Big-Data-Based Techniques for Predictive Intelligence

Big-data-analyzed finding patterns derive meaning and make decisions on data to produce responses to the world with intelligence. It is an emerging area used in business intelligence (BI) for competitive advantage to analyze the structured, semi-structured, and unstructured data stored in different formats. As the big data technology continues to evolve, businesses are turning to predictive intelligence to deepen the engagement to customers with optimization in processes to reduce the operational costs. Predictive intelligence uses sets of advanced technologies that enable organizations to use data stored in real time that move from a historical and descriptive view to a forward-looking perspective of data. The comparison and other security issue of this technology is covered in this book chapter. The combination of big data technology and predictive analytics is sometimes referred to as a never-ending process and has the possibility to deliver significant competitive advantage. This chapter provides an extensive review of literature on big data technologies and its usage in the predictive intelligence.

Improved Usability of IOT Devices in Healthcare Using Big Data Analysis

Sensor data takes the microcontroller and sends it to doctors through the wi-fi network and provides real-time healthcare parameter monitoring. The clinician can analyze the sensor generated information. Patients provide their measures to the arrangement and identify their fitness status without human intervention. In this chapter, MapReduce algorithm is used to identify the patient health status. The controller is connected with the signal to alert the attendee about dissimilarity in sensor output data. If the situation is sever, an alert message is sent to the doctor through the IOT devices that can provide quick provisional medication to the ill person. The system improves usability of medical devices with less power consumption, simple setup, and high performance and response.

Big-Data-Based Architectures and Techniques

This chapter covers the essentials of big data analytics ecosystems primarily from the business and technology context. It delivers insight into key concepts and terminology that define the essence of big data and the promise it holds to deliver sophisticated business insights. The various characteristics that distinguish big data datasets are articulated. It also describes the conceptual and logical reference architecture to manage a huge volume of data generated by various data sources of an enterprise. It also covers drivers, opportunities, and benefits of big data analytics implementation applicable to the real world.

Interference Management Techniques for Device-to-Device Communications

The snowballing of many different electronic gadgets connected to different networks and to the internet is a clear indication that the much-anticipated internet of things (IoT) is fast becoming a reality. It is generally agreed that the next generation mobile networks should offer wireless connection to anything and anyone with a proper enabling device at any time leading to the full realization of IoT. Device-to device (D2D) communication is one technology that the research community believes will aid the implementation of the next generation of mobile networks, specifically 5G. Full roll out of D2D is however being impeded by the resulting interference. This chapter looks at the state-of-the-art research works on interference management technologies proposed for device-to-device communications. A comprehensive analysis of the proposed schemes is given and open challenges and issues that need to be considered by researchers in D2D communication for it to become a key enabler for 5G technology are highlighted and recommendations provided.

Application of Predictive Intelligence in Water Quality Forecasting of the River Ganga Using Support Vector Machines

Predicting the water quality of rivers has attracted a lot of researchers all around the globe. A precise prediction of river water quality may benefit the water management bodies. However, due to the complex relationship existing among various factors, the prediction is a challenging job. Here, the authors attempted to develop a model for forecasting or predicting the water quality of the river Ganga using application of predictive intelligence based on machine learning approach called support vector machine (SVM). The monthly data sets of five water quality parameters from 2001 to 2015 were taken from five sampling stations from Devprayag to Roorkee in the Uttarakhand state of India. The experiments are conducted in Python 2.7.13 language (Anaconda2 4.3.1) using the radial basis function (RBF) as a kernel for developing the non-linear SVM-based classifier as a model for water quality prediction. The results indicated a prediction performance of 96.66% for best parameter combination which proved the significance of predictive intelligence in water quality forecasting.

IoT-Based Cold Chain Logistics Monitoring

This chapter aims to reduce the extent of human presence all along the cold chain by means of a powerful tool in the form of the IoT. It should also be ensured that any details regarding instances of equipment failure leading to product spoilage or an event of a successful delivery must be communicated to the manufacturer's end. It also seeks to fill gaps involving location tracking and environment control by means of a GPS module and an IoT-based sensor platform respectively used here.

