To see the other types of publications on this topic, follow the link: Minority class boosted framework.
Journal articles on the topic 'Minority class boosted framework'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Minority class boosted framework.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Zhang, Jue, Li Chen, and Fazeel Abid. "Prediction of Breast Cancer from Imbalance Respect Using Cluster-Based Undersampling Method." Journal of Healthcare Engineering 2019 (October 16, 2019): 1–10. http://dx.doi.org/10.1155/2019/7294582.
Full textAbstract:
To overcome the two-class imbalanced problem existing in the diagnosis of breast cancer, a hybrid of K-means and Boosted C5.0 (K-Boosted C5.0) is proposed which is based on undersampling. K-means is utilized to select the informative samples near the boundary. During the training phase, the K-means algorithm clusters the majority and minority instances and selects a similar number of instances from each cluster. Boosted C5.0 is then used as the classifier. As there is one different instance selection factor via clustering that encourages the diversity of the training subspace in K-Boosted C5.0, it would be a great advantage to get better performance. To test the performance of the new hybrid classifier, it is implemented on 12 small-scale and 2 large-scale datasets, which are the often used datasets in class imbalanced learning. The extensive experimental results show that our proposed hybrid method outperforms most of the competitive algorithms in terms of Matthews’ correlation coefficient (MCC) and accuracy indices. It can be a good alternative to the well-known machine learning methods.
2
Lee, Sunbok, and Jae Young Chung. "The Machine Learning-Based Dropout Early Warning System for Improving the Performance of Dropout Prediction." Applied Sciences 9, no. 15 (July 31, 2019): 3093. http://dx.doi.org/10.3390/app9153093.
Full textAbstract:
A dropout early warning system enables schools to preemptively identify students who are at risk of dropping out of school, to promptly react to them, and eventually to help potential dropout students to continue their learning for a better future. However, the inherent class imbalance between dropout and non-dropout students could pose difficulty in building accurate predictive modeling for a dropout early warning system. The present study aimed to improve the performance of a dropout early warning system: (a) by addressing the class imbalance issue using the synthetic minority oversampling techniques (SMOTE) and the ensemble methods in machine learning; and (b) by evaluating the trained classifiers with both receiver operating characteristic (ROC) and precision–recall (PR) curves. To that end, we trained random forest, boosted decision tree, random forest with SMOTE, and boosted decision tree with SMOTE using the big data samples of the 165,715 high school students from the National Education Information System (NEIS) in South Korea. According to our ROC and PR curve analysis, boosted decision tree showed the optimal performance.
3
Stanton-Salazar, Ricardo. "A Social Capital Framework for Understanding the Socialization of Racial Minority Children and Youths." Harvard Educational Review 67, no. 1 (January 1, 1997): 1–41. http://dx.doi.org/10.17763/haer.67.1.140676g74018u73k.
Full textAbstract:
In this article, Ricardo Stanton-Salzar offers a network-analytic framework for understanding the socialization and schooling experiences of working-class racial minority youth. Unlike many previous writers who have examined the role of "significant others," he examines the role that relationships between youth and institutional agents, such as teachers and counselors, play in the greater multicultural context in which working-class minority youth must negotiate. Stanton-Salazar provides the conceptual foundations of a framework built around the concepts of social capital and institutional support. He concentrates on illuminating those institutional and ideological forces that he believes make access to social capital and institutional support within schools and other institutional settings so problematic for working-class minority children and adolescents. Stanton-Salazar also provides some clues as to how some working-class minority youth are able to manage their difficult participation in multiple worlds, how they develop cultural strategies for overcoming various obstacles, and how they manage to develop sustaining and supportive relationships with institutional agents.
4
Lin, Hsien-I., and Mihn Cong Nguyen. "Boosting Minority Class Prediction on Imbalanced Point Cloud Data." Applied Sciences 10, no. 3 (February 2, 2020): 973. http://dx.doi.org/10.3390/app10030973.
Full textAbstract:
Data imbalance during the training of deep networks can cause the network to skip directly to learning minority classes. This paper presents a novel framework by which to train segmentation networks using imbalanced point cloud data. PointNet, an early deep network used for the segmentation of point cloud data, proved effective in the point-wise classification of balanced data; however, performance degraded when imbalanced data was used. The proposed approach involves removing between-class data point imbalances and guiding the network to pay more attention to majority classes. Data imbalance is alleviated using a hybrid-sampling method involving oversampling, as well as undersampling, respectively, to decrease the amount of data in majority classes and increase the amount of data in minority classes. A balanced focus loss function is also used to emphasize the minority classes through the automated assignment of costs to the various classes based on their density in the point cloud. Experiments demonstrate the effectiveness of the proposed training framework when provided a point cloud dataset pertaining to six objects. The mean intersection over union (mIoU) test accuracy results obtained using PointNet training were as follows: XYZRGB data (91%) and XYZ data (86%). The mIoU test accuracy results obtained using the proposed scheme were as follows: XYZRGB data (98%) and XYZ data (93%).
5
Krishnan, Ulagapriya, and Pushpa Sangar. "A Rebalancing Framework for Classification of Imbalanced Medical Appointment No-show Data." Journal of Data and Information Science 6, no. 1 (January 27, 2021): 178–92. http://dx.doi.org/10.2478/jdis-2021-0011.
Full textAbstract:
Abstract Purpose This paper aims to improve the classification performance when the data is imbalanced by applying different sampling techniques available in Machine Learning. Design/methodology/approach The medical appointment no-show dataset is imbalanced, and when classification algorithms are applied directly to the dataset, it is biased towards the majority class, ignoring the minority class. To avoid this issue, multiple sampling techniques such as Random Over Sampling (ROS), Random Under Sampling (RUS), Synthetic Minority Oversampling TEchnique (SMOTE), ADAptive SYNthetic Sampling (ADASYN), Edited Nearest Neighbor (ENN), and Condensed Nearest Neighbor (CNN) are applied in order to make the dataset balanced. The performance is assessed by the Decision Tree classifier with the listed sampling techniques and the best performance is identified. Findings This study focuses on the comparison of the performance metrics of various sampling methods widely used. It is revealed that, compared to other techniques, the Recall is high when ENN is applied CNN and ADASYN have performed equally well on the Imbalanced data. Research limitations The testing was carried out with limited dataset and needs to be tested with a larger dataset. Practical implications This framework will be useful whenever the data is imbalanced in real world scenarios, which ultimately improves the performance. Originality/value This paper uses the rebalancing framework on medical appointment no-show dataset to predict the no-shows and removes the bias towards minority class.
6
Asam, Muhammad, Shaik Javeed Hussain, Mohammed Mohatram, Saddam Hussain Khan, Tauseef Jamal, Amad Zafar, Asifullah Khan, Muhammad Umair Ali, and Umme Zahoora. "Detection of Exceptional Malware Variants Using Deep Boosted Feature Spaces and Machine Learning." Applied Sciences 11, no. 21 (November 8, 2021): 10464. http://dx.doi.org/10.3390/app112110464.
Full textAbstract:
Malware is a key component of cyber-crime, and its analysis is the first line of defence against cyber-attack. This study proposes two new malware classification frameworks: Deep Feature Space-based Malware classification (DFS-MC) and Deep Boosted Feature Space-based Malware classification (DBFS-MC). In the proposed DFS-MC framework, deep features are generated from the customized CNN architectures and are fed to a support vector machine (SVM) algorithm for malware classification, while, in the DBFS-MC framework, the discrimination power is enhanced by first combining deep feature spaces of two customized CNN architectures to achieve boosted feature spaces. Further, the detection of exceptional malware is performed by providing the deep boosted feature space to SVM. The performance of the proposed malware classification frameworks is evaluated on the MalImg malware dataset using the hold-out cross-validation technique. Malware variants like Autorun.K, Swizzor.gen!I, Wintrim.BX and Yuner.A is hard to be correctly classified due to their minor inter-class differences in their features. The proposed DBFS-MC improved performance for these difficult to discriminate malware classes using the idea of feature boosting generated through customized CNNs. The proposed classification framework DBFS-MC showed good results in term of accuracy: 98.61%, F-score: 0.96, precision: 0.96, and recall: 0.96 on stringent test data, using 40% unseen data.
7
Kakkar, Misha, Sarika Jain, Abhay Bansal, and P. S. Grover. "Nonlinear Geometric Framework for Software Defect Prediction." International Journal of Decision Support System Technology 12, no. 3 (July 2020): 85–100. http://dx.doi.org/10.4018/ijdsst.2020070105.
