Handbook of Artificial Intelligence

Machine Learning has become part of our daily life directly or indirectly. Several Machine Learning techniques are being used in several areas to increase the effective usage of computers by human beings. Over the past few decades, the concepts of AI and ML have rapidly increased their importance in various application areas, and a lot of research has taken place and is still in progress. Even then, there is a lot more to explore regarding the applications of AI and ML in our day-to-day lives. The reason to do so is only to improve the existing process of work in various areas and also to give valuable suggestions and scope for further research. In this context, here we tried to discuss basic concepts related to machine learning and gave a brief overview of various application areas of machine learning.

In this chapter, we briefly discuss various real-time applications of machine learning algorithms. Machine Learning Algorithms explain the following topics: Introduction to ML algorithms, Supervised Learning, Classification, Regression (Linear Regression, Logistic Regression, Decision Tree, Naive Bayes, Support Vector Machine, Random Forest, AdaBoost, Gradient-Boosting Trees), and Unsupervised Learning (K-Means Clustering, Gaussian Mixture Model, Hierarchical Clustering, Recommender Systems, PCA/T-SNE). Application of Machine Learning explains various real-time applications like augmentation, automation, finance, government, healthcare, marketing, traffic alerts, image recognition, video surveillance, sentiment analysis, product recommendation, online support using chatbots, Google translate, online video streaming applications, virtual professional assistants, machine learning usage in social media, stock market signals using machine learning, auto-driven cars, and real-time dynamic pricing. 

This chapter begins with a concise introduction to machine learning and the classification of machine learning systems (supervised learning, unsupervised learning, and reinforcement learning). ‘Breast Cancer Prediction Using ML Techniques’ is the topic of Chapter 2. This chapter describes various breast cancer prediction algorithms, including convolutional neural networks (CNN), support vector machines, Nave Bayesian classification, and weighted Nave Bayesian classification. Prediction of Heart Disease Using Machine Learning Techniques is the topic of Chapter 3. This chapter describes the numerous heart disease prediction algorithms, including Support Vector Machines (SVM), Logistic Regression, KNN, Random Forest Classifier, and Deep Neural Networks. Prediction of IPL Data Using Machine Learning Techniques is the topic of Chapter 4. The following algorithms are covered in this chapter: decision trees, naive bayes, K-Nearest Neighbour Random Forest, data mining techniques, fuzzy clustering logic, support vector machines, reinforcement learning algorithms, data analytics approaches and Bayesian prediction techniques. Chapter Five: Software Error Prediction by means of machine learning- The AR model and the Known Power Model (POWM), as well as artificial neural networks (ANNs), particle swarm optimisation (PSO), decision trees (DT), Nave Bayes (NB), and linear classifiers, are among the approaches (K-nearest neighbours, Nave Bayes, C-4.5, and decision trees) Prediction of Rainfall Using Machine Learning Techniques, Chapter 6: The following are discussed: LASSO (Least Absolute Shrinkage and Selection Operator) Regression, ANN (Artificial Neural Network), Support Vector Machine, Multi-Layer Perception, Decision Tree, Adaptive Neuro-Fuzzy Inference System, Wavelet Neural Network, Ensemble Prediction Systems, ARIMA model, PCA and KMeans algorithms, Recurrent Neural Network (RNN), statistical KNN classifier, and neural SOM Weather Prediction Using Machine Learning Techniques that includes Bayesian Networks, Linear Regression, Logistic Regression, KNN Decision Tree, Random Forest, K-Means, and Apriori's Algorithm, as well as Linear Regression, Polynomial Regression, Random Forest Regression, Artificial Neural Networks, and Recurrent Neural Networks.

In Machine Learning, classification is considered a supervised learning technique to predict class samples based on labeled data. Classification techniques have been applied to various domains such as intrusion detection, credit card fraud detection, etc. However, classification techniques on all these domains have been applied to balanced datasets. Balanced datasets are those which contain equal proportion of majority and minority examples. However, in real-time, obtaining balanced datasets is difficult because majority of the datasets tend to be imbalanced. Developing a model for classifying imbalanced datasets is a challenge, particularly in the medical domain. Accurate identification of a disease-affected patient within time is critical as any misclassification leads to severe consequences. However the imbalanced nature of most of the real-time datasets presents a challenge for most of the conventional machine learning algorithms. For the past few years, researchers have developed models using Conventional machine learning algorithms (linear and nonlinear) are stating unsatisfactory performance in classifying imbalanced datasets. To address this problem of skewed datasets several statistics techniques & robust machine Learning techniques have been developed by the researchers. The discussion on handling imbalanced datasets in the healthcare domain using machine learning techniques is a primary focus of this chapter. 