Learning-Aided IoT Set-Up for Home Surveillance Applications

Of late, home surveillance systems have been enhanced considerably by resorting to increased use of automated systems. The automation aspect has reduced human intervention and made such systems reliable and efficient. With the proliferation of wireless devices, networking among the connected devices is leading to the formation of internet of things (IoT). This has made it essential that home surveillance systems be also automate using IoT. The decision support system (DSS) in such platforms necessitates that automation be extensive. It necessitates the use of learning-aided systems. This chapter reports the design of IoT-driven learning-aided system for home surveillance application.

Cloud-Based Predictive Intelligence and Its Security Model

Predictive computing is a relatively new area of research. Predictive computing helps people to predict the future or unknown events. It combines various statistical approaches like predictive analytics, predictive modeling, data mining, big data, and machine learning. Predictive computing uses current and historical facts to predict future events. It looks for relationships and patterns between data variables. The outcomes of data variables can be predicted if we know the values of explanatory variables. Cloud computing is another new technology that provides everything-as-a-service (XaaS) and is used widely in various businesses. All storage and computing devices use cloud platform due to its elasticity, scalability, and dynamicity. Cloud-based predictive computing is a technology that uses data available on the cloud. Presently, the data from the social sites (e.g., Facebook, Gmail, LinkedIn, election data, etc.) are stored on cloud, and the volume of this data is enormous which needs innovative predictive computing design and architecture. This chapter represents the cloud-based predictive intelligence and its security model. Architecture for predictive intelligence is proposed and compared with the existing models. An attack prediction algorithm is also proposed and compared for the accuracy in the predictive intelligence.

Big Data Analytics

Due to an increase in the number of digital transactions and data sources, a huge amount of unstructured data is generated by every interaction. In such a scenario, the concepts of data mining assume great significance as useful information/trends/predictions can be retrieved from this large amount of data, known as big data. Big data predictive analytics are making big inroads into the educational field because with the adoption of new technologies, new academic trends are being introduced into educational systems. This accumulation of large data of different varieties throws a new set of challenges to the learners as well as educational institutions in ensuring the quality of their education by improving strategic/operational decision-making capabilities. Therefore, the authors address this issue by proposing a support system that can guide the student to choose and to focus on the right course(s) based on their personal preferences. This chapter provides the readers with the requisite information about educational frameworks and related data mining.

Quality Assurance Issues for Big Data Applications in Supply Chain Management

Heterogeneous data types, widely distributed data sources, huge data volumes, and large-scale business-alliance partners describe typical global supply chain operational environments. Mobile and wireless technologies are putting an extra layer of data source in this technology-enriched supply chain operation. This environment also needs to provide access to data anywhere, anytime to its end-users. This new type of data set originating from the global retail supply chain is commonly known as big data because of its huge volume, resulting from the velocity with which it arrives in the global retail business environment. Such environments empower and necessitate decision makers to act or react quicker to all decision tasks. Academics and practitioners are researching and building the next generation of big-data-based application software systems. This new generation of software applications is based on complex data analysis algorithms (i.e., on data that does not adhere to standard relational data models). The traditional software testing methods are insufficient for big-data-based applications. Testing big-data-based applications is one of the biggest challenges faced by modern software design and development communities because of lack of knowledge on what to test and how much data to test. Big-data-based applications developers have been facing a daunting task in defining the best strategies for structured and unstructured data validation, setting up an optimal test environment, and working with non-relational databases testing approaches. This chapter focuses on big-data-based software testing and quality-assurance-related issues in the context of Hadoop, an open source framework. It includes discussion about several challenges with respect to massively parallel data generation from multiple sources, testing methods for validation of pre-Hadoop processing, software application quality factors, and some of the software testing mechanisms for this new breed of applications