Full textAbstract:
Humans use the software in every walk of life thus it is essential to have the best quality software. Software defect prediction models assist in identifying defect prone modules with the help of historical data, which in turn improves software quality. Historical data consists of data related to modules /files/classes which are labeled as buggy or clean. As the number of buggy artifacts as less as compared to clean artifacts, the nature of historical data becomes imbalance. Due to this uneven distribution of the data, it difficult for classification algorithms to build highly effective SDP models. The objective of this study is to propose a new nonlinear geometric framework based on SMOTE and ensemble learning to improve the performance of SDP models. The study combines the traditional SMOTE algorithm and the novel ensemble Support Vector Machine (SVM) is used to develop the proposed framework called SMEnsemble. SMOTE algorithm handles the class imbalance problem by generating synthetic instances of the minority class. Ensemble learning generates multiple classification models to select the best performing SDP model. For experimentation, datasets from three different software repositories that contain both open source as well as proprietary projects are used in the study. The results show that SMEnsemble performs better than traditional methods for identifying the minority class i.e. buggy artifacts. Also, the proposed model performance is better than the latest state of Art SDP model- SMOTUNED. The proposed model is capable of handling imbalance classes when compared with traditional methods. Also, by carefully selecting the number of ensembles high performance can be achieved in less time.
8
Lin, Christopher, Mausam Mausam, and Daniel Weld. "Active Learning with Unbalanced Classes and Example-Generation Queries." Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 6 (June 15, 2018): 98–107. http://dx.doi.org/10.1609/hcomp.v6i1.13334.
Full textAbstract:
Machine learning in real-world high-skew domains is difficult, because traditional strategies for crowdsourcing labeled training examples are ineffective at locating the scarce minority-class examples. For example, both random sampling and traditional active learning (which reduces to random sampling when just starting) will most likely recover very few minority-class examples. To bootstrap the machine learning process, researchers have proposed tasking the crowd with finding or generating minority-class examples, but such strategies have their weaknesses as well. They are unnecessarily expensive in well-balanced domains, and they often yield samples from a biased distribution that is unrepresentative of the one being learned.This paper extends the traditional active learning framework by investigating the problem of intelligently switching between various crowdsourcing strategies for obtaining labeled training examples in order to optimally train a classifier. We start by analyzing several such strategies (e.g., annotate an example, generate a minority-class example, etc.), and then develop a novel, skew-robust algorithm, called MB-CB, for the control problem. Experiments show that our method outperforms state-of-the-art GL-Hybrid by up to 14.3 points in F1 AUC, across various domains and class-frequency settings.
9
Wu, Kaiyuan, Zhiming Zheng, and Shaoting Tang. "BVDT: A Boosted Vector Decision Tree Algorithm for Multi-Class Classification Problems." International Journal of Pattern Recognition and Artificial Intelligence 31, no. 05 (February 27, 2017): 1750016. http://dx.doi.org/10.1142/s0218001417500161.
Full textAbstract:
In this paper, we propose a powerful weak learner (Vector Decision Tree (VDT)) and a new Boosted Vector Decision Tree (BVDT) algorithm framework for the task of multi-class classification. Unlike the traditional scalar valued boosting algorithms, the BVDT algorithm directly maps the feature space to the decision space in the multi-class setting, which facilitates convenient implementations of the multi-class classification algorithms using diverse loss functions. By viewing the explicit hard threshold on the leaf node value applied in the LogitBoost as a constraint optimization problem, we further develop two new variants of the BVDT algorithm: the [Formula: see text]-BVDT and the [Formula: see text]-BVDT. The performance of the proposed algorithm is evaluated on different datasets and compared with three state-of-the-art boosting algorithms, [Formula: see text]-Nearest Neighbor (KNN) and Support Vector Machine (SVM). The results show that the performance of the proposed algorithm ranks first in all but one dataset and reduces the test error rate by 4% up to 58% with respect to the state-of-the-art boosting algorithms based on the scalar-valued weak learner. Furthermore, we present a case study on the Abalone dataset by designing a new loss function that combines the negative log-likelihood loss function of classification problem and square loss function of regression problem.
10
Wang, Ke, Qingwen Xue, and Jian John Lu. "Risky Driver Recognition with Class Imbalance Data and Automated Machine Learning Framework." International Journal of Environmental Research and Public Health 18, no. 14 (July 15, 2021): 7534. http://dx.doi.org/10.3390/ijerph18147534.
Full textAbstract:
Identifying high-risk drivers before an accident happens is necessary for traffic accident control and prevention. Due to the class-imbalance nature of driving data, high-risk samples as the minority class are usually ill-treated by standard classification algorithms. Instead of applying preset sampling or cost-sensitive learning, this paper proposes a novel automated machine learning framework that simultaneously and automatically searches for the optimal sampling, cost-sensitive loss function, and probability calibration to handle class-imbalance problem in recognition of risky drivers. The hyperparameters that control sampling ratio and class weight, along with other hyperparameters, are optimized by Bayesian optimization. To demonstrate the performance of the proposed automated learning framework, we establish a risky driver recognition model as a case study, using video-extracted vehicle trajectory data of 2427 private cars on a German highway. Based on rear-end collision risk evaluation, only 4.29% of all drivers are labeled as risky drivers. The inputs of the recognition model are the discrete Fourier transform coefficients of target vehicle’s longitudinal speed, lateral speed, and the gap between the target vehicle and its preceding vehicle. Among 12 sampling methods, 2 cost-sensitive loss functions, and 2 probability calibration methods, the result of automated machine learning is consistent with manual searching but much more computation-efficient. We find that the combination of Support Vector Machine-based Synthetic Minority Oversampling TEchnique (SVMSMOTE) sampling, cost-sensitive cross-entropy loss function, and isotonic regression can significantly improve the recognition ability and reduce the error of predicted probability.
11
Allan, Blake A., Elliot A. Tebbe, Lauren M. Bouchard, and Ryan D. Duffy. "Access to Decent and Meaningful Work in a Sexual Minority Population." Journal of Career Assessment 27, no. 3 (February 14, 2018): 408–21. http://dx.doi.org/10.1177/1069072718758064.
Full textAbstract:
People who identify as sexual minorities consistently face barriers to decent and meaningful employment, especially when coupled with additional constraints such as low socioeconomic status or marginalization experiences. Drawing from the psychology of working theory as our theoretical framework, this study examined the relations of economic constraints (social class) and marginalization (negative sexual minority workplace climate) to work volition, decent work, and meaningful work with a sample of working adults identifying with sexual minority identities. Consistent with hypotheses, social class and workplace climate indirectly predicted decent work, via work volition, and workplace climate also directly predicted decent work. Decent work and work volition were each direct predictors of meaningful work and decent work partially mediated the relation of work volition to meaningful work. Results highlight the importance of advocacy and adequate workplace supports for sexual minority individuals.
12
Brennan, Michael J. "The Environmental Roots of Urban Renewal in Boston." Journal of Urban History 45, no. 1 (April 6, 2017): 23–43. http://dx.doi.org/10.1177/0096144217701259.
Full textAbstract:
This essay argues that discourse related to residents of Boston’s South End as environmental agents justified the removal of minority and working-class residents from the neighborhood, and, in particular, the New York Streets section in the 1950s. It combines analytical approaches of urban ecology and traditional elements of social history to examine how the neighborhood orientated to the city in an economic sense, how residents created a mixed-use neighborhood, how social institutions functioned as contested spaces of cultural production, how settlement house workers created a framework of discourse about the South End, how negative perceptions of working-class and minority residents coalesced across American life, and how city officials activated the discourse to create the first steps of urban renewal in Boston. The conclusion examines how minority groups understood environmental factors to be central to urban renewal and how social justice groups took an environmental focus in their activism.
13
Zeytinoglu, Isik Urla, and Jacinta Khasiala Muteshi. "Gender, Race and Class Dimensions of Nonstandard Work." Articles 55, no. 1 (April 12, 2005): 133–67. http://dx.doi.org/10.7202/051294ar.
Full textAbstract:
This review article critically analyzes and synthesizes the academic literature on nonstandard work and its gender, race and class dimensions. We argue that it is important and crucial to understand these dimensions of nonstandard work in order to develop appropriate labour policies. We present our discussion in a conceptual framework of duality within which nonstandard workforms are located. We discuss the role the unions could play in achieving equity in labour markets and conclude the paper with recommended labour policy changes to respond to the needs of women, particularly those racial minority and low economic class women employed in nonstandard jobs.
