CSAP

The current proposal of C++20 features suggests that the coroutines will have dedicated support for the native language. This chapter will provide an analysis that is performed based on a comprehensive survey of coroutines that are used in the development process of the embedded systems and how they are used on dedicated platforms based on their constrained resources. Another important aspect of the work consists of analyzing the performance of designing and implementation of coroutines in software applications related to IoT and embedded devices focusing on the security vulnerabilities of the devices within an IoT ecosystem. The research analysis that forms the basis of the current work is based on metrics, such as software and hardware platform requirements, computation power, scenarios, advantages, and designing user interfaces based on the programming language used. The current work will be completed by adding a comparison with C# 8 programming language and C++20.

Motion Imitation for Monocular Videos

This work represents a simple method for motion transfer (i.e., given a source video of a subject [person] performing some movements or in motion, that movement/motion is transferred to amateur target in different motion). The pose is used as an intermediate representation to perform this translation. To transfer the motion of the source subject to the target subject, the pose is extracted from the source subject, and then the target subject is generated by applying the learned pose to-appearance mapping. To perform this translation, the video is considered as a set of images consisting of all the frames. Generative adversarial networks (GANs) are used to transfer the motion from source subject to the target subject. GANs are an evolving field of deep learning.

Impact of Deep Learning on Semantic Sentiment Analysis

Online social media (forums, blogs, and social networks) are increasing explosively, and utilization of these new sources of information has become important. Semantics plays a significant role in accurate analysis of an emotion speech context. Adding to this area, the already advanced semantic technologies have proven to increase the precision of the tests. Deep learning has emerged as a prominent machine learning technique that learns multiple layers or data characteristics and delivers state-of-the-art output. Throughout recent years, deep learning has been widely used in the study of sentiments, along with the growth of deep learning in many other fields of use. This chapter will offer a description of deep learning and its application in the analysis of sentiments. This chapter will focus on the semantic orientation-based approaches for sentiment analysis. In this work, a semantically enhanced methodology for the annotation of sentiment polarity in Twitter/ Facebook data will be presented.

An Investigation for Cellular Automata-Based Lightweight Data Security Model Towards Possible Uses in Fog Networks

A lightweight data security model is of much importance in view of security and privacy of data in several networks (e.g., fog networks) where available computing units at edge nodes are often constrained with low computing capacity and limited storage/availability of energy. To facilitate lightweight data security at such constrained scenarios, cellular automata (CA)-based lightweight data security model is presented in this chapter to enable low-cost physical implementation. For this reason, a detailed investigation is presented in this chapter to explore the potential capabilities of CA-based scheme towards the design of lightweight data security model. Further, a comparison among several existing lightweight data security models ensure the effectiveness for proposed CA-based lightweight data security model. Thus, application suitability in view of fog networks is explored for the proposed CA-based model which has further potential for easy training of a reservoir of computers towards uses in IoT (internet of things)-based multiple industry applications.

Deep Learning in Social Media Analysis

Social media analytics keep on collecting the information from different media platforms and then calculating the statistical data. Twitter is one of the social network services which has ample amount of data where many users used post significant amounts of data on a regular basis. Handling such a large amount of data using traditional tools and technologies is very complicated. One of the solutions to this problem is the use of machine learning and deep learning approaches. In this chapter, the authors present a case study showing the use of Twitter data for predicting the election result of the political parties.

Deep Learning for Moving Object Detection and Tracking

Moving object detection and tracking is the process of identifying and locating the class objects such as people, vehicle, toy, and human faces in the video sequences more precisely without background disturbances. It is the first and foremost step in any kind of video analytics applications, and it is greatly influencing the high-level abstractions such as classification and tracking. Traditional methods are easily affected by the background disturbances and achieve poor results. With the advent of deep learning, it is possible to improve the results with high level features. The deep learning model helps to get more useful insights about the events in the real world. This chapter introduces the deep convolutional neural network and reviews the deep learning models used for moving object detection. This chapter also discusses the parameters involved and metrics used to assess the performance of moving object detection in deep learning model. Finally, the chapter is concluded with possible recommendations for the benefit of research community.

IoT and Deep Learning for Livestock Management

Livestock management is a critical issue for the farming industry as proper management including their health and well-being directly impacts the production. It is difficult for a farmer or shed owner to monitor big herds of cattle manually. This chapter proposes a layered framework that utilizes the power of internet of things (IoT) and deep learning (DL) to real-time livestock monitoring supporting the effective management of cattle. The framework consists of sensor layer where sensor-rich devices or gadgets are used to collect various contextual data related to livestock, data processing layer which deals with various outlier rejections and processing of the data followed by DL approaches to analyze the collected contextual data in detecting sick and on heat animals, and finally, insightful information is sent to shed owner for necessary action. An experimental study conducted is helpful to make wise decisions to increase production cost-effectively. The chapter concludes with the different future aspects that may be further explored by the researchers.

Use of Artificial Intelligence (AI) in Fighting With the Novel Coronavirus (COVID-19)

2020 started with the outbreak of the novel coronavirus (COVID-19) virus. In this panic situation, the combination of artificial intelligence (AI) can help us in fight against the deadliest virus attack worldwide. This tool can be used to control and prevention of the outbreak disease. The AI tool can be helpful in prediction, detection, response, recovery, drug discovery of the disease. The AI-driven tools can be used in identifying the nature of outbreak as well as in forecasting the spread and coverage worldwide. In this case, so many AI-based tools can be applied and trained using active learning-based models for the detection, prevention, treatment, and recovery of the patients. Also, they can help us for identifying infected persons from the non-infected to stop the spread of the virus. This chapter mainly focuses on the AI-assisted methodology and models that can help in fighting COVID-19.

The Replacement of HMI (Human-Machine Interface) in Industry Using Single Interface Through IoT

The new era of computing is internet of things (IoT). Internet of things (IoT) represents the ability of network devices to sense and collect data from around the world and then share that data across the internet where it can be processed and utilize for different converging systems. Most of the organisation and industries needs up-to-date data and information about the hardware machines. In most industries, HMI (human-machine interface) is used mostly for connecting the hardware devices. In many manufacturing industries, HMI is the only way to access information about the configuration and performance of machine. It is difficult to take the history of data or data analysis of HMI automatically. HMI is used once per machine which is quite hard to handle. Due to frequent use of HMI, it leads to loss of time, high costs, and fragility, and it needs to be replaced, which was found to be costlier. An internet of things (IOT) is a good platform where all the machines in the industry are able to be handled from a single IoT-based web portal.

Automated Microcontroller-Based Irrigation System

Traditional irrigation systems do not take into consideration the conservation of water. Therefore, automating the plant watering systems to reduce water wastage and loss would be key to water conservation as a means of making use of water wisely and responsibly. In this chapter, a smart irrigation system that helps control the amount of water applied to crops is proposed and developed. The system controls the ON/OFF state of the water pumping motor based on the soil moisture sensor reading. Other sensors incorporated in the system are the water level sensor and light dependent resistor. The system leverages on the Arduino Uno microcontroller development board to collect input signals from the three sensors. The water pump operates depending on the value of the output signal received by the relay module. This technique of watering is feasible and very affordable and reduces human intervention in field watering.