Paradigms of Machine Learning and Data Analytics

Paradigms of Machine Learning and Data Analytics

Pawan Kumar Chaurasia
DOI: 10.4018/978-1-7998-2491-6.ch009
(Individual Chapters)
No Current Special Offers


This chapter conducts a critical review on ML and deep learning tools and techniques in the field of heart disease related to heart disease complexity, prediction, and diagnosis. Only specific papers are selected for the study to extract useful information, which stimulated a new hypothesis to understand further investigation of the heart disease patient.
Chapter Preview


Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL) are emerging fields that can provide businesses with a competitive environment. Machine learning is being developed as one of the most interesting tools for the organizations which are cautious for innovations to help the businesses on a new height. Today, world is investing heavy money to adopt new technology and computational methods developed by researchers, medical practitioners and patients. ML is related with the computing task where designing and programming algorithms are applied. It is sometimes mix with data mining which is more focused on intended data analytics. Machine learning and pattern recognition can be seen as the same field. It is important for organization to realize and make use of relevant advance techniques to preside over development and to be focused on arising changes. It is a systematic approach to look into investigation on advance algorithms and models to continuously train data set and test with other data to put on the most convenient algorithms for the machine learning. Data scientists have already started focusing on using the right algorithm by using the most appropriate data with the best operating models. If all these components come together, it is potential of the model to learn from the data by pattern recognition techniques and performs actions by learning from outputs.

Data is continuously increasing, therefore appropriate models are required to change and predict the future. ML helps and alters a system to acquire knowledge from data rather than programming. It adopts a variety of algorithms that continuously learn from data to improve the existing system and outputs. A ML model generates the output when the algorithms of machine learning train the data. After training of the model, when input is provided to model, the output will be generated. ML and DL provides methodology and technology to extract valuable knowledge for the decision making. Today, healthcare industry generates huge amount of data such as clinical data, e-health data, data generated from health records and prescriptions of medicines. Various machine learning algorithms are used for the structure and study of algorithms that can learn from and prediction on that data. Pattern recognition is one of the fundamental concepts of artificial intelligence. ML and data analytics are the subset of Artificial Intelligence (AI). There are various machine learning techniques and tools available today to extract effective knowledge from databases and to use this knowledge for decision making, fraud detection, email filtering, supermarket analysis etc. AI is being used to make machine intelligent, which can take decision on its own level. The requisite for data analytics has been developed in most of the scientific indoctrination in addition to engineering; economics; business; healthcare and life sciences. Data scientists are using ML techniques to accomplish business objectives. Healthcare deals with the skill, transmission, storage and retrieval of accurate information for the early detection, diagnosis and then for the treatment of the patients. For providing better healthcare facilities, all over world is focusing on providing economic, quality, approachable and seamless healthcare facilities.

There are many grounds to start the machine learning. The modern field of data science (part of supervised learning) has grown in a complex and interesting format to get inputs from various sources, disciplines and fields. It is also a process that involves the use of a machine to make decision based on multiple data inputs. Machine learning is defined as an autonomous process taken out the patterns from data. It restrains an adamant of methods, which give a machine to learn revelatory patterns from data directly with very less human cooperation. The effectiveness of a ML technique relies on human skills. Such skills can make it easier for a machine to learn more accurately through the techniques like effective feature detection, relocation learning and multi-task learning. The most successful kind of ML algorithms is to control a decision making steps by globalizing from known examples. The objective of healthcare is related with diseases, healthcare records and the computational techniques associated with handling of such data. ML algorithms are robotizing the steps of learning a model that is gaining the relationship between the expressive features and the intended features in a dataset.

Complete Chapter List

Search this Book: