Automated Video Generation of Moving Digits from Text Using Deep Deconvolutional Generative Adversarial Network

Generating realistic and synthetic video from text is a highly challenging task due to the multitude of issues involved,including digit deformation,noise interference between frames,blurred output,and the need for temporal coherence across frames.In this paper,we propose a novel approach for generating coherent videos of moving digits from textual input using a Deep Deconvolutional Generative Adversarial Network(DD-GAN).The DDGAN comprises a Deep Deconvolutional Neural Network(DDNN)as a Generator(G)and a modified Deep Convolutional Neural Network(DCNN)as a Discriminator(D)to ensure temporal coherence between adjacent frames.The proposed research involves several steps.First,the input text is fed into a Long Short Term Memory(LSTM)based text encoder and then smoothed using Conditioning Augmentation(CA)techniques to enhance the effectiveness of the Generator(G).Next,using a DDNN to generate video frames by incorporating enhanced text and random noise and modifying a DCNN to act as a Discriminator(D),effectively distinguishing between generated and real videos.This research evaluates the quality of the generated videos using standard metrics like Inception Score(IS),Fréchet Inception Distance(FID),Fréchet Inception Distance for video(FID2vid),and Generative Adversarial Metric(GAM),along with a human study based on realism,coherence,and relevance.By conducting experiments on Single-Digit Bouncing MNIST GIFs(SBMG),Two-Digit Bouncing MNIST GIFs(TBMG),and a custom dataset of essential mathematics videos with related text,this research demonstrates significant improvements in both metrics and human study results,confirming the effectiveness of DD-GAN.This research also took the exciting challenge of generating preschool math videos from text,handling complex structures,digits,and symbols,and achieving successful results.The proposed research demonstrates promising results for generating coherent videos from textual input.

A framework for stochastic estimation of electric vehicle charging behavior for risk assessment of distribution networks

Power systems are being transformed to enhance the sustainability.This paper contributes to the knowledge regarding the operational process of future power networks by developing a realistic and stochastic charging model of electric vehicles(EVs).Large-scale integration of EVs into residential distribution networks(RDNs)is an evolving issue of paramount significance for utility operators.Unbalanced voltages prevent effective and reliable operation of RDNs.Diversified EV loads require a stochastic approach to predict EVs charging demand,consequently,a probabilistic model is developed to account several realistic aspects comprising charging time,battery capacity,driving mileage,state-of-charge,traveling frequency,charging power,and time-of-use mechanism under peak and off-peak charging strategies.An attempt is made to examine risks associated with RDNs by applying a stochastic model of EVs charging pattern.The output of EV stochastic model obtained from Monte-Carlo simulations is utilized to evaluate the power quality parameters of RDNs.The equipment capability of RDNs must be evaluated to determine the potential overloads.Performance specifications of RDNs including voltage unbalance factor,voltage behavior,domestic transformer limits and feeder losses are assessed in context to EV charging scenarios with various charging power levels at different penetration levels.Moreover,the impact assessment of EVs on RDNs is found to majorly rely on the type and location of a power network.