A NEW BINARY SUPPORT VECTOR SYSTEM FOR INCREASING DETECTION RATE OF CREDIT CARD FRAUD

Recently, a new personalized model has been developed to prevent credit card fraud. This model is promising; however, there remains some problems. Existing approaches cannot identify well credit card frauds from few data with skewed distributions. This paper proposes to address the problem using a binary support vector system (BSVS). The proposed BSVS is based on the support vectors in the support vector machines (SVM) and the genetic algorithm (GA) is employed to select support vectors. To obtain a high true negative rate, self-organizing mapping (SOM) is first employed to estimate the distribution model of the input data. Then BSVS is used to best train the data according to the input data distribution to obtain a high detection rate. Experimental results show that the proposed BSVS is effective especially for predicting a high true negative rate.

Download Full-text

Probabilistic Support Vector Regression Classification Model for Credit Card Fraud Detection

International Journal of Computer Sciences and Engineering ◽

10.26438/ijcse/v6i9.840843 ◽

2018 ◽

Vol 6 (9) ◽

pp. 840-843

Author(s):

Nikita Sawhney ◽

B. Kaur ◽

H. Kaur

Keyword(s):

Support Vector Regression ◽

Credit Card ◽

Fraud Detection ◽

Classification Model ◽

Support Vector ◽

Credit Card Fraud ◽

Probabilistic Support

Download Full-text

True Negative Rate

Encyclopedia of Machine Learning ◽

10.1007/978-0-387-30164-8_854 ◽

2011 ◽

pp. 999-999

Author(s):

William Uther ◽

Dunja Mladenić ◽

Massimiliano Ciaramita ◽

Bettina Berendt ◽

Aleksander Kołcz ◽

...

Keyword(s):

True Negative ◽

True Negative Rate ◽

Negative Rate

Download Full-text

Credit Card Fraud Detection Using Weighted Support Vector Machine

Applied Mathematics ◽

10.4236/am.2020.1112087 ◽

2020 ◽

Vol 11 (12) ◽

pp. 1275-1291

Author(s):

Dongfang Zhang ◽

Basu Bhandari ◽

Dennis Black

Keyword(s):

Support Vector Machine ◽

Credit Card ◽

Fraud Detection ◽

Support Vector ◽

Credit Card Fraud

Download Full-text

Incorporation of relative cerebral blood flow into CT perfusion maps reduces false ’at risk' penumbra

Journal of NeuroInterventional Surgery ◽

10.1136/neurintsurg-2017-013268 ◽

2017 ◽

Vol 10 (7) ◽

pp. 657-662 ◽

Cited By ~ 2

Author(s):

Shlomi Peretz ◽

David Orion ◽

David Last ◽

Yael Mardor ◽

Yotam Kimmel ◽

...

Keyword(s):

At Risk ◽

Acute Stroke ◽

Ct Perfusion ◽

False Negative ◽

Stroke Patients ◽

True Negative ◽

True Negative Rate ◽

Negative Rate ◽

Perfusion Maps

PurposeThe region defined as ‘at risk’ penumbra by current CT perfusion (CTP) maps is largely overestimated. We aimed to quantitate the portion of true ‘at risk’ tissue within CTP penumbra and to determine the parameter and threshold that would optimally distinguish it from false ‘at risk’ tissue, that is, benign oligaemia.MethodsAmong acute stroke patients evaluated by multimodal CT (NCCT/CTA/CTP) we identified those that had not undergone endovascular/thrombolytic treatment and had follow-up NCCT. Maps of absolute and relative CBF, CBV, MTT, TTP and Tmax as well as summary maps depicting infarcted and penumbral regions were generated using the Intellispace Portal (Philips Healthcare, Best, Netherlands). Follow-up CT was automatically co-registered to the CTP scan and the final infarct region was manually outlined. Perfusion parameters were systematically analysed – the parameter that resulted in the highest true-negative-rate (ie, proportion of benign oligaemia correctly identified) at a fixed, clinically relevant false-negative-rate (ie, proportion of ‘missed’ infarct) of 15%, was chosen as optimal. It was then re-applied to the CTP data to produce corrected perfusion maps.ResultsForty seven acute stroke patients met selection criteria. Average portion of infarcted tissue within CTP penumbra was 15%±2.2%. Relative CBF at a threshold of 0.65 yielded the highest average true-negative-rate (48%), enabling reduction of the false ‘at risk’ penumbral region by ~half.ConclusionsApplying a relative CBF threshold on relative MTT-based CTP maps can significantly reduce false ‘at risk’ penumbra. This step may help to avoid unnecessary endovascular interventions.

Download Full-text

Assisting in Auditing of Buffer Overflow Vulnerabilities via Machine Learning

Mathematical Problems in Engineering ◽

10.1155/2017/5452396 ◽

2017 ◽

Vol 2017 ◽

pp. 1-13 ◽

Cited By ~ 5

Author(s):

Qingkun Meng ◽

Chao Feng ◽

Bin Zhang ◽

Chaojing Tang

Keyword(s):

Machine Learning ◽

Machine Learning Algorithms ◽

Buffer Overflow ◽

Analysis Method ◽

True Negative ◽

True Negative Rate ◽

Negative Rate ◽

Training Samples ◽

Extended Code ◽

Code Property

Buffer overflow vulnerability is a kind of consequence in which programmers’ intentions are not implemented correctly. In this paper, a static analysis method based on machine learning is proposed to assist in auditing buffer overflow vulnerabilities. First, an extended code property graph is constructed from the source code to extract seven kinds of static attributes, which are used to describe buffer properties. After embedding these attributes into a vector space, five frequently used machine learning algorithms are employed to classify the functions into suspicious vulnerable functions and secure ones. The five classifiers reached an average recall of 83.5%, average true negative rate of 85.9%, a best recall of 96.6%, and a best true negative rate of 91.4%. Due to the imbalance of the training samples, the average precision of the classifiers is 68.9% and the average F1 score is 75.2%. When the classifiers were applied to a new program, our method could reduce the false positive to 1/12 compared to Flawfinder.

