Leveraging Natural Language Processing Applications Using Machine Learning

The enormous increase of information along with the computational abilities of machines created innovative applications in natural language processing by invoking machine learning models. This chapter will project the trends of natural language processing by employing machine learning and its models in the context of text summarization. This chapter is organized to make the researcher understand technical perspectives regarding feature representation and their models to consider before applying on language-oriented tasks. Further, the present chapter revises the details of primary models of deep learning, its applications, and performance in the context of language processing. The primary focus of this chapter is to illustrate the technical research findings and gaps of text summarization based on deep learning along with state-of-the-art deep learning models for TS.

Self-Driving Cars

Human errors are the main cause of vehicle crashes. Self-driving cars bear the promise to significantly reduce accidents by taking the human factor out of the equation, while in parallel monitor the surroundings, detect and react immediately to potentially dangerous situations and driving behaviors. Artificial intelligence tool trains the computers to do things like detect lane lines and identify cyclists by showing them millions of examples of the subject at hand. The chapter in this book discusses the technological advancement in transportation. It also covers the autonomy used according to The National Highway Traffic Safety Administration (NHTSA). The functional architecture of self-driving cars is further discussed. The chapter also talks about two algorithms for detection of lanes as well as detection of vehicles on the road for self-driving cars. Next, the ethical discussions surrounding the autonomous vehicle involving stakeholders, technologies, social environments, and costs vs. quality have been discussed.

Multi-Layer Hybrid Credit Scoring Model Based on Feature Selection, Ensemble Learning, and Ensemble Classifier

Credit scoring is a process to calculate the risk associated with a credit product, and it directly affects the profitability of that industry. Periodically, financial institutions apply credit scoring in various steps. The main focus of this study is to improve the predictive performance of the credit scoring model. To improve the predictive performance of the model, this study proposes a multi-layer hybrid credit scoring model. The first stage concerns pre-processing, which includes treatment for missing values, data-transformation, and reduction of irrelevant and noisy features because they may affect predictive performance of model. The second stage applies various ensemble learning approaches such as Bagging, Adaboost, etc. At the last layer, it applies ensemble classifiers approach, which combines three heterogeneous classifiers, namely: random forest (RF), logistic regression (LR), and sequential minimal optimization (SMO) approaches for classification. Further, the proposed multi-layer model is validated on various real-world credit scoring datasets.

Evolution of Data Analytics in Healthcare

In recent years, a huge volume of data has been generated by the sensors, social media, and other sources. Researchers proposed various data analytics models for handling these data and to extract insight that can improve the business of various domains. Data analytics in healthcare (DAiHC) is recent and attracted many researchers due to its importance in improving the value of people's lives. In this perspective, the chapter focuses on the various recent models proposed in DAiHC and dissects the works based on various vital parameters. As an initial part, the work provides comprehensive information on DAiHC and its various application illustrations. Moreover, the study presented in the work categorizes the literature on DAiHC based on factors like algorithms used, application dataset utilized, insight type, and tools used for evaluation of the work. This survey will be helpful for novice to expert researchers who works in DAiHC, and various challenges in DAiHC are also discussed which may help in defining new problems associated with the domain.

Deep Learning Approaches for Textual Sentiment Analysis

Sentiment analysis is computational measurement of attitude, opinions, and emotions (like positive/negative) with the help of text mining and natural language processing of words and phrases. Incorporation of machine learning techniques with natural language processing helps in analysing and predicting the sentiments in more precise manner. But sometimes, machine learning techniques are incapable in predicting sentiments due to unavailability of labelled data. To overcome this problem, an advanced computational technique called deep learning comes into play. This chapter highlights latest studies regarding use of deep learning techniques like convolutional neural network, recurrent neural network, etc. in sentiment analysis.

