scholarly journals Secure machine learning against adversarial samples at test time

2022 ◽  
Vol 2022 (1) ◽  
Author(s):  
Jing Lin ◽  
Laurent L. Njilla ◽  
Kaiqi Xiong
Keyword(s):  
Machine Learning ◽  
Parallel Implementation ◽  
Standard Test ◽  
Test Time ◽  
Test Accuracy ◽  
Learning Approaches ◽  
Complex Models ◽  
Projected Gradient Descent ◽  
Adversarial Example ◽  
Human Eyes

AbstractDeep neural networks (DNNs) are widely used to handle many difficult tasks, such as image classification and malware detection, and achieve outstanding performance. However, recent studies on adversarial examples, which have maliciously undetectable perturbations added to their original samples that are indistinguishable by human eyes but mislead the machine learning approaches, show that machine learning models are vulnerable to security attacks. Though various adversarial retraining techniques have been developed in the past few years, none of them is scalable. In this paper, we propose a new iterative adversarial retraining approach to robustify the model and to reduce the effectiveness of adversarial inputs on DNN models. The proposed method retrains the model with both Gaussian noise augmentation and adversarial generation techniques for better generalization. Furthermore, the ensemble model is utilized during the testing phase in order to increase the robust test accuracy. The results from our extensive experiments demonstrate that the proposed approach increases the robustness of the DNN model against various adversarial attacks, specifically, fast gradient sign attack, Carlini and Wagner (C&W) attack, Projected Gradient Descent (PGD) attack, and DeepFool attack. To be precise, the robust classifier obtained by our proposed approach can maintain a performance accuracy of 99% on average on the standard test set. Moreover, we empirically evaluate the runtime of two of the most effective adversarial attacks, i.e., C&W attack and BIM attack, to find that the C&W attack can utilize GPU for faster adversarial example generation than the BIM attack can. For this reason, we further develop a parallel implementation of the proposed approach. This parallel implementation makes the proposed approach scalable for large datasets and complex models.

scholarly journals Classification of multiwavelength transients with Machine Learning

2020 ◽  
Author(s):  
K Sooknunan ◽  
M Lochner ◽  
Bruce A Bassett ◽  
H V Peiris ◽  
R Fender ◽  
...  
Keyword(s):  
Machine Learning ◽  
Small Sample ◽  
Light Curves ◽  
Machine Learning Techniques ◽  
Optical Data ◽  
Test Time ◽  
Test Accuracy ◽  
Training Set ◽  
The Impact

Abstract With the advent of powerful telescopes such as the Square Kilometer Array and the Vera C. Rubin Observatory, we are entering an era of multiwavelength transient astronomy that will lead to a dramatic increase in data volume. Machine learning techniques are well suited to address this data challenge and rapidly classify newly detected transients. We present a multiwavelength classification algorithm consisting of three steps: (1) interpolation and augmentation of the data using Gaussian processes; (2) feature extraction using wavelets; (3) classification with random forests. Augmentation provides improved performance at test time by balancing the classes and adding diversity into the training set. In the first application of machine learning to the classification of real radio transient data, we apply our technique to the Green Bank Interferometer and other radio light curves. We find we are able to accurately classify most of the eleven classes of radio variables and transients after just eight hours of observations, achieving an overall test accuracy of 78%. We fully investigate the impact of the small sample size of 82 publicly available light curves and use data augmentation techniques to mitigate the effect. We also show that on a significantly larger simulated representative training set that the algorithm achieves an overall accuracy of 97%, illustrating that the method is likely to provide excellent performance on future surveys. Finally, we demonstrate the effectiveness of simultaneous multiwavelength observations by showing how incorporating just one optical data point into the analysis improves the accuracy of the worst performing class by 19%.

