Proposed Learning Scheme Research Articles

An Effective Intrusion Detection Scheme over Wireless Communication Environment based on Artificial Intelligence Enabled Modified Learning Strategy

based on Artificial Intelligence Enabled Modified Learning Strategy In this present digital world, each and every document need to be in system format as well as preserved into the server end. So, that the transactions between client and server entities are handled by using wireless communication schemes. There are millions of individuals hooked up to the internet enabled network today, and each of them possesses some level of sensitive information. Nowadays, the most valuable asset is knowledge about the organization or its users. This attracts the attackers or hackers to acquire the personal or private information from the server end or else the path that is used for communication. Numerous types of hackers attempt to penetrate a private system in order to obtain access and extract all critical data that could harm the infrastructure, posing a significant threat to the firm. These kinds of attacks are called intrusions and the attackers are termed as intruders. This paper has a detailed study of the past detection scheme and proposed a novel intrusion detection scheme to support users to prevent the data from intruders. The major objective of this paper is to design a novel Intrusion Detection System with full of attack handling and identification capabilities as well as prevent the data safe in server end without give a lead to intruders to make an attempt. The motto of this work is to introduce a modified learning strategy with respect to the conventional learning scheme called Artificial Neural Network (ANN) and provides a robust support and resistance to identify the intruders over the wireless communication environment. To make the users more convenient to preserve the data over the remote server environment and make transactions in secured manner with the help of the proposed learning scheme. These objectives are clearly illustrated with graphical representations over the resulting section of this paper. This paper introduced a modified learning scheme called Artificial Intelligence Enabled Modified Learning Strategy (AIeMLS), in which it provides a support to genuine network users to carry on with their private data as well as preserve the data over the server end without any threats. The proposed logic called AIeMLS is derived from the conventional learning scheme called ANN, in which it is composed of a number of processing components that accept inputs and generate outputs according to their predetermined activation functions and it is being used to characterize complex situations and to anticipate the contents of specified model parameters based on their learning data. By modifying the last layer of the ANN and adapt the logic of Support Vector Machine (SVM) into it to customize the model into a novel design. This is helpful to identify the intrusions in an intellectual manner with maximum level of accuracy and performance ratio.The proposed modified learning approach AIeMLS attains the maximum accuracy ratio of 98.5% in an outcome, whereas the other conventional algorithms such as ANN and SVM attain 98% and 96% accuracy in results. These resulting performance and efficiency is portrayed in the resulting section using graphical outputs.This approach of identifying the intrusions over the wireless communication environment is helpful to users in real-time environment and significantly preserves the data in proper manner. In future the work can further be enhanced by means of adding some crypto security features to enhance the security level more in the proposed work.

Optimal Service Caching and Pricing in Edge Computing: A Bayesian Gaussian Process Bandit Approach

Motivated by the emergence of function-as-a-service (FaaS) as a programming abstraction for edge computing, we consider the problem of caching and pricing applications for edge computation offloading in a dynamic environment where <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Wirelesss Devices</i> (WDs) can be active or inactive at any point in time. We model the problem as a single leader multiple-follower Stackelberg game, where the service operator is the leader and decides what applications to cache and how much to charge for their use, while the WDs are the followers and decide whether or not to offload their computations. We show that the WDs' interaction can be modeled as a player-specific congestion game and show the existence and computability of equilibria. We then show that under perfect and complete information the equilibrium price of the service operator can be computed in polynomial time for any cache placement. For the incomplete information case, we propose a Bayesian Gaussian Process Bandit algorithm for learning an optimal price for a cache placement and provide a bound on its asymptotic regret. We then propose a Gaussian process approximation-based greedy heuristic for computing the cache placement. We use extensive simulations to evaluate the proposed learning scheme, and show that it outperforms state of the art algorithms by up to 50% at little computational overhead.

