An Approach for Anomaly Detection in GPR Data using Machine Learning Techniques

Ozkan-Okay, Merve; Samet, Refik; Stirenko, Sergii

doi:10.3997/2214-4609.2020geo082

Cited by 2 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To maximize “General Accuracy” ( Table 4 ), it was recommended to use the RBF, but the KNN method had some examples of high “Identified Accuracy” ( Table 5 ). KNN is one of the simplest machine learning algorithms [ 38 ], and the RBF is an improvement on it that uses the distance between input and trained datasets to better determine confidence and provide “Unknown” confidences [ 39 ]. This addition appeared to improve the models’ accuracy, as the 10 best models that had “Unknown” classifications had reduced Unclear outputs, regardless of if they were Correct or Incorrect.…”

Section: Resultsmentioning

confidence: 99%

“…While KNN is a commonly used method [38][39] , it is not recommended for this dataset due to the poor performance compared to RBF. Standardizations that were AC-or control-specific are also not recommended, as the highest "General Accuracy" of either was 82.9% for 6pt-control-RBF-"Unanimous" at 82.9% (S1 File).…”

Section: Application Of a Machine Learning Model To Effectively Classify Acsmentioning

confidence: 99%

See 1 more Smart Citation

Reading the ground: Understanding the response of bioelectric microbes to anthropogenic compounds in soil based terrestrial microbial fuel cells

et al. 2021

View full text Add to dashboard Cite

Electrogenic bacteria produce power in soil based terrestrial microbial fuel cells (tMFCs) by growing on electrodes and transferring electrons released from the breakdown of substrates. The direction and magnitude of voltage production is hypothesized to be dependent on the available substrates. A sensor technology was developed for compounds indicative of anthropological activity by exposing tMFCs to gasoline, petroleum, 2,4-dinitrotoluene, fertilizer, and urea. A machine learning classifier was trained to identify compounds based on the voltage patterns. After 5 to 10 days, the mean voltage stabilized (+/- 0.5 mV). After the entire incubation, voltage ranged from -59.1 mV to 631.8 mV, with the tMFCs containing urea and gasoline producing the highest (624 mV) and lowest (-9 mV) average voltage, respectively. The machine learning algorithm effectively discerned between gasoline, urea, and fertilizer with greater than 94% accuracy, demonstrating that this technology could be successfully operated as an environmental sensor for change detection.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Application Of a Machine Learning Model To Effectively Classify Acsmentioning

confidence: 99%

Reading the ground: Understanding the response of bioelectric microbes to anthropogenic compounds in soil based terrestrial microbial fuel cells

et al. 2021

View full text Add to dashboard Cite

show abstract

“…KNN is one of the simplest ML algorithms, [ 81 ] and RBF improves on it by using the distance between the input and the training data set to evaluate confidence and provide “unknown” confidence. [ 82 ] For KNN, the classification of the test input is defined by its K nearest neighbors in the training input, with the majority of the K nearest neighbors having the same classification as the test input. Because the KNN approach fires all neurons, it cannot produce an “unknown” confidence level.…”

Section: Applications Of Machine Learning In Bioelectrocatalysismentioning

confidence: 99%

Machine Learning in Bioelectrocatalysis

Huang,

Gao,

Chang

et al. 2023

Advanced Science

View full text Add to dashboard Cite

At present, the global energy crisis and environmental pollution coexist, and the demand for sustainable clean energy has been highly concerned. Bioelectrocatalysis that combines the benefits of biocatalysis and electrocatalysis produces high‐value chemicals, clean biofuel, and biodegradable new materials. It has been applied in biosensors, biofuel cells, and bioelectrosynthesis. However, there are certain flaws in the application process of bioelectrocatalysis, such as low accuracy/efficiency, poor stability, and limited experimental conditions. These issues can possibly be solved using machine learning (ML) in recent reports although the combination of them is still not mature. To summarize the progress of ML in bioelectrocatalysis, this paper first introduces the modeling process of ML, then focuses on the reports of ML in bioelectrocatalysis, and ultimately makes a summary and outlook about current issues and future directions. It is believed that there is plenty of scope for this interdisciplinary research direction.

show abstract

An Approach for Anomaly Detection in GPR Data using Machine Learning Techniques

Cited by 2 publications

References 7 publications

Reading the ground: Understanding the response of bioelectric microbes to anthropogenic compounds in soil based terrestrial microbial fuel cells

Reading the ground: Understanding the response of bioelectric microbes to anthropogenic compounds in soil based terrestrial microbial fuel cells

Machine Learning in Bioelectrocatalysis

Contact Info

Product

Resources

About