Machine Learning Techniques in Spam Detection

Spam, a contraction of rotten email (or junk email), is a global and massive phenomenon. And as long as email exists, this real problem will always exist. However, it is possible to significantly limit the effects of spam. To do this, you just have to use various anti-spam technologies wisely. In this chapter, the authors present the definitions of spam and its evolution, its objectives and impacts, as well as the different approaches and techniques used for detecting and filtering it.

Study on South Asian Diabetic Subjects on Different Attributes

Diabetes is a serious problem in today's world. Stress TTH (tension type headache) is another epidemic which is growing with a very fast pace. Diabetes is a disease of the body that prevents the metabolism of blood sugar (glucose). This increases the blood glucose to a risky level. The present study aims to analyze diabetes with the latest IoT and big data analysis techniques and its correlation with stress (TTH) on human health. Authors have tried to include age, gender, and insulin factor and its correlation with diabetes. IoT helps us to connect each other, that is, it is known a smart connecting thing (a sort of “universal global neural network” in cloud). It comprises of smart connecting machine with other machine, object, and a lot more. Big data refers to huge sets of data that are also large enough in terms of variety and velocity. Due to this, it becomes more difficult to handle, organise, store, process, and manipulate such data using traditional techniques of storage and processing. Stress especially TTH (tension type headache) is a serious problem in today's world. Now every person in this world is facing headache and stress-related problems in daily life. The authors have collected this big data and studied the people; they have studied their tension level and helped them to cure it. In this chapter, they analyze the correlation between diabetes and stressors. For the analysis, they collected sample of 30 subjects from hospitals of Delhi in random fashion who have been suffering from diabetes from their health insurance providers without disclosing any personal information (PI) or sensitive personal information (SPI) by law. To identify each case sample IDs like S1, S2, etc. has been allotted to the subjects. Sample data has been collected for following parameters: gender, age, diabetes type, insulin dependency, obesity status, CAD status, and CAN status. They have used the Tableau s/w for this analysis. Overall, an interesting observation during the research was that none of the female subjects having diabetes is below 25 years, that is, early age diabetes cases are less comparative to males subjected to the case sampling should not be impacted for age group gender biasing.

Research Information

This chapter describes the framework of an analytical study around the computational intelligence algorithms, which are prompted by natural mechanisms and complex biological phenomena. These algorithms are numerous and can be classified in two great families: firstly the family of evolutionary algorithms (EA) such as genetic algorithms (GAs), genetic programming (GP), evolutionary strategy (ES), differential evolutionary (DE), paddy field algorithm (PFA); secondly, the swarm intelligence algorithms (SIA) such as particle swarm optimisation (PSO), ant colony optimization (ACO), bacteria foraging optimisation (BFO), wolf colony algorithm (WCA), fireworks algorithm (FA), bat algorithm (BA), cockroaches algorithm (CA), social spiders algorithm (SSA), cuckoo search algorithm (CSA), wasp swarm optimisation (WSO), mosquito optimisation algorithm (MOA). The authors have detailed the functioning of each algorithm following a structured organization (the descent of the algorithm, the inspiration source, the summary, and the general process) that offers for readers a thorough understanding. This study is the fruit of many years of research in the form of synthesis, which groups the contributions offered by several researchers in the meta-heuristic field. It can be the beginning point for planning and modelling new algorithms or improving existing algorithms.

Physical Characteristics of Type 1 and 2 Diabetic Subjects

The Delhi and NCR healthcare systems are rapidly registering electronic health records, diagnostic information available electronically. Furthermore, clinical analysis is rapidly advancing—large quantities of information are examined and new insights are part of the analysis of this technology—and experienced as big data. It provides tools for storing, managing, studying, and assimilating large amounts of robust, structured, and unstructured data generated by existing medical organizations. Recently, data analysis data have been used to help provide care and diagnose disease. In the current era, systems need connected devices, people, time, places, and networks that are fully integrated on the internet (IoT). The internet has become new in developing health monitoring systems. Diabetes is defined as a group of metabolic disorders affecting human health worldwide. Extensive research (diagnosis, path physiology, treatment, etc.) produces a great deal of data on all aspects of diabetes. The main purpose of this chapter is to provide a detailed analysis of healthcare using large amounts of data and analysis. From the Hospitals of Delhi and NCR, a sample of 30 subjects has been collected in random fashion, who have been suffering from diabetes from their health insurance providers without disclosing any personal information (PI) or sensitive personal information (SPI) by law. The present study aimed to analyse diabetes with the latest IoT and big data analysis techniques and its correlation with stress (TTH) on human health. Authors have tried to include age, gender, and insulin factor and its correlation with diabetes. Overall, in conclusion, TTH cases increase with age in case of males and do not follow the pattern of diabetes variation with age while in the case of female TTH pattern variation (i.e., increasing trend up to age of 60 then decreasing).

