On relationships between imbalance and overlapping of datasets

Almutairi, Waleed A.; Janicki, Ryszard

doi:10.29007/h71z

Cited by 5 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A similar photothermal effect has been observed before when using plasmonic gold nanoparticles, as PTT agent, mixed in butter. [27] Stability of the PTT agents is of extreme importance, as any photodamage will result in poor photothermal conversion. Our results show that the photoactive UCNPs have unmatched photostability ( Figure S4b, Supporting Information), compared to common dyes, and quantum dots, and may be used for PTT in biomedical applications.…”

Section: Resultsmentioning

confidence: 99%

Photothermal Disintegration of 3T3 Derived Fat Droplets by Irradiated Silica Coated Upconversion Nanoparticles

Gupta¹,

Lam²,

et al. 2018

Part & Part Syst Charact

View full text Add to dashboard Cite

Excessive accumulation of fat cells leads to obesity—a predominantly urban public health concern. Photothermal therapy (PTT) can be a novel strategy to control the fat droplets using deep penetrating infra‐red light absorption in upconversion nanoparticles (UCNPs). First, silica (SiO2) coated UCNPs embedded in commercial butter is shown to demonstrate photothermal heating (with photothermal conversion efficiency ≈60%) to gain a maximum temperature rise of ≈26 ºC (to 50 ºC) when exposed to 980 nm laser (5 min, 1 W) irradiation that melts the butter. The same UCNPs @SiO2 are used to study the PTT effect in mouse 3T3 cell derived fat cells in vitro. The 3‐(4,5‐dimethylthiazol‐2‐yl)‐2,5‐diphenyl tetrazolium bromide (MTT) assay on differentiated 3T3 cells reveals low cytotoxicity (cell viability >70%) up to 400 ppm concentration of the UCNP@SiO2. Absorption studies on Oil Red O stained fat droplets, in 3T3 cells incubated with 50 ppm (50 μL) of UCNP@SiO2, shows 50% (untreated control = 100%) decrease of the 510 nm band post irradiation indicating ≈50% of droplet disintegration by PTT. Time lapse videography shows severe droplet agitation resulting in cytoskeletal re‐arrangement in the irradiated, as well as only resistively heated cells with the UCNPs confirming a thermal effect.

show abstract

Section: Resultsmentioning

confidence: 99%

Photothermal Disintegration of 3T3 Derived Fat Droplets by Irradiated Silica Coated Upconversion Nanoparticles

Gupta¹,

Lam²,

et al. 2018

Part & Part Syst Charact

View full text Add to dashboard Cite

show abstract

“…In data imbalance, the overlap is a common problem faced by researchers and becomes a crucial problem when the data is highly skewed ( Vuttipittayamongkol and Elyan, 2020 ). The problem of overlapping is also supported by the results of the paper, which indicate that there is a very strong relationship between class imbalance and class overlap that influences the performance of the classification ( García et al, 2006 ) ( Almutairi and Janicki, 2020 ) ( Stefanowski, 2013 ). One way to overcome overlap is to select instances to be sampled ( Fernández et al, 2018 ).…”

Section: Related Workmentioning

confidence: 65%

Pruning-based oversampling technique with smoothed bootstrap resampling for imbalanced clinical dataset of Covid-19

Wibowo

Fatichah

2022

Journal of King Saud University - Computer and Information Scie

View full text Add to dashboard Cite

The Coronavirus Disease (COVID-19) was declared a pandemic disease by the World Health Organization (WHO), and it has not ended so far. Since the infection rate of the COVID-19 increases, the computational approach is needed to predict patients infected with COVID-19 in order to speed up the diagnosis time and minimize human error compared to conventional diagnoses. However, the number of negative data that is higher than positive data can result in a data imbalance situation that affects the classification performance, resulting in a bias in the model evaluation results. This study proposes a new oversampling technique, i.e., TRIM-SBR, to generate the minor class data for diagnosing patients infected with COVID-19. It is still challenging to develop the oversampling technique due to the data’s generalization issue. The proposed method is based on pruning by looking for specific minority areas while retaining data generalization, resulting in minority data seeds that serve as benchmarks in creating new synthesized data using bootstrap resampling techniques. Accuracy, Specificity, Sensitivity, F-measure, and AUC are used to evaluate classifier performance in data imbalance cases. The results show that the TRIM-SBR method provides the best performance compared to other oversampling techniques.

show abstract

“…Precision is known as Positive Predicted Value (PPV), it represents the percentage of relevant samples that are identified in prediction. It can be computed by divide true (TP) by (TP) plus false positive samples (FP) as shown in Equation 7: precision = XY XYZ\Y (7) Recall is known as True Positive Rate (TPR), it represents the percentage of samples in prediction that are relevant. It can be computed by divide true (TP) by (TP) plus false negative samples (FN) as shown in Equation 8:…”

Section: Resultsmentioning

confidence: 99%

“…Introducing new samples may increase overlapping between classes if the distribution of majority is not taken into consideration, where some of the new samples are produced in the majority class space. This problem known as class overlapping [7]. To avoid data overlapping problems, suitable samples need to be determined as a seed to generate new samples.…”

Section: Introductionmentioning

confidence: 99%

Imbalanced Data Oversampling Technique Based on Convex Combination Method

Elnahas

Hussein

Keshk

2021

IJCI. International Journal of Computers and Information

View full text Add to dashboard Cite

Classification process is the predicting a label for a specific set of inputs. In such process, it is difficult to classify given inputs when a dataset is imbalanced. Most of existing machine learning classifiers suffer from dealing with the imbalanced data, because it makes the classifiers highly biased towards the majority class. This bias may lead to less accuracy in minority class prediction. Data oversampling is one of the most important solutions used to balance the data particularly when dataset is small and/or imbalanced dataset. Synthetic Minority Over-sampling Technique (SMOTE), Borderline-SMOTE, Adaptive Synthetic (ADASYN) and Weighted SMOTE(W-SMOTE) are the most popular techniques used for data oversampling. However, the main drawback of SMOTE and ADASYN techniques is they increase the overlapping between classes and then the produced samples are not representative of the original data distribution. The Borderline-SMOTE may neglect some important samples to produce new samples. To overcome, the problems in the existing over-sampling techniques, in this paper, we propose a new data over-sampling method that depends on the convex combination method to generate new samples of the minority class. The convex combination allows us to produce new samples that have the same original data distribution. We evaluated our approach over four standard imbalanced datasets (Yeast, Glass Identification, Paw, and Wisconsin Prognosis Breast Cancer (WPBC)). The experimental results show that our proposed method gives better performance in terms of accuracy, precision, recall. F1-measure and Area under the curve (AUC).

show abstract

On relationships between imbalance and overlapping of datasets

Cited by 5 publications

References 17 publications

Photothermal Disintegration of 3T3 Derived Fat Droplets by Irradiated Silica Coated Upconversion Nanoparticles

Photothermal Disintegration of 3T3 Derived Fat Droplets by Irradiated Silica Coated Upconversion Nanoparticles

Pruning-based oversampling technique with smoothed bootstrap resampling for imbalanced clinical dataset of Covid-19

Imbalanced Data Oversampling Technique Based on Convex Combination Method

Contact Info

Product

Resources

About