Text, Images, and Video Analytics for Fog Computing

Today, images and image sequences (videos) make up about 80% of all corporate and public unstructured big data. As growth of unstructured data increases, analytical systems must assimilate and interpret images and videos as well as they interpret structured data such as text and numbers. An image is a set of signals sensed by the human eye and processed by the visual cortex in the brain creating a vivid experience of a scene that is instantly associated with concepts and objects previously perceived and recorded in one's memory. To a computer, images are either a raster image or a vector image. Simply put, raster images are a sequence of pixels with discreet numerical values for color; vector images are a set of color-annotated polygons. To perform analytics on images or videos, the geometric encoding must be transformed into constructs depicting physical features, objects and movement represented by the image or video. This chapter explores text, images, and video analytics in fog computing.

Fog Computing and Virtualization

The essence of cloud computing is moving out the processing from the local systems to remote systems. Cloud is an umbrella of physical/virtual services/resources easily accessible over the internet. With more companies adopting cloud either fully through public cloud or hybrid model, the challenges in maintaining a cloud capable infrastructure is also increasing. About 42% of CTOs say that security is their main concern for moving into cloud. Another problem, which is mainly problem with infrastructure, is the connectivity issue. The datacenter could be considered as the backbone of cloud computing architecture. Handling this new generation of requirements of volume, variety, and velocity in IoT data requires us to evaluate the tools and technologies. As the processing power and storage capabilities of the end devices like mobile phones, routers, sensor hubs improve, we can increase leverage these resources to improve your quality and reliability of services. Applications of fog computing is as diverse as IoT and cloud computing itself. What IoT and fog computing have in common is to monitor and analyse real-time data from network connected things and acting on them. Machine-to-machine coordination or human-machine interaction can be a part of this action. This chapter explores fog computing and virtualization.

Voice Biometrics

Biometric technology is spearheading the existing authentication methods in the IoT. Considering the balance between security and convenience, voice biometrics seems to be the most logical biometric technologies to be used. The authors present an extensive survey to identify, analyze, and compare various methods and algorithms for the different phases in the process of speaker identification/recognition, which is the part and parcel in voice biometrics. The chapter is intended to provide essential background information to those interested in learning or planning to design voice authentication systems. The chapter highlights the need for a biometric authentication system, the reason why we prefer voice, its present state of affairs, and its scope with fog computing to be used in IoT.

Comparison Study of Different NoSQL and Cloud Paradigm for Better Data Storage Technology

Advancements in web-based technology and the proliferation of sensors and mobile devices interacting with the internet have resulted in immense data management requirements. These data management activities include storage, processing, demand of high-performance read-write operations of big data. Large-scale and high-concurrency applications like SNS and search engines have appeared to be facing challenges in using the relational database to store and query dynamic user data. NoSQL and cloud computing has emerged as a paradigm that could meet these requirements. The available diversity of existing NoSQL and cloud computing solutions make it difficult to comprehend the domain and choose an appropriate solution for a specific business task. Therefore, this chapter reviews NoSQL and cloud-system-based solutions with the goal of providing a perspective in the field of data storage technology/algorithms, leveraging guidance to researchers and practitioners to select the best-fit data store, and identifying challenges and opportunities of the paradigm.

Remote Elderly Health Monitoring System Using Cloud-Based WBANs

Monitoring the physical condition of patients is a major errand for specialists. The development of wireless remote elderly patient monitoring system has been intensive in the past. RPM (remote patient monitoring) is reliant on the person's inspiration to deal with their wellbeing. The flow of patient data requires a group of medicinal services suppliers to deal with the information. RPM sending is reliant on a wireless telecommunication infrastructure, which may not be accessible/practical in provincial territories. Patients' data are shared as service on cloud in hospitals. Therefore, in the current research, a new approach of cloud-based wireless remote patient monitoring system during emergency is proposed as a model to monitor the critical health data. The vital parameters are measured and transmitted. In this chapter, the authors present an extensive review of the significant technologies associated with wireless patient monitoring using wireless sensor networks and cloud.

Software-Defined Cloud Infrastructure

Cloud computing suggests that the applications conveyed as services over the internet and frameworks programming in the server that give various services and offers in “pay as you go” trend which means pay only for what you use. The information and services are managed as software as a service (SaaS). Some sellers utilize terms, for example, IaaS (infrastructure as a service) and PaaS (platform as a service). The purpose of cloud computing is quickly expanding in everyday life. Today the use of cloud computing is widespread to the point that it is being utilized even in the medicinal services industry. As the development of cloud computing in healthcare is happening at a fast rate, we can expect a noteworthy piece of the healthcare administrations to move onto the Cloud and along these lines more focus is laid on giving cost-effective and efficient services to the general population all around the world. Cloud these days are turning into the new building pieces of significant organizations spread the world over. They offer assistance in servicing to offer different frameworks. Cloud computing has enhanced its technique and technologies in a better way to provide better services. Existing e-healthcare has many difficulties from advancement to usage. In this chapter, the authors discuss how cloud computing is utilized and the services provided by the Cloud and their models and its infrastructure.

Expounding the Edge/Fog Computing Infrastructures for Data Science

Data is the new fuel for any system to deliver smart and sophisticated services. Data is being touted as the strategic asset for any organization to plan ahead and provide next-generation capabilities with all the clarity and confidence. Whether data is internally sourced or aggregated from different and distributed source, it is essential for all kinds of data to be continuously and consciously collected, transmitted, cleansed, and hosted on storage systems. There are several types of analytical methods and machines to do deeper and decisive analytics on those curated and consolidated data to extract actionable insights in real-time. Precise and concise analytics guarantee perfect decision-making and action. We need competent and highly integrated analytics platform for speeding up, simplifying and streamlining data analytics, which is becoming a hard nut to crack due to the multi-structured and massive quantities of data. On the infrastructure front, we need highly optimized compute, storage and network infrastructure for achieving data analytics with ease. Another noteworthy point is that there are batch, real-time, and interactive processing of data. Most of the personal and professional applications need real-time insights in order to produce real-time applications. That is, real-time capture, processing, and decision-making are being insisted and hence the edge or fog computing concept has become very popular. This chapter is exclusively designed in order to tell all on how to accomplish real-time analytics on fog devices data.

Fast Data vs. Big Data With IoT Streaming Analytics and the Future Applications

Big data depicts information volume – petabytes to exabytes in organized, semi-organized, and unstructured information that can possibly be broken down for data. Fast data are facts streaming into applications and computing environments from hundreds of thousands to millions of endpoints. Fast data is totally different from big data. There is no question that we will continue generating large volumes of data, especially with the wide variety of handheld units and internet-connected devices expected to grow exponentially. Data streaming analytics is vital for disruptive applications. Streaming analytics permits the processing of terabytes of data in memory. This chapter explores fast data and big data with IoT streaming analytics.

Data Mining Algorithms, Fog Computing

Different methods are used to mine the large amount of data presents in databases, data warehouses, and data repositories. The methods used for mining include clustering, classification, prediction, regression, and association rule. This chapter explores data mining algorithms and fog computing.

Machine Learning

Machine learning is a subfield of artificial intelligence that encompass the automatic computing to make predictions. The key difference between a traditional program and machine-learning model is that it allows the model to learn from the data and helps to make its own decisions. It is one of the fastest growing areas of computing. The goal of this chapter is to explore the foundations of machine learning theory and mathematical derivations, which transform the theory into practical algorithms. This chapter also focuses a comprehensive review on machine learning and its types and why machine learning is important in real-world applications, and popular machine learning algorithms and their impact on fog computing. This chapter also gives further research directions on machine learning algorithms.