Physics-Assisted Learning Scheme for Quantitative Imaging via Near-Field Scanning Microwave Microscopy

Quantitative determination of the dielectric property is important to the analysis and evaluation of the investigated samples’ performance. This article proposes a physics-assisted learning scheme (PALS) for the quantitative imaging via the near-field scanning microwave microscopy (NFSMM) in a nondestructive way. To avoid using the machine learning in a black-box way, an efficient input generation is realized by utilizing the Rayleigh approximation method. Numerical and experimental examples demonstrate that the PALS recovers the dielectric parameters of the subsurface perturbation more accurately and shows a better generalization ability. The proposed learning scheme provides a reasonable way to combine the machine learning with underlying physics in the NFSMM, rather than utilizing machine learning in a black-box way. The same principle is also potential to be applied in other types of scanning microscopies, such as optical and thermal ones.

Learning-Based Control With Decentralized Dynamic Event-Triggering for Vehicle Systems

The optimal control of multi-input system can be described by a multiplayer nonzero-sum differential game. This article theoretically presents an event-based adaptive learning scheme to approximate the Nash equilibrium, and practically addresses the cruise control problem for Caltech vehicle systems. This design is deployed in two aspects. On one hand, the reinforcement learning is implemented through critic neural network architecture and recalling stored experience data. On the other hand, in view of that each player’s preference is different, the decentralized triggering manner is considered to reduce communication. Based on the continuous state, the local sampled state is defined for each player, and a static triggering mechanism is formulated first. The decentralized dynamic triggering is then promoted by designing an auxiliary variable whose dynamics are constructed using static triggering information. Next, the proposed learning scheme is examined on a four-player numerical system. Finally, the learning-based controller is tested on a single-vehicle system under different tracking commands, and then, it is extended to multivehicle systems to realize cooperative optimization by introducing a novel game-in-game structure.

Generalized Modified Blake–Zisserman Robust Sparse Adaptive Filters

In the past years, the generalized maximum correntropy criterion (GMCC) has been widely used in adaptive filters to provide robust behavior under non-Gaussian/impulsive noise environments. However, GMCC-based adaptive filters are affected by high steady-state misalignment. In order to enhance the robustness under non-Gaussian noise environments and reduce steady-state misalignment, a generalized modified Blake–Zisserman (GMBZ) robust loss function is introduced in this correspondence. Furthermore, a GMBZ adaptive filter (GMBZ-AF) has been developed that provides improved convergence performance over other existing algorithms. The proposed learning scheme has a computational complexity very similar to that of the GMCC-based adaptive filtering method. In order to further exploit the sparse nature of the system for identifying sparse systems and simultaneously provide robust convergence, two new robust sparse adaptive filters: 1) zero attracting GMBZ-AF (ZA-GMBZ-AF) and 2) reweighted ZA-GMBZ-AF (RZA-GMBZ-AF) have also been proposed. To further enhance the filter convergence performance, a new robust and sparsity-aware loss function called generalized modified dual Blake–Zisserman (GMDBZ) is also introduced in this correspondence and the corresponding GMDBZ adaptive filter (GMDBZ-AF) has been developed.

Deep reinforcement learning autoencoder with RA-GAN and GAN

Deep learning utilization to optimize block-structured communication systems has attracted tremendous attention from researchers. Nevertheless, owing to the extensive data transmission between the transmitter and the receiver, communication, in this case, is hard to establish and maintain effectively. As a solution for this, we first investigate typical end-to-end learning for a communication system, Generative Adversarial Network (GAN). Then, two problems associated with GAN-based systems, the gradient vanishing and overfitting, are reviewed. Subsequently, a residual aided GAN (RA-GAN) is proposed as means to overcome these problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. Finally, the numerical results performed in MATLAB for simulation and Codelabs for training have proven that the RA-GAN scheme has near-optimal performance and outperforms the conventional GAN scheme. Throughout this case study, readers can understand the issues that would occur when deep learning is applied to a communication system and possible approaches to address them.