The introduction of high-performance genomic technologies into plant science has resulted in the generation of huge volumes of genomic information. Moreover, for biologists to deal with such complex, voluminous dataand infer some significant findings in order to improve crop quality and quantity has presented a big challenge to them. The advent of Artificial Intelligence (AI), Machine learning (ML) and Deep Learning (DL), facilitated automated tools for more efficient and better analysis of the data. Another crucial process that needs to be automated in field farming is the timely and precise diagnosis of crop diseases which plays a vital role in the prevention of productivity loss and reduced quantity of agricultural products. ML provides a solution to solve these problems by automatic field crop inspection. Recently, DL techniques have been widely applied for processing images to obtain enhanced accuracy. This chapter describes the need of AI in Agri-Genomics; it also includes various contemporary AI solutions for the Crop Improvement process and presents the proposed AI-based Crop Improvement Model (AI-CIM). 

 The term “object detection” refers to a technology that enables humans to recognise specific types of things present in visual media. One of the important applications of the technique is autonomous driving cars. In the application, the activity is to detect the various objects present in the single image frame. Examples of objects belonging to multiple classes are trucks, bikes, persons, cars, dogs, and cats. For this task, we use object localization and classification as we have to locate multiple objects in the image. Various techniques available in the market based on Deep Learning use inbuilt architectures such as VGG-16 and InceptionV3. Using these techniques to solve the problem is a reasonable solution but the response time from these architectures may not be feasible as the autonomous vehicles have to react in less than 0.02 milliseconds in order to avoid collisions of all sorts. So using YOLO, we simply predict the classes and the bounded co-ordinates of the object in a single run of the model and detect multiple objects from the image rather than focusing only on the interested regions of the image as formerly employed by various models. YOLO is fast and accurate with the help of Convolution Neural Networks and is less likely to produce localization errors.

Image is an important medium to express information easily. This paper deals with the content of image segmentation with machine learning. Segmentation is the process of extracting the information required from the image. Machine learning is the process that helps to classify to obtain good results. A number of algorithms are designed for the segmentation process. The algorithms are selected based on the application. Quality segmentation can be applied if the algorithm is fixed at the application level. Standalone methods can be used for real-time applications. Schematic segmentation is one of the best techniques used for segmenting images. Machine learning combines basic techniques to produce good results. The algorithms vary for different input images like MRI, CT Scans, Colour images, etc. Algorithms like k-mean clustering are mostly used in processing. Many problems occur in segmentation which can be removed by Bayesian architectures. The usage of machine learning improves accuracy and efficiency. Labeling, training and testing are some of the methods used in segmentation through machine learning. 

Personalized webpage ranking is one of the key components in search engines. Moreover, most of the existing search engines focus only on answering user queries, although personalization will be more and more important as the amount of information available on the Web increases. Even though various re-ranking algorithms are developed, providing prompt responses to the user query results in a major challenge in web page personalization. Therefore, an efficient and effective ranking algorithm named the Oppositional Grass Bee optimization algorithm is developed to re-rank the web documents in the webpage personalization system. The proposed algorithm is designed by integrating the Oppositional Grass Hopper (OGHO) and Artificial Bee Colony optimization (ABC) algorithms. The concept of fictional computing and the foraging behavior realize the re-ranking process more effectively in the web environment. However, the semantic features extracted from the web pages make the process more effective and achieve optimal global solutions through the fitness measure. The proposed OGBEE Ranking algorithm effectively captures and analyzes the ranking scores of different search engines in order to generate the reranked score result.

This chapter covers text analytics definitions, how to get started with text analytics, examples and approaches, and a case study. The chapter gives examples of existing text analytics applications to show the wide range of real-world implications. Finally, as a guide to text analytics and the book, we give a process road map. Chapter 2 (How to Get Started with Text Analytics) briefly explains the Analyse Your Data, Use BI Tools to Understand Your Data and Final Words. Chapter 3 (Examples and Methods for Text Analytics) explains various Text Analytics Approaches 1: Word Spotting Text Analytics Approach 2. Manual Rules Text Analytics Approach 3. Text Categorization Approach 4: Topic Modelling Approach and 5. Thematic Analysis. Applications of Word Spotting Text Analytics Approach, Manual Rules, Text Categorization Approach, Topic Modelling Approach and Thematic Analysis are discussed with real-time examples. Chapter 4 discusses the case study, the following real-time application, Word Cloud Explorer, to illustrate its analytic capabilities.