14
Peiwen, Lu, Huang Yongjing, and Khushnood Abbas. "Transformers Fault Prediction: An Improved Ensembled Method." International Journal of Electronics and Electrical Engineering 8, no. 4 (December 2020): 82–87. http://dx.doi.org/10.18178/ijeee.8.4.82-87.
Full textAbstract:
In this study we present a data driven prediction approach to early prediction of transformer’s fault. To make such prediction we have collected dissolve gas data of transformer. We have solved this problem bagging based ensembled algorithm. Further we have found that our data has imbalanced class examples. To overcome this, we have removed class bias by using Synthetic Minority Over Sampling Technology (SMOTE). SMOTE is best known for generating synthetic data for minority classes. It is also proven to be better than random sampling. SMOTE oversamples the minority classes data by fitting the linear lines among them. In that way we can generate as many data as we want. Thus, it helped us in avoiding overfitting problem. Our empirical results show that proposed framework outperforms the state-of-the-art methods such as BP neural network, and support vector machine. Our method achieves 90.67 % precision accuracy which is better than the base lines.
15
Barrios, Mauricio, Miguel Jimeno, Pedro Villalba, and Edgar Navarro. "Framework to Diagnose the Metabolic Syndrome Types without Using a Blood Test Based on Machine Learning." Applied Sciences 10, no. 23 (November 26, 2020): 8404. http://dx.doi.org/10.3390/app10238404.
Full textAbstract:
Metabolic Syndrome (MetS) is a set of risk factors that increase the probability of heart disease or even diabetes mellitus. The diagnosis of the pathology implies compliance with at least three of five risk factors. Doctors obtain two of those factors in a medical consultation: waist circumference and blood pressure. The other three factors are biochemical variables that require a blood test to determine triglyceride, high-density lipoprotein cholesterol, and fasting plasma glucose. Consequently, scientists are developing technology for non-invasive diagnostics, but medical personnel also need the risk factors involved in MetS to start a treatment. This paper describes the segmentation of MetS into ten types based on harmonized Metabolic Syndrome criteria. It proposes a framework to diagnose the types of MetS based on Artificial Neural Networks and Random undersampling Boosted tree using non-biochemical variables such as anthropometric and clinical information. The framework works over imbalanced and balanced datasets using the Synthetic Minority Oversampling Technique and for validation uses random subsampling to get performance evaluation indicators between the classifiers. The results showed an excellent framework for diagnosing the 10 MetS types that have Area under Receiver Operating Characteristic (AROC) curves with a range of 71% to 93% compared with AROC 82.86% from traditional MetS.
16
Louk, Maya Hilda Lestari, and Bayu Adhi Tama. "Exploring Ensemble-Based Class Imbalance Learners for Intrusion Detection in Industrial Control Networks." Big Data and Cognitive Computing 5, no. 4 (December 6, 2021): 72. http://dx.doi.org/10.3390/bdcc5040072.
Full textAbstract:
Classifier ensembles have been utilized in the industrial cybersecurity sector for many years. However, their efficacy and reliability for intrusion detection systems remain questionable in current research, owing to the particularly imbalanced data issue. The purpose of this article is to address a gap in the literature by illustrating the benefits of ensemble-based models for identifying threats and attacks in a cyber-physical power grid. We provide a framework that compares nine cost-sensitive individual and ensemble models designed specifically for handling imbalanced data, including cost-sensitive C4.5, roughly balanced bagging, random oversampling bagging, random undersampling bagging, synthetic minority oversampling bagging, random undersampling boosting, synthetic minority oversampling boosting, AdaC2, and EasyEnsemble. Each ensemble’s performance is tested against a range of benchmarked power system datasets utilizing balanced accuracy, Kappa statistics, and AUC metrics. Our findings demonstrate that EasyEnsemble outperformed significantly in comparison to its rivals across the board. Furthermore, undersampling and oversampling strategies were effective in a boosting-based ensemble but not in a bagging-based ensemble.
17
De Jager, Koos-jan. "Die Mij tergen, hebben verzekeringen." Religie & Samenleving 13, no. 2 (May 1, 2018): 87–106. http://dx.doi.org/10.54195/rs.11853.
Full textAbstract:
In 1919, the Disability Law came into force as part of the Dutch social insurance system. Goal of the law was to protect the working class against financial losses due to an industrial accident. The so-called ‘bevindelijk’ (pietistic) gereformeerden, a minority group of ultraorthodox protestants had religious objections against the law. Founder and political leader of the SGP (Reformed Political Party) G.H. Kersten led the protest movement against the assurance laws. He insisted to his followers that they should not take part in the administrative preparations for the Disability Law and presented a petition to the minister, who on his turn prepared an exception for the conscientious objectors, which took effect in December 1920. After 1919, G.H. Kersten became the spokesperson of the conscientious objectors, asking the minister for exceptions for his group. Officials of the ministry observed that it seemed that Kersten strongly boosted the conscientious objections among his followers, since some of them became conscientious objectors only after Kersten made it into a political battle cry. The political actions against the Disability Law offer a new perspective to the history of the bevindelijk gereformeerden and the SGP. This can be described as subjectification, the process when a minority group becomes aware of its own existence and claims a place in the political and religious order. Kersten constructed his bevindelijk gereformeerde minority group, which did before only exist as small, scattered communities of orthodox protestants. He successfully claimed a place for his group on the Dutch political scene.
18
Duan, Huajuan, Yongqing Wei, Peiyu Liu, and Hongxia Yin. "A Novel Ensemble Framework Based on K-Means and Resampling for Imbalanced Data." Applied Sciences 10, no. 5 (March 2, 2020): 1684. http://dx.doi.org/10.3390/app10051684.
Full textAbstract:
Imbalanced classification is one of the most important problems of machine learning and data mining, existing in many real datasets. In the past, many basic classifiers such as SVM, KNN, and so on have been used for imbalanced datasets in which the number of one sample is larger than that of another, but the classification effect is not ideal. Some data preprocessing methods have been proposed to reduce the imbalance ratio of data sets and combine with the basic classifiers to get better performance. In order to improve the whole classification accuracy, we propose a novel classifier ensemble framework based on K-means and resampling technique (EKR). First, we divide the data samples in the majority class into several sub-clusters using K-means, k-value is determined by Average Silhouette Coefficient, and then adjust the number of data samples of each sub-cluster to be the same as that of the minority classes through resampling technology, after that each adjusted sub-cluster and the minority class are combined into several balanced subsets, the base classifier is trained on each balanced subset separately, and finally integrated into a strong ensemble classifier. In this paper, the extensive experimental results on 16 imbalanced datasets demonstrate the effectiveness and feasibility of the proposed algorithm in terms of multiple evaluation criteria, and EKR can achieve better performance when compared with several classical imbalanced classification algorithms using different data preprocessing methods.
19
Almuayqil, Saleh Naif, Mamoona Humayun, N. Z. Jhanjhi, Maram Fahaad Almufareh, and Danish Javed. "Framework for Improved Sentiment Analysis via Random Minority Oversampling for User Tweet Review Classification." Electronics 11, no. 19 (September 25, 2022): 3058. http://dx.doi.org/10.3390/electronics11193058.
Full textAbstract:
Social networks such as twitter have emerged as social platforms that can impart a massive knowledge base for people to share their unique ideas and perspectives on various topics and issues with friends and families. Sentiment analysis based on machine learning has been successful in discovering the opinion of the people using redundantly available data. However, recent studies have pointed out that imbalanced data can have a negative impact on the results. In this paper, we propose a framework for improved sentiment analysis through various ordered preprocessing steps with the combination of resampling of minority classes to produce greater performance. The performance of the technique can vary depending on the dataset as its initial focus is on feature selection and feature combination. Multiple machine learning algorithms are utilized for the classification of tweets into positive, negative, or neutral. Results have revealed that random minority oversampling can provide improved performance and it can tackle the issue of class imbalance.
20
Gharagozlou, Hamid, Javad Mohammadzadeh, Azam Bastanfard, and Saeed Shiry Ghidary. "RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm." Computational Intelligence and Neuroscience 2022 (May 6, 2022): 1–21. http://dx.doi.org/10.1155/2022/7839840.
