Graphical Models in Reconstructability Analysis and Bayesian Networks

Harris, Marcus; Zwick, Martin

doi:10.3390/e23080986

Cited by 3 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the variables in the backup model (shown in bold) are not the first five individually predictive variables as may be expected due to the condition that the backup model must have 0% missing data. Theoretically the BN method has the potential to perform as well as RA loopless models [28] which were used in this analysis. However, the ABN algorithm resulted in a simpler BN (less degrees of freedom) than the best RA Model.…”

Section: Best Ra Model Point Estimate Resultsmentioning

confidence: 99%

“…In RA, information theory uses the data to characterize the precise nature and the strength of the relations. Data applied to a graph structure yields a probabilistic graphical model of the data (This paragraph from [28]).…”

Section: Reconstructability Analysismentioning

confidence: 99%

“…Discrete variables are most common in BNs, but BNs accommodate continuous variables without discretization [37] (As has been noted, in principle RA could also accommodate continuous variables but this feature has not yet been implemented.). For a three variable BN lattice, there are 5 general graphs and 11 specific graphs; for four variables there are 20 general graphs and 185 specific graphs with unique probability distributions [28]. In the confirmatory mode, BNs can test the significance of a model relative to another model used as a reference [38]; in the exploratory mode, BNs can search for the best possible model given a scoring metric.…”

Section: Bayesian Networkmentioning

confidence: 99%

“…BNs are used to model expert knowledge about uncertainty and causality [32,33] and are also used for exploratory data analysis with no use of expert knowledge [39]. Like RA, BN applications in machine learning and artificial intelligence are broad including classification, prediction, compression, pattern recognition, image processing, time-series, decision analysis and many others (This paragraph from [28]).…”

Section: Bayesian Networkmentioning

confidence: 99%

See 3 more Smart Citations

Machine Learning Predictions of Electricity Capacity

et al. 2022

Self Cite

View full text Add to dashboard Cite

This research applies machine learning methods to build predictive models of Net Load Imbalance for the Resource Sufficiency Flexible Ramping Requirement in the Western Energy Imbalance Market. Several methods are used in this research, including Reconstructability Analysis, developed in the systems community, and more well-known methods such as Bayesian Networks, Support Vector Regression, and Neural Networks. The aims of the research are to identify predictive variables and obtain a new stand-alone model that improves prediction accuracy and reduces the INC (ability to increase generation) and DEC (ability to decrease generation) Resource Sufficiency Requirements for Western Energy Imbalance Market participants. This research accomplishes these aims. The models built in this paper identify wind forecast, sunrise/sunset and the hour of day as primary predictors of net load imbalance, among other variables, and show that the average size of the INC and DEC capacity requirements can be reduced by over 25% with the margin of error currently used in the industry while also significantly improving closeness and exceedance metrics. The reduction in INC and DEC capacity requirements would yield an approximate cost savings of $4 million annually for one of nineteen Western Energy Imbalance market participants. Reconstructability Analysis performs the best among the machine learning methods tested.

show abstract

Section: Best Ra Model Point Estimate Resultsmentioning

confidence: 99%

Section: Reconstructability Analysismentioning

confidence: 99%

Section: Bayesian Networkmentioning

confidence: 99%

Section: Bayesian Networkmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Predictions of Electricity Capacity

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Given an attribute which is the target, the feature's children, parents and co-parents of the target's children forms up together to be the MB of the target. MB encapsulates nodes dependencies and influences within the network, facilitating efficient probabilistic interference [6].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Markov Blanket Based Feature Ranking for Android Malware Detection

Yusfrizal,

Andrian Syahputra,

Yahya Tanjung

et al. 2024

j. of artif. intell. and eng. appl.

View full text Add to dashboard Cite

The ubiquity of Android applications in our daily lives has brought forth an indispensable need for robust app security mechanisms. Malware-infested applications not only jeopardize user privacy but also compromise data integrity and overall device security. Detecting and mitigating malicious behavior within Android applications is becoming increasingly challenging due to the high-dimensional nature of the data. Moving forward, employing Machine Learning (ML) techniques to detect malware in Android apps has become the norm. High dimensional feature space poses several formidable challenges, including data scarcity, over fitting, and heightened computational demands. While dimensionality reduction techniques are a potential remedy, they often result in loss of crucial information essential for comprehending and identifying malicious behaviors accurately. Feature ranking based feature subset selection emerges as a promising alternative, as it allows us to retain the original feature space, ensuring precise representation of app behaviors. This article explores various Markov Blanket (MB) based feature ranking techniques, proposes a variant of Grow Shrink (GS) MB technique, GS++ which demonstrates enhanced performance within the context of Android malware detection.

show abstract

Information-Theoretic Modeling of Categorical Spatiotemporal GIS Data

Percy,

Zwick

2024

Entropy

View full text Add to dashboard Cite

An information-theoretic data mining method is employed to analyze categorical spatiotemporal Geographic Information System land use data. Reconstructability Analysis (RA) is a maximum-entropy-based data modeling methodology that works exclusively with discrete data such as those in the National Land Cover Database (NLCD). The NLCD is organized into a spatial (raster) grid and data are available in a consistent format for every five years from 2001 to 2021. An NLCD tool reports how much change occurred for each category of land use; for the study area examined, the most dynamic class is Evergreen Forest (EFO), so the presence or absence of EFO in 2021 was chosen as the dependent variable that our data modeling attempts to predict. RA predicts the outcome with approximately 80% accuracy using a sparse set of cells from a spacetime data cube consisting of neighboring lagged-time cells. When the predicting cells are all Shrubs and Grasses, there is a high probability for a 2021 state of EFO, while when the predicting cells are all EFO, there is a high probability that the 2021 state will not be EFO. These findings are interpreted as detecting forest clear-cut cycles that show up in the data and explain why this class is so dynamic. This study introduces a new approach to analyzing GIS categorical data and expands the range of applications that this entropy-based methodology can successfully model.

show abstract

Graphical Models in Reconstructability Analysis and Bayesian Networks

Cited by 3 publications

References 31 publications

Machine Learning Predictions of Electricity Capacity

Machine Learning Predictions of Electricity Capacity

Analysis of Markov Blanket Based Feature Ranking for Android Malware Detection

Information-Theoretic Modeling of Categorical Spatiotemporal GIS Data

Contact Info

Product

Resources

About