Dynamic Features Spaces and Machine Learning: Open Problems and Synthetic Data Sets

Abstract There is a growing demand for the uptake of modern artificial intelligence technologies within healthcare systems. Many of these technologies exploit historical patient health data to build powerful predictive models that can be used to improve diagnosis and understanding of disease. However, there are many issues concerning patient privacy that need to be accounted for in order to enable this data to be better harnessed by all sectors. One approach that could offer a method of circumventing privacy issues is the creation of realistic synthetic data sets that capture as many of the complexities of the original data set (distributions, non-linear relationships, and noise) but that does not actually include any real patient data. While previous research has explored models for generating synthetic data sets, here we explore the integration of resampling, probabilistic graphical modelling, latent variable identification, and outlier analysis for producing realistic synthetic data based on UK primary care patient data. In particular, we focus on handling missingness, complex interactions between variables, and the resulting sensitivity analysis statistics from machine learning classifiers, while quantifying the risks of patient re-identification from synthetic datapoints. We show that, through our approach of integrating outlier analysis with graphical modelling and resampling, we can achieve synthetic data sets that are not significantly different from original ground truth data in terms of feature distributions, feature dependencies, and sensitivity analysis statistics when inferring machine learning classifiers. What is more, the risk of generating synthetic data that is identical or very similar to real patients is shown to be low.

Download Full-text

Reconstructing Complex Cardiac Excitation Waves From Incomplete Data Using Echo State Networks and Convolutional Autoencoders

Frontiers in Applied Mathematics and Statistics ◽

10.3389/fams.2020.616584 ◽

2021 ◽

Vol 6 ◽

Author(s):

Sebastian Herzog ◽

Roland S. Zimmermann ◽

Johannes Abele ◽

Stefan Luther ◽

Ulrich Parlitz

Keyword(s):

Machine Learning ◽

Incomplete Data ◽

Synthetic Data ◽

Data Reconstruction ◽

Heart Cells ◽

Data Sets ◽

Electrical Excitation ◽

Echo State Networks ◽

Cardiac Dynamics ◽

Cardiac Excitation

The mechanical contraction of the pumping heart is driven by electrical excitation waves running across the heart muscle due to the excitable electrophysiology of heart cells. With cardiac arrhythmias these waves turn into stable or chaotic spiral waves (also called rotors) whose observation in the heart is very challenging. While mechanical motion can be measured in 3D using ultrasound, electrical activity can (so far) not be measured directly within the muscle and with limited resolution on the heart surface, only. To bridge the gap between measurable and not measurable quantities we use two approaches from machine learning, echo state networks and convolutional autoencoders, to solve two relevant data modelling tasks in cardiac dynamics: Recovering excitation patterns from noisy, blurred or undersampled observations and reconstructing complex electrical excitation waves from mechanical deformation. For the synthetic data sets used to evaluate both methods we obtained satisfying solutions with echo state networks and good results with convolutional autoencoders, both clearly indicating that the data reconstruction tasks can in principle be solved by means of machine learning.

Download Full-text

Machine Learning Approaches for the Analysis of Non-Metallic Inclusion Data Sets

AISTech2019 Proceedings of the Iron and Steel Technology Conference ◽

10.33313/377/275 ◽

2019 ◽

Author(s):

M. Webler ◽

B. Abdulsalam

Keyword(s):

Machine Learning ◽

Data Sets ◽

Learning Approaches ◽

Metallic Inclusion

Download Full-text

Trade-off Predictivity and Explainability for Machine-Learning Powered Predictive Toxicology: An in-Depth Investigation with Tox21 Data Sets

Chemical Research in Toxicology ◽

10.1021/acs.chemrestox.0c00373 ◽

2021 ◽

Vol 34 (2) ◽

pp. 541-549 ◽

Cited By ~ 1

Author(s):

Leihong Wu ◽

Ruili Huang ◽

Igor V. Tetko ◽

Zhonghua Xia ◽

Joshua Xu ◽

...

Keyword(s):

Machine Learning ◽

Data Sets ◽

Predictive Toxicology ◽

Trade Off

Download Full-text

Using Machine Learning Methods to Identify Particle Types from Doppler Lidar Measurements in Iceland

Remote Sensing ◽

10.3390/rs13132433 ◽

2021 ◽

Vol 13 (13) ◽

pp. 2433

Author(s):

Shu Yang ◽

Fengchao Peng ◽

Sibylle von Löwis ◽

Guðrún Nína Petersen ◽

David Christian Finger

Keyword(s):

