performance in learning and controlling unknown dynamical systems to address them. We address these issues by designing sparsity aware learning mechanisms in feedback driven recurrent neural networks (RNNs), incorporate biologically plausible neuron models, and integrate computational neuroscience to build data driven AI systems. We explore brain-inspired neuronal dynamics to build AI systems that can mimic and classify dynamical systems. We propose full-FORCE (FF) SNN, Reservoir-in-reservoir (R-i-R) architecture, and SNN based applications learning, We pro- pose sparsity aware learning in RNNs, full-FORCE based sparsity regularization in recurrent spiking neural networks (RSNN) and an RSNN based BLE application for dynamical systems learning. Our proposed learning methods and architectures exhibit strong performance, noise robustness and energy efficiency in simulated and real-world adaptive system emulation. We evaluate bio signals, motion trajectories, Lorenz systems, real-world dynamic variable datasets, and other dynamical systems in this dissertation.

The abstraction tasks are challenging for multi- modal sequences as they require a deeper semantic understanding and a novel text generation for the data. Although the recurrent neural networks (RNN) can be used to model the context of the time-sequences, in most cases the long-term dependencies of multi-modal data make the back-propagation through time training of RNN tend to vanish in the time domain. Recently, inspired from Multiple Time-scale Recurrent Neural Network (MTRNN), an extension of Gated Recurrent Unit (GRU), called Multiple Time-scale Gated Recurrent Unit (MTGRU), has been proposed to learn the long-term dependencies in natural language processing. Particularly it is also able to accomplish the abstraction task for paragraphs given that the time constants are well defined. In this paper, we compare the MTRNN and MTGRU in terms of its learning performances as well as their abstraction representation on higher level (with a slower neural activation). This was done by conducting two studies based on a smaller data- set (two-dimension time sequences from non-linear functions) and a relatively large data-set (43-dimension time sequences from iCub manipulation tasks with multi-modal data). We conclude that gated recurrent mechanisms may be necessary for learning long-term dependencies in large dimension multi-modal data-sets (e.g. learning of robot manipulation), even when natural language commands was not involved. But for smaller learning tasks with simple time-sequences, generic version of recurrent models, such as MTRNN, were sufficient to accomplish the abstraction task.

Modelling of long-wave chaotic radar system for anti-stealth applications