scholarly journals ML-CB: Machine Learning Canvas Block

2021 ◽  
Vol 2021 (3) ◽  
pp. 453-473
Author(s):  
Nathan Reitinger ◽  
Michelle L. Mazurek
Keyword(s):  
Machine Learning ◽  
Supervised Learning ◽  
Semantic Representation ◽  
Source Code ◽  
Online Privacy ◽  
Learning Approach ◽  
Learning Models ◽  
One Step ◽  
The Web ◽  
Machine Learning Models

Abstract With the aim of increasing online privacy, we present a novel, machine-learning based approach to blocking one of the three main ways website visitors are tracked online—canvas fingerprinting. Because the act of canvas fingerprinting uses, at its core, a JavaScript program, and because many of these programs are reused across the web, we are able to fit several machine learning models around a semantic representation of a potentially offending program, achieving accurate and robust classifiers. Our supervised learning approach is trained on a dataset we created by scraping roughly half a million websites using a custom Google Chrome extension storing information related to the canvas. Classification leverages our key insight that the images drawn by canvas fingerprinting programs have a facially distinct appearance, allowing us to manually classify files based on the images drawn; we take this approach one step further and train our classifiers not on the malleable images themselves, but on the more-difficult-to-change, underlying source code generating the images. As a result, ML-CB allows for more accurate tracker blocking.

scholarly journals A Web Interface for Analyzing Hate Speech

2021 ◽  
Vol 13 (3) ◽  
pp. 80
Author(s):  
Lazaros Vrysis ◽  
Nikolaos Vryzas ◽  
Rigas Kotsakis ◽  
Theodora Saridou ◽  
Maria Matsiola ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Graphical User Interface ◽  
Hate Speech ◽  
Web Interface ◽  
Learning Models ◽  
Speech Detection ◽  
Media Services ◽  
The Web ◽  
Machine Learning Models

Social media services make it possible for an increasing number of people to express their opinion publicly. In this context, large amounts of hateful comments are published daily. The PHARM project aims at monitoring and modeling hate speech against refugees and migrants in Greece, Italy, and Spain. In this direction, a web interface for the creation and the query of a multi-source database containing hate speech-related content is implemented and evaluated. The selected sources include Twitter, YouTube, and Facebook comments and posts, as well as comments and articles from a selected list of websites. The interface allows users to search in the existing database, scrape social media using keywords, annotate records through a dedicated platform and contribute new content to the database. Furthermore, the functionality for hate speech detection and sentiment analysis of texts is provided, making use of novel methods and machine learning models. The interface can be accessed online with a graphical user interface compatible with modern internet browsers. For the evaluation of the interface, a multifactor questionnaire was formulated, targeting to record the users’ opinions about the web interface and the corresponding functionality.

Telugu News Data Classification Using Machine Learning Approach

2022 ◽  
pp. 181-194
Author(s):  
Bala Krishna Priya G. ◽  
Jabeen Sultana ◽  
Usha Rani M.
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Research Work ◽  
Learning Approach ◽  
Fake News ◽  
Learning Models ◽  
Machine Learning Classifiers ◽  
Proposed Model ◽  
Machine Learning Approach ◽  
Machine Learning Models

Mining Telugu news data and categorizing based on public sentiments is quite important since a lot of fake news emerged with rise of social media. Identifying whether news text is positive, negative, or neutral and later classifying the data in which areas they fall like business, editorial, entertainment, nation, and sports is included throughout this research work. This research work proposes an efficient model by adopting machine learning classifiers to perform classification on Telugu news data. The results obtained by various machine-learning models are compared, and an efficient model is found, and it is observed that the proposed model outperformed with reference to accuracy, precision, recall, and F1-score.

scholarly journals Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning

2019 ◽  
Vol 10 (35) ◽  
pp. 8154-8163 ◽  
Author(s):  
Yao Zhang ◽  
Alpha A. Lee
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Supervised Learning ◽  
Molecular Properties ◽  
Learning Models ◽  
Molecular Properties Prediction ◽  
Design Experiments ◽  
Machine Learning Models