Recognition of human activity has a wide range of applications in medical research and human survey systems. We present a powerful activity recognition system based on a Smartphone in this paper. The system collects time series signals with a 3- dimensional Smartphone accelerometer as the only sensor, from which 31 features in the time domain and frequency domain are created. The quadratic classifier, k-nearest neighbor algorithm, support vector machine, and artificial neural networks are used to classify activities. Feature extraction and subset selection are used to reduce dimensionality. In addition to passive learning, we use active learning techniques to lower the cost of data tagging. The findings of the experiment demonstrate that the categorization rate of passive learning is 84.4 percent and that it is resistant to common cell phone postures and poses. 

Working people have forgotten the importance of water intake. Smart Water Bottle will blow an alarm if it is being used by homemakers or people at home. This device can also be configured to their smartphones, which would send a message or alarm to their smartphones, making the user remember the intake of water by keeping some time interval. If configured to their mobiles, it would send a record of the amount of water taken by the user. The latest emerging technology like IoT, Android and many others will definitely be useful to the user. 

Machine learning (ML), a subset of artificial intelligence, is used to construct algorithms for monitoring, diagnosing, forecasting, and predicting clinical results. Health is a major concern for human beings. The current success in ML is due to deep learning (DL), using huge artificial neural networks. In the past, machine learning has demonstrated its usefulness and skills in detecting cancer. It is one of the most feasible solutions for top healthcare pioneers to detect anomalies. When healthcare companies succeed in using predictive models, they face challenges in demonstrating their value and gaining trust across the company. Recently, established standards for reporting machine learning-based clinical research will aid in connecting the clinical and computer science communities and realizing the full potential of machine learning techniques. The researchers have many objectives in the design of machine Learning Algorithms for different applications. Many papers discussed how machine learning algorithms are involved in health monitoring which will be updated so that patients, doctors, or any individuals can view the information. The main goal of this paper is to discuss basic types of Machine Learning and the challenges faced by Artificial intelligence (AI) in health care. The possible risks in clinical research give practical information on how to accurately and effectively analyze performance and avoid frequent pitfalls, particularly when dealing with applications for health and wellness contexts.

Healthcare is essential in pandemic times, but it is crucial for the well-being of daily life. Many countries allocate substantial funds towards providing high-quality healthcare services. As healthcare expenses escalate, policymakers and funders are increasingly focused on investigating the underlying factors driving the high costs of medical resources. A comprehensive analysis carried the required expenses towards identification, valuation, and measurement of resources utilized for the diagnosis process. The objective of the chapter is to provide how the data analysis is carried which helps to identify fraudulent behaviors. The generated model assists health management organizations in identifying suspicious behaviors toward claims. Healthcare fraud is a severe threat to global health results, and could lead to misuse, scarce resources, and negative impacts on healthcare access, infrastructures, and social determinants of health. Healthcare fraud is associated with increased healthcare costs in most of the leading countries. The proposed research work provides an estimation mechanism for utilizing health resources and their impacts on healthcare costs. This chapter proposes strategic ways of handling healthcare data to prevent future healthcare fraud, decrease healthcare expenditure, and adequately use resources to benefit the population. This chapter works on three primary datasets and a synthetic dataset aggregated from the primary datasets. The data preprocessing is carried out at different levels of the model, which truly enhances the data quality. The model is constructed at three levels; the first level analyzes datasets in which it extracts the primary features and provides constructive decisions and outcomes on the processing of data. Regressive analysis of the hierarchical grouping mechanism helps to know the detailed features that could affect healthcare and prevent resource misuse. 

Machine Learning refers to computer programming or data science that can learn from data. For example, the performance of T is increased with experience E if a computer program is learned from E in some tasks T, and performance is measured as P. The learning of computers is allowed without explicit programming in Machine Learning, which is a field of research. Machine learning can be used in various applications, such as banking, travel and tourism, healthcare, marketing, insurance, and human resources. Machine learning is a powerful tool for implementing security applications.