We present a new model based on a global hybridization of the most popular machine learning methods applied to the challenging problem of customer churning prediction in the telecommunications industry. In the first p...
详细信息
ISBN:
(纸本)9781728100036
We present a new model based on a global hybridization of the most popular machine learning methods applied to the challenging problem of customer churning prediction in the telecommunications industry. In the first phase of our experiments, all models were applied and evaluated using cross-validation on a popular, public domain dataset. In the second phase, we describe our model and show the performance improvement. In order to determine the most efficient parameter combinations w e performed various simulations for each method and for a wide range of parameters. Our results demonstrate clear superiority of the proposed model against the popular existing ML models.
The main telecom operator goal is to build end user loyalty towards offered services. Computing the perceived quality, known, Quality of Experience (QoE) has become a crucial topic for investigation. Machine learning ...
详细信息
ISBN:
(纸本)9781538617342
The main telecom operator goal is to build end user loyalty towards offered services. Computing the perceived quality, known, Quality of Experience (QoE) has become a crucial topic for investigation. Machine learning algorithms provide a solution to tease out the complex relationships between several influencing factors and QoE. This paper proposes a novel QoE estimation model for video service, namely, boosting Support Vector Regression (BSVR) based QoE model. The purpose of this model is to investigate the effectiveness of combining multiple learners instead of classical individual learner, in order to improve prediction accuracy of the QoE. The BSVR is based on a combination of two principal techniques: boosting algorithm and Support Vector Regression (SVR). More precisely, multiple SVR models were trained in an iterative boosting algorithm to create a powerful predictive model. In fact, the use of SVRs as weak learners has several advantages. First, the SVR is based on a convex optimization problem, where a global optimal solution exploits a limited number of support vectors, which results in improved prediction accuracy, while maintaining low computational complexity. Second, each SVR uses flexible Radial Basis Function (RBF) kernel function to model QoE data efficiently. Comparative evaluation of our proposed BSVR-based QoE model is performed to show its superiority over relevant ensemble learning methods and regression models based on single learner, in terms of prediction accuracy and computational complexity
Although there is no strict consensus, some studies have reported that Postictal generalized EEG suppression (PGES) is a potential electroencephalographic (EEG) biomarker for risk of sudden unexpected death in epileps...
详细信息
Although there is no strict consensus, some studies have reported that Postictal generalized EEG suppression (PGES) is a potential electroencephalographic (EEG) biomarker for risk of sudden unexpected death in epilepsy (SUDEP). PGES is an epoch of EEG inactivity after a seizure, and the detection of PGES in clinical data is extremely difficult due to artifacts from breathing, movement and muscle activity that can adversely affect the quality of the recorded EEG data. Even clinical experts visually interpreting the EEG will have diverse opinions on the start and end of PGES for a given patient. The development of an automated EEG suppression detection tool can assist clinical personnel in the review and annotation of seizure files, and can also provide a standard for quantifying PGES in large patient cohorts, possibly leading to further clarification of the role of PGES as a biomarker of SUDEP risk. In this paper, we develop an automated system that can detect the start and end of PGES using frequency domain features in combination with boosting classification algorithms. The average power for different frequency ranges of EEG signals are extracted from the prefiltered recorded signal using the fast fourier transform and are used as the feature set for the classification algorithm. The underlying classifiers for the boosting algorithm are linear classifiers using a logistic regression model. The tool is developed using 12 seizures annotated by an expert then tested and evaluated on another 20 seizures that were annotated by 11 experts.
作者：
Yao, LeGe, ZhiqiangZhejiang Univ
Coll Control Sci & Engn Inst Ind Proc Control State Key Lab Ind Control Technol Hangzhou 310027 Zhejiang Peoples R China
In this paper, two enhanced Binary Differential Evolution (BDE) algorithms are proposed to select variables for nonlinear process soft sensor development. Firstly, the Parallel BDE (PBDE) algorithm is presented to ext...
详细信息
In this paper, two enhanced Binary Differential Evolution (BDE) algorithms are proposed to select variables for nonlinear process soft sensor development. Firstly, the Parallel BDE (PBDE) algorithm is presented to extract the optimal individuals of several parallel short evolution paths of basic BDE, where the spurious variables are effectively eliminated. And the most relevant variables are selected through a double-layer selection strategy with the validating Root Mean Square Error (RMSE) for evaluating criterion. Secondly, the boosting BDE (BBDE) algorithm is proposed through applying the boosting technique to the parallel evolution paths. The performance of the previous path needs to be taken into account when conducting the current evolution path. The selected probabilities of variables are given through the weighted summation of the selection results of all paths. Also, a double-layer selection is conducted on BBDE algorithm. The feasibility and effectiveness of the proposed methods are demonstrated through a nonlinear numerical example and a real industrial process. (C) 2017 Elsevier Ltd. All rights reserved.
In order to make a monitoring system that predicts correctly the QoE of the users, we need to make a model based on obtained MOS. To define our model, we go with the first Step 1: Create the learning (development) and...
详细信息
In order to make a monitoring system that predicts correctly the QoE of the users, we need to make a model based on obtained MOS. To define our model, we go with the first Step 1: Create the learning (development) and test (validation) data samples from the original data. Then, in Step 2, we try to develop the model on the training data and use it to predict the distance. We tried some used models: decision tree model, random forest model, linear regression model, logistic regression, and decision tree regressor, etc. to build our model using obtained dataset (development). In Step 3, we calculate prediction accuracy and error rates for each model and conclude which algorithm can give us the best prediction parameters.