We report a statistically principled method to quantify the uncertainty of machine learning models for molecular properties prediction. We show that this uncertainty estimate can be used to judiciously design experiments.

scholarly journals Forecasting admissions in psychiatric hospitals before and during Covid-19

2021 ◽  
Author(s):  
Jan Wolff ◽  
Ansgar Klimke ◽  
Michael Marschollek ◽  
Tim Kacprowski
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Hospital Admissions ◽  
Model Performance ◽  
Psychiatric Hospitals ◽  
Time Series Models ◽  
Learning Models ◽  
One Step ◽  
Machine Learning Models ◽  
Better Than

Introduction The COVID-19 pandemic has strong effects on most health care systems and individual services providers. Forecasting of admissions can help for the efficient organisation of hospital care. We aimed to forecast the number of admissions to psychiatric hospitals before and during the COVID-19 pandemic and we compared the performance of machine learning models and time series models. This would eventually allow to support timely resource allocation for optimal treatment of patients. Methods We used admission data from 9 psychiatric hospitals in Germany between 2017 and 2020. We compared machine learning models with time series models in weekly, monthly and yearly forecasting before and during the COVID-19 pandemic. Our models were trained and validated with data from the first two years and tested in prospectively sliding time-windows in the last two years. Results A total of 90,686 admissions were analysed. The models explained up to 90% of variance in hospital admissions in 2019 and 75% in 2020 with the effects of the COVID-19 pandemic. The best models substantially outperformed a one-step seasonal naive forecast (seasonal mean absolute scaled error (sMASE) 2019: 0.59, 2020: 0.76). The best model in 2019 was a machine learning model (elastic net, mean absolute error (MAE): 7.25). The best model in 2020 was a time series model (exponential smoothing state space model with Box-Cox transformation, ARMA errors and trend and seasonal components, MAE: 10.44), which adjusted more quickly to the shock effects of the COVID-19 pandemic. Models forecasting admissions one week in advance did not perform better than monthly and yearly models in 2019 but they did in 2020. The most important features for the machine learning models were calendrical variables. Conclusion Model performance did not vary much between different modelling approaches before the COVID-19 pandemic and established forecasts were substantially better than one-step seasonal naive forecasts. However, weekly time series models adjusted quicker to the COVID-19 related shock effects. In practice, different forecast horizons could be used simultaneously to allow both early planning and quick adjustments to external effects.

Confederated learning in healthcare: training machine learning models using disconnected data separated by individual, data type and identity for Large-Scale Health System Intelligence (Preprint)

2020 ◽  
Author(s):  
Dianbo Liu ◽  
Kathe Fox ◽  
Griffin Weber ◽  
Tim Miller
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Ischemic Heart Disease ◽  
Psychological Disorders ◽  
Data Type ◽  
Learning Approach ◽  
Learning Method ◽  
Learning Models ◽  
Data Types ◽  
Machine Learning Models