Machine Learning ◽

Weather Conditions ◽

Dust Storms ◽

Machine Learning Algorithms ◽

Lidar Data ◽

Data Sets ◽

Doppler Lidar ◽

Lidar Measurements ◽

Using Data ◽

Filter Noise

Doppler lidars are used worldwide for wind monitoring and recently also for the detection of aerosols. Automatic algorithms that classify the lidar signals retrieved from lidar measurements are very useful for the users. In this study, we explore the value of machine learning to classify backscattered signals from Doppler lidars using data from Iceland. We combined supervised and unsupervised machine learning algorithms with conventional lidar data processing methods and trained two models to filter noise signals and classify Doppler lidar observations into different classes, including clouds, aerosols and rain. The results reveal a high accuracy for noise identification and aerosols and clouds classification. However, precipitation detection is underestimated. The method was tested on data sets from two instruments during different weather conditions, including three dust storms during the summer of 2019. Our results reveal that this method can provide an efficient, accurate and real-time classification of lidar measurements. Accordingly, we conclude that machine learning can open new opportunities for lidar data end-users, such as aviation safety operators, to monitor dust in the vicinity of airports.

Download Full-text

A top-level model of case-based argumentation for explanation: Formalisation and experiments

Argument & Computation ◽

10.3233/aac-210009 ◽

2021 ◽

pp. 1-36

Author(s):

Henry Prakken ◽

Rosa Ratsma

Keyword(s):

Machine Learning ◽

Decision Making ◽

Linear Models ◽

Evaluation Studies ◽

Data Sets ◽

Machine Learning Applications ◽

Level Model ◽

Similarities And Differences ◽

Further Development ◽

Case Based

This paper proposes a formal top-level model of explaining the outputs of machine-learning-based decision-making applications and evaluates it experimentally with three data sets. The model draws on AI & law research on argumentation with cases, which models how lawyers draw analogies to past cases and discuss their relevant similarities and differences in terms of relevant factors and dimensions in the problem domain. A case-based approach is natural since the input data of machine-learning applications can be seen as cases. While the approach is motivated by legal decision making, it also applies to other kinds of decision making, such as commercial decisions about loan applications or employee hiring, as long as the outcome is binary and the input conforms to this paper’s factor- or dimension format. The model is top-level in that it can be extended with more refined accounts of similarities and differences between cases. It is shown to overcome several limitations of similar argumentation-based explanation models, which only have binary features and do not represent the tendency of features towards particular outcomes. The results of the experimental evaluation studies indicate that the model may be feasible in practice, but that further development and experimentation is needed to confirm its usefulness as an explanation model. Main challenges here are selecting from a large number of possible explanations, reducing the number of features in the explanations and adding more meaningful information to them. It also remains to be investigated how suitable our approach is for explaining non-linear models.

Download Full-text

A novel framework for designing a multi-DoF prosthetic wrist control using machine learning

Scientific Reports ◽

10.1038/s41598-021-94449-1 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Chinmay P. Swami ◽

Nicholas Lenhard ◽

Jiyeon Kang

Keyword(s):

Machine Learning ◽

Random Forest ◽

Upper Limb ◽

Daily Living ◽

Machine Learning Algorithms ◽

Data Sets ◽

Random Forest Regression ◽

Prosthetic Devices ◽

Upper Limb Function ◽

The Neural Network

AbstractProsthetic arms can significantly increase the upper limb function of individuals with upper limb loss, however despite the development of various multi-DoF prosthetic arms the rate of prosthesis abandonment is still high. One of the major challenges is to design a multi-DoF controller that has high precision, robustness, and intuitiveness for daily use. The present study demonstrates a novel framework for developing a controller leveraging machine learning algorithms and movement synergies to implement natural control of a 2-DoF prosthetic wrist for activities of daily living (ADL). The data was collected during ADL tasks of ten individuals with a wrist brace emulating the absence of wrist function. Using this data, the neural network classifies the movement and then random forest regression computes the desired velocity of the prosthetic wrist. The models were trained/tested with ADLs where their robustness was tested using cross-validation and holdout data sets. The proposed framework demonstrated high accuracy (F-1 score of 99% for the classifier and Pearson’s correlation of 0.98 for the regression). Additionally, the interpretable nature of random forest regression was used to verify the targeted movement synergies. The present work provides a novel and effective framework to develop an intuitive control for multi-DoF prosthetic devices.

Download Full-text

Analysis of Risk Factors in Dementia Through Machine Learning

Journal of Alzheimer s Disease ◽

10.3233/jad-200955 ◽

2020 ◽

pp. 1-17

Author(s):

Francisco Javier Balea-Fernandez ◽

Beatriz Martinez-Vega ◽

Samuel Ortega ◽

Himar Fabelo ◽

Raquel Leon ◽

...