Text Classification Using Self-Structure Extended Multinomial Naive Bayes

With the advent of neural networks and its subfields like deep neural networks and convolutional neural networks, it is possible to make text classification predictions with high accuracy. Among the many subtypes of naive Bayes, multinomial naive Bayes is used for text classification. Many attempts have been made to somehow develop an algorithm that uses the simplicity of multinomial naive Bayes and at the same time incorporates feature dependency. One such effort was put in structure extended multinomial naive Bayes, which uses one-dependence estimators to inculcate dependencies. Basically, one-dependence estimators take one of the attributes as features and all other attributes as its child. This chapter proposes self structure extended multinomial naïve Bayes, which presents a hybrid model, a combination of the multinomial naive Bayes and structure extended multinomial naive Bayes. Basically, it tries to classify the instances that were misclassified by structure extended multinomial naive Bayes as there was no direct dependency between attributes.

A Survey on Precision Treatment for Humans Using Cognitive Machine Learning Techniques

Personalized treatment (PT) is an emerging area in healthcare that provides personalized health. Personalized, targeted, or customized treatment gains more attention by providing the right treatment to the right person at the right time. Traditional treatment follows a whole systems approach, whereas PT unyokes the people into groups and helps them in rendering proper treatment based on disease risk. In PT, case by case analysis identifies the current status of each patient and performs detailed investigation of their health along with symptoms, signs, and difficulties. Case by case analysis also aids in constructing the clinical knowledge base according to the patient's needs. Thus, PT is a preventive medicine system enabling optimal therapy and cost-effective treatment. This chapter aims to explore how PT is served in works of literature by fusing machine learning (ML) and artificial intelligence (AI) techniques, which creates cognitive machine learning (CML). This chapter also explores the issues, challenges of traditional medicine, applications, models, pros, and cons of PT.

Machine Learning in Higher Education

Machine learning aims to give computers the ability to automatically learn from data. It can enable computers to make intelligent decisions by recognizing complex patterns from data. Through data mining, humongous amounts of data can be explored and analyzed to extract useful information and find interesting patterns. Classification, a supervised learning technique, can be beneficial in predicting class labels for test data by referring the already labeled classes from available training data set. In this chapter, educational data mining techniques are applied over a student dataset to analyze the multifarious factors causing alarmingly high number of dropouts. This work focuses on predicting students at risk of dropping out using five classification algorithms, namely, K-NN, naive Bayes, decision tree, random forest, and support vector machine. This can assist in improving pedagogical practices in order to enhance the performance of students predicted at risk of dropping out, thus reducing the dropout rates in higher education.

Tool Condition Monitoring Using Artificial Neural Network Models

Tool wear is a major factor that affects the productivity of any machining operation and needs to be controlled for achieving automation. It affects the surface finish, tolerances, dimensions of the workpiece, increases machine down time, and sometimes performance of machine tool and personnel are affected. This chapter deals with the application of artificial neural network (ANN) models for tool condition monitoring (TCM) in milling operations. The data required for training and testing the models studied and developed are from live experiments conducted in a machine shop on a widely used steel, medium carbon steel (En 8) using uncoated carbide inserts. Acoustic emission data and surface roughness data has been used in model development. The goal is for developing an optimal ANN model, in terms of compact architecture, least training time, and its ability to generalize well on unseen (test) data. Growing cell structures (GCS) network has been found to achieve these requirements.

Overview of Machine Learners in Classifying of Speech Signals

Machine learning (ML) remains a buzzword during the last few decades due to the requirement of a huge amount of data for adequate processing, the continuously surfacing of better innovative and efficient algorithms, and the advent of powerful computers with enormous computation power. The ML algorithms are mostly based on data mining, clustering, classification, and regression approaches for efficient utilization. Many vivid application domains in the field of speech and image signal processing, market forecast, biomedical signal processing, robotics, trend analysis of data, banking and finance sectors, etc. benefits from such techniques. Among these modules, the classification of speech and speaker identification has been a predominant area of research as it has been alone medium of communication via phone. This has made the author to provide an overview of a few state-of-art ML algorithms, their advantages and limitations, including the advancement to enhance the application domain in this field.