No abstract

In the telecom sector, a huge volume of data is being generated on a daily basis due to a vast client base. Decision makers and business analysts emphasized that attaining new customers is costlier than retaining the existing ones. Business analysts and customer relationship management (CRM) analyzers need to know the reasons for churn customers, as well as, behavior patterns from the existing churn customers' data. This paper proposes a churn prediction model that uses classification, as well as, clustering techniques to identify the churn customers and provides the factors behind the churning of customers in the telecom sector. Feature selection is performed by using information gain and correlation attribute ranking filter. The proposed model first classifies churn customers data using classification algorithms, in which the Random Forest (RF) algorithm performed well with 88.63% correctly classified instances. Creating effective retention policies is an essential task of the CRM to prevent churners. After classification, the proposed model segments the churning customer's data by categorizing the churn customers in groups using cosine similarity to provide group-based retention offers. This paper also identified churn factors that are essential in determining the root causes of churn. By knowing the significant churn factors from customers' data, CRM can improve productivity, recommend relevant promotions to the group of likely churn customers based on similar behavior patterns, and excessively improve marketing campaigns of the company. The proposed churn prediction model is evaluated using metrics, such as accuracy, precision, recall, f-measure, and receiving operating characteristics (ROC) area. The results reveal that our proposed churn prediction model produced better churn classification using the RF algorithm and customer profiling using k-means clustering. Furthermore, it also provides factors behind the churning of churn customers through the rules generated by using the attribute-selected classifier algorithm.

No abstract

In many industries inclusive of automotive vehicle industry, predictive maintenance has become more important. It is hard to diagnose failure in advance in the vehicle industry because of the limited availability of sensors and some of the designing exertions. However with the great development in automotive industry, it looks feasible today to analyze sensor's data along with machine learning techniques for failure prediction. In this article, an approach is presented for fault prediction of four main subsystems of vehicle, fuel system, ignition system, exhaust system, and cooling system. Sensor is collected when vehicle is on the move, both in faulty condition (when any failure in specific system has occurred) and in normal condition. The data is transmitted to the server which analyzes the data. Interesting patterns are learned using four classifiers, Decision Tree, Support Vector Machine, Nearest Neighbor, and Random Forest. These patterns are later used to detect future failures in other vehicles which show the similar behavior. The approach is produced with the end goal of expanding vehicle up-time and was demonstrated on 70 vehicles of Toyota Corolla type. Accuracy comparison of all classifiers is performed on the basis of Receiver Operating Characteristics (ROC) curves.

No abstract

The use of biomarkers for early detection of Alzheimer's disease (AD) improves the accuracy of imaging‐based prediction of AD and its prodromal stage that is mild cognitive impairment (MCI). Brain parcellation‐based computer‐aided methods for detecting AD and MCI segregate the brain in different anatomical regions and use their features to predict AD and MCI. Brain parcellation generally is carried out based on existing anatomical atlas templates, which vary in the boundaries and number of anatomical regions. This works considers dividing the brain based on different atlases and combining the features extracted from these anatomical parcellations for a more holistic and robust representation. We collected data from the ADNI database and divided brains based on two well‐known atlases: LONI Probabilistic Brain Atlas (LPBA40) and Automated Anatomical Labeling (AAL). We used baselines images of structural magnetic resonance imaging (MRI) and 18F‐fluorodeoxyglucose positron emission tomography (FDG‐PET) to calculate average gray‐matter density and average relative cerebral metabolic rate for glucose in each region. Later, we classified AD, MCI and cognitively normal (CN) subjects using the individual features extracted from each atlas template and the combined features of both atlases. We reduced the dimensionality of individual and combined features using principal component analysis, and used support vector machines for classification. We also ranked features mostly involved in classification to determine the importance of brain regions for accurately classifying the subjects. Results demonstrated that features calculated from multiple atlases lead to improved performance compared to those extracted from one atlas only.

Breast cancer is the second most common cause of cancer-related deaths among women. Early detection leads to better prognosis and saves lives. The 5-year survival rate of breast cancer is 99% if it is located only in breast. Conventional computer-aided diagnosis (CADx) systems for breast cancer use the single view information of mammograms to assist the radiologists. More recent work has focused on more than one views. Existing multi-view based CADx systems normally employ only two views namely Cranio-Caudal (CC) and Medio-Lateral-Oblique (MLO). The information fusion of the two views proved the effectiveness of the system for mammogram classification which cannot be achieved by single view information. However, combining the information of four views of mammograms increases the performance of classification. In this study, we propose Multi-View Feature Fusion (MVFF) based CADx system using feature fusion technique of four views for classification of mammogram. The complete CADx tool contains three stages, the first stage have the ability to classify mammogram into abnormal or normal, second stage is about classification of mass or calcification and in the final stage classification of malignant or benign classification is performed. Convolutional Neural Network (CNN) based feature extraction models operate on each view separately. These extracted features were fused into one final layer for ultimate prediction. Our proposed system is trained on four views of mammograms, after data augmentation. We performed our experiments on publicly available datasets such as CBIS-DDSM (Curated Breast Imaging Subset of DDSM) and mini-MIAS database of mammograms. In comparison with literature the MVFF based system is performed better than a single view-based system for mammogram classification. We have achieved area under ROC curve (AUC) of 0.932 for mass and calcification and 0.84 for malignant and benign, which is higher than all single-view based systems. The value of AUC for normal and abnormal classification is 0.93.

The volume of research articles in digital repositories is increasing. This spectacular growth of repositories makes it rather difficult for researchers to obtain related research papers in response to their queries. The problem becomes worse when a researcher with insufficient knowledge of searching research articles uses these repositories. In the traditional recommendation approaches, the results of the query miss many high-quality papers, in the related work section, which are either published recently or have low citation count. To overcome this problem, there needs to be a solution which considers not only structural relationships between the papers but also inspects the quality of authors publishing those articles. Many research paper recommendation approaches have been implemented which includes collaborative filtering-based, content-based, and citation analysis-based techniques. The collaborative filtering-based approaches primarily use paper-citation matrix for recommendations, whereas the content-based approaches only consider the content of the paper. The citation analysis considers the structure of the network and focuses on papers citing or cited by the paper of interest. It is therefore very difficult for a recommender system to recommend high-quality papers without a hybrid approach that incorporates multiple features, such as citation information and author information. The proposed method creates a multilevel citation and relationship network of authors in which the citation network uses the structural relationship between the papers to extract significant papers, and authors' collaboration network finds key authors from those papers. The papers selected by this hybrid approach are then recommended to the user. The results have shown that our proposed method performs exceedingly well as compared with the state-of-the-art existing systems, such as Google scholar and multilevel simultaneous citation network.