scholarly journals Text Classification Algorithms: A Survey

Information ◽  
2019 ◽  
Vol 10 (4) ◽  
pp. 150 ◽  
Author(s):  
Kowsari ◽  
Jafari Meimandi ◽  
Heidarysafa ◽  
Mendu ◽  
Barnes ◽  
...  
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Language Processing ◽  
Text Classification ◽  
Classification Algorithms ◽  
Learning Approaches ◽  
Machine Learning Methods ◽  
Linear Relationships ◽  
Reduction Methods ◽  
Complex Models

In recent years, there has been an exponential growth in the number of complex documentsand texts that require a deeper understanding of machine learning methods to be able to accuratelyclassify texts in many applications. Many machine learning approaches have achieved surpassingresults in natural language processing. The success of these learning algorithms relies on their capacityto understand complex models and non-linear relationships within data. However, finding suitablestructures, architectures, and techniques for text classification is a challenge for researchers. In thispaper, a brief overview of text classification algorithms is discussed. This overview covers differenttext feature extractions, dimensionality reduction methods, existing algorithms and techniques, andevaluations methods. Finally, the limitations of each technique and their application in real-worldproblems are discussed.

Using Machine Learning Approaches to Explore Non-Cognitive Variables Influencing Reading Proficiency in English among Filipino Learners

2021 ◽  
Vol 11 (10) ◽  
pp. 628
Author(s):  
Allan B. I. Bernardo ◽  
Macario O. Cordel ◽  
Rochelle Irene G. Lucas ◽  
Jude Michael M. Teves ◽  
Sashmir A. Yap ◽  
...  
Keyword(s):  
Machine Learning ◽  
School Environment ◽  
Binary Classification ◽  
Reading Proficiency ◽  
Classification Model ◽  
Support Vector ◽  
Test Accuracy ◽  
Learning Approaches ◽  
Classification Methods ◽  
Poor Reading

Filipino students ranked last in reading proficiency among all countries/territories in the PISA 2018, with only 19% meeting the minimum (Level 2) standard. It is imperative to understand the range of factors that contribute to low reading proficiency, specifically variables that can be the target of interventions to help students with poor reading proficiency. We used machine learning approaches, specifically binary classification methods, to identify the variables that best predict low (Level 1b and lower) vs. higher (Level 1a or better) reading proficiency using the Philippine PISA data from a nationally representative sample of 15-year-old students. Several binary classification methods were applied, and the best classification model was derived using support vector machines (SVM), with 81.2% average test accuracy. The 20 variables with the highest impact in the model were identified and interpreted using a socioecological perspective of development and learning. These variables included students’ home-related resources and socioeconomic constraints, learning motivation and mindsets, classroom reading experiences with teachers, reading self-beliefs, attitudes, and experiences, and social experiences in the school environment. The results were discussed with reference to the need for a systems perspective to addresses poor proficiency, requiring interconnected interventions that go beyond students’ classroom reading.

scholarly journals A deep learning approach for staging embryonic tissue isolates with small data

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0244151
Author(s):  
Adam Joseph Ronald Pond ◽  
Seongwon Hwang ◽  
Berta Verd ◽  
Benjamin Steventon
Keyword(s):  
Machine Learning ◽  
Three Dimensional ◽  
3D Culture ◽  
Large Data ◽  
Test Accuracy ◽  
Small Data ◽  
Neural Net ◽  
Learning Approaches ◽  
Data Set

