Current Trends

This chapter addresses the key role of machine learning and artificial intelligence for various applications of the internet of things. The following are the most significant applications of IoT: (1) manufacturing industry: automation of industries is on the rise; there is an urge for analyzing the energy in the process industry; (2) anomaly detection: to detect the existing fault and abnormality in functioning by using ML algorithms thereby avoiding the adverse effect during its operation; (3) smart campus: in-order to efficiently handle the energy in buildings, smart campus systems are developed; (4) improving product decisions: with the help of the predictive analytics system products are designed and developed based on the user's requirements and usability; (5) healthcare industry: IoT with machine learning provides numerous ways for the betterment of the human wellbeing. In this chapter, the most predominant approaches to machine learning that can be useful in the IoT applications to achieve a significant set of outcomes will be discussed.

Machine Learning Techniques for Internet of Things

The idea of an intelligent, independent learning machine has fascinated humans for decades. The philosophy behind machine learning is to automate the creation of analytical models in order to enable algorithms to learn continuously with the help of available data. Since IoT will be among the major sources of new data, data science will make a great contribution to make IoT applications more intelligent. Machine learning can be applied in cases where the desired outcome is known (guided learning) or the data is not known beforehand (unguided learning) or the learning is the result of interaction between a model and the environment (reinforcement learning). This chapter answers the questions: How could machine learning algorithms be applied to IoT smart data? What is the taxonomy of machine learning algorithms that can be adopted in IoT? And what are IoT data characteristics in real-world which requires data analytics?

Modelling and Designing of IoT Systems Using UML Diagrams

Despite the rapid growth in IoT research, a general principled software engineering approach for the systematic development of IoT systems and applications is still missing. Software engineering as a discipline provides the necessary platform to carry on the underlying design, coding, implementation, as well as maintenance of such systems. UML diagrams present a visually comprehensible outlay of the construction of IoT systems. The chapter covers the modelling of IoT systems using UML diagrams. Starting with the architectural design of any IoT system to behavioral aspects is covered in this chapter using a case study of IoT-based remote patient health monitoring system. The diagrams shown in this chapter are the sample diagrams for understanding IoT-based complex systems. The chapter focuses on the work carried out by Franco Zambonelli in context of developing abstract model of an IoT system using software engineering concepts. The chapter also focus on the pioneer work carried by J. F. Peters in intelligent system design patterns for robotic devices using pattern classification.

Social Internet of Things

Internet of things has gathered significance within the latest technology domain and trends. As a result, it offers greater ways of accessing data and utilizing intelligent systems. IoT applications are developed for specific scenarios (i.e., smart home, smart transportation, smart agriculture, e-health, etc.). Such IoT applications are inefficient for sharing data and knowledge through services. This results in an inefficient exploitation of different IoT service applications. Social internet of things (SIoT) has efficient and effective ways to support these kinds of services. A concept of social internet of things has been proposed in this chapter in order to support efficient data sharing. This chapter explores related work and literature study on social internet of things, concentrates on mapping IoT with SIoT, and describes a possible architecture for SIoT, components, layers and processes of SIoT. It also illustrates applications, where SIoT can be used, and at the end, the authors provide a few challenges related to SIoT.

Internet of Things Testing Framework, Automation, Challenges, Solutions and Practices

The internet of things (IoT) is aimed at modifying the life of people by adopting the possible computing techniques to the physical world, and thus transforming the computing environment from centralized form to decentralized form. Most of the smart devices receive the data from other smart devices over the network and perform actions based on their implemented programs. Thus, testing becomes an intensive process in the IoT that will require some normalization too. The composite architecture of IoT systems and their distinctive characteristics require different variants of testing to be done on the components of IoT systems. This chapter will discuss the necessity for IoT testing in terms of various criteria of identifying and fixing the problems in the IoT systems. In addition, this chapter examines the core components to be focused on IoT testing and testing scope based on IoT device classification. It also elaborates the various types of testing applied on healthcare IoT applications, and finally, this chapter summarizes the various challenges faced during IoT testing.

Current Trends in Integrating the Internet of Things Into Software Engineering Practices

The chapter summarizes the concepts and challenges of DevOps in IoT, DevSecOps in IoT, integrating security into IoT, machine learning and AI in IoT of software engineering practices. DevOps is a software engineering culture and practice that aims at unifying software development (Dev) and software operation (Ops). The main characteristic of DevOps is the automation and monitoring at all steps of software construction, from integration, testing, releasing to deployment and infrastructure management. DevSecOps is a practice of integrating security into every aspect of an application lifecycle from design to development.

A New Process Model for IoT-Based Software Engineering

Internet of things (IoT) is a new trending paradigm for advanced technological development which has drawn significant research attention in the recent years. IoT comprises intelligent communicating “things,” putting a big challenge on ensuring security, reliability, efficiency, and safety in their interaction. Staying connected always, constant evolution, and grappling with multiple life cycles are the major factors of concern. In this context, a new process model for IoT-based software development has a greater relevance in order to reduce the associated risk. To exploit the capability of IoT-driven innovations which enable organizations to enhance their revenue streams, reduce time to market while increasing business agility, organizations need to determine how best to employ IoT-enabled business models that promote sustainable competitive advantage.

Smart Pollution Alert System Using Machine Learning

This chapter proposes a novel mobile-based pollution alert system. The level of the pollutants is available in the air quality repository. This data is updated periodically by collecting the information from the sensors placed at the monitoring stations of different regions. A model using artificial neural network (ANN) is proposed to predict the AQI values based on the present and previous values of the pollutants. The ANN model processes the normalized data and predicts whether the region is hazardous or not. A novel mobile application which could be used by the user to know about the present and future pollution level could be developed using a progressive web application development environment. This mobile application uses the location information of the user and helps the user to predict the hazardous level of the pollutants in that particular location.

Best Practices

Internet of things (IoT) describes an emerging trend where a large number of embedded devices (things) are connected to the internet to participate in automating activities that create compounded value for the end consumers as well as for the enterprises. One of the greatest concerns in IoT is security, and how software engineers address it will play a deeper role. As devices interact with each other, businesses need to be able to securely handle the data deluge. With focused approach, it is possible to minimize the vulnerabilities and risks exposed to the devices and networks. Adopting security-induced software development lifecycle (SDL) is one of the major steps in identifying and minimizing the zero-day vulnerabilities and hence to secure the IoT applications and devices. This chapter focuses best practices for adopting security into the software development process with the help of two approaches: cryptographic and machine learning techniques to integrate secure coding and security testing ingrained as part of software development lifecycle.

IoT Functional Testing Using UML Use Case Diagrams

In the IoT applications development process, the consumers expectations are always high. Thus, the development environment should be focusing on virtual provisioning, manipulation, and testing and debugging. This has also raised more challenges in terms of proper testing to be done in both user interface level as well as the functionality level. It will be really challenging to test a connected device within a full IoT environment, which will have more devices with varied functionalities and data processing. These challenges have made a new way of testing to be done so that the test cases will be more efficient in revealing the errors in the software. In this chapter, UML use case diagram-based test cases generation for an IoT environment is explained in detail. Also, a real-time case study IoT application is taken to showcase how this approach helps in generating the test cases to test the embedded software in these IoT devices in terms of data flow, control flow, and functionalities with improved performance.