Local search enhanced Aquila optimization algorithm ameliorated with an ensemble of Wavelet mutation strategies for complex optimization problems

Aquila Optimization Algorithm (AQUILA) is a newly emerged metaheuristic optimizer for solving global optimization problems, which is based on intrinsic hunting behaviors of the foraging aquila individuals. However, this stochastic optimization method suffers from some algorithm-specific drawbacks, such as premature convergence to the local optimum points over the search hyperspace due to the lack of solution diversity in the population. To conquer this algorithmic deficiency, an ensemble of Wavelet mutation operators has been implemented into the standard AQUILA to enhance the explorative capabilities of the algorithm by diversifying the search domain as much as possible. Furthermore, a brand-new local search scheme empowered by the synergetic interactions of elite opposition-based learning and a simple-yet-effective exploitative manipulation equation is introduced into the base AQUILA to intensify on the previously visited promising regions. The proposed learning schemes are stochastically applied to the obtained solutions from the base Aquila algorithm to refine the overall solution quality and amend the premature convergence problem. It is also aimed to investigate whether the collective application of Wavelet mutation operators with different types entails a significant improvement in the general search effectivity of the algorithm rather than their individual efforts. Numerical experiments made on a suite of unconstrained unimodal and multimodal benchmark functions reveal that this hybridization with AQUILA has improved the general solution accuracy and stability to very high standards, outperforming its contemporary counterparts in the comparative statistical analysis. Furthermore, an exhaustive benchmark analysis has been performed on fourteen constrained real-world complex engineering problems.

An approximate randomization-based neural network with dedicated digital architecture for energy-constrained devices

Variable energy constraints affect the implementations of neural networks on battery-operated embedded systems. This paper describes a learning algorithm for randomization-based neural networks with hard-limit activation functions. The approach adopts a novel cost function that balances accuracy and network complexity during training. From an energy-specific perspective, the new learning strategy allows to adjust, dynamically and in real time, the number of operations during the network’s forward phase. The proposed learning scheme leads to efficient predictors supported by digital architectures. The resulting digital architecture can switch to approximate computing at run time, in compliance with the available energy budget. Experiments on 10 real-world prediction testbeds confirmed the effectiveness of the learning scheme. Additional tests on limited-resource devices supported the implementation efficiency of the overall design approach.

Beyond fine-tuning: Classifying high resolution mammograms using function-preserving transformations.

The task of classifying mammograms is very challenging because the lesion is usually small in the high resolution image. The current state-of-the-art approaches for medical image classification rely on using the de-facto method for convolutional neural networks-fine-tuning. However, there are fundamental differences between natural images and medical images, which based on existing evidence from the literature, limits the overall performance gain when designed with algorithmic approaches. In this paper, we propose to go beyond fine-tuning by introducing a novel framework called MorphHR, in which we highlight a new transfer learning scheme. The idea behind the proposed framework is to integrate function-preserving transformations, for any continuous non-linear activation neurons, to internally regularise the network for improving mammograms classification. The proposed solution offers two major advantages over the existing techniques. Firstly and unlike fine-tuning, the proposed approach allows for modifying not only the last few layers but also several of the first ones on a deep ConvNet. By doing this, we can design the network front to be suitable for learning domain specific features. Secondly, the proposed scheme is scalable to hardware. Therefore, one can fit high resolution images on standard GPU memory. We show that by using high resolution images, one prevents losing relevant information. We demonstrate, through numerical and visual experiments, that the proposed approach yields to a significant improvement in the classification performance over state-of-the-art techniques, and is indeed on a par with radiology experts. Moreover and for generalisation purposes, we show the effectiveness of the proposed learning scheme on another large dataset, the ChestX-ray14, surpassing current state-of-the-art techniques.