Machine learning approaches are becoming increasingly widespread and are now present in most areas of research. Their recent surge can be explained in part due to our ability to generate and store enormous amounts of data with which to train these models. The requirement for large training sets is also responsible for limiting further potential applications of machine learning, particularly in fields where data tend to be scarce such as developmental biology. However, recent research seems to indicate that machine learning and Big Data can sometimes be decoupled to train models with modest amounts of data. In this work we set out to train a CNN-based classifier to stage zebrafish tail buds at four different stages of development using small information-rich data sets. Our results show that two and three dimensional convolutional neural networks can be trained to stage developing zebrafish tail buds based on both morphological and gene expression confocal microscopy images, achieving in each case up to 100% test accuracy scores. Importantly, we show that high accuracy can be achieved with data set sizes of under 100 images, much smaller than the typical training set size for a convolutional neural net. Furthermore, our classifier shows that it is possible to stage isolated embryonic structures without the need to refer to classic developmental landmarks in the whole embryo, which will be particularly useful to stage 3D culture in vitro systems such as organoids. We hope that this work will provide a proof of principle that will help dispel the myth that large data set sizes are always required to train CNNs, and encourage researchers in fields where data are scarce to also apply ML approaches.

scholarly journals Machine learning approaches classify clinical malaria outcomes based on haematological parameters

2020 ◽  
Author(s):  
Collins M Morang'a ◽  
Lucas Amenga-Etego ◽  
Saikou Y Bah ◽  
Vincent Appiah ◽  
Dominic S Amuzu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Clinical Decision Support ◽  
Clinical Decision ◽  
Clinical Malaria ◽  
Haematological Parameters ◽  
Test Accuracy ◽  
Learning Approaches ◽  
Binary Classifiers ◽  
Multi Classification

Background: Malaria is still a major global health burden, with more than 3.2 billion people in 91 countries remaining at risk of the disease. Accurately distinguishing malaria from other diseases, especially uncomplicated malaria (UM) from non-malarial infections (nMI) remains a challenge. Furthermore, the success of rapid diagnostic tests (RDT) is threatened by Pfhrp2/3 deletions and decreased sensitivity at low parasitemia. Analysis of haematological indices can be used to support identification of possible malaria cases for further diagnosis, especially in travelers returning from endemic areas. As a new application for precision medicine, we aimed to evaluate machine learning (ML) approaches that can accurately classify nMI, UM and severe malaria (SM) using haematological parameters. Methods: We obtained haematological data from 2,207 participants collected in Ghana; nMI (n=978), UM (n=526), and SM (n=703). Six different machine learning approaches were tested, to select the best approach. An artificial neural network (ANN) with three hidden layers was used for multi-classification of UM, SM, and uMI. Binary classifiers were developed to further identify the parameters that can distinguish UM or SM from nMI. Local interpretable model-agonistic explanations (LIME) were used to explain the binary classifiers. Results: The multi-classification model had greater than 85 % training and testing accuracy to distinguish clinical malaria from nMI. To distinguish UM from nMI, our approach identified platelet counts, red blood cell (RBC) counts, lymphocyte counts and percentages as the top classifiers of UM with 0.801 test accuracy (AUC = 0.866 and F1-score = 0.747). To distinguish SM from nMI, the classifier had a test accuracy of 0.960 (AUC= 0.983, and F1-score = 0.944) with mean platelet volume and mean cell volume being the unique classifiers of SM. Random forest was used to confirm the classifications and it showed that platelet and RBC counts were the major classifiers of UM, regardless of possible confounders such as patient age and sampling location. Conclusions: The study provides proof of concept methods that classify UM and SM from nMI, showing that ML approach is a feasible tool for clinical decision support. In the future, ML approaches could be incorporated into clinical decision-support algorithms for the diagnosis of acute febrile illness, and monitoring response to acute SM treatment particularly in endemic settings.

scholarly journals Machine learning for diagnosis and monitoring of sleep apnea

2020 ◽  
pp. 43-58
Author(s):  
Dmytro Tkachenko ◽  
Ihor Krush ◽  
Vitalii Mykhalko ◽  
Anatolii Petrenko
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Sleep Apnea ◽  
Wearable Devices ◽  
Learning Approaches ◽  
Learning Models ◽  
Multimodal Data ◽  
Severity Level ◽  
Complex Models ◽  
Apnea Detection

