Skip to main content

About this book

This book discusses Internet of Things (IoT) as it relates to enterprise applications, systems, and infrastructures. The authors discuss IoT and how it’s disrupting industries such as enterprise manufacturing, enterprise transportation, enterprise smart market, enterprise utilities, and enterprise healthcare. They cover how IoT in the enterprise will have a major impact on the lives of consumers and professionals around the world and how it will change the way we think about professional and consumer networks. The book's topics include IoT enterprise system architecture, IoT enabling enterprise technologies, and IoT enterprise services and applications. Examples include enterprise on demand, market impacts, and implications on smart technologies, big data enterprise management, and future enterprise Internet design for various IoT use cases, such as share markets, healthcare, smart cities, smart environments, smart communications and smart homes.

Table of Contents


Chapter 1. Internet of Things (IoTs) Evolutionary Computation, Enterprise Modelling and Simulation

The knowledge of the Internet of Things (IoTs) is one of the vital competencies in determining the future state of smart homes, smart industries and smart cities. IoTs is also applied in small communication devices that can be accessed by users at an affordable price. This research begins with the evaluation of novel Internet Technology (IT) and manufacturing paradigms. As such the chapter acknowledges the necessities of enterprise models that enhance effective application of IoTs, admitting the novel infrastructure and their use in urban environment. IoTs enhances and assures the chances of linking various methods, for instance, the approaches requiring capacity architecture for gateways and devices based on a recognized model that is acknowledged in the domains of enterprise data systems. Due to the fact that there are a lot of modelling approaches, there is need to review the challenges and contributions of technologies used in various levels. This research therefore proposes the IoTs Sim-Edge simulators, which are meant to permit users to analyse the edge computing cases more easily since this simulator is more customizable and configurable in the ecosystem. The model is created based on the simulators that have been proposed in the past. However, the model purpose is to capture the general behaviour of IoTs and the edge computing planning deployment and development. Mostly, this model deals with the challenges that have been discussed.
A. Haldorai, A. Ramu, M. Suriya

Chapter 2. Organization Internet of Things (IoTs): Supervised, Unsupervised, and Reinforcement Learning

Currently, in the entire economic globe, the aspect of downtime has been considered as a vital performance determinant for field service industries. The introduction of Internet of Things (IoTs) has initiated unique advancement probabilities to different organizations such as field service and manufacturing company. The ideology of IoTs is a fundamental segment of the upcoming generation of data. Wireless sensor networking includes self-regulating disseminated smart sensor gateways and nodes. The distinct sensors persistently consider external physical data, like sound, vibration, and temperature. In this chapter, we evaluated the present machine learning (ML)-based remedies that mitigate various security problems in IoTs. One of the issues to be mitigated includes the accessibility and authentication controls in IoTs. Authentication remains to be the vital security element in IoTs. The users have to be authenticated so as to utilize various applications and services of IoTs. Normally, IoTs services and applications are centered on information exchange over various platforms. The information obtained from IoTs devices is processed, pre-processed, and forwarded via decision-support frameworks to enhance user experience. All these processes are varied and depend on the fundamental IoTs architecture.
A. Haldorai, A. Ramu, M. Suriya

Chapter 3. Enterprise IoT Modeling: Supervised, Unsupervised, and Reinforcement Learning