FT-EALU: fault-tolerant arithmetic and logic unit for critical embedded and real-time systems

This paper presents a fault-tolerant ALU (“FT-EALU”) based on time redundancy and reward/punishment-based learning approaches for real-time embedded systems that face limitations in hardware and power consumption budgets. In this method, operations are diversified to three versions in order to correct permanent faults along with the transient ones. The diversities of versions considered in FT-EALU are provided by lightweight modifications to differentiate them and clear the effect of permanent faults. Selecting lightweight modifications such as shift and swap would avoid high timing overhead in computation while providing significant differences which are necessary for fault detection. Next, the replicated versions are executed serially in time, and their corresponding results are voted based on the derived learned weights. The proposed weighted voting module generates the final output based on the results and their weights. In the proposed weighted voting module, a reward/punishment strategy is employed to provide the weight of each version of execution indicating its effectiveness in the final output. To this aim, in the method defined for each version of execution, a weight is defined according to its correction capability confronting several faulty scenarios. Thus, this weight defines the reliability of the temporal results as well as their effect on the final result. The final result is generated bit by bit based on the weight of each version of execution and its computed result. Based on the proposed learning scheme, positive or negative weights are assigned to execution versions. These weights are derived in bit level based on the capability of execution versions in mitigating permanent faults in several fault injection scenarios. Thus, our proposed method is low cost and more efficient compared to related research which are mainly based on information and hardware redundancy due to employing time redundancy and static learning approach in correcting permanent faults. Several experiments are performed to reveal the efficiency of our proposed approach based on which FT-EALU is capable of correcting about \(84.93\%\) and \(69.71\%\) of permanent injected faults on single and double bits of input data.

Asynchronous learning for actor–critic neural networks and synchronous triggering for multiplayer system

In this paper, based on actor–critic neural network structure and reinforcement learning scheme, a novel asynchronous learning algorithm with event communication is developed, so as to solve Nash equilibrium of multiplayer nonzero-sum differential game in an adaptive fashion. From the point of optimal control view, each player or local controller wants to minimize the individual infinite-time cost function by finding an optimal policy. In this novel learning framework, each player consists of one critic and one actor, and implements distributed asynchronous policy iteration to optimize decision-making process. In addition, communication burden between the system and players is effectively reduced by setting up a central event generator. Critic network executes fast updates by gradient-descent adaption while actor network gives event-induced updates using the gradient projection. The closed-loop asymptotic stability is ensured along with uniform ultimate convergence. Then, the effectiveness of the proposed algorithm is substantiated on a four-player nonlinear system, revealing that it can significantly reduce sampling numbers without impairing learning accuracy. Finally, by leveraging nonzero-sum game idea, the proposed learning scheme is also applied to solve the lateral-directional stability of a linear aircraft system, and is further extended to a nonlinear vehicle system for achieving adaptive cruise control.

A Generalizable and Discriminative Learning Method for Deep EEG-Based Motor Imagery Classification.

Convolutional neural networks (CNNs) have been widely applied to the motor imagery (MI) classification field, significantly improving the state-of-the-art (SoA) performance in terms of classification accuracy. Although innovative model structures are thoroughly explored, little attention was drawn toward the objective function. In most of the available CNNs in the MI area, the standard cross-entropy loss is usually performed as the objective function, which only ensures deep feature separability. Corresponding to the limitation of current objective functions, a new loss function with a combination of smoothed cross-entropy (with label smoothing) and center loss is proposed as the supervision signal for the model in the MI recognition task. Specifically, the smoothed cross-entropy is calculated by the entropy between the predicted labels and the one-hot hard labels regularized by a noise of uniform distribution. The center loss learns a deep feature center for each class and minimizes the distance between deep features and their corresponding centers. The proposed loss tries to optimize the model in two learning objectives, preventing overconfident predictions and increasing deep feature discriminative capacity (interclass separability and intraclass invariant), which guarantee the effectiveness of MI recognition models. We conduct extensive experiments on two well-known benchmarks (BCI competition IV-2a and IV-2b) to evaluate our method. The result indicates that the proposed approach achieves better performance than other SoA models on both datasets. The proposed learning scheme offers a more robust optimization for the CNN model in the MI classification task, simultaneously decreasing the risk of overfitting and increasing the discriminative power of deeply learned features.