Full textAbstract:
Answer selection (AS) is a critical subtask of the open-domain question answering (QA) problem. The present paper proposes a method called RLAS-BIABC for AS, which is established on attention mechanism-based long short-term memory (LSTM) and the bidirectional encoder representations from transformers (BERT) word embedding, enriched by an improved artificial bee colony (ABC) algorithm for pretraining and a reinforcement learning-based algorithm for training backpropagation (BP) algorithm. BERT can be comprised in downstream work and fine-tuned as a united task-specific architecture, and the pretrained BERT model can grab different linguistic effects. Existing algorithms typically train the AS model with positive-negative pairs for a two-class classifier. A positive pair contains a question and a genuine answer, while a negative one includes a question and a fake answer. The output should be one for positive and zero for negative pairs. Typically, negative pairs are more than positive, leading to an imbalanced classification that drastically reduces system performance. To deal with it, we define classification as a sequential decision-making process in which the agent takes a sample at each step and classifies it. For each classification operation, the agent receives a reward, in which the prize of the majority class is less than the reward of the minority class. Ultimately, the agent finds the optimal value for the policy weights. We initialize the policy weights with the improved ABC algorithm. The initial value technique can prevent problems such as getting stuck in the local optimum. Although ABC serves well in most tasks, there is still a weakness in the ABC algorithm that disregards the fitness of related pairs of individuals in discovering a neighboring food source position. Therefore, this paper also proposes a mutual learning technique that modifies the produced candidate food source with the higher fitness between two individuals selected by a mutual learning factor. We tested our model on three datasets, LegalQA, TrecQA, and WikiQA, and the results show that RLAS-BIABC can be recognized as a state-of-the-art method.
21
Karim, Abdul, Zheng Su, Phillip K. West, Matthew Keon, Jannah Shamsani, Samuel Brennan, Ted Wong, et al. "Molecular Classification and Interpretation of Amyotrophic Lateral Sclerosis Using Deep Convolution Neural Networks and Shapley Values." Genes 12, no. 11 (October 30, 2021): 1754. http://dx.doi.org/10.3390/genes12111754.
Full textAbstract:
Amyotrophic lateral sclerosis (ALS) is a prototypical neurodegenerative disease characterized by progressive degeneration of motor neurons to severely effect the functionality to control voluntary muscle movement. Most of the non-additive genetic aberrations responsible for ALS make its molecular classification very challenging along with limited sample size, curse of dimensionality, class imbalance and noise in the data. Deep learning methods have been successful in many other related areas but have low minority class accuracy and suffer from the lack of explainability when used directly with RNA expression features for ALS molecular classification. In this paper, we propose a deep-learning-based molecular ALS classification and interpretation framework. Our framework is based on training a convolution neural network (CNN) on images obtained from converting RNA expression values into pixels based on DeepInsight similarity technique. Then, we employed Shapley additive explanations (SHAP) to extract pixels with higher relevance to ALS classifications. These pixels were mapped back to the genes which made them up. This enabled us to classify ALS samples with high accuracy for a minority class along with identifying genes that might be playing an important role in ALS molecular classifications. Taken together with RNA expression images classified with CNN, our preliminary analysis of the genes identified by SHAP interpretation demonstrate the value of utilizing Machine Learning to perform molecular classification of ALS and uncover disease-associated genes.
22
Duan, Yijun, Xin Liu, Adam Jatowt, Hai-tao Yu, Steven Lynden, Kyoung-Sook Kim, and Akiyoshi Matono. "SORAG: Synthetic Data Over-Sampling Strategy on Multi-Label Graphs." Remote Sensing 14, no. 18 (September 8, 2022): 4479. http://dx.doi.org/10.3390/rs14184479.
Full textAbstract:
In many real-world networks of interest in the field of remote sensing (e.g., public transport networks), nodes are associated with multiple labels, and node classes are imbalanced; that is, some classes have significantly fewer samples than others. However, the research problem of imbalanced multi-label graph node classification remains unexplored. This non-trivial task challenges the existing graph neural networks (GNNs) because the majority class can dominate the loss functions of GNNs and result in the overfitting of the majority class features and label correlations. On non-graph data, minority over-sampling methods (such as the synthetic minority over-sampling technique and its variants) have been demonstrated to be effective for the imbalanced data classification problem. This study proposes and validates a new hypothesis with unlabeled data over-sampling, which is meaningless for imbalanced non-graph data; however, feature propagation and topological interplay mechanisms between graph nodes can facilitate the representation learning of imbalanced graphs. Furthermore, we determine empirically that ensemble data synthesis through the creation of virtual minority samples in the central region of a minority and generation of virtual unlabeled samples in the boundary region between a minority and majority is the best practice for the imbalanced multi-label graph node classification task. Our proposed novel data over-sampling framework is evaluated using multiple real-world network datasets, and it outperforms diverse, strong benchmark models by a large margin.
23
Alabrah, Amerah. "A Novel Study: GAN-Based Minority Class Balancing and Machine-Learning-Based Network Intruder Detection Using Chi-Square Feature Selection." Applied Sciences 12, no. 22 (November 16, 2022): 11662. http://dx.doi.org/10.3390/app122211662.
Full textAbstract:
The network security problem becomes a routine problem for networks and cyber security specialists. The increased data on every minute not only creates big data problems, but also it expands the network size on the cloud and other computing technologies. Due to the big size and data, the network becomes more vulnerable to cyber-attacks. However, the detection of cyber-attacks on networks before or on time is a challenging task to solve. Therefore, the network intruder detection system (NIDS) is used to detect it. The network provided data-based NIDS were proposed previously, but still needed improvements. From the network data, it is also essential to find the most contributing features to avoid overfitting and lack of confidence in NIDS. The previously proposed solutions of NIDS mostly ignored the class imbalance problems that were normally found in the training of machine learning (ML) methods used in NIDS. However, few studies have tried to solve class imbalance and feature selection separately by achieving significant results on different datasets. The performance of these NIDS needs improvements in terms of classification and class balancing robust solutions. Therefore, to solve the class imbalance problem of minority classes in public datasets of NIDS and to select the most significant features, the proposed study gives a framework. In this framework, the minority class instances are generated using Generative Adversarial Network (GAN) model hyperparameter optimization and then the chi-square method of feature selection is applied to the fed six ML classifiers. The binary and multi-class classifications are applied on the UNSW-NB15 dataset with three versions of it. The comparative analysis on binary, multi-class classifications showed dominance as compared to previous studies in terms of accuracy (98.14%, 87.44%), precision (98.14%, 87.81%), F1-score (98.14%, 86.79%), Geometric-Mean (0.976, 0.923) and Area Under Cover (0.976, 0.94).
24
Wu, Jheng-Long, and Shuoyen Huang. "Application of Generative Adversarial Networks and Shapley Algorithm Based on Easy Data Augmentation for Imbalanced Text Data." Applied Sciences 12, no. 21 (October 29, 2022): 10964. http://dx.doi.org/10.3390/app122110964.
Full textAbstract:
Imbalanced data constitute an extensively studied problem in the field of machine learning classification because they result in poor training outcomes. Data augmentation is a method for increasing minority class diversity. In the field of text data augmentation, easy data augmentation (EDA) is used to generate additional data that would otherwise lack diversity and exhibit monotonic sentence patterns. Generative adversarial network (GAN) models can generate diverse sentence patterns by using the probability corresponding to each word in a language model. Therefore, hybrid EDA and GAN models can generate highly diverse and appropriate sentence patterns. This study proposes a hybrid framework that employs a generative adversarial network and Shapley algorithm based on easy data augmentation (HEGS) to improve classification performance. The experimental results reveal that the HEGS framework can generate highly diverse training sentences to form balanced text data and improve text classification performance for minority classes.
25
Escalante, Cesar L., Rodney L. Brooks, James E. Epperson, and Forrest E. Stegelin. "Credit Risk Assessment and Racial Minority Lending at the Farm Service Agency." Journal of Agricultural and Applied Economics 38, no. 1 (April 2006): 61–75. http://dx.doi.org/10.1017/s1074070800022070.
Full textAbstract:
The nature of credit risk assessment and basis of loan approval decisions of the Farm Service Agency are analyzed in the aftermath of the black farmers' 1997 class action suit against the U.S. Department of Agriculture. This study did not uncover convincing evidence of racial discrimination against nonwhite borrowers under a binomial logistic framework based on the probability of a loan application's approval. Moreover, the collective use of more stringent and objective credit-scoring measures usually employed by commercial lenders is less evident in the Farm Service Agency's evaluation of loan applications.
