Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Financial fraud is an ever growing menace with far consequences in the financial industry. Data mining had played an imperative role in the detection of credit card fraud in online transactions. Credit card fraud detection, which is a data mining problem, becomes challenging due to two major reasons — first, the profiles of normal and fraudulent behaviours change constantly and secondly, credit card fraud data sets are highly skewed. The performance of fraud detection in credit card transactions is greatly affected by the sampling approach on dataset, selection of variables and detection technique(s) used. This paper investigates the performance of naive bayes, k-nearest neighbor and logistic regression on highly skewed credit card fraud data. Dataset of credit card transactions is sourced from European cardholders containing 284,807 transactions. A hybrid technique of under-sampling and oversampling is carried out on the skewed data. The three techniques are applied on the raw and preprocessed data. The work is implemented in Python. The performance of the techniques is evaluated based on accuracy, sensitivity, specificity, precision, Matthews correlation coefficient and balanced classification rate. The results shows of optimal accuracy for naive bayes, k-nearest neighbor and logistic regression classifiers are 97.92%, 97.69% and 54.86% respectively. The comparative results show that k-nearest neighbour performs better than naive bayes and logistic regression techniques.

Credit card fraud detection using machine learning techniques: A comparative analysis

Credit risk prediction models seek to predict quality factors such as whether an individual will default (bad applicant) on a loan or not (good applicant). This can be treated as a kind of machine learning (ML) problem. Recently, the use of ML algorithms has proven to be of great practical value in solving a variety of risk problems including credit risk prediction. One of the most active areas of recent research in ML has been the use of ensemble (combining) classifiers. Research indicates that ensemble individual classifiers lead to a significant improvement in classification performance by having them vote for the most popular class. This paper explores the predicted behaviour of five classifiers for different types of noise in terms of credit risk prediction accuracy, and how such accuracy could be improved by using classifier ensembles. Benchmarking results on four credit datasets and comparison with the performance of each individual classifier on predictive accuracy at various attribute noise levels are presented. The experimental evaluation shows that the ensemble of classifiers technique has the potential to improve prediction accuracy.

Multiple classifier application to credit risk assessment

In recent years, the aspect of vehicular ad hoc network (VANET) is becoming an interesting research area; VANET is a mobile ad hoc network considered as a special case of mobile ad hoc network (MANET). Similar to MANET, VANET is characterized as autonomous and self-configured wireless network. However, VANET has very dynamic topology, large and variable network size, and constrained mobility; these characteristics led to the need for efficient routing and resource saving VANET protocols, to fit with different VANET environments. These differences render traditional MANET's protocols unsuitable for VANET. The aim of this work is to give a survey of the VANETs routing mechanisms, this paper gives an overview of Vehicular ad hoc networks (VANETs) and the existing VANET routing protocols; mainly it focused on vehicle to vehicle (V2V) communication and protocols. The paper also represents the general outlines and goals of VANETs, investigates different routing schemes that have been developed for VANETs, as well as providing classifications of VANET routing protocols (focusing on two classification forms), and gives summarized comparisons between different classes in the context of their methodologies used, strengths, and limitations of each class scheme compared to other classes. Finally, it extracts the current trends and the challenges for efficient routing mechanisms in VANETs.

http://www.issr-journals.org/links/papers.php?journal=ijias&application=pdf&article=IJIAS-13-122-09

A Survey of Vehicular Ad hoc Networks Routing Protocols

Sign language is important for facilitating communication between hearing impaired and the rest of society. Two approaches have traditionally been used in the literature: image-based and sensor-based systems. Sensor-based systems require the user to wear electronic gloves while performing the signs. The glove includes a number of sensors detecting different hand and finger articulations. Image-based systems use camera(s) to acquire a sequence of images of the hand. Each of the two approaches has its own disadvantages. The sensor-based method is not natural as the user must wear a cumbersome instrument while the imagebased system requires specific background and environmental conditions to achieve high accuracy. In this paper, we propose a new approach for Arabic Sign Language Recognition (ArSLR) which involves the use of the recently introduced Leap Motion Controller (LMC). This device detects and tracks the hand and fingers to provide position and motion information. We propose to use the LMC as a backbone of the ArSLR system. In addition to data acquisition, the system includes a preprocessing stage, a feature extraction stage, and a classification stage. We compare the performance of Multilayer Perceptron (MLP) neural networks with the Nave Bayes classifier. Using the proposed system on the Arabic sign alphabets gives 98% classification accuracy with the Nave Bayes classifier and more than 99% using the MLP.