Machine Learning in Sentiment Analysis Over Twitter

Social networks are the main resources to gather information about people's opinions and sentiments towards different topics as they spend hours daily on social media and share their opinions. Twitter is a platform widely used by people to express their opinions and display sentiments on different occasions. Sentiment analysis's (SA) task is to label people's opinions as different categories such as positive and negative from a given piece of text. Another task is to decide whether a given text is subjective, expressing the writer's opinions, or objective. These tasks were performed at different levels of analysis ranging from the document level to the sentence and phrase level. Another task is aspect extraction, which originated from aspect-based sentiment analysis in phrase level. All these tasks are under the umbrella of SA. In recent years, a large number of methods, techniques, and enhancements have been proposed for the problem of SA in different tasks at different levels. Sentiment analysis is an approach to analyze data and retrieve sentiment that it embodies. Twitter sentiment analysis is an application of sentiment analysis on data from Twitter (tweets) in order to extract sentiments conveyed by the user. In the past decades, the research in this field has consistently grown. The reason behind this is the challenging format of the tweets, which makes the processing difficult. The tweet format is very small, which generates a whole new dimension of problems like use of slang, abbreviations, etc. The chapter elaborately discusses three supervised machine learning algorithms—naïve Bayes, k-nearest neighbor (KNN), and decision tree—and compares their overall accuracy, precisions, as well as recall values; f-measure; number of tweets correctly classified; number of tweets incorrectly classified; and execution time.

Introduction of Big Data With Analytics of Big Data

This chapter explained big data and how to do the data analytics in big data along with the basics of big data with its common traits. This chapter described technology that is used to handle the big data like, NoSQL, Hadoop, MangoDB, MapReduce, etc. This chapter explained the challenges that we are facing to handle big data and discussed some live projects in big data.

Challenges and Applications of Data Analytics in Social Perspectives

This chapter introduces data science with its history and importance in this modern era briefly. This chapter also elaborates the discussion by relating data science to various modern fields like big data analytics, artificial intelligence, deep learning, and machine learning. This chapter also discuss the necessary of data analytics in this big data era. This chapter also briefly introduces another emerging field, Internet of Things (IoT) and explores the contribution IoT towards big data analytics and data science in research perspective. It also briefly introduces the programming and non-programming tools used in the data science field.

On Swarm Intelligence and Its Integration With Internet of Things

Internet of Things (IoT) network is growing at a tremendous speed and is expected to occupy every field in the near future. Swarm Intelligence (SI) algorithms came into existence from the inspiration of nature, especially biological systems. SI algorithms gained importance among researchers due to their properties of decentralized control, self-organised structure, scalable framework, flexible nature, and getting solution for complex problems. This chapter examines some basic SI algorithms and explores the functioning of IoT network. It aims to bestow the exploitation of swarm intelligence for the betterment of IoT.

DeepLearning for Computer Vision Problems

Deep learning is a combined area between neural network and machine learning. Over the last years, deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields. With computer vision being one of the most prominent cases, the deep learning methodology applies nonlinear transformations and model abstractions of high levels in large databases. Therefore, an overview of DL methodology is provided along with its major modal principals and its hierarchy, which are presented and compared with the more conventional algorithms. Likewise, its popularity and usefulness in the artificial intelligence world are discussed, and some important techniques that increase DL performance are highlighted.

Deep Learning for Social Media Text Analytics

Text analytics is the process of extracting high quality information from the text. A set of statistical, linguistic, and machine learning techniques are used to represent the information content from various textual sources such as data analysis, research, or investigation. Text is the common way of communication in social media. The understanding of text includes a variety of tasks including text classification, slang, and other languages. Traditional Natural Language Processing (NLP) techniques require extensive pre-processing techniques to handle the text. When a word “Amazon” occurs in the social media text, there should be a meaningful approach to find out whether it is referring to forest or Kindle. Most of the time, the NLP techniques fail in handling the slang and spellings correctly. Messages in Twitter are so short such that it is difficult to build semantic connections between them. Some messages such as “Gud nite” actually do not contain any real words but are still used for communication.