26
Kao, Robert M. "Helping Students SOAR: Quizfolio Tips to Engage First-Generation, Under-Represented Minority Undergraduates in Scientific Inquiry." American Biology Teacher 80, no. 3 (March 1, 2018): 228–34. http://dx.doi.org/10.1525/abt.2018.80.3.228.
Full textAbstract:
Engaging and gauging (engauging) first-generation, under-represented minority undergraduate general biology students through processes of inquiry, critical thinking, and affective learning is vital as they develop their scientific identity. An important challenge is how we can establish communities of practice and instill in our first-generation students self-awareness and reflection as they apply, analyze, and evaluate data on biological principles. In my article, I describe an innovative weekly assignment for my first generation Hispanic and Native Indigenous students called Quizfolio: quiz and mini-portfolios on biological principles and themes outlined in Vision and Change. Within a SOAR framework that will be introduced in my article, quizfolios provide an active learning space for students to integrate inclusive student-centered, in-class discussions and longitudinal lab inquiries in a first-year undergraduate biology course through metacognition and reflection-in-action. This transformative, culturally responsive mentoring approach encourages first-generation undergraduates to bring self-awareness to unclear or confusing topics that are clarified at the start of class or lab settings, and provides future framework for long-term retention of biological concepts.
27
Jian, Ming, and Rony Lim. "Minority shareholders dispute tang Plaza’s value." CASE Journal 16, no. 4 (August 6, 2020): 455–74. http://dx.doi.org/10.1108/tcj-03-2019-0025.
Full textAbstract:
Theoretical basis This case covers the framework and process to determine fair value as specified in International Financial Reporting Standards (IFRS) 13. It illustrates an instance in which auditors interpret the concept of fair value to be consistent with other principles in standards such as the principle of prudence in the conceptual framework. In addition, a lot of the discussion in the case is applicable to accounting education in any regulatory jurisdictions given the convergence of US generally accepted accounting principles (GAAP) and IFRS 13. In addition, while fair value accounting may have been designed to give investors more useful information, in practise it could involve highly subjective judgement and the resulting implementation may be affected by incentives of different stakeholders. The CK Tang’s case provides an excellent opportunity to discuss incentives of varies parties in determining the fair value in financial reporting decisions. In short, this case could be a good jumping-off point to talk about management and auditors’ incentives in financial reporting in general. Research methodology Publicly available information (e.g. financial reporting standards, corporate announcements and reports, news reports) was used as the basis for this case. Case overview/synopsis The case centres on an iconic Singaporean integrated retailing and property landlord entity: Tang holdings. As part of its succession planning, the company’s founding family decided to take its listing arm, C.K. Tang Limited (CK Tang hereafter), private in May 2006. The Tang brothers, who represented the controlling family, initiated several attempts to delist the company. The minority shareholders of CK Tang were unhappy that the offer price was below the net asset value of the company. The minority shareholders also highlighted that the reported fair value of the flagship Tang Plaza complex understated its highest and best use and might not possibly comply with International Financial Reporting Standards (IFRS) 13. Complexity academic level The case can be used for class discussions with undergraduate students or master students in intermediate accounting courses.
28
Yuan, Zhenjie, Junxi Qian, and Hong Zhu. "The Xinjiang Class: Multi-ethnic Encounters in an Eastern Coastal City." China Quarterly 232 (September 21, 2017): 1094–115. http://dx.doi.org/10.1017/s0305741017001096.
Full textAbstract:
AbstractThe Xinjiang Class (Xinjiang neidi ban, or Xinjiangban) has far-reaching implications for Beijing's governance of ethnic minorities in Xinjiang. Existing literature has focused primarily on the Uyghur–Han dichotomy, with limited attention being paid to the actual multi-ethnic interactions that constitute the situated dynamics of policy implementation. Utilizing the notions of the space of prescription and the space of negotiation to develop an analytical framework, this paper argues that social relations in the Xinjiangban are ongoing constructions borne by everyday experiences of domination and negotiation, and that space is constitutive of this situated dynamic. Based on nearly four years of research at a Xinjiangban, we make a case for the fluidity and incoherence of the implementation of the Xinjiangban policy. Those who implement it at the school level produce a space of prescription that deploys specific spatial–temporal arrangements to manage expressions of ethnic identity. Driven by the need to achieve upward mobility, minority students are open-minded about the Han- and patriotism-centred education. However, they use innovative and improvised tactics to create spaces of negotiation to re-assert their ethnicities. In the Xinjiangban, minority students do comply with spaces of prescription, but they simultaneously keep their ethnic and religious practices alive.
29
Hamidullah, Madinah F., and Norma M. Riccucci. "Intersectionality and Family-Friendly Policies in the Federal Government." Administration & Society 49, no. 1 (July 27, 2016): 105–20. http://dx.doi.org/10.1177/0095399715623314.
Full textAbstract:
This is an exploratory study that examines federal employee’s satisfaction with work–life balance or family-friendly policies. We rely on intersectionality as a theoretical framework to examine how gender, race, and class interact in the formation of their views. Drawing from the 2014 Federal Employee Viewpoint Survey, we examine how minority women compare with non-minority women regarding their perception of fairness of programs and policies aimed at the promotion of work–life balance. This topic is significant because satisfaction and participation in work–life balance programs can have implications for overall job performance and satisfaction. Our findings suggest that race, education, and proximity to retirement all play a role in work–life balance (family-friendly) policy satisfaction.
30
Hu, Xinqian, Junfeng Man, Hengfu Yang, Jiangmin Deng, and Yi Liu. "An Improved Metalearning Framework to Optimize Bearing Fault Diagnosis under Data Imbalance." Journal of Sensors 2022 (October 18, 2022): 1–20. http://dx.doi.org/10.1155/2022/1809482.
Full textAbstract:
The intelligent diagnosis of rotating machinery with big data has been widely studied. However, due to the variability of working conditions and difficulty in marking fault samples, it is difficult to obtain enough high-quality fault marking data for training bearing fault diagnosis models in practical industrial application scenarios. Aiming at the problem of training data imbalance caused by lack of fault samples, a novel metalearning fault diagnosis method (MOFD) is proposed to get the bearing fault diagnosis solution under data imbalance. Firstly, in order to enhance the variety of fault samples, a Feature Space Density Adaptive Synthetic Minority Oversampling Technique (FSDA-SMOTE) is proposed in this paper, which takes the density difference of minority samples in the spatial domain within the class as the constraint of local neighbor similarity to generate new fault samples for data augmentation. In addition, in order to strengthen the model’s learning ability and diagnosis performance under limited fault samples, a residual-attention convolutional neural network (RA-CNN) was constructed to identify the deep features of fault signals, and a metalearning strategy based on parameter gradient optimization was applied to RA-CNN for refining the learning process of the diagnosis model. Finally, the reliability of the proposed method is verified through experimental analysis of public bearing dataset.
31
Katalinić, Kristina, and Eszter Tamaskó. "“We were that small, special group in that large school with »normal« classes” Education in a Minority Language in the Context of Hungarians From Zagreb." Hungarian Studies Yearbook 4, no. 1 (November 1, 2022): 92–112. http://dx.doi.org/10.2478/hsy-2022-0005.
Full textAbstract:
Abstract The latest research conducted in the Hungarian community of the City of Zagreb has shown that the Hungarian language is slowly losing its communication functions in informal domains (family, friends, the sphere of intimacy) and is withdrawing before Croatian, i.e., that language shift is in progress. As one of the key factors affecting language shift, school is mentioned as support in families in intergenerational language transmission and language preservation in the community. Croatia has ensured an institutional framework for education in minority languages to its minorities through a series of regulatory acts. However, exercising this right is often followed by numerous difficulties. In case of the Hungarian minority, this is due to geographical dispersity. Nevertheless, during the 1990s, a Hungarian group in kindergarten, a bilingual class and nurturing language for primary- and secondary-school pupils were launched in Zagreb. In order to obtain a clearer image of how various class models in a minority language actually function and which problems their participants are faced with, we conducted a preliminary research among younger members of the community who attended classes in Hungarian at least at one point during their education. We completed the results with information obtained through informal conversations with preschool and school teachers as well as through immediate observations of the community.
32
Kruse, Timothy A. "Minority shareholder treatment surrounding the Dell MBO." Managerial Finance 47, no. 8 (March 12, 2021): 1077–93. http://dx.doi.org/10.1108/mf-09-2019-0480.
