This paper presents an online policy iteration (PI) algorithm to learn the continuous-time optimal control solution for unknown constrained-input systems. The proposed PI is implemented on actor-critic structure where two neural networks (NNs) are tuned and simultaneously generate bounded policy. requirement of complete knowledge system dynamics obviated by employing a novel NN identifier in conjunction with actor critic NNs. It shown how weights estimation error affects convergence NN. A...

In this paper, an output-feedback solution to the infinite-horizon linear quadratic tracking (LQT) problem for unknown discrete-time systems is proposed. An augmented system composed of dynamics and reference trajectory constructed. The state constructed from a limited number measurements past input, output, in history system. A novel Bellman equation developed that evaluates value function related fixed policy by using only data By approximate dynamic programming, class reinforcement...

SUMMARY In this paper, we present an online learning algorithm to find the solution H ∞ control problem of continuous‐time systems with input constraints. A suitable nonquadratic functional is utilized encode constraints into problem, and related formulated as a two‐player zero‐sum game performance. Then, policy iteration on actor–critic–disturbance structure developed solve Hamilton–Jacobi–Isaacs (HJI) equation associated game. That is, three NN approximators, namely, actor, critic,...

<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> This paper presents a novel fuzzy model and logic controller for an isolated signalized intersection. The controls the traffic light timings phase sequence to ensure smooth flow of with minimal waiting time length queue. Usually controllers are optimized maximize flows/minimize under typical conditions. Consequentially, these not optimal exceptional cases such as roadblocks road accidents. We...

This paper proposes an emotional stress recognition system with EEG signals using higher order spectra (HOS). A visual induction based acquisition protocol is designed for recording the in five channels (FP1, FP2, T3, T4 and Pz) under two states of participants, Calm neutral Negatively exited. After pre-processing signals, are employed to extract features classifying human emotions. We used Genetic Algorithm optimum selection classifier. Using SVM classifier, our study achieved average...

A target localization method based on color recogni-tion and connected component analysis is presented in this paper. The raw image converted to HSI space through a lookup table binarized, then followed by line-by-line scan find all the domains. By setting appropriate threshold for size of each domain, most pseudo targets can be omitted coordinates could calculated mean time. main advantage absence extra filtering process, therefore real-time performance whole system greatly improved....

In this paper, an online optimal distributed learning algorithm is proposed to solve leader-synchronization problem of nonlinear multi-agent differential graphical games. Each player approximates its control policy using a single-network approximate dynamic programming (ADP) where only one critic neural network (NN) employed instead typical actorcritic structure composed two NNs. The weight tuning laws for NNs guarantee stability in the sense uniform ultimate boundedness (UUB) and...

The rapid advancement of ‘deepfake’ video technology— which uses deep learning artificial intelligence algorithms to create fake videos that look real—has given urgency the question how policymakers and technology companies should moderate inauthentic content. We conduct an experiment measure people’s alertness ability detect a high-quality deepfake among set videos. First, we find in natural setting with no content warnings, individuals who are exposed neutral more likely anything out...

As a key pillar of smart transportation in city applications, Electric Vehicles (EVs) are becoming increasingly popular for their contribution reducing greenhouse gas emissions. The lack charging infrastructure and range detection is one the most significant barriers to Vehicle adoption. To address problem EV detection, employing Machine Learning (ML) algorithms predict analysis, which beneficial drivers. ML (EV) refers application computational statistical models that enable EVs supporting...

The owner's income drop in a sports equipment firm stems from insufficient consumer interest the physical store of particular company, attributed to unattractive product displays and difficult-to-access location. This study presents recommendation system based on searches for items analogous desired sports, which can significantly enhance revenue streamline purchasing experience consumers without necessitating visit store. utilizes descriptive methodology data acquisition, encompassing...

The system aims to collect data on user behaviour and preferences various social media platforms such as Instagram Twitter. aim is determine influential users increase engagement. In contrast conventional methods that focus a single platform at time, the Multiple Platform Hub Authority Topic (MPHAT) model provides an overall view of by examining their connections, interests, favourite networks. MPHAT seeks bring less prominent into limelight overcoming limitations within recommendation...

This letter presents a distributed solution for consensus control of network single-integrator incommensurate fractional-order systems with nonlinear and uncertain dynamics. To consider broader class systems, compared to existing results, the fractional derivative orders agents' dynamics are assumed non-identical, which makes design more challenging. cope non-identical orders, Mittag-Leffler function method is adopted develop novel scheme that guarantees under mild assumptions. deal dynamic...

This paper proposes a maximum power point tracking (MPPT) technique based on the tip speed ratio control for small scale wind turbines (WTs). In this paper, artificial neural network particle swarm optimization has been trained offline to learn characteristic of turbine as function and machine speeds. Afterwards, it realized online estimate varying speed. It is essential design controller that can track peak energy regardless changes. Therefore, work provides novel robust direct adaptive...

A chaos-ANFIS approach is presented for analysis of EEG signals fo r epileptic seizure recognition.The non-linear dynamics the original EEGs are quantified in form hurst exponent (H) and largest lyapunov (λ).The process consists two phases, namely qualitative quantitative analysis.The classification ability H λ measures tested using ANFIS classifier.This method evaluated with a benchmark dataset, results presented.Our inter-ictal based diagnostic achieves 97.4% accuracy 4-fo ld cross...