Keyword(s):

Machine Learning ◽

Optimization Algorithms ◽

Progressive Increase ◽

Control Group ◽

Data Sets ◽

Modifiable Factors ◽

Validation Set ◽

The One ◽

And Control ◽

Potential Tool

Background: Sociodemographic data indicate the progressive increase in life expectancy and the prevalence of Alzheimer’s disease (AD). AD is raised as one of the greatest public health problems. Its etiology is twofold: on the one hand, non-modifiable factors and on the other, modifiable. Objective: This study aims to develop a processing framework based on machine learning (ML) and optimization algorithms to study sociodemographic, clinical, and analytical variables, selecting the best combination among them for an accurate discrimination between controls and subjects with major neurocognitive disorder (MNCD). Methods: This research is based on an observational-analytical design. Two research groups were established: MNCD group (n = 46) and control group (n = 38). ML and optimization algorithms were employed to automatically diagnose MNCD. Results: Twelve out of 37 variables were identified in the validation set as the most relevant for MNCD diagnosis. Sensitivity of 100%and specificity of 71%were achieved using a Random Forest classifier. Conclusion: ML is a potential tool for automatic prediction of MNCD which can be applied to relatively small preclinical and clinical data sets. These results can be interpreted to support the influence of the environment on the development of AD.

Download Full-text

Detection of Malicious Software by Analyzing Distinct Artifacts Using Machine Learning and Deep Learning Algorithms

Electronics ◽

10.3390/electronics10141694 ◽

2021 ◽

Vol 10 (14) ◽

pp. 1694

Author(s):

Mathew Ashik ◽

A. Jyothish ◽

S. Anandaram ◽

P. Vinod ◽

Francesco Mercaldo ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Deep Learning ◽

Support Vector ◽

Malware Analysis ◽

Learning Approaches ◽

Dynamic Features ◽

System Calls ◽

Prevention Methods ◽

Structural Aspects

Malware is one of the most significant threats in today’s computing world since the number of websites distributing malware is increasing at a rapid rate. Malware analysis and prevention methods are increasingly becoming necessary for computer systems connected to the Internet. This software exploits the system’s vulnerabilities to steal valuable information without the user’s knowledge, and stealthily send it to remote servers controlled by attackers. Traditionally, anti-malware products use signatures for detecting known malware. However, the signature-based method does not scale in detecting obfuscated and packed malware. Considering that the cause of a problem is often best understood by studying the structural aspects of a program like the mnemonics, instruction opcode, API Call, etc. In this paper, we investigate the relevance of the features of unpacked malicious and benign executables like mnemonics, instruction opcodes, and API to identify a feature that classifies the executable. Prominent features are extracted using Minimum Redundancy and Maximum Relevance (mRMR) and Analysis of Variance (ANOVA). Experiments were conducted on four datasets using machine learning and deep learning approaches such as Support Vector Machine (SVM), Naïve Bayes, J48, Random Forest (RF), and XGBoost. In addition, we also evaluate the performance of the collection of deep neural networks like Deep Dense network, One-Dimensional Convolutional Neural Network (1D-CNN), and CNN-LSTM in classifying unknown samples, and we observed promising results using APIs and system calls. On combining APIs/system calls with static features, a marginal performance improvement was attained comparing models trained only on dynamic features. Moreover, to improve accuracy, we implemented our solution using distinct deep learning methods and demonstrated a fine-tuned deep neural network that resulted in an F1-score of 99.1% and 98.48% on Dataset-2 and Dataset-3, respectively.

Download Full-text

Generation of geometric interpolations of building types with deep variational autoencoders

Design Science ◽

10.1017/dsj.2020.31 ◽

2020 ◽

Vol 6 ◽

Author(s):

Jaime de Miguel Rodríguez ◽

Maria Eugenia Villafañe ◽

Luka Piškorec ◽

Fernando Sancho Caparrini

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Large Data ◽

Learning Model ◽

Large Data Sets ◽

Data Sets ◽

Connectivity Map ◽

Data Set ◽

3D Objects ◽

Machine Learning Model

Abstract This work presents a methodology for the generation of novel 3D objects resembling wireframes of building types. These result from the reconstruction of interpolated locations within the learnt distribution of variational autoencoders (VAEs), a deep generative machine learning model based on neural networks. The data set used features a scheme for geometry representation based on a ‘connectivity map’ that is especially suited to express the wireframe objects that compose it. Additionally, the input samples are generated through ‘parametric augmentation’, a strategy proposed in this study that creates coherent variations among data by enabling a set of parameters to alter representative features on a given building type. In the experiments that are described in this paper, more than 150 k input samples belonging to two building types have been processed during the training of a VAE model. The main contribution of this paper has been to explore parametric augmentation for the generation of large data sets of 3D geometries, showcasing its problems and limitations in the context of neural networks and VAEs. Results show that the generation of interpolated hybrid geometries is a challenging task. Despite the difficulty of the endeavour, promising advances are presented.

Download Full-text