The Future of Virtual Reality and Deep Learning in Visual Field Testing

2022 ◽  
pp. 233-248
Author(s):  
Scott E. Lee ◽  
Deborah Chen ◽  
Nikita Chigullapally ◽  
Suzy Chung ◽  
Allan Lu Lee ◽  
...  
Keyword(s):  
Machine Learning ◽  
Virtual Reality ◽  
Deep Learning ◽  
Eye Movements ◽  
Visual Field ◽  
Field Testing ◽  
Ocular Diseases ◽  
Clinical Tool ◽  
Subjective Bias ◽  
Improving Accuracy

The visual field (VF) examination is a useful clinical tool for monitoring a variety of ocular diseases. Despite its wide utility in eye clinics, the test as currently conducted is subject to an array of issues that interfere in obtaining accurate results. Visual field exams of patients suffering from additional ocular conditions are often unreliable due to interference between the comorbid diseases. To improve upon these shortcomings, virtual reality (VR) and deep learning are being explored as potential solutions. Virtual reality has been incorporated into novel visual field exams to provide a portable, 3D exam experience. Deep learning, a specialization of machine learning, has been used in conjunction with VR, such as in the iGlaucoma application, to limit subjective bias occurring from patients' eye movements. This chapter seeks to analyze and critique how VR and deep learning can augment the visual field experience by improving accuracy, reducing subjective bias, and ultimately, providing clinicians with a greater capacity to enhance patient outcomes.

scholarly journals The Use of Synthetic Electronic Health Record Data and Deep Learning to Improve Timing of High-Risk Heart Failure Surgical Intervention by Predicting Proximity to Catastrophic Decompensation

2020 ◽  
Vol 2 ◽  
Author(s):  
Aixia Guo ◽  
Randi E. Foraker ◽  
Robert M. MacGregor ◽  
Faraz M. Masood ◽  
Brian P. Cupps ◽  
...  
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Deep Learning ◽  
High Risk ◽  
Electronic Health Record ◽  
Surgical Intervention ◽  
Health Record ◽  
Predictive Capability ◽  
Clinical Tool ◽  
Electronic Health

Objective: Although many clinical metrics are associated with proximity to decompensation in heart failure (HF), none are individually accurate enough to risk-stratify HF patients on a patient-by-patient basis. The dire consequences of this inaccuracy in risk stratification have profoundly lowered the clinical threshold for application of high-risk surgical intervention, such as ventricular assist device placement. Machine learning can detect non-intuitive classifier patterns that allow for innovative combination of patient feature predictive capability. A machine learning-based clinical tool to identify proximity to catastrophic HF deterioration on a patient-specific basis would enable more efficient direction of high-risk surgical intervention to those patients who have the most to gain from it, while sparing others. Synthetic electronic health record (EHR) data are statistically indistinguishable from the original protected health information, and can be analyzed as if they were original data but without any privacy concerns. We demonstrate that synthetic EHR data can be easily accessed and analyzed and are amenable to machine learning analyses.Methods: We developed synthetic data from EHR data of 26,575 HF patients admitted to a single institution during the decade ending on 12/31/2018. Twenty-seven clinically-relevant features were synthesized and utilized in supervised deep learning and machine learning algorithms (i.e., deep neural networks [DNN], random forest [RF], and logistic regression [LR]) to explore their ability to predict 1-year mortality by five-fold cross validation methods. We conducted analyses leveraging features from prior to/at and after/at the time of HF diagnosis.Results: The area under the receiver operating curve (AUC) was used to evaluate the performance of the three models: the mean AUC was 0.80 for DNN, 0.72 for RF, and 0.74 for LR. Age, creatinine, body mass index, and blood pressure levels were especially important features in predicting death within 1-year among HF patients.Conclusions: Machine learning models have considerable potential to improve accuracy in mortality prediction, such that high-risk surgical intervention can be applied only in those patients who stand to benefit from it. Access to EHR-based synthetic data derivatives eliminates risk of exposure of EHR data, speeds time-to-insight, and facilitates data sharing. As more clinical, imaging, and contractile features with proven predictive capability are added to these models, the development of a clinical tool to assist in timing of intervention in surgical candidates may be possible.

A cybersickness review: causes, strategies, and classification methods

2021 ◽  
Vol 12 (1) ◽  
pp. 269-282
Author(s):  
Thiago Porcino ◽  
Daniela Trevisan ◽  
Esteban Clua
Keyword(s):  
Machine Learning ◽  
Virtual Reality ◽  
Deep Learning ◽  
Learning Approaches ◽  
Classification Methods ◽  
Review Of The Literature ◽  
Profile Data ◽  
Head Mounted Displays ◽  
Decision Paths ◽  
High Sense

Virtual reality (VR) and head-­mounted displays are continually gaining popularity in various fields such as education, military, entertainment, and health. Although such technologies provide a high sense of immersion, they can also trigger symptoms of discomfort. This condition is called cybersickness (CS) and is quite popular in recent virtual reality research. In this work we first present a review of the literature on theories of discomfort manifestations usually attributed to virtual reality environments. Following, we reviewed existing strategies aimed at minimizing CS problems and discussed how the CS measurement has been conducted based on subjective, bio­signal (or objective), and users profile data. We also describe and discuss related works that are aiming to mitigate cybersickness problems using deep and symbolic machine learning approaches. Although some works used methods to make deep learning explainable, they are not strongly affirmed by literature. For this reason in this work we argue that symbolic classifiers can be a good way to identify CS causes, once they possibilities human-­readability which is crucial for analyze the machine learning decision paths. In summary, from a total of 157 observed studies, 24 were excluded. Moreover, we believe that this work facilitates researchers to identify the leading causes for most discomfort situations in virtual reality environments, associate the most recommended strategies to minimize such discomfort, and explore different ways to conduct experiments involving machine learning to overcome cybersickness.