Adaptive Network Pruning for Wireless Federated Learning

In this letter, we apply the model compression, i.e., network pruning, into wireless federated learning (FL) system to mitigate the local computation and communication bottlenecks. Firstly, the convergence rate and learning latency of the FL system are mathematically analyzed. Then, an optimization problem is formulated to maximize the convergence rate while guaranteeing the learning latency via jointly optimizing the pruning ratio and spectrum allocation. Finally, the experimental results show that the proposed learning scheme can improve the performance of the wireless FL as compared with other conventional schemes.

Recurrently-Trained Super-Resolution

We are motivated by the observation that for problems where inputs and outputs are in the same form such as in image enhancement, deep neural networks can be reinforced by retraining the network using a new target set to the output for the original target. As an example, we introduce a new learning strategy for super-resolution by recurrently training the same simple network. Unlike the existing self-trained SR, which involves a single stage of learning with multiple runs at test time, our method trains the same SR network multiple times with increasingly better targets requiring only a single inference at test time. At each stage of the proposed learning scheme, a new target for training is obtained by applying the most recently trained SR network to the original image and downscaling the resultant SR image to normalize the size. Even if downscaling is involved, we argue that the downscaled SR image acts as a better target compared to the old target. We could mathematically demonstrate that this process is similar to unsharp masking when it is linearly approximated and that this process makes the image sharper. However, unlike unsharp masking, the proposed recurrent learning tends to converge to a specific target. By retraining the existing network aiming at a more enhanced target, the proposed method can achieve a similar effect of applying SR multiple times without increasing implementation cost and inference time. To objectively verify the supremacy of our approach by experiments, we propose to use VIQET MOS, which does not require a reference image as a measure of image quality. As far as we know, our work of using an objective quality measure in image enhancement is the first one whose validity was verified by showing similar results to the actual user's subjective evaluation. The proposed recurrent learning scheme makes existing SR algorithms more useful by clearly improving the effect of SR. Codes are available at https://github.com/rtsr82/rtsr.git.

Adaptive output‐feedback quadratic tracking control of continuous‐time systems via value iteration with its application

This study is dedicated to develop an adaptive output-feedback (OPFB) tracking control scheme for continuous-time linear systems to achieve the infinite-horizon linear quadratic tracking (LQT) solution. The existence conditions of the OPFB control for LQT solution are proposed and an upper bound is found for the discount factor to assure the stability of the OPFB solution. To develop an online learning solution without knowing the system drift dynamics, a novel value iteration (VI) algorithm is presented based on the integral reinforcement learning technique which requires measured augmented system states. Moreover, a convergence analysis is proposed for the VI algorithm. Compared to the policy iteration method, the VI algorithm relaxes the initial stabilising control policy requirement. Specifically, in order to further obviate the knowledge of system states, a neural network-based adaptive observer is used during learning and it is no longer needed after the online learning algorithm converges. Effectiveness of the proposed learning scheme is illustrated through an interesting application into a single-phase grid-connected PV power inverter.

Language-Guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning

The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments according to the given language instruction. The main challenges of VLN arise mainly from two aspects: first, the agent needs to attend to the meaningful paragraphs of the language instruction corresponding to the dynamically-varying visual environments; second, during the training process, the agent usually imitate the shortest-path to the target location. Due to the discrepancy of action selection between training and inference, the agent solely on the basis of imitation learning does not perform well. Sampling the next action from its predicted probability distribution during the training process allows the agent to explore diverse routes from the environments, yielding higher success rates. Nevertheless, without being presented with the shortest navigation paths during the training process, the agent may arrive at the target location through an unexpected longer route. To overcome these challenges, we design a cross-modal grounding module, which is composed of two complementary attention mechanisms, to equip the agent with a better ability to track the correspondence between the textual and visual modalities. We then propose to recursively alternate the learning schemes of imitation and exploration to narrow the discrepancy between training and inference. We further exploit the advantages of both these two learning schemes via adversarial learning. Extensive experimental results on the Room-to-Room (R2R) benchmark dataset demonstrate that the proposed learning scheme is generalized and complementary to prior arts. Our method performs well against state-of-the-art approaches in terms of effectiveness and efficiency.