Full textAbstract:
PurposeThis paper is a clinical examination of the October 2013 Management Buyout of Dell Inc. by founder Michael Dell and Silver Lake Partners for a total consideration of $13.88 per share. The proposed transaction was targeted by shareholders unhappy with the deal price and voting framework. Various shareholders went on to file an appraisal suit. Examining these events yields insights into shareholder rights issues in a major transaction.Design/methodology/approachThe paper examines events surrounding the acquisition including the negotiation process, go-shop period, shareholder activist demands for a higher price, shareholder voting and the subsequent appraisal trial and appeal.FindingsDespite suggesting Dell's board fulfilled its fiduciary duties, Delaware Vice Chancellor Travis Laster awarded petitioning shareholders $17.62 per share, a 27% premium to the final deal consideration. This article draws on Laster's decision and research examining topics raised by the surrounding events to argue minority shareholder interests were not sufficiently protected.Research limitations/implicationsThe Dell transaction represents only one data point. Moreover, Vice Chancellor Laster's decision was reversed on appeal.Originality/valueNevertheless, the paper discusses the nuances surrounding many issues of interest to practitioners involving large going private transactions. It could also be used to illustrate many “real world” perspectives in an advanced corporate finance or mergers and acquisitions class.
33
Költő, András, Aoife Gavin, Elena Vaughan, Colette Kelly, Michal Molcho, and Saoirse Nic Gabhainn. "Connected, Respected and Contributing to Their World: The Case of Sexual Minority and Non-Minority Young People in Ireland." International Journal of Environmental Research and Public Health 18, no. 3 (January 27, 2021): 1118. http://dx.doi.org/10.3390/ijerph18031118.
Full textAbstract:
Outcome 5 of the Irish Better Outcomes, Brighter Futures national youth policy framework (“Connected, respected, and contributing to their world”) offers a suitable way to study psychosocial determinants of adolescent health. The present study (1) provides nationally representative data on how 15- to 17-year-olds score on these indicators; (2) compares sexual minority (same- and both-gender attracted youth) with their non-minority peers. We analyzed data from 3354 young people (aged 15.78 ± 0.78 years) participating in the Health Behaviour in School-aged Children (HBSC) study in Ireland. Age and social class were associated with the indicators only to a small extent, but girls were more likely than boys to report discrimination based on gender and age. Frequency of positive answers ranged from 67% (feeling comfortable with friends) to 12% (being involved in volunteer work). Sexual minority youth were more likely to feel discriminated based on sexual orientation, age, and gender. Both-gender attracted youth were less likely than the other groups to report positive outcomes. Same-gender attracted youth were twice as likely as non-minority youth to volunteer. The results indicate the importance of a comprehensive approach to psycho-social factors in youth health, and the need for inclusivity of sexual minority (especially bisexual) youth.
34
V., Krishnakumar. "Parallel Processing Framework for Minority Oversampling in Kernel Canonical Correlation Analysis (KCCA) Adaptive Subspaces for Class Imbalanced Datasets." Journal of Advanced Research in Dynamical and Control Systems 12, SP4 (March 31, 2020): 250–61. http://dx.doi.org/10.5373/jardcs/v12sp4/20201487.
Full text
35
Lim, Chjan, and Weituo Zhang. "Social opinion dynamics is not chaotic." International Journal of Modern Physics B 30, no. 15 (June 16, 2016): 1541006. http://dx.doi.org/10.1142/s0217979215410064.
Full textAbstract:
Motivated by the research on social opinion dynamics over large and dense networks, a general framework for verifying the monotonicity property of multi-agent dynamics is introduced. This allows a derivation of sociologically meaningful sufficient conditions for monotonicity that are tailor-made for social opinion dynamics, which typically have high nonlinearity. A direct consequence of monotonicity is that social opinion dynamics is nonchaotic. A key part of this framework is the definition of a partial order relation that is suitable for a large class of social opinion dynamics such as the generalized naming games. Comparisons are made to previous techniques to verify monotonicity. Using the results obtained, we extend many of the consequences of monotonicity to this class of social dynamics, including several corollaries on their asymptotic behavior, such as global convergence to consensus and tipping points of a minority fraction of zealots or leaders.
36
Manzano Sanchez, Ricardo Alejandro, Marzia Zaman, Nishith Goel, Kshirasagar Naik, and Rohit Joshi. "Towards Developing a Robust Intrusion Detection Model Using Hadoop–Spark and Data Augmentation for IoT Networks." Sensors 22, no. 20 (October 12, 2022): 7726. http://dx.doi.org/10.3390/s22207726.
Full textAbstract:
In recent years, anomaly detection and machine learning for intrusion detection systems have been used to detect anomalies on Internet of Things networks. These systems rely on machine and deep learning to improve the detection accuracy. However, the robustness of the model depends on the number of datasamples available, quality of the data, and the distribution of the data classes. In the present paper, we focused specifically on the amount of data and class imbalanced since both parameters are key in IoT due to the fact that network traffic is increasing exponentially. For this reason, we propose a framework that uses a big data methodology with Hadoop–Spark to train and test multi-class and binary classification with one-vs-rest strategy for intrusion detection using the entire BoT IoT dataset. Thus, we evaluate all the algorithms available in Hadoop–Spark in terms of accuracy and processing time. In addition, since the BoT IoT dataset used is highly imbalanced, we also improve the accuracy for detecting minority classes by generating more datasamples using a Conditional Tabular Generative Adversarial Network (CTGAN). In general, our proposed model outperforms other published models including our previous model. Using our proposed methodology, the F1-score of one of the minority class, i.e., Theft attack was improved from 42% to 99%.
37
Verver, Michiel, David Passenier, and Carel Roessingh. "Contextualising ethnic minority entrepreneurship beyond the west." International Journal of Entrepreneurial Behavior & Research 25, no. 5 (August 13, 2019): 955–73. http://dx.doi.org/10.1108/ijebr-03-2019-0190.
Full textAbstract:
Purpose Literature on immigrant and ethnic minority entrepreneurship almost exclusively focusses on the west, while neglecting other world regions. This neglect is problematic not only because international migration is on the rise outside the west, but also because it reveals an implicit ethnocentrism and creates particular presumptions about the nature of ethnic minority entrepreneurship that may not be as universally valid as is often presumed. The purpose of this paper is to examine ethnic minority entrepreneurship in non-western contexts to critically assess two of these presumptions, namely that it occurs in the economic margins and within clear ethnic community boundaries. Design/methodology/approach The authors draw on academic literature (including the authors’ own) to develop two case descriptions of ethnic minority entrepreneurship outside the west: the Mennonites in Belize and the Chinese in Cambodia. For each case, the authors describe the historic entrepreneurial trajectory, i.e. the historical emergence of entrepreneurship in light of relevant community and society contexts. Findings The two cases reveal that, in contrast to characterisations of ethnic minority entrepreneurship in the west, the Mennonites in Belize and the Chinese in Cambodia have come to comprise the economic upper class, and their business activities are not confined to ethnic community boundaries. Originality/value The paper is the first to elaborate the importance of studying ethnic minority entrepreneurship outside the west, both as an aim in itself and as a catalyst to work towards a more neutral framework.
38
Tiwari, Anoop Kumar, Abhigyan Nath, Karthikeyan Subbiah, and Kaushal Kumar Shukla. "Enhanced Prediction for Observed Peptide Count in Protein Mass Spectrometry Data by Optimally Balancing the Training Dataset." International Journal of Pattern Recognition and Artificial Intelligence 31, no. 12 (September 17, 2017): 1750040. http://dx.doi.org/10.1142/s0218001417500409.
Full textAbstract:
Imbalanced dataset affects the learning of classifiers. This imbalance problem is almost ubiquitous in biological datasets. Resampling is one of the common methods to deal with the imbalanced dataset problem. In this study, we explore the learning performance by varying the balancing ratios of training datasets, consisting of the observed peptides and absent peptides in the Mass Spectrometry experiment on the different machine learning algorithms. It has been observed that the ideal balancing ratio has yielded better performance than the imbalanced dataset, but it was not the best as compared to some intermediate ratio. By experimenting using Synthetic Minority Oversampling Technique (SMOTE) at different balancing ratios, we obtained the best results by achieving sensitivity of 92.1%, specificity value of 94.7%, overall accuracy of 93.4%, MCC of 0.869, and AUC of 0.982 with boosted random forest algorithm. This study also identifies the most discriminating features by applying the feature ranking algorithm. From the results of current experiments, it can be inferred that the performance of machine learning algorithms for the classification tasks can be enhanced by selecting optimally balanced training dataset, which can be obtained by suitably modifying the class distribution.
