NMVI: A data-splitting based imputation technique for distinct types of missing data

Bhagat, Hutashan Vishal; Singh, Manminder

doi:10.1016/j.chemolab.2022.104518

Cited by 9 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various factors lead to missing values in databases, which adversely affects the performance of data mining (DM) algorithms [1], [3]. In real-world datasets, the presence of missing values is a significant challenge, impairing data analytics [4]- [6], impeding efficient data use, and diminishing the effectiveness of data-driven models [7]. Learning from data with missing values is a widespread issue across disciplines [8].…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Bibliometric Analysis of Missing Value Imputation

Nugroho,

Surendro

2024

IEEE Access

View full text Add to dashboard Cite

Data quality plays a crucial role in tasks, such as enhancing the accuracy of data analytics and avoiding the accumulation of redundant data. One of the significant challenges in data quality is dealing with missing data, which has been extensively explored by the scholarly community and has resulted in a significant increase in related publications. It is important to recognize that the landscape of missing data in computer science offers numerous opportunities for further research. However, upon closer examination of existing studies, it becomes evident that many have not fully utilized bibliometric analysis tools and software for comprehensive literature reviews. Therefore, this study aims to explore the essential characteristics, trends, and prevailing themes in the field of missing data imputation. Through a thorough bibliometric analysis, this study demonstrated the evolution of knowledge and key focal points in the field of missing data imputation. The analysis consisted of 352 journal papers in social sciences published between 2012 and 2023, all centered on missing data imputation. Among these publications, "IEEE Access" has become a highly respected source. To systematically explore various aspects of missing data imputation, a conceptual framework was used to uncover potential research directions and underlying themes. Ultimately, a thematic map serves as a valuable tool for providing a comprehensive understanding, categorizing significant concepts into basic or overarching, developing, or declining, central, highly developed, and isolated themes. These overarching and underlying themes offer valuable insights and pave the way for prospective directions and critical areas of study.

show abstract

Section: Introductionmentioning

confidence: 99%

A Comprehensive Bibliometric Analysis of Missing Value Imputation

Nugroho,

Surendro

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Different imputation methods, viz., MICE, KNN, and RF-based imputation were implemented to impute the missing data in the sensor data of the internet of things [ 17 ]. A data splitting-based imputation method named “nullify the missing values before the imputation” was proposed to impute the missing data [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Ensemble Classifiers for Anomaly Handling in Smart Home Energy Consumption Data

Prakash

Kumar

Moganti

et al. 2022

Sensors

View full text Add to dashboard Cite

Addressing data anomalies (e.g., garbage data, outliers, redundant data, and missing data) plays a vital role in performing accurate analytics (billing, forecasting, load profiling, etc.) on smart homes’ energy consumption data. From the literature, it has been identified that the data imputation with machine learning (ML)-based single-classifier approaches are used to address data quality issues. However, these approaches are not effective to address the hidden issues of smart home energy consumption data due to the presence of a variety of anomalies. Hence, this paper proposes ML-based ensemble classifiers using random forest (RF), support vector machine (SVM), decision tree (DT), naive Bayes, K-nearest neighbor, and neural networks to handle all the possible anomalies in smart home energy consumption data. The proposed approach initially identifies all anomalies and removes them, and then imputes this removed/missing information. The entire implementation consists of four parts. Part 1 presents anomaly detection and removal, part 2 presents data imputation, part 3 presents single-classifier approaches, and part 4 presents ensemble classifiers approaches. To assess the classifiers’ performance, various metrics, namely, accuracy, precision, recall/sensitivity, specificity, and F1 score are computed. From these metrics, it is identified that the ensemble classifier “RF+SVM+DT” has shown superior performance over the conventional single classifiers as well the other ensemble classifiers for anomaly handling.

show abstract

Data Imputation Using Correlation-Based Machine Learning Algorithms

Aruna Devi,

Karthik

2024

Intelligent Systems Design and Applications

View full text Add to dashboard Cite

NMVI: A data-splitting based imputation technique for distinct types of missing data

Cited by 9 publications

References 39 publications

A Comprehensive Bibliometric Analysis of Missing Value Imputation

A Comprehensive Bibliometric Analysis of Missing Value Imputation

Machine Learning-Based Ensemble Classifiers for Anomaly Handling in Smart Home Energy Consumption Data

Data Imputation Using Correlation-Based Machine Learning Algorithms

Contact Info

Product

Resources

About