Edge-Coordinated Energy-Efficient Video Analytics for Digital Twin in 6G

Camera networks are essential to constructing fast and accurate mapping between virtual and physical space for digital twin.In this paper,with the aim of developing energy-efficient digital twin in 6G,we investigate real-time video analytics based on cameras mounted on mobile devices with edge coordination.This problem is challenging because 1)mobile devices are with limited battery life and lightweight computation capability,and 2)the captured video frames of mobile devices are continuous changing,which makes the corresponding tasks arrival uncertain.To achieve energy-efficient video analytics in digital twin,by taking energy consumption,analytics accuracy,and latency into consideration,we formulate a deep reinforcement learning based mobile device and edge coordination video analytics framework,which can utilized digital twin models to achieve joint offloading decision and configuration selection.The edge nodes help to collect the information on network topology and task arrival.Extensive simulation results demonstrate that our proposed framework outperforms the benchmarks on accuracy improvement and energy and latency reduction.

Video Analytics Framework for Human Action Recognition

Human action recognition(HAR)is an essential but challenging task for observing human movements.This problem encompasses the observations of variations in human movement and activity identification by machine learning algorithms.This article addresses the challenges in activity recognition by implementing and experimenting an intelligent segmentation,features reduction and selection framework.A novel approach has been introduced for the fusion of segmented frames and multi-level features of interests are extracted.An entropy-skewness based features reduction technique has been implemented and the reduced features are converted into a codebook by serial based fusion.A custom made genetic algorithm is implemented on the constructed features codebook in order to select the strong and wellknown features.The features are exploited by a multi-class SVM for action identification.Comprehensive experimental results are undertaken on four action datasets,namely,Weizmann,KTH,Muhavi,and WVU multi-view.We achieved the recognition rate of 96.80%,100%,100%,and 100%respectively.Analysis reveals that the proposed action recognition approach is efficient and well accurate as compare to existing approaches.

Data Layout and Scheduling Tasks in a Meteorological Cloud Environmen

With the proliferation of the internet,big data continues to grow exponentially,and video has become the largest source.Video big data intro-duces many technological challenges,including compression,storage,trans-mission,analysis,and recognition.The increase in the number of multimedia resources has brought an urgent need to develop intelligent methods to organize and process them.The integration between Semantic link Networks and multimedia resources provides a new prospect for organizing them with their semantics.The tags and surrounding texts of multimedia resources are used to measure their semantic association.Two evaluation methods including clustering and retrieval are performed to measure the semantic relatedness between images accurately and robustly.A Fuzzy Rule-Based Model for Semantic Content Extraction is designed which performs classification with fuzzy rules.The features extracted are trained with the neural network where each network contains several layers among them each layer of neurons is dedicated to measuring the weight towards different semantic events.Each neuron measures its weight according to different features like shape,size,direction,speed,and other features.The object is identified by subtracting the background features and trained to detect based on the features like size,shape,and direction.The weight measurement is performed according to the fuzzy rules and based on the weight measures.These frameworks enhance the video analytics feature and help in video surveillance systems with better accuracy and precision.

Video-based trajectory extraction with deep learning for High-Granularity Highway Simulation(HIGH-SIM)

High-granularity vehicle trajectory data can help researchers develop traffic simulation models,understand traffic flow characteristics,and thus propose insightful strategies for road traffic management.This paper proposes a novel vehicle trajectory extraction method that can extract high-granularity vehicle trajectories from aerial videos.The proposed method includes video calibration,vehicle detection and tracking,lane marking identification,and vehicle motion characteristics calculation.In particular,the authors propose a Monte-Carlo-based lane marking identification approach to identify each vehicle's lane.This is a challenging problem for vehicle trajectory extraction,especially when the aerial videos are taken from a high altitude.The authors applied the proposed method to extract vehicle trajectories from several high-resolution aerial videos recorded from helicopters.The extracted dataset is named by the High-Granularity Highway Simulation(HIGH-SIM)vehicle trajectory dataset.To demonstrate the effectiveness of the proposed method and understand the quality of the HIGHSIM dataset,we compared the HIGH-SIM dataset with a well-known dataset,the NGSIM US-101 dataset,regarding the accuracy and consistency aspects.The comparison results showed that the HIGH-SIM dataset has more reasonable speed and acceleration distributions than the NGSIM US-101 dataset.Also,the internal and platoon consistencies of the HIGH-SIM dataset give lower errors compared to the NGSIM US-101 dataset.To benefit future research,the authors have published the HIGH-SIM dataset online for public use.

A Systematic Review Towards Big Data Analytics in Social Media

The recent advancement in internet 2.0 creates a scope to connect people worldwide using society 2.0 and web 2.0 technologies.This new era allows the consumer to directly connect with other individuals,business corporations,and the government.People are open to sharing opinions,views,and ideas on any topic in different formats out loud.This creates the opportunity to make the"Big Social Data"handy by implementing machine learning approaches and social data analytics.This study offers an overview of recent works in social media,data science,and machine learning to gain a wide perspective on social media big data analytics.We explain why social media data are significant elements of the improved data-driven decision-making process.We propose and build the"Sunflower Model of Big Data"to define big data and bring it up to date with technology by combining 5 V’s and 10 Bigs.We discover the top ten social data analytics to work in the domain of social media platforms.A comprehensive list of relevant statistical/machine learning methods to implement each of these big data analytics is discussed in this work."Text Analytics"is the most used analytics in social data analysis to date.We create a taxonomy on social media analytics to meet the need and provide a clear understanding.Tools,techniques,and supporting data type are also discussed in this research work.As a result,researchers will have an easier time deciding which social data analytics would best suit their needs.

3D convolutional selective autoencoder for instability detection in combustion systems

While analytical solutions of critical(phase)transitions in dynamical systems are abundant for simple nonlinear systems,such analysis remains intractable for real-life dynamical systems.A key example is thermoacoustic insta-bility in combustion,where prediction or early detection of the onset of instability is a hard technical challenge,which needs to be addressed to build safer and more energy-efficient gas turbine engines powering aerospace and energy industries.The instabilities arising in combustion chambers of engines are mathematically too complex to model.To address this issue in a data-driven manner instead,we propose a novel deep learning architecture called 3D convolutional selective autoencoder(3D-CSAE)to detect the evolution of self-excited oscillations using spatiotemporal data,i.e.,hi-speed videos taken from a swirl-stabilized combustor(laboratory surrogate of gas turbine engine combustor).3D-CSAE consists of filters to learn,in a hierarchical fashion,the complex visual and dynamic features related to combustion instability from the training videos(i.e.,two spatial dimensions for the image frames and the third dimension for time).We train the 3D-CSAE on frames of videos obtained from a limited set of operating conditions.We select the 3D-CSAE hyper-parameters that are effective for characterizing hierarchical and multiscale instability structure evolution by utilizing the dynamic information available in the video.The proposed model clearly shows performance improvement in detecting the precursors and the onset of instability.The machine learning-driven results are verified with physics-based off-line measures.Advanced active control mechanisms can directly leverage the proposed online detection capability of 3D-CSAE to mitigate the adverse effects of combustion instabilities on the engine operating under various stringent requirements and conditions.