39
Graf, Arnulf B. A., Olivier Bousquet, Gunnar Rätsch, and Bernhard Schölkopf. "Prototype Classification: Insights from Machine Learning." Neural Computation 21, no. 1 (January 2009): 272–300. http://dx.doi.org/10.1162/neco.2009.01-07-443.
Full textAbstract:
We shed light on the discrimination between patterns belonging to two different classes by casting this decoding problem into a generalized prototype framework. The discrimination process is then separated into two stages: a projection stage that reduces the dimensionality of the data by projecting it on a line and a threshold stage where the distributions of the projected patterns of both classes are separated. For this, we extend the popular mean-of-class prototype classification using algorithms from machine learning that satisfy a set of invariance properties. We report a simple yet general approach to express different types of linear classification algorithms in an identical and easy-to-visualize formal framework using generalized prototypes where these prototypes are used to express the normal vector and offset of the hyperplane. We investigate non-margin classifiers such as the classical prototype classifier, the Fisher classifier, and the relevance vector machine. We then study hard and soft margin classifiers such as the support vector machine and a boosted version of the prototype classifier. Subsequently, we relate mean-of-class prototype classification to other classification algorithms by showing that the prototype classifier is a limit of any soft margin classifier and that boosting a prototype classifier yields the support vector machine. While giving novel insights into classification per se by presenting a common and unified formalism, our generalized prototype framework also provides an efficient visualization and a principled comparison of machine learning classification.
40
Falanga Bolognesi, Salvatore, Edoardo Pasolli, Oscar Belfiore, Carlo De Michele, and Guido D’Urso. "Harmonized Landsat 8 and Sentinel-2 Time Series Data to Detect Irrigated Areas: An Application in Southern Italy." Remote Sensing 12, no. 8 (April 17, 2020): 1275. http://dx.doi.org/10.3390/rs12081275.
Full textAbstract:
Lack of accurate and up-to-date data associated with irrigated areas and related irrigation amounts is hampering the full implementation and compliance of the Water Framework Directive (WFD). In this paper, we describe the framework that we developed and implemented within the DIANA project to map the actual extent of irrigated areas in the Campania region (Southern Italy) during the 2018 irrigation season. For this purpose, we considered 202 images from the Harmonized Landsat Sentinel-2 (HLS) products (57 images from Landsat 8 and 145 images from Sentinel-2). Such data were preprocessed in order to extract a multitemporal Normalized Difference Vegetation Index (NDVI) map, which was then smoothed through a gap-filling algorithm. We further integrated data coming from high-resolution (4 km) global satellite precipitation Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN)-Cloud Classification System (CCS) products. We collected an extensive ground truth in the field represented by 2992 data points coming from three main thematic classes: bare soil and rainfed (class 0), herbaceous (class 1), and tree crop (class 2). This information was exploited to generate irrigated area maps by adopting a machine learning classification approach. We compared six different types of classifiers through a cross-validation approach and found that, in general, random forests, support vector machines, and boosted decision trees exhibited the best performances in terms of classification accuracy and robustness to different tested scenarios. We found an overall accuracy close to 90% in discriminating among the three thematic classes, which highlighted promising capabilities in the detection of irrigated areas from HLS products.
41
Strangfeld, Jennifer A. "I Just Don’t Want to Be Judged: Cultural Capital’s Impact on Student Plagiarism." SAGE Open 9, no. 1 (January 2019): 215824401882238. http://dx.doi.org/10.1177/2158244018822382.
Full textAbstract:
This research explores how college students’ broader educational histories affect their decisions to plagiarize. While research typically categorizes plagiarism as intentional or unintentional, explanations revealed in interviews of first-generation, working-class, and/or racial minority students suggests that these typologies inadequately capture the complex reasons some students express for plagiarizing. Specifically, students in this study plagiarize primarily because they are concerned that not only are their vocabulary and writing skills subpar, but that they do not fit into the college student role. Their explanations are situated within Bourdieu’s framework of cultural capital, whereby students’ decisions to plagiarize are rooted in the outcomes stemming from educational practices that reinforce class hierarchies. Consequently, students’ plagiarism experiences are contextualized within their broader educational histories rather than limited to the immediate circumstances surrounding their academic dishonesty.
42
Filby, Michael P. "The Newmarket Racing Lad: Tradition and Change in a Marginal Occupation." Work, Employment and Society 1, no. 2 (June 1987): 205–24. http://dx.doi.org/10.1177/0950017087001002004.
Full textAbstract:
This paper describes the work of a widely seen but little known occupation, the racing lad. It relates some changes which have taken place in the organisation of work and the subjective responses to these of a significant minority of the occupation in the locality studied. Such changes as are apparent are accounted for in terms of developments in the local labour market which have served to erode the traditionalist framework within which work has been organised. At root, the core activity is seen to depend on some particularly intangible qualities which working class youngsters have typically brought to this form of work.
43
Zhao, Yang, Zoie Shui-Yee Wong, and Kwok Leung Tsui. "A Framework of Rebalancing Imbalanced Healthcare Data for Rare Events’ Classification: A Case of Look-Alike Sound-Alike Mix-Up Incident Detection." Journal of Healthcare Engineering 2018 (2018): 1–11. http://dx.doi.org/10.1155/2018/6275435.
Full textAbstract:
Identifying rare but significant healthcare events in massive unstructured datasets has become a common task in healthcare data analytics. However, imbalanced class distribution in many practical datasets greatly hampers the detection of rare events, as most classification methods implicitly assume an equal occurrence of classes and are designed to maximize the overall classification accuracy. In this study, we develop a framework for learning healthcare data with imbalanced distribution via incorporating different rebalancing strategies. The evaluation results showed that the developed framework can significantly improve the detection accuracy of medical incidents due to look-alike sound-alike (LASA) mix-ups. Specifically, logistic regression combined with the synthetic minority oversampling technique (SMOTE) produces the best detection results, with a significant 45.3% increase in recall (recall=75.7%) compared with pure logistic regression (recall=52.1%).
44
Potter, Daniel, and David S. Morris. "Family and Schooling Experiences in Racial/Ethnic Academic Achievement Gaps." Sociological Perspectives 60, no. 1 (August 2, 2016): 132–67. http://dx.doi.org/10.1177/0731121416629989.
Full textAbstract:
The gap in academic skills between white and historically disadvantaged racial/ethnic minority children exists at school entry and grows over time. Research over the last two decades has identified the important role of schools in perpetuating these disparities and the limited role of family experiences. Much of this research, however, has relied on strategies that consider only snapshots of children’s experiences and has assumed that family and schooling experiences have the same benefit for everyone. For this study, we examine racial/ethnic differences in children’s achievement through a cumulative framework that focuses on differences in the overall amounts of accumulated experiences and whether these experiences have similar benefits for all children. Using the Early Childhood Longitudinal Study—Kindergarten Class of 1998–1999 (ECLS-K), we find that cumulative experiences explain a moderate portion of the gap in reading and math gains between white and historically disadvantaged minority children. In addition, there is evidence that family and schooling experiences matter differently by race/ethnicity.
45
Yan, Yilin, and Mei-Ling Shyu. "Correlation-Assisted Imbalance Multimedia Concept Mining and Retrieval." International Journal of Semantic Computing 11, no. 02 (June 2017): 209–27. http://dx.doi.org/10.1142/s1793351x17400098.
Full textAbstract:
In the past decades, we have witnessed an explosion of multimedia data, especially with the development of social media websites and blooming popularity of smart devices. As a result, multimedia semantic concept mining and retrieval whose objective is to mine useful information from the large amount of multimedia data including texts, images, and videos has become more and more important. The huge amount of multimedia data and the semantic gap between low-level features and high-level semantic concepts have made it even more challenging. To address these challenges, the correlations among the classes can provide important context cues to help bridge the semantic gap. Meanwhile, many real-world datasets do not have uniform class distributions while the minority instances actually represent the concept of interests, like frauds in transactions, intrusions in network security, and unusual events in surveillance. Despite extensive research efforts, imbalanced concept retrieval remains one of the most challenging research problems in multimedia data mining. Different from existing frameworks regarding concept correlations among labels, this paper presents a novel concept correlation analysis model using the correlation between the retrieval scores and labels. Experimental results on the TRECVID benchmark datasets demonstrate that the proposed framework can enhance imbalanced concept mining and retrieval even with trivial scores from the minority class.