BACKGROUND A patient’s health information is generally fragmented across silos because it follows how care is delivered: multiple providers in multiple settings. Though it is technically feasible to reunite data for analysis in a manner that underpins a rapid learning healthcare system, privacy concerns and regulatory barriers limit data centralization for this purpose. OBJECTIVE Machine learning can be conducted in a federated manner on patient datasets with the same set of variables, but separated across storage. But federated learning cannot handle the situation where different data types for a given patient are separated vertically across different organizations and when patient ID matching across different institutions is difficult. We call methods that enable machine learning model training on data separated by two or more dimensions “confederated machine learning.” We propose and evaluate confederated learning for training machine learning models to stratify the risk of several diseases among silos when data are horizontally separated by individual, vertically separated by data type, and separated by identity without patient ID matching. METHODS The confederated learning method can be intuitively understood as a distributed learning method with representation learning, generative model, imputation method and data augmentation elements.The confederated learning method we developed consists of three steps: Step 1) Conditional generative adversarial networks with matching loss (cGAN) were trained using data from the central analyzer to infer one data type from another, for example, inferring medications using diagnoses. Generative (cGAN) models were used in this study because a considerable percentage of individuals has not paired data types. For instance, a patient may only have his or her diagnoses in the database but not medication information due to insurance enrolment. cGAN can utilize data with paired information by minimizing matching loss and data without paired information by minimizing adversarial loss. Step 2) Missing data types from each silo were inferred using the model trained in step 1. Step 3) Task-specific models, such as a model to predict diagnoses of diabetes, were trained in a federated manner across all silos simultaneously. RESULTS We conducted experiments to train disease prediction models using confederated learning on a large nationwide health insurance dataset from the U.S that is split into 99 silos. The models stratify individuals by their risk of diabetes, psychological disorders or ischemic heart disease in the next two years, using diagnoses, medication claims and clinical lab test records of patients (See Methods section for details). The goal of these experiments is to test whether a confederated learning approach can simultaneously address the two types of separation mentioned above. CONCLUSIONS we demonstrated that health data distributed across silos separated by individual and data type can be used to train machine learning models without moving or aggregating data. Our method obtains predictive accuracy competitive to a centralized upper bound in predicting risks of diabetes, psychological disorders or ischemic heart disease using previous diagnoses, medications and lab tests as inputs. We compared the performance of a confederated learning approach with models trained on centralized data, only data with the central analyzer or a single data type across silos. The experimental results suggested that confederated learning trained predictive models efficiently across disconnected silos. CLINICALTRIAL NA

scholarly journals Predicting unstable software benchmarks using static source code features

2021 ◽  
Vol 26 (6) ◽  
Author(s):  
Christoph Laaber ◽  
Mikael Basmaci ◽  
Pasquale Salza
Keyword(s):  
Machine Learning ◽  
Source Code ◽  
Prediction Performance ◽  
Repeated Measurements ◽  
Good Prediction ◽  
Testing Time ◽  
Learning Models ◽  
Actual Performance ◽  
Meta Information ◽  
Machine Learning Models

AbstractSoftware benchmarks are only as good as the performance measurements they yield. Unstable benchmarks show high variability among repeated measurements, which causes uncertainty about the actual performance and complicates reliable change assessment. However, if a benchmark is stable or unstable only becomes evident after it has been executed and its results are available. In this paper, we introduce a machine-learning-based approach to predict a benchmark’s stability without having to execute it. Our approach relies on 58 statically-computed source code features, extracted for benchmark code and code called by a benchmark, related to (1) meta information, e.g., lines of code (LOC), (2) programming language elements, e.g., conditionals or loops, and (3) potentially performance-impacting standard library calls, e.g., file and network input/output (I/O). To assess our approach’s effectiveness, we perform a large-scale experiment on 4,461 Go benchmarks coming from 230 open-source software (OSS) projects. First, we assess the prediction performance of our machine learning models using 11 binary classification algorithms. We find that Random Forest performs best with good prediction performance from 0.79 to 0.90, and 0.43 to 0.68, in terms of AUC and MCC, respectively. Second, we perform feature importance analyses for individual features and feature categories. We find that 7 features related to meta-information, slice usage, nested loops, and synchronization application programming interfaces (APIs) are individually important for good predictions; and that the combination of all features of the called source code is paramount for our model, while the combination of features of the benchmark itself is less important. Our results show that although benchmark stability is affected by more than just the source code, we can effectively utilize machine learning models to predict whether a benchmark will be stable or not ahead of execution. This enables spending precious testing time on reliable benchmarks, supporting developers to identify unstable benchmarks during development, allowing unstable benchmarks to be repeated more often, estimating stability in scenarios where repeated benchmark execution is infeasible or impossible, and warning developers if new benchmarks or existing benchmarks executed in new environments will be unstable.