Download Full-text

Fuzzy Asymmetric Support Vector Machines

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.433-440.7479 ◽

2012 ◽

Vol 433-440 ◽

pp. 7479-7486

Author(s):

Rui Kong ◽

Qiong Wang ◽

Gu Yu Hu ◽

Zhi Song Pan

Keyword(s):

Support Vector Machines ◽

Medical Diagnosis ◽

Credit Card ◽

Training Data ◽

Support Vector ◽

Imbalanced Datasets ◽

Credit Card Fraud ◽

Vector Machines ◽

Imbalanced Training Data ◽

Error Costs

Support Vector Machines (SVM) has been extensively studied and has shown remarkable success in many applications. However the success of SVM is very limited when it is applied to the problem of learning from imbalanced datasets in which negative instances heavily outnumber the positive instances (e.g. in medical diagnosis and detecting credit card fraud). In this paper, we propose the fuzzy asymmetric algorithm to augment SVMs to deal with imbalanced training-data problems, called FASVM, which is based on fuzzy memberships, combined with different error costs (DEC) algorithm. We compare the performance of our algorithm against these two algorithms, along with different error costs and regular SVM and show that our algorithm outperforms all of them.

Download Full-text

Mastoid, middle ear and inner ear analysis in CT scan – a possible contribution for the identification of remains

Medicine Science and the Law ◽

10.1177/0025802419893424 ◽

2020 ◽

Vol 60 (2) ◽

pp. 102-111

Author(s):

Henrique Rodrigues ◽

Rosa Ramos ◽

Leoni Fagundes ◽

Orlando Galego ◽

David Navega ◽

...

Keyword(s):

Positive Predictive Value ◽

Predictive Value ◽

Visual Assessment ◽

True Positive Rate ◽

Observer Agreement ◽

True Positive ◽

True Negative ◽

True Negative Rate ◽

Negative Rate ◽

Positive Rate

Objective We aimed to evaluate whether the internal structures of the human ear have anatomical characteristics that are sufficiently distinctive to contribute to human identification and use in a forensic context. Materials and methods After data anonymisation, a dataset containing temporal bone CT scans of 100 subjects was processed by a radiologist who was not involved in the study. Four reference images were selected for each subject. Of the original sample, 10 examinations were used for visual comparison, case by case, against the dataset of 100 patients. This visual assessment was performed independently by four observers, who evaluated the anatomical agreement using a Likert scale (1–5). Inter-observer agreement, true positive rate, positive predictive value, true negative rate, negative predictive value, false positive rate, false negative rate and positive likelihood ratio (LR+) were evaluated. Results Inter-observer agreement obtained an overall Cohen’s Kappa = 99.59%. True positive rate, positive predictive value, true negative rate and negative predictive value were all 100%. Conclusion Visual assessment of the mastoid examinations was shown to be a robust and reliable approach to identify unique osseous features and contribute to human identification. The statistical analysis indicates that regardless of the examiner’s background and training, the approach has a high degree of accuracy.

Download Full-text

DARQ: Deep learning of quality control for stereotaxic registration of human brain MRI

10.1101/2021.08.16.456514 ◽

2021 ◽

Author(s):

Vladimir Fonov ◽

Mahsa Dadar ◽

D. Louis Collins ◽

◽

Keyword(s):

Image Processing ◽

Quality Control ◽

Deep Learning ◽

Human Brain ◽

Brain Mri ◽

True Negative ◽

Available N ◽

True Negative Rate ◽

Negative Rate ◽

Mri Scans

Linear registration to stereotaxic space is a common first step in many automated image-processing tools for analysis of human brain MRI scans. This step is crucial for the success of the subsequent image-processing steps. Several well-established algorithms are commonly used in the field of neuroimaging for this task, but none have a 100% success rate. Manual assessment of the registration is commonly used as part of quality control. To reduce the burden of this time-consuming step, we propose Deep Automated Registration Qc (DARQ), a fully automatic quality control method based on deep learning that can replace the human rater and accurately perform quality control assessment for stereotaxic registration of T1w brain scans. In a recently published study from our group comparing linear registration methods, we used a database of 9325 MRI scans from several publicly available datasets and applied seven linear registration tools to them. In this study, the resulting images that were assessed and labeled by a human rater are used to train a deep neural network to detect cases when registration failed. We further validated the results on an independent dataset of patients with multiple sclerosis, with manual QC labels available (n=1200). In terms of agreement with a manual rater, our automated QC method was able to achieve 89% accuracy and 85% true negative rate (equivalently 15% false positive rate) in detecting scans that should pass quality control in a balanced cross-validation experiments, and 96.1% accuracy and 95.5% true negative rate (or 4.5% FPR) when evaluated in a balanced independent sample, similar to manual QC rater (test-retest accuracy of 93%). The results show that DARQ is robust, fast, accurate, and generalizable in detecting failure in linear stereotaxic registrations and can substantially reduce QC time (by a factor of 20 or more) when processing large datasets.

Download Full-text