This paper contains a review and analysis of applications of modern ma-chine learning approaches to solve sleep apnea severity level detection by localization of apnea episodes and prediction of the subsequent apnea episodes. We demonstrate that signals provided by cheap wearable devices can be used to solve typical tasks of sleep apnea detection. We review major publicly available datasets that can be used for training respective deep learning models, and we analyze the usage options of these datasets. In particular, we prove that deep learning could improve the accuracy of sleep apnea classification, sleep apnea localization, and sleep apnea prediction, especially using more complex models with multimodal data from several sensors.

scholarly journals Prediction of acute myocardial infarction or death in acute chest pain patients with machine learning models or first troponin T alone

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
P Olsson De Capretz ◽  
A Bjorkelund ◽  
A Mokhtari ◽  
J Bjork ◽  
M Ohlsson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Predictive Value ◽  
Troponin T ◽  
Learning Approaches ◽  
Learning Models ◽  
Complex Models ◽  
Machine Learning Models ◽  
Rule Out

Abstract Background Machine learning approaches are increasingly being explored for use in healthcare systems, but there is a trade-off between increased accuracy and decreased explainability with more complex models. We aimed to evaluate the diagnostic performance for acute myocardial infarction (AMI) or death within 30 days of index visit. Machine learning models were trained using demographic factors, ECG and blood markers, and to compare them to a single high sensitivity TnT (hs-cTnT) value. Methods Using records from 9519 ED patients from two hospitals in Skåne, Sweden, we created machine learning models based on both logistic regression and artificial neural networks. Inputs in the models varied and included sex and age, first hs-cTnT value at the ED, glucose, creatinine, hemoglobin, and ECG signal data. The models were adapted to meet the following criteria for safe rule-out of 30-day myocardial infarction or death: Negative predictive value (NPV) >99.5% and sensitivity >99%. For rule-in of myocardial infarction or death, a positive predictive value (PPV) of >70% was set. The models were then compared to the performance of a first hs-cTnT <5 ng/L for rule-out, and >51 ng/L for rule-in. The patient population was split by arrival date and models were trained on the initial 50% of patients. Thresholds were selected from the subsequent 25%, and tests were performed on the final 25% (2379 patients). Results The best model, a convolutional neural network, identified 1309 (55%) patients for rule-out and 125 (5.3%) for rule-in, with the required NPV, sensitivity and PPV. In comparison, a single hs-cTnT value identified 1123 (47.2%) patients for rule-out and 158 (6.6%) for rule-in, but failed to reach the required sensitivity and PPV levels. Conclusions These results indicate that more complex models are able to safely identify a large proportion of patients for early rule-out or rule-in without the need for serial troponin tests. In future studies attempts should be made to improve the explainability of these models. FUNDunding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): VR; grant no. 2019-00198

Multiple vehicles detection and tracking for intelligent transport systems using machine learning approaches

2019 ◽  
Vol 70 (3) ◽  
pp. 214-224
Author(s):  
Bui Ngoc Dung ◽  
Manh Dzung Lai ◽  
Tran Vu Hieu ◽  
Nguyen Binh T. H.
Keyword(s):  
Machine Learning ◽  
Gaussian Mixture ◽  
Research Field ◽  
Transport Systems ◽  
Learning Approaches ◽  
Subtraction Method ◽  
Intelligent Transport Systems ◽  
Intelligent Transport ◽  
Detection And Tracking ◽  
Multiple Vehicles

Video surveillance is emerging research field of intelligent transport systems. This paper presents some techniques which use machine learning and computer vision in vehicles detection and tracking. Firstly the machine learning approaches using Haar-like features and Ada-Boost algorithm for vehicle detection are presented. Secondly approaches to detect vehicles using the background subtraction method based on Gaussian Mixture Model and to track vehicles using optical flow and multiple Kalman filters were given. The method takes advantages of distinguish and tracking multiple vehicles individually. The experimental results demonstrate high accurately of the method.

Sign in / Sign up

Export Citation Format

Share Document