Arabic sign language recognition using the leap motion controller

Probability theory is the framework for making decision under uncertainty. In classification, Bayes' rule is used to calculate the probabilities of the classes and it is a big issue how to classify raw data rationally to minimize expected risk. Bayesian theory can roughly be boiled down to one principle: to see the future, one must look at the past. Naive Bayes classifier is one of the mostly used practical Bayesian learning methods. K-nearest neighbor is a supervised learning algorithm where the result of new instance query is classified based on majority of k-nearest neighbor category. The classifiers do not use any model to fit and only based on memory/training data. In this paper, after reviewing Bayesian theory, the naive Bayes classifier and k-nearest neighbor classifier is implemented and applied to a dataset \"credit card approval\" application. Eventually the performance of these two classifiers is observed on this application in terms of the correct classification and misclassification and how the performance of k-nearest neighbor classifier can be improved by varying the value of k.

Investigating the Performance of Naive- Bayes Classifiers and K- Nearest Neighbor Classifiers

Probability theory is the framework for making decision under uncertainty. In classification, Bayes' rule is used to calculate the probabilities of the classes and it is a big issue how to classify raw data rationally to minimize expected risk. Bayesian theory can roughly be boiled down to one principle: to see the future, one must look at the past. Naive Bayes classifier is one of the mostly used practical Bayesian learning methods. K-nearest neighbor is a supervised learning algorithm where the result of new instance query is classified based on majority of k-nearest neighbor category. The classifiers do not use any model to fit and only based on memory/training data. In this paper, after reviewing Bayesian theory, the naive Bayes classifier and k-nearest neighbor classifier is implemented and applied to a dataset "credit card approval" application. Eventually the performance of these two classifiers is observed on this application in terms of the correct classification and misclassification and how the performance of k-nearest neighbor classifier can be improved by varying the value of k.

https://www.vlsi.uwindsor.ca/presentations/2007/14-classifiers.pdf

VANET (Vehicular Ad-hoc Network) is an emerging new technology with some unique characteristics that makes it different from other ad hoc network. Due to rapid topology changing and frequent disconnection it is also difficult to design an efficient routing protocol for routing data among vehicles, called V2V or vehicle to vehicle communication and vehicle to road side infrastructure, called V2I. Because of road accident daily occurrence VANET is one of the influencing areas for the improvement of Intelligent Transportation System (ITS) which can increase road safety and provide traffic information etc. The existing routing protocols for VANET are not efficient to meet every traffic scenarios. Suitable routing protocols are required to establish communication between vehicles in future for road safety. In this paper, we focus on the merits and demerits of routing protocols which will help to develop new routing protocols or improvement of existing routing protocol in near future.

/pdf/survey-over-vanet-routing-protocols-for-vehicle-to-vehicle-4fhgoeebn8.pdf

Survey over VANET Routing Protocols for Vehicle to Vehicle Communication

In this paper we present an efficient computer aided mass classification method in digitized mammograms using Artificial Neural Network (ANN), which performs benign-malignant classification on region of interest (ROI) that contains mass. One of the major mammographic characteristics for mass classification is texture. ANN exploits this important factor to classify the mass into benign or malignant. The statistical textural features used in characterizing the masses are mean, standard deviation, entropy, skewness, kurtosis and uniformity. The main aim of the method is to increase the effectiveness and efficiency of the classification process in an objective manner to reduce the numbers of false-positive of malignancies. Three layers artificial neural network (ANN) with seven features was proposed for classifying the marked regions into benign and malignant and 90.91% sensitivity and 83.87% specificity is achieved that is very much promising compare to the radiologist's sensitivity 75%.

Mohammed J. Islam

Papers

Investigating the Performance of Naive- Bayes Classifiers and K- Nearest Neighbor Classifiers

Investigating the Performance of Naive- Bayes Classifiers and K- Nearest Neighbor Classifiers

Survey over VANET Routing Protocols for Vehicle to Vehicle Communication

An Efficient Automatic Mass Classification Method In Digitized Mammograms Using Artificial Neural Network

An Efficient Automatic Mass Classification Method In Digitized Mammograms Using Artificial Neural Network