Many salient object detection approaches share the common drawback that they cannot uniformly highlight heterogeneous regions of salient objects, and thus, parts of the salient objects are not discriminated from backg...
详细信息
Many salient object detection approaches share the common drawback that they cannot uniformly highlight heterogeneous regions of salient objects, and thus, parts of the salient objects are not discriminated from background regions in a saliency map. In this paper, we focus on this drawback and accordingly propose a novel algorithm that more uniformly highlights the entire salient object as compared to many approaches. Our method consists of two stages: boosting the object-level distinctiveness and saliency refinement. In the first stage, a coarse object-level saliency map is generated based on boosting the distinctiveness of the object proposals in the test images, using a set of object-level features and the Modest AdaBoost algorithm. In the second stage, several saliency refinement steps are executed to obtain a final saliency map in which the boundaries of salient objects are preserved. Quantitative and qualitative comparisons with state-of-the-art approaches demonstrate the superior performance of our approach. (C) 2017 Elsevier Inc. All rights reserved.
The novel approach for automatic detection and classification of road defects is proposed based on shape and texture features analysis. The system includes three main steps: defects position detection, feature contour...
详细信息
The novel approach for automatic detection and classification of road defects is proposed based on shape and texture features analysis. The system includes three main steps: defects position detection, feature contour extraction followed by classification of defects. The proposed approach is implemented in Matlab for automatic detection and classification of defects based on digital images analysis combined with machine learning algorithms such as the random forest algorithm and boosting. Segmentation is implemented using graph-cuts method and Markov random fields. The efficiency of proposed approach is demonstrated on the real data set.
Today, people's new way of life leads their eating habits towards fast-foods and ready-to-use products more than before. These foods contain large amounts of sugar and fat, which increase the number of people at r...
详细信息
ISBN:
(纸本)9781509050017
Today, people's new way of life leads their eating habits towards fast-foods and ready-to-use products more than before. These foods contain large amounts of sugar and fat, which increase the number of people at risk of diabetes. Many people are required to get diabetes diagnosis by various blood tests regularly. These tests bring significant amounts of cost and take facilities and time when it comes to a large number of people. Machine learning algorithms can be used as computer aided systems to predict if a person is highly probable to have diabetes or not, in order to reduce huge number of people who require to take diagnosis blood tests, to save time and money. In this study, we proposed a learning algorithm which ensemble boosting algorithm with perceptron algorithm to improve performance of perceptron algorithm in prediction of undiagnosed patients. Proposed method is tested on three different publicly available datasets and compared with performance of perceptron algorithm. The results show that proposed algorithm outperform perceptron algorithm on average AUC basis.
This paper presents a novel approach for lecture video indexing using a boosted deep convolutional neural network system. The indexing is performed by matching high quality slide images, for which text is either known...
详细信息
ISBN:
(纸本)9781538614174
This paper presents a novel approach for lecture video indexing using a boosted deep convolutional neural network system. The indexing is performed by matching high quality slide images, for which text is either known or extracted, to lower resolution video frames with possible noise, perspective distortion, and occlusions. We propose a deep neural network integrated with a boosting framework composed of two sub-networks targeting feature extraction and similarity determination to perform the matching. The trained network is given as input a pair of slide image and a candidate video frame image and produces the similarity between them. A boosting framework is integrated into our proposed network during the training process. Experimental results show that the proposed approach is much more capable of handling occlusion, spatial transformations, and other types of noises when compared with known approaches.
Purpose: This paper aims to provide a predictive framework of customer churn through six stages for accurate prediction and preventing customer churn in the field of business. Design/methodology/approach: The six stag...
详细信息
Purpose: This paper aims to provide a predictive framework of customer churn through six stages for accurate prediction and preventing customer churn in the field of business. Design/methodology/approach: The six stages are as follows: first, collection of customer behavioral data and preparation of the data;second, the formation of derived variables and selection of influential variables, using a method of discriminant analysis;third, selection of training and testing data and reviewing their proportion;fourth, the development of prediction models using simple, bagging and boosting versions of supervised machine learning;fifth, comparison of churn prediction models based on different versions of machine-learning methods and selected variables;and sixth, providing appropriate strategies based on the proposed model. Findings: According to the results, five variables, the number of items, reception of returned items, the discount, the distribution time and the prize beside the recency, frequency and monetary (RFM) variables (RFMITSDP), were chosen as the best predictor variables. The proposed model with accuracy of 97.92 per cent, in comparison to RFM, had much better performance in churn prediction and among the supervised machine learning methods, artificial neural network (ANN) had the highest accuracy, and decision trees (DT) was the least accurate one. The results show the substantially superiority of boosting versions in prediction compared with simple and bagging models. Research limitations/implications: The period of the available data was limited to two years. The research data were limited to only one grocery store whereby it may not be applicable to other industries;therefore, generalizing the results to other business centers should be used with caution. Practical implications: Business owners must try to enforce a clear rule to provide a prize for a certain number of purchased items. Of course, the prize can be something other than the purchased item. Bu
暂无评论