46
Rashid, Tooba, Muhammad Sultan Zia, Najam-ur-Rehman Najam-ur-Rehman, Talha Meraj, Hafiz Tayyab Rauf, and Seifedine Kadry. "A Minority Class Balanced Approach Using the DCNN-LSTM Method to Detect Human Wrist Fracture." Life 13, no. 1 (January 3, 2023): 133. http://dx.doi.org/10.3390/life13010133.
Full textAbstract:
The emergency department of hospitals receives a massive number of patients with wrist fracture. For the clinical diagnosis of a suspected fracture, X-ray imaging is the major screening tool. A wrist fracture is a significant global health concern for children, adolescents, and the elderly. A missed diagnosis of wrist fracture on medical imaging can have significant consequences for patients, resulting in delayed treatment and poor functional recovery. Therefore, an intelligent method is needed in the medical department to precisely diagnose wrist fracture via an automated diagnosing tool by considering it a second option for doctors. In this research, a fused model of the deep learning method, a convolutional neural network (CNN), and long short-term memory (LSTM) is proposed to detect wrist fractures from X-ray images. It gives a second option to doctors to diagnose wrist facture using the computer vision method to lessen the number of missed fractures. The dataset acquired from Mendeley comprises 192 wrist X-ray images. In this framework, image pre-processing is applied, then the data augmentation approach is used to solve the class imbalance problem by generating rotated oversamples of images for minority classes during the training process, and pre-processed images and augmented normalized images are fed into a 28-layer dilated CNN (DCNN) to extract deep valuable features. Deep features are then fed to the proposed LSTM network to distinguish wrist fractures from normal ones. The experimental results of the DCNN-LSTM with and without augmentation is compared with other deep learning models. The proposed work is also compared to existing algorithms in terms of accuracy, sensitivity, specificity, precision, the F1-score, and kappa. The results show that the DCNN-LSTM fusion achieves higher accuracy and has high potential for medical applications to use as a second option.
47
Vrkljan, Brenda H. "Dispelling the Disability Stereotype: Embracing a Universalistic Perspective of Disablement." Canadian Journal of Occupational Therapy 72, no. 1 (February 2005): 57–60. http://dx.doi.org/10.1177/000841740507200111.
Full textAbstract:
Background. The notion of universalism was introduced to me during my first year of PhD studies in Rehabilitation Science. During a class discussion, we debated the merits of two theoretical perspectives that offered contradicting views as to the most effective means to facilitating a shift in societal perceptions of disability. As exemplified by the World Health Organization's current model of health, the International Classification of Functioning, Disability and Health (ICF), there has been a shift from a minority group analysis towards a universalistic perspective of disablement. Purpose. This paper introduces readers to the underlying concepts of both minority group analysis and universalism and, in doing so, proposes that universalism is closely aligned with the underlying constructs of occupational therapy. Universalism provides a comprehensive framework that can be utilized by occupational therapists to encourage the development of health and social-related policies that promote inclusiveness, yet still the respect the differences that exist among individuals. Practice Implications. By improving their familiarity with such theories, occupational therapists may be better positioned to contribute to policy development within their respective treatment and/or community settings.
48
Butler, III, James, Craig S. Fryer, Mary A. Garza, Sandra C. Quinn, and Stephen B. Thomas. "Commentary: Critical Race Theory Training to Eliminate Racial and Ethnic Health Disparities: The Public Health Critical Race Praxis Institute." Ethnicity & Disease 28, Supp 1 (August 8, 2018): 279. http://dx.doi.org/10.18865/ed.28.s1.279.
Full textAbstract:
<p class="Pa6"> Racism is a fundamental cause of racial and ethnic disparities in health outcomes. Researchers have a critical role to play in confronting racism by understanding it and intervening on its impact on the health and well-being of minority populations. This requires new paradigms and theoretical frameworks that are responsive to structural racism’s present-day influence on health, health disparities, and research. To address the complexity with which racism influences both health and the production of knowledge about minority populations, the field must accelerate the professional development of researchers who are committed to eliminating racial and ethnic health disparities and achieving health equity. In this commentary, we describe a unique and vital training experience, the Public Health Critical Race Praxis Institute at the University of Maryland’s Center for Health Equity. Through this training institute, we have focused on the experiential knowledge of diverse researchers committed to examining racism and trained them on putting racism at the forefront of their research agendas. The Institute brought together investigators from across the United States, including junior and senior faculty as well as postdoctoral fellows. The public health critical race methodology was purposefully used to structure the Institute’s curriculum, which instructed the scholars on Critical Race Theory as a framework in research. During a 2.5-day training in February 2014, scholars participated in activities, attended presentations, joined in reflections, and interacted with Institute faculty. The scholars indicated a strong desire to focus on race and racism and adopt a Public Health Critical Race Praxis framework by utilizing Critical Race Theory in their research. <em></em></p><p class="Pa6"><em>Ethn Dis. </em>2018;28(Suppl 1):279-284; doi:10.18865/ed.28.S1.279.</p>
49
Rezaei, Mina, Janne J. Näppi, Christoph Lippert, Christoph Meinel, and Hiroyuki Yoshida. "Generative multi-adversarial network for striking the right balance in abdominal image segmentation." International Journal of Computer Assisted Radiology and Surgery 15, no. 11 (September 8, 2020): 1847–58. http://dx.doi.org/10.1007/s11548-020-02254-4.
Full textAbstract:
Abstract Purpose The identification of abnormalities that are relatively rare within otherwise normal anatomy is a major challenge for deep learning in the semantic segmentation of medical images. The small number of samples of the minority classes in the training data makes the learning of optimal classification challenging, while the more frequently occurring samples of the majority class hamper the generalization of the classification boundary between infrequently occurring target objects and classes. In this paper, we developed a novel generative multi-adversarial network, called Ensemble-GAN, for mitigating this class imbalance problem in the semantic segmentation of abdominal images. Method The Ensemble-GAN framework is composed of a single-generator and a multi-discriminator variant for handling the class imbalance problem to provide a better generalization than existing approaches. The ensemble model aggregates the estimates of multiple models by training from different initializations and losses from various subsets of the training data. The single generator network analyzes the input image as a condition to predict a corresponding semantic segmentation image by use of feedback from the ensemble of discriminator networks. To evaluate the framework, we trained our framework on two public datasets, with different imbalance ratios and imaging modalities: the Chaos 2019 and the LiTS 2017. Result In terms of the F1 score, the accuracies of the semantic segmentation of healthy spleen, liver, and left and right kidneys were 0.93, 0.96, 0.90 and 0.94, respectively. The overall F1 scores for simultaneous segmentation of the lesions and liver were 0.83 and 0.94, respectively. Conclusion The proposed Ensemble-GAN framework demonstrated outstanding performance in the semantic segmentation of medical images in comparison with other approaches on popular abdominal imaging benchmarks. The Ensemble-GAN has the potential to segment abdominal images more accurately than human experts.
50
Mirshokraei, Mehrdad, Carlo Iapige De Gaetani, and Federica Migliaccio. "A Web-Based BIM–AR Quality Management System for Structural Elements." Applied Sciences 9, no. 19 (September 23, 2019): 3984. http://dx.doi.org/10.3390/app9193984.
Full textAbstract:
This paper investigates quality management (QM) during the execution phase of structural elements by proposing, developing, and testing a complete framework by integrating building information modeling (BIM) and augmented reality (AR) technology. QM during execution is boosted by BIM–AR integration through a dedicated web-based system aimed at reducing the occurrence of omissions and negligence. With such a system, efficiency is improved by allowing the entering of inspection data directly in a shared digital environment, where people involved in QM have permanent access to updated information and inspection results, clearly organized, and entered in real time. The system has been developed in the asp.net framework using C# language where, by generating a web-based checklist and establishing its link to AR, it can enhance the process of information extraction from industry foundation class (IFC) 4D BIM models and the recording of inspection data. A test has been performed on a real case study in Budapest, to assess the effectiveness of the system in the field. Results demonstrate the following benefits brought by such a type of QM system: improved understanding of the design, access to information, and overview of the quality status of the project, leading to reductions in defects and reworking, as well as improved and quicker response and decision-making.