Deep Learning Based High-Resolution Remote Sensing Image classification

2017 ◽  
Vol 7 (10) ◽  
pp. 22
Author(s):  
Sumit Kaur
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Image Classification ◽  
Language Processing ◽  
Object Perception ◽  
Remote Sensing Image ◽  
Research Area ◽  
Remote Sensing Image Classification ◽  
Unsupervised Algorithms

Abstract- Deep learning is an emerging research area in machine learning and pattern recognition field which has been presented with the goal of drawing Machine Learning nearer to one of its unique objectives, Artificial Intelligence. It tries to mimic the human brain, which is capable of processing and learning from the complex input data and solving different kinds of complicated tasks well. Deep learning (DL) basically based on a set of supervised and unsupervised algorithms that attempt to model higher level abstractions in data and make it self-learning for hierarchical representation for classification. In the recent years, it has attracted much attention due to its state-of-the-art performance in diverse areas like object perception, speech recognition, computer vision, collaborative filtering and natural language processing. This paper will present a survey on different deep learning techniques for remote sensing image classification. 

Data science in economics: comprehensive review of advanced machine learning and deep learning methods

2020 ◽  
Author(s):  
Saeed Nosratabadi ◽  
Amir Mosavi ◽  
Puhong Duan ◽  
Pedram Ghamisi ◽  
Ferdinand Filip ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Data Science ◽  
State Of The Art ◽  
Science Methods ◽  
Learning Models ◽  
Diverse Range ◽  
Hybrid Machine ◽  
Economics Research

This paper provides a state-of-the-art investigation of advances in data science in emerging economic applications. The analysis was performed on novel data science methods in four individual classes of deep learning models, hybrid deep learning models, hybrid machine learning, and ensemble models. Application domains include a wide and diverse range of economics research from the stock market, marketing, and e-commerce to corporate banking and cryptocurrency. Prisma method, a systematic literature review methodology, was used to ensure the quality of the survey. The findings reveal that the trends follow the advancement of hybrid models, which, based on the accuracy metric, outperform other learning algorithms. It is further expected that the trends will converge toward the advancements of sophisticated hybrid deep learning models.

Eye movements in sports research and practice: Immersive technologies as optimal environments for the study of gaze behaviour

2020 ◽  
Author(s):  
David Harris ◽  
Mark Wilson ◽  
Tim Holmes ◽  
Toby de Burgh ◽  
Samuel James Vine
Keyword(s):  
Virtual Reality ◽  
Eye Movements ◽  
Eye Tracking ◽  
Visual Information ◽  
Successful Performance ◽  
Experimental Control ◽  
Research And Practice ◽  
Gaze Behaviour ◽  
Immersive Technologies

Head-mounted eye tracking has been fundamental for developing an understanding of sporting expertise, as the way in which performers sample visual information from the environment is a major determinant of successful performance. There is, however, a long running tension between the desire to study realistic, in-situ gaze behaviour and the difficulties of acquiring accurate ocular measurements in dynamic and fast-moving sporting tasks. Here, we describe how immersive technologies, such as virtual reality, offer an increasingly compelling approach for conducting eye movement research in sport. The possibility of studying gaze behaviour in representative and realistic environments, but with high levels of experimental control, could enable significant strides forward for eye tracking in sport and improve understanding of how eye movements underpin sporting skills. By providing a rationale for virtual reality as an optimal environment for eye tracking research, as well as outlining practical considerations related to hardware, software and data analysis, we hope to guide researchers and practitioners in the use of this approach.

Visual asymmetries during face encoding Increased dwell time and fixations in the upper and left hemifields

2018 ◽  
Author(s):  
Fatima Maria Felisberti
Keyword(s):  
Face Recognition ◽  
Eye Movements ◽  
Visual Field ◽  
Face Processing ◽  
Dwell Time ◽  
The Other ◽  
Environmental Cues ◽  
Reading Habits ◽  
The Right

Visual field asymmetries (VFA) in the encoding of groups rather than individual faces has been rarely investigated. Here, eye movements (dwell time (DT) and fixations (Fix)) were recorded during the encoding of three groups of four faces tagged with cheating, cooperative, or neutral behaviours. Faces in each of the three groups were placed in the upper left (UL), upper right (UR), lower left (LL), or lower right (LR) quadrants. Face recognition was equally high in the three groups. In contrast, the proportion of DT and Fix were higher for faces in the left than the right hemifield and in the upper rather than the lower hemifield. The overall time spent looking at the UL was higher than in the other quadrants. The findings are relevant to the understanding of VFA in face processing, especially groups of faces, and might be linked to environmental cues and/or reading habits.

Deep Learning for text in limted data settings

2020 ◽  
Author(s):  
Pathikkumar Patel ◽  
Bhargav Lad ◽  
Jinan Fiaidhi
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Transfer Learning ◽  
Text Classification ◽  
State Of The Art ◽  
Time Series Forecasting ◽  
Text Data ◽  
Performance Levels

During the last few years, RNN models have been extensively used and they have proven to be better for sequence and text data. RNNs have achieved state-of-the-art performance levels in several applications such as text classification, sequence to sequence modelling and time series forecasting. In this article we will review different Machine Learning and Deep Learning based approaches for text data and look at the results obtained from these methods. This work also explores the use of transfer learning in NLP and how it affects the performance of models on a specific application of sentiment analysis.

Sign in / Sign up

Export Citation Format

Share Document