The Internet of Things (IoT)—the internetworking of physical devices—has been a significant advancement in recent decades and has been the catalyst for several other innovations. New Industrial Internet of Things (IIoT) platforms aim to solve the most complex challenge of manufacturers: consolidating all production systems into a single data model. They are used in smart cities, security and emergencies, environmental applications, energy, healthcare, logistics, industrial control, home automation, agriculture, and animal farming. These objects/devices/appliances can generate, collect, and exchange data without human-to-human or human-to-computer interactions. The IIoT is creating an explosion in structured and unstructured data from a growing army of sensors capable of registering locations, voices, faces, audio, temperature, sentiment, health, and others. Billions of IoT devices are interconnected and a huge volume of data is generated. Every device features automation to assist people in the planning, management, and decision-making of their day-to-day activities. Machine learning (ML) techniques are applied to further enhance the intelligence and capabilities of an application. Many researchers are interested in producing advanced IoT technology, combining ML and IoT Techniques. Through ML, IIoT devices learn to perform tasks such as predication, pattern recognition, classification, and clustering. To provide for a learning process, IoT devices are trained using various algorithms in ML and statistical models to analyze sample data. The various fields of data sets (structured and unstructured data) are characterized by measuring functional parameters. Later, ML algorithms are applied to the data set to find features, provide useful output, identify patterns or make decisions based on the data set, draw inferences from real-time data streams, make their results available to analysts, and embed their results directly in business processes. In ML, the real-time problem is classified by classification, clustering, regression models, and association rules. Based on the learning style, ML algorithms can be categorized as supervised, unsupervised, semi-supervised, and reinforcement learning.
Rajesh Kumar Dhanaraj, K. Rajkumar, U. Hariharan

Chapter 4. An Overall Perspective on Establishing End-to-End Security in Enterprise IoT (E-IoT)

With the increase of Internet of Things (IoT) applications, the number of devices communicating over the Internet is also increasing. These devices are generating numerous amounts of sensitive data that are being communicated over an unprotected network. The manufacturers are providing the least preferences for the device-level security due to resource-constrained properties of the IoT devices. The existing research has shown large computational cryptographic solutions that both consume power and occupy more space on the device. Thereby, it is required to develop lightweight cryptographic solutions that are suitable for low-powered resources of IoT applications. In this chapter, a detailed study of various attacks that can be encountered on various layers of IoT architecture is generalized with possible lightweight measures. Also, threat modeling using Microsoft’s threat modeling tool is explained that helps in the early identification of threats in IoT applications. Finally, security practices that should be followed by enterprise IoT are covered.
Vidya Rao, K. V. Prema, Shreyas Suresh Rao

Chapter 5. Advanced Machine Learning for Enterprise IoT Modeling

Machine-to-machine communication is now enabled and will rule the world in the future. This is achieved through the Internet and this is called the Internet of Things (IoT) as it enables all the things in the real world to communicate with each other. IoT achieves this by bridging various other software technologies and hardware devices. IoT has flourished in all domains starting with simple home automation to businesses. As everything in this real world is business, enabling IoT in business will be of great help to the enterprises and the decision makers in the field. So here this chapter portrays what an enterprise Internet of Things deals with, its issues, and its applications. Also the importance of business forecast for an enterprise and how it is achieved via various techniques for the business forecast are discussed. For better forecasting results, the advanced machine learning algorithms that can be employed in a different perspective of enterprise IoT and their applications are presented here. This would be a great help for the researchers and practitioners in the field of enterprise IoT.
N. Deepa, B. Prabadevi

Chapter 6. Enterprise Architecture for IoT: Challenges and Business Trends

Due to the advent of the IoT, a new prototype whereby the global networks of devices and machines interact with each other has been established. As such, the new paradigm is initiating digitalized tech advancements in the business world. As such, in different IoTs segments, the industrial IoTs has therefore been considered as the largest networking segment. IoTs is a prototype in which the Internet links the environment to users using the various key services and devices that have been applied in various sectors of human lives. In this case, various devices, services, and agents are capable of transforming knowledge and data with the application of common forms of mapping and vocabulary, which integrate and represent the various heterogeneous sources. With reference to the advancing significance of the industrial IoTs and study gaps in the networking segment, this research signifies the overview of industrial IoTs. Moreover, the chapter evaluates the IoTs architecture, its services, and the relevant challenges, including the models that are vital for the deployment and selection of the various IoTs services in different industrial settings which will be analyzed in various case studies.
A. Haldorai, A. Ramu, M. Suriya