Online learning with stability guarantees: A memory-based warm starting for real-time MPC

We propose and analyze a real-time model predictive control (MPC) scheme that utilizes stored data to improve its performance by learning the value function online with stability guarantees. For linear and nonlinear systems, a learning method is presented that makes use of basic analytic properties of the cost function and is proven to learn the MPC control law and the value function on the limit set of the closed-loop state trajectory. The main idea is to generate a smart warm start based on historical data that improves future data points and thus future warm starts. We show that these warm starts are asymptotically exact and converge to the solution of the MPC optimization problem. Thereby, the suboptimality of the applied control input resulting from the real-time requirements vanishes over time. Numerical examples show that existing real-time MPC schemes can be improved by storing optimization data and using the proposed learning scheme.

Geometry-aware manipulability learning, tracking, and transfer

Body posture influences human and robot performance in manipulation tasks, as appropriate poses facilitate motion or the exertion of force along different axes. In robotics, manipulability ellipsoids arise as a powerful descriptor to analyze, control, and design the robot dexterity as a function of the articulatory joint configuration. This descriptor can be designed according to different task requirements, such as tracking a desired position or applying a specific force. In this context, this article presents a novel manipulability transfer framework, a method that allows robots to learn and reproduce manipulability ellipsoids from expert demonstrations. The proposed learning scheme is built on a tensor-based formulation of a Gaussian mixture model that takes into account that manipulability ellipsoids lie on the manifold of symmetric positive-definite matrices. Learning is coupled with a geometry-aware tracking controller allowing robots to follow a desired profile of manipulability ellipsoids. Extensive evaluations in simulation with redundant manipulators, a robotic hand and humanoids agents, as well as an experiment with two real dual-arm systems validate the feasibility of the approach.

Dynamic Multi-Swarm Differential Learning Quantum Bird Swarm Algorithm and Its Application in Random Forest Classification Model.

Bird swarm algorithm is one of the swarm intelligence algorithms proposed recently. However, the original bird swarm algorithm has some drawbacks, such as easy to fall into local optimum and slow convergence speed. To overcome these short-comings, a dynamic multi-swarm differential learning quantum bird swarm algorithm which combines three hybrid strategies was established. First, establishing a dynamic multi-swarm bird swarm algorithm and the differential evolution strategy was adopted to enhance the randomness of the foraging behavior's movement, which can make the bird swarm algorithm have a stronger global exploration capability. Next, quantum behavior was introduced into the bird swarm algorithm for more efficient search solution space. Then, the improved bird swarm algorithm is used to optimize the number of decision trees and the number of predictor variables on the random forest classification model. In the experiment, the 18 benchmark functions, 30 CEC2014 functions, and the 8 UCI datasets are tested to show that the improved algorithm and model are very competitive and outperform the other algorithms and models. Finally, the effective random forest classification model was applied to actual oil logging prediction. As the experimental results show, the three strategies can significantly boost the performance of the bird swarm algorithm and the proposed learning scheme can guarantee a more stable random forest classification model with higher accuracy and efficiency compared to others.

Process-monitoring-for-quality — A machine learning-based modeling for rare event detection

Abstract Process Monitoring for Quality is a Big Data-driven quality philosophy aimed at defect detection through binary classification and empirical knowledge discovery. It is founded on Big Models, a predictive modeling paradigm that applies Machine Learning, statistics and optimization techniques to process data to create a manufacturing functional model. Functional refers to a parsimonious model with high detection ability that can be trusted by engineers, and deployed to control production. A parsimonious modeling scheme is presented aimed at rare quality event detection, parsimony is induced through feature selection and model selection. Its unique ability to deal with highly/ultra-unbalanced data structures and diverse learning algorithms is validated with four case studies, using the Support Vector Machine, Logistic Regression, Naive Bayes and k-Nearest Neighbors learning algorithms. And according to experimental results, the proposed learning scheme significantly outperformed typical learning approaches based on the l 1 -regularized logistic regression and Random Undersampling Boosting learning algorithms, with respect to parsimony and prediction.