Missing Value Imputation with Unsupervised Backpropagation

نویسندگان

  • Michael S. Gashler
  • Michael R. Smith
  • Richard G. Morris
  • Tony R. Martinez
چکیده

Many data mining and data analysis techniques operate on dense matrices or complete tables of data. Realworld data sets, however, often contain unknown values. Even many classification algorithms that are designed to operate with missing values still exhibit deteriorated accuracy. One approach to handling missing values is to fill in (impute) the missing values. In this paper, we present a technique for unsupervised learning called Unsupervised Backpropagation (UBP), which trains a multi-layer perceptron to fit to the manifold sampled by a set of observed point-vectors. We evaluate UBP with the task of imputing missing values in datasets, and show that UBP is able to predict missing values with significantly lower sum-squared error than other collaborative filtering and imputation techniques. We also demonstrate with 24 datasets and 9 supervised learning algorithms that classification accuracy is usually higher when randomly-withheld values are imputed using UBP, rather than with other methods.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Missing data imputation in multivariable time series data

Multivariate time series data are found in a variety of fields such as bioinformatics, biology, genetics, astronomy, geography and finance. Many time series datasets contain missing data. Multivariate time series missing data imputation is a challenging topic and needs to be carefully considered before learning or predicting time series. Frequent researches have been done on the use of diffe...

متن کامل

Imputation of Missing Data Using Machine Learning Techniques

A serious problem in mining industrial data bases is that they are often incomplete, and a significant amount of data is missing, or erroneously entered. This paper explores the use of machine-learning based alternatives to standard statistical data completion (data imputation) methods, for dealing with missing data. We have approached the data completion problem using two well-known machine le...

متن کامل

Imputation of Missing Values for Unsupervised Data Using the Proximity in Random Forests

This paper presents a new procedure that imputes missing values by random forests for unsupervised data. We found that it works pretty well compared with k-nearest neighbor (kNN) and rough imputations replacing the median of the variables. Moreover, this procedure can be expanded to semisupervised data sets. The rate of the correct classification is higher than that of other conventional method...

متن کامل

چند رویکرد برخورد با مقادیر گمشده‌ متغیرهای کمی و بررسی اثر آنها بر نتایج حاصل از یک کارآزمایی‌ بالینی

Background and Objectives: A major challenge that affects the longitudinal studies is the problem of missing data. Missing in the data may result in the loss of part of the information which reduces the accuracy of the estimator and obtain the results will be biased and inaccurate. Therefore, it is necessary to evaluate the missing data mechanism from a longitudinal research and to consider thi...

متن کامل

تحلیل مشاهدات گمشده در مطالعه اثر دوزهای مختلف مکمل ویتامین D بر مقاومت به انسولین در دوران بارداری

Introduction: The aim  of  this  study  was to impute missing data  and  to compare the effect  of  different doses of  vitamin D supplementation on  insulin resistance during  pregnancy. Methods: A clinical trial  study   was done on 104  women  with diabetes and gestational age less than 12 weeks between 1391 and...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Computational Intelligence

دوره 32  شماره 

صفحات  -

تاریخ انتشار 2016