Chapter 7. Semi-Supervised Machine Learning Algorithm for Predicting Diabetes Using Big Data Analytics

Due to the rapid adoption of Information Technology (IT) in healthcare systems, health data has grown exponentially and is available in different forms. Data mining and pattern extraction are challenging with such a quickly increasing amount of data, in terms of both information and time. A promising computing trend known as Big Data can help. Big Data combines large-scale computing with machine learning techniques to build predictive analytics for intrinsic information extraction. Cloud computing has emerged as a service-oriented computing model for processing large volumes of rapidly growing data at a faster scale, which is a requirement for Big Data computing. Big Data frameworks Hadoop and Spark can be used along with machine learning techniques. This chapter focuses on predictive analytics with machine learning to analyze Big Data for predicting future complications in patients with diabetes.
Senthilkumar Subramaniyan, R. Regan, Thiyagarajan Perumal, K. Venkatachalam

Chapter 8. On-the-Go Network Establishment of IoT Devices to Meet the Need of Processing Big Data Using Machine Learning Algorithms

This chapter rolls on about the infrastructure capabilities of Internet of Things in managing the huge amount of big data and the future research context in developing a dynamic environment where IoT devices can connect and manage their resources on their own. New services are needed to progress the performance and service quality provided by the old services. Self-adaptation is essential for the IoT devices in a dynamic environment. These devices could publish/subscribe/notify/search/retrieve the data autonomously in a dynamic environment. In opportunistic networks, mobile collaboration could be utilized in case of direct communication failure and in cases of handling large data. These networks are mainly used during short-range communication when nodes are closer to each other. During communication, the routes are constructed dynamically according to the availability of the nodes learned based on machine learning algorithms. Data distribution is made on the basis of publishing/subscribing method. For continuous connectivity of devices in wired and wireless links, standard communication protocols are essential to manage the high traffic in the network as well. Added to it, new solutions are required for efficient storage, fetching, and searching of data in these complex environments.
S. Sountharrajan, E. Suganya, M. Karthiga, S. S. Nandhini, B. Vishnupriya, B. Sathiskumar

Chapter 9. Analysis of Virtual Machine Placement and Optimization Using Swarm Intelligence Algorithms

Internet of Things devices are highly distributed over a large geographical area, and these devices have limited resources in terms of computing, connectivity, energy, and memory. If the virtual machine is placed nearer to the Internet of Things nodes, it increases their efficiency by manifold. Virtual machine placement optimization is a trial and error method. Many new algorithms will be proposed and their results are tested against the desired metrics, and the successful ones are continuously modified to get better results. Placement of the virtual machines is the main goal. Resources should be available based on the need and cannot be allocated statistically based on the peak workload elasticity of cloud traffic engineering. In this area, nature-inspired algorithms are preferred as they are capable of finding a better candidate solution in a vast problem search space. A few notable nature-inspired algorithms are flower pollination algorithm, particle swarm optimization algorithm, ant colony algorithm, ant bee colony algorithm, and firefly algorithm. Out of all these algorithms, particle swarm optimization and ant colony algorithms are the ones that attracted many researchers. In this chapter we discuss about how efficiently we managed the placement of the virtual machines, using these two nature-inspired algorithms, so that efficiency of the Internet of Things network is increased.
R. B. Madhumala, Harshvardhan Tiwari

Chapter 10. Performance Evaluation of Different Neural Network Classifiers for Sanskrit Character Recognition