scholarly journals Comparative Analysis of Machine Learning Models for Day-Ahead Photovoltaic Power Production Forecasting

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 1081
Author(s):  
Spyros Theocharides ◽  
Marios Theristis ◽  
George Makrides ◽  
Marios Kynigos ◽  
Chrysovalantis Spanias ◽  
...  
Keyword(s):  
Machine Learning ◽  
Supervised Learning ◽  
Regression Tree ◽  
Training Data ◽  
Support Vector ◽  
Learning Models ◽  
Bayesian Neural Network ◽  
Production Forecasting ◽  
Main Challenge ◽  
Machine Learning Models

A main challenge for integrating the intermittent photovoltaic (PV) power generation remains the accuracy of day-ahead forecasts and the establishment of robust performing methods. The purpose of this work is to address these technological challenges by evaluating the day-ahead PV production forecasting performance of different machine learning models under different supervised learning regimes and minimal input features. Specifically, the day-ahead forecasting capability of Bayesian neural network (BNN), support vector regression (SVR), and regression tree (RT) models was investigated by employing the same dataset for training and performance verification, thus enabling a valid comparison. The training regime analysis demonstrated that the performance of the investigated models was strongly dependent on the timeframe of the train set, training data sequence, and application of irradiance condition filters. Furthermore, accurate results were obtained utilizing only the measured power output and other calculated parameters for training. Consequently, useful information is provided for establishing a robust day-ahead forecasting methodology that utilizes calculated input parameters and an optimal supervised learning approach. Finally, the obtained results demonstrated that the optimally constructed BNN outperformed all other machine learning models achieving forecasting accuracies lower than 5%.

scholarly journals Development and Validation of a Machine Learning Approach for Automated Severity Assessment of COVID-19 Based on Clinical and Imaging Data: Retrospective Study

10.2196/24572 ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. e24572
Author(s):  
Juan Carlos Quiroz ◽  
You-Zhen Feng ◽  
Zhong-Yuan Cheng ◽  
Dana Rezazadegan ◽  
Ping-Kang Chen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Predictive Power ◽  
Care Delivery ◽  
Learning Approach ◽  
Imaging Features ◽  
Severity Assessment ◽  
Imaging Data ◽  
Learning Models ◽  
Machine Learning Approach ◽  
Machine Learning Models

Background COVID-19 has overwhelmed health systems worldwide. It is important to identify severe cases as early as possible, such that resources can be mobilized and treatment can be escalated. Objective This study aims to develop a machine learning approach for automated severity assessment of COVID-19 based on clinical and imaging data. Methods Clinical data—including demographics, signs, symptoms, comorbidities, and blood test results—and chest computed tomography scans of 346 patients from 2 hospitals in the Hubei Province, China, were used to develop machine learning models for automated severity assessment in diagnosed COVID-19 cases. We compared the predictive power of the clinical and imaging data from multiple machine learning models and further explored the use of four oversampling methods to address the imbalanced classification issue. Features with the highest predictive power were identified using the Shapley Additive Explanations framework. Results Imaging features had the strongest impact on the model output, while a combination of clinical and imaging features yielded the best performance overall. The identified predictive features were consistent with those reported previously. Although oversampling yielded mixed results, it achieved the best model performance in our study. Logistic regression models differentiating between mild and severe cases achieved the best performance for clinical features (area under the curve [AUC] 0.848; sensitivity 0.455; specificity 0.906), imaging features (AUC 0.926; sensitivity 0.818; specificity 0.901), and a combination of clinical and imaging features (AUC 0.950; sensitivity 0.764; specificity 0.919). The synthetic minority oversampling method further improved the performance of the model using combined features (AUC 0.960; sensitivity 0.845; specificity 0.929). Conclusions Clinical and imaging features can be used for automated severity assessment of COVID-19 and can potentially help triage patients with COVID-19 and prioritize care delivery to those at a higher risk of severe disease.

Sign in / Sign up

Export Citation Format

Share Document