Evidential reasoning for preprocessing uncertain categorical data for trustworthy decisions: An application on healthcare and finance

Sachan, Swati; Almaghrabi, Fatima; Yang, Jian‐Bo; Xu, Dong-Ling

doi:10.1016/j.eswa.2021.115597

Cited by 50 publications

(9 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) The presence of categorical (qualitative) attributes increases the information uncertainty, so we apply automatic techniques for preprocessing (i.e., transform categorical attributes into numbers) the input data such as one-hot, target and label encoding [38]. In particular, one-hot and label methods were discarded: the former due to its inefficiency when categorical attributes have high cardinality (a large number of categories), and the latter because it induces misunderstanding in the learning process since the value automatically assigned lacks of semantics.…”

Section: Main Contributionmentioning

confidence: 99%

The impact of aggregated demand response to energy communities: Results of a community survey in Spain

Palomar,

Cruz,

Hernandez

et al. 2023

Preprint

View full text Add to dashboard Cite

This article presents a study which links the technical, awareness, motivation and behavioural factors affecting the adoption of demand response programmes, aggregation and other domestic energy efficiency measures. The aim is to statistically correlate those factors (and variables) to better understand the role of each one of them played in the effectiveness of future design and deployment of energy efficiency and sustainable energy community initiatives. The data for this study was collected from 102 general population responses to an online categorical multiple response survey (https://putdr2test.web.uah.es/) carried out between November 2022 and March 2023. We apply chi-square test of association, contingency tables, and clustering and k-nearest neighbours algorithms to the dataset, amongst other statistical and machine learning methods, paying special attention to the data preprocessing. Despite the lack of strong associations between those variables as revealed by our experimentation, it showcases a number of four patterns in which factors like the consumer motivation dominate the effective participation in RD initiatives and pilots. Three conclusions can be drawn. The technical dimension is not the weakest, resulting in a promising opportunity to raise awareness of the tangible benefits achieved by using more efficient technologies and engaging in new energy initiatives to motivate the change. Moreover, inconsistent, incomplete or imprecise media, market and regulatory messages can lead to a decline in confidence and loss of motivation among consumers, even between the environmentally concerned ones. To that end, we encourage strategies that relate energy efficiency with quality and innovation, not with effort and a loss of comfort, to overcome the barrier of ignorance and reluctance towards change.

show abstract

Section: Main Contributionmentioning

confidence: 99%

The impact of aggregated demand response to energy communities: Results of a community survey in Spain

Palomar,

Cruz,

Hernandez

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We applied some pre-processing steps as the collected dataset were having missing values and class imbalance problems. Referring the CVD dataset, the dataset contained a total of 43400 patient records out of which 14754 values Attribute Description i.d patient's i.d gender includes ("male": 0, "female": 1, "other": 2) age patient's age (continuous) hypertension suffering from hypertension ("yes":1, "no":0) heart _disease suffering heart disease ("yes":1, "no":0) ever_married marital status of patient ("yes":1, "no":0) work_type job status ("children":0, "govt_job":1, "never_worked":2, "private":3, "self_employed":4) residence_type ("rural:0, "urban":1) avg_glucose_level average glucose level of blood (continuous) bmi body mass index (decimal value) smoking_status ("never smoked":0, "formerly smoked":1, "smokes":2) stroke ("yes":1, "no":0) in handling the missing data, however their usage in medical field is limited and specific efficacy for disease detection is not clear [27]. Most of the times, researchers do not consider the observations with missing values and drop the incomplete cases intentionally, since the traditional data imputation methods are not sufficient to capture the missing data complexities in health care applications [28,29].…”

Section: Pre-processingmentioning

confidence: 99%

Analyzing the impact of feature selection on the accuracy of heart disease prediction

Pathan¹,

Nag²,

Pathan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Heart Disease has become one of the most serious diseases that has a significant impact on human life. It has emerged as one of the leading causes of mortality among the people across the globe during the last decade. In order to prevent patients from further damage, an accurate diagnosis of heart disease on time is an essential factor. Recently we have seen the usage of noninvasive medical procedures, such as artificial intelligence-based techniques in the field of medical. Specially machine learning employs several algorithms

show abstract

“…Preprocessing is essential to improve data quality so that machine learning can function properly [19]. An unprocessed dataset is usually ambiguous and incomplete because some of its attributes are missing, either in its inputs or outputs, which may negatively affect the machine learning modeling [20]. Moreover, Qlattice models immediately detect data types; incorrect detection of data types leads to poor machine learning models.…”

Section: Preprocessing Datasetmentioning

confidence: 99%

Linkage Detection of Features that Cause Stroke using Feyn Qlattice Machine Learning Model

Purwono

Ma’arif

Negara

et al. 2021

Jurnal Ilmiah Teknik Elektro Komputer Dan Informatika

View full text Add to dashboard Cite

Stroke is a disease caused by brain tissue damage because of blockage in the cerebrovascular system that disrupts body sensory and motoric systems Stroke disease is one of the highest death cause in the world. Data collection from Electronic Health Records (EHR) is increasing and has been included in the health service big data. It can be processed and analyzed using machine learning to determine the risk group of stroke disease. Machine learning can be used as a predictor of stroke causes, while the predictor clarifies the influence of each cause factor of the disease. Our contribution in this research is to evaluate Feyn Qlattice machine learning models to detect the influence of stroke disease's main cause features. We attempt to obtain a correlation between features of the stroke disease, especially on the gender as a feature, whether any other features can influence the gender feature. This research utilizes 4908 data of the disease predictor using the Feyn Qlattice model. The result implies that gender highly impacts age and hypertension on stroke disease causes. Autorun in Feyn Qlattice model was run with ten epochs, resulting in 17596 test models at 57s. Query string parameter that was focused on age and hypertension features resulted in 1245 models at 4s. An increase of accuracy was found in training metrics from 0.723 to 0.732 and in testing metrics from 0.695 to 0.708. Evaluation results showed that the model is reasonably good as a predictor of stroke disease, indicated with blue lines of AUC in training and testing metrics close to ROC's left side peak curve.

show abstract

Evidential reasoning for preprocessing uncertain categorical data for trustworthy decisions: An application on healthcare and finance

Cited by 50 publications

References 61 publications

The impact of aggregated demand response to energy communities: Results of a community survey in Spain

The impact of aggregated demand response to energy communities: Results of a community survey in Spain

Analyzing the impact of feature selection on the accuracy of heart disease prediction

Linkage Detection of Features that Cause Stroke using Feyn Qlattice Machine Learning Model

Contact Info

Product

Resources

About