Handwritten character recognition (HCR) is one of the significant issues in today’s emerging world. It is very difficult to identify the characters from a handwritten document using optical character recognition (OCR) technique. In our work, geometrical feature extraction and neural network computational algorithm are used for recognizing the offline handwritten Sanskrit characters. Initially the binarization and denoising processes are performed on the scanned handwritten document. Later, skeletonization, skewness detection, and correction processes are performed. Image is segmented and required features are extracted and fed into the different classifiers for character recognition. Then, the comparative study of the Sanskrit character recognition is done by employing the RCS with BPNN, BPNN with RBF, and MLP. The proposed character recognition system deploys precision, mean square error rate, recall, false error rate, false-positive error rate, sensitivity, specificity, and accuracy for effective analysis of the handwritten Sanskrit characters.
R. Dinesh Kumar, C. Sridhathan, M. Senthil Kumar

Chapter 11. GA with Repeated Crossover for Rectifying Optimization Problems

There have been various genetic algorithms (GAs) that have been initiated for the purpose of solving optimization issues in the course of research purposes in optimization. Because of the variability in the features of various optimization issues, none of these algorithms are capable of displaying a more robust performance. The differentiating aim of every optimizing issue potentially makes it more difficult. The success of the GA is dependent on the search operators. In this research, we have proposed the GA that basically works on until we obtain an effective offspring. To determine the performance of the algorithms, we have compared our algorithm with some well-known single-objective optimization problems and analyzed the results. The experimental evaluation indicated that the algorithm arrives quicker than its counterparts to the optimal solution. Also, the results produced were better in terms of the objective value, thus exhibiting a superior performance in terms of both runtime and fitness value.
Mayank Jha, Sunita Singhal

Chapter 12. An Algorithmic Approach to System Identification in the Delta Domain Using FAdFPA Algorithm

This chapter addresses the identification of linear dynamic framework with static nonlinearity in the delta domains, dependent on the firefly-centered hybrid metaheuristic algorithm that integrates firefly algorithm (FA) with the dynamic flower pollination algorithm (dFPA). FA analyzes the complete search domain, whereas the dFPA is utilized in the process of refining the solutions. The two models (Wiener and Hammerstein models) are used in the process of identifying the delta domains. The delta operator’s parameterization joins the system models of continuous systems and the discrete-delta results at a high sampling limit. The hybrid algorithm proves its superiority as compared to other algorithms existing in the literature.
Souvik Ganguli, Gagandeep Kaur, Prasanta Sarkar, S. Suman Rajest

Chapter 13. An IoT-Based Controller Realization for PV System Monitoring and Control

The increased penetration of PV-based micro-grid in distributed feeder system leads to power quality issues, especially under islanded condition. In this study, the artificial neural network is considered as the inverter control system in PV-based micro-grid, which is optimally placed in a 13-node feeder system. Artificial neural network (ANN) improves the performance and efficiency of the inverter and adjusts power quality. The proposed method is simulated through MATLAB/Simulink, and the results are compared for IoT-based PI and IoT-based ANN controllers. IoT-based systems are beneficial from the point of view of historical big data analysis for effective system planning and design. The total harmonic distortion, voltage, and phase angle variations are to be monitored and maintained within a satisfactory range for the enhancement of micro-grid power quality during grid-connected and islanded modes of operation.
Jyoti Gupta, Manish Kumar Singla, Parag Nijhawan, Souvik Ganguli, S. Suman Rajest

Chapter 14. Development of an Efficient, Cheap, and Flexible IoT-Based Wind Turbine Emulator

Nowadays reliability and efficiency of the renewable system have become the aim; in this process Internet of Things (IoT) came out as a very beneficial factor. IoT plays a very crucial role in monitoring the system. In this chapter, the authors proposed a new topology for monitoring the wind turbine emulator using IoT. The results of the various output parameters are obtained by varying the duty cycle of the wind turbine emulator; this can be improved by IoT, which receives the data from the wind turbine system and can convert it into actionable information. The only challenging task in IoT is obtaining data of each element of the wind power system and monitoring at each level. However, it provides the freedom to an operator to regulate the output of the wind power system remotely using either a smartphone or a personal computer and also reduces the operating cost significantly. Thus, this system proves to be very efficient, cheaper, and flexible in operation.
Manish Kumar Singla, Jyoti Gupta, Parag Nijhawan, Souvik Ganguli, S. Suman Rajest

