Usage and Analysis of Big Data in E-Health Domain

Big data analytics is a growth area with the potential to provide useful insight in healthcare. Big Data can unify all patient related data to get a 360-degree view of the patient to analyze and predict outcomes. It can improve clinical practices, new drug development and health care financing process. It offers a lot of benefits such as early disease detection, fraud detection and better healthcare quality and efficiency. This chapter introduces the Big Data concept and characteristics, health care data and some major issues of Big Data. These issues include Big Data benefits, its applications and opportunities in medical areas and health care. Methods and technology progress about Big Data are presented in this study. Big Data challenges in medical applications and health care are also discussed. While many dimensions of big data still present issues in its use and adoption, such as managing the volume, variety, velocity, veracity, and value, the accuracy, integrity, and semantic interpretation are of greater concern in clinical application.

A Succinct Analysis of Applications and Services Provided by IoT

The phrase Internet of Things (IoT) heralds a vision of the future Internet where connecting physical things, from banknotes to bicycles, through a network will let them take an active part in the Internet, exchanging information about themselves and their surroundings. This will give immediate access to information about the physical world and the objects in it leading to innovative services and increase in efficiency and productivity. In general, it may be beneficial to incorporate a number of the technologies of IoT with the use of services that can act as the bridge between each technology and the applications that developers wish to implement in IoT. This chapter studies the state-of-the-art of IoT and presents the key potential applications, challenges and future research areas in the domain of IoT. This chapter presents four main categories of services according to technical features. Some major issues of future research in IoT are identified and discussed briefly.

Big Data Analysis for Cardiovascular Diseases

In the healthcare field, plenty of clinical data is generated every day from patient records, surveys, research papers, medical devices, among others sources. These data can be exploited to discover new insights about health issues. For helping decision makers and healthcare data managers, a survey of research works and tools covering the process of handling big data in the healthcare field is included. A methodology for CVD prevention, detection and management through the use of tools for big data analysis is proposed. Also, it is important to maintain privacy of patients when handling healthcare data; therefore, a list of recommendations for maintaining privacy when handling healthcare data is presented. Specific clinical analysis are recommended on those regions where the incidence rate of CVD is high, but a weak relation with the common risk factors is observed according to historical data. Finally, challenges which need to be addressed are presented.

Data Reduction Techniques for Near Real-Time Decision Making in Fall Prediction Systems

Unintentional falls are a frequent cause of hospitalization that mostly increases health service costs due to injuries. Fall prediction systems strive to reduce injuries and provide fast help to the users. Typically, such systems collect data continuously at a high speed through a device directly attached to the user. Whereas such systems are implemented in devices with limited resources, data volume is significantly important. In this chapter, a real-time data analyzer and reducer is proposed in order to manage the data volume of fall prediction systems.

Security Issues and Challenges Related to Big Data

Availability of huge amount of data has opened up a new area and challenge to analyze these data. Analysis of these data become essential for each organization and these analyses may yield some useful information for their future prospectus. To store, manage and analyze such huge amount of data traditional database systems are not adequate and not capable also, so new data term is introduced – “Big Data”. This term refers to huge amount of data which are used for analytical purpose and future prediction or forecasting. Big Data may consist of combination of structured, semi structured or unstructured data and managing such data is a big challenge in current time. Such heterogeneous data is required to maintained in very secured and specific way. In this chapter, we have tried to identify such challenges and issues and also tried to resolve it with specific tools.

Exploration of Healthcare Using Data Mining Techniques

Huge amount of data is generated from Healthcare transactions where data are complex, voluminous and heterogeneous in nature. This large dataset can be used as an ideal store which can be analyzed for knowledge discovery as well as various future predictions. So, Data mining is becoming increasingly popular as it offers set of innovative tools and techniques to handle this kind of data set whereas traditional methods have limitations for that. In summary, providing the better patient care and reduction in healthcare cost are two major goals of application of data mining in healthcare. Initially, this chapter explores on the various types of eHealth data and its characteristics. Subsequently it explores various domains in healthcare sector and shows how data mining plays a major role in those domains. Finally, it describes few common data mining techniques and their applications in eHealth domain.

Diabetes Preventive Knowledge Management System for Recommending an Ice Cream to University Grads Based on Their Life Style and Eating Habits

Lifestyle and eating habits with the special focus on young university grads are considered to design and develop a Knowledge Management System (KMS). An appropriate ice cream is suggested via KMS to university grads, which keeps blood glucose level in control and acts as a diabetes preventive KMS. Designed KMS is based on effective Data Science (DS), Big Data techniques considering standalone and proposed distributed versions of Analytical Hierarchy Process (AHP), Monte Carlo AHP (MC-AHP), Goal Programming (GP), K-Means and Artificial Neural Network (ANN) Clustering and Collaborative Filtering (CF). Incremental-learning gains and updates knowledge at each level of applied DS techniques. Developed KMS analyzed ice cream consumption pattern, lifestyle & health condition attributes of university students to promote a novel KM strategy in terms of ice cream recommendation and can give altogether novel trigger to health-conscious students. The confluence of health, students, ice creams and DS is achieved and discussed in this chapter.

Secured Optimal Cost Approach for Bimodal Deep Face Recognition in IoT and Its Applications

This chapter proposes an optimal cost security approach for the current and emerging trends in the Engineering centric IoT applications that offer an optimized infrastructure and human safety through bimodal deep face recognition. Human face determines the person identity that reveals information like age, gender, emotions, attractiveness and others. Face recognition attracted researchers to enhance its performance because of its potential usage in several commercial, law enforcement, government and video surveillance applications in which individuals perceive each other. In this chapter, authors propose a new secured optimal cost approach for deep face recognition based on feature level fusion of bi-features extracted through unsupervised deep learner, Autoencoder and Local Binary Patterns (LBP) respectively. The dimensionality of fused feature map is reduced and protected through Forward Error Correction (FEC) technique. An efficient optimal cost region matcher (OCRM) is accomplished with Canny edge detector to maximize the face recognition accuracy. OCRM uses north-west corner rule of the transportation problem that fulfills the Monge property. The experimental results demonstrate the superiority of the proposed face recognition system over unimodal systems (Autoencoder and LBP alone) when tested on ORL and Real face datasets with OCRM matcher which is interfaced through diverse IoT applications.

Smart Senior Residences

Population aging is the most significant social transformations of our century. In this context, affordable senior housing with supportive services is a key component to the world's long-term care continuum. One of the main issues is how to cost-efficiently provide adapted (and increasingly complex) care services in senior residences to an exponentially growing number of people considering staff shortage. The rise in operating costs (energy, food, etc.) forces companies to find new ways to stay competitive. In that context, this chapter tries to propose avenues of solutions by giving some answers to a simple question: how to optimize the work of the staff to meet the growing demand considering the context of staff shortage. More precisely, this chapter studies methods and strategies to exploit Ambient Intelligence and Big Data to increase the number of residents an employee can support by automating a part of his daily work.

Kernel-Based Machine Learning Techniques

Health care is considered as the fundamental right of every citizen and it is principle duty of every country to provide good health care facilities. Many developed countries spend substantial amount of gross domestic product (GDP) on healthcare. In this chapter, we discuss kernel based machine learning techniques, i.e., k-PCA (Kernel principal component analysis) and its related properties with a aim to prescribe cost effective treatments and easy diagnosis of diseases. This objective could be met only by the serious collaboration between physician and data scientist. We discussed that how we could construct a kernel and exact features based on the given dataset. Also, we compared the proposed method with the other methods. For the sake of easy understanding, applications of the proposed method are included in the text.