Chapter 15. An Application of IoT to Develop Concept of Smart Remote Monitoring System

Solar power is a crucial source of energy for energy production. It requires solar panels for conversion of solar energy directly into electricity. The solar power system can be highly regulated anywhere. The main challenge for the solar power system is the evaluation of productivity against different conditions and parameters. Consequently, some evaluation techniques are required for the purpose of assessing results. This analysis is meant to summarize the utility of the Internet of Things (IoT) to enhance and monitor the performance in the actual time before formulating a virtual machine-centered parameter on IoT. The IoT is observed to be able to facilitate automatic control of hydraulic systems, troubleshooting, maintenance, electrical assistance, and efficient and effective work monitoring, even in the remote areas.
Meera Sharma, Manish Kumar Singla, Parag Nijhawan, Souvik Ganguli, S. Suman Rajest

Chapter 16. Heat Maps for Human Group Activity in Academic Blocks

For the purpose of detecting human group activity and its recognition, a novel algorithm based on heat map is presented using PIR sensors in order to optimize the targeted digital advertising in shopping complexes. Firstly, we use the PIR (pyroelectric infrared) sensors to detect the presence of people. The projected algorithm first represents trajectories of people as sequence of “heat sources” followed by the application of a thermal diffusion process to consequently generate a heat map (HM) in order to depict and illustrate the group activities. The heat maps are generated with respect to multiple factors like temporal factors such as time of day and day of week/month, cultural factors such as during festivals or other notable occasions, etc. The generated heat map brings forth an original surface fitting (SF) method, which can also be applied for identifying human group activities in academic buildings and hostel blocks. The proposed heat map can effectively retain the temporal motion knowledge of the crowd of humans, and the proposed surface fitting can efficiently fetch the features of the heat map for activity discovery and perception. By using heat maps in targeted digital advertising, signs and billboards can be optimized.
Rajkumar Rajasekaran, Fiza Rasool, Sparsh Srivastava, Jolly Masih, S. Suman Rajest

Chapter 17. Emphasizing on Space Complexity in Enterprise Social Networks for the Investigation of Link Prediction Using Hybrid Approach

This Social Network Analysis (SNA) has risen as a key strategy which has also gained a significant influence in several domains like healthcare, anthropology, social psychology, and sociolinguistics. Link prediction is a basic computational problem that has recently fascinated the attention of many researchers as an effective technique to be used in SNA in order to know about associations between nodes in any social communities. In link prediction, there is real urge to reduce its size, since the social network data is massive. This chapter aims at reducing the space complexity with respect to dimensionality reduction using soft set theory. Further a friend link algorithm is used to find the node similarities between the social entities, by traversing the entire path of limited length, with the support of “algorithmic small world hypothesis.” The experiments on UCI network data repository show that this approach can reduce the space complexity for forecasting the links that will occur in future. The proposed approach significantly improves the performance of link prediction in social networks.
J. Gowri Thangam, A. Sankar

Chapter 18. Overview on Deep Neural Networks: Architecture, Application and Rising Analysis Trends

Public awareness of deep neural networks has exploded mainly because our planet is filled with predictive and analytical products in countless intelligent human-centered tools, including interpreters, targeted advertising, and prototyping intelligent transport systems. However, the underlying mechanisms allow these smart, human-centered products to remain obscure. By contrast, researchers from all fields incorporated deep neural networks into their experiments to solve problems that could not be solved before. In this chapter, we aim to thoroughly examine the applications and mechanisms of deep learning. We specifically aim to offer those who wish to know the depth of their understanding and its varied applications, classification in a range of smart world systems as a categorical compilation of the latest research. However, we also hope to develop fresh fields of study which include various kinds of deep learning.
V. Niranjani, N. Saravana Selvam


Additional information

Premium Partner

    Image Credits