scholarly journals Two hours in Hollywood: A manually annotated ground truth data set of eye movements during movie clip watching

2020 ◽  
Vol 13 (4) ◽  
Author(s):  
Ioannis Agtzidis ◽  
Mikhail Startsev ◽  
Michael Dorr
Keyword(s):  
Eye Movement ◽  
Large Scale ◽  
Ground Truth ◽  
Training Set ◽  
Event Type ◽  
Short Article ◽  
Data Set ◽  
Ground Truth Data ◽  
The Gaze ◽  
Movie Clip

In this short article we present our manual annotation of the eye movement events in a subset of the large-scale eye tracking data set Hollywood2. Our labels include fixations, saccades, and smooth pursuits, as well as a noise event type (the latter representing either blinks, loss of tracking, or physically implausible signals). In order to achieve more consistent annotations, the gaze samples were labelled by a novice rater based on rudimentary algorithmic suggestions, and subsequently corrected by an expert rater. Overall, we annotated eye movement events in the recordings corresponding to 50 randomly selected test set clips and 6 training set clips from Hollywood2, which were viewed by 16 observers and amount to a total of approximately 130 minutes of gaze data. In these labels, 62.4% of the samples were attributed to fixations, 9.1% – to saccades, and, notably, 24.2% – to pursuit (the remainder marked as noise). After evaluation of 15 published eye movement classification algorithms on our newly collected annotated data set, we found that the most recent algorithms perform very well on average, and even reach human-level labelling quality for fixations and saccades, but all have a much larger room for improvement when it comes to smooth pursuit classification. The data set is made available at https://gin.g- node.org/ioannis.agtzidis/hollywood2_em.

scholarly journals Characterizing and automatically detecting smooth pursuit in a large-scale ground-truth data set of dynamic natural scenes

2019 ◽  
Vol 19 (14) ◽  
pp. 10 ◽  
Author(s):  
Mikhail Startsev ◽  
Ioannis Agtzidis ◽  
Michael Dorr
Keyword(s):  
Smooth Pursuit ◽  
Large Scale ◽  
Ground Truth ◽  
Natural Scenes ◽  
Data Set ◽  
Ground Truth Data

scholarly journals Systematic prediction of drug resistance caused by transporter genes in cancer cells

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yao Shen ◽  
Zhipeng Yan
Keyword(s):  
Drug Resistance ◽  
Large Scale ◽  
Ground Truth ◽  
Data Sets ◽  
Drug Transporter ◽  
Data Set ◽  
Ground Truth Data ◽  
Public Data ◽  
The Difference ◽  
Novel Drug

AbstractTo study the drug resistance problem caused by transporters, we leveraged multiple large-scale public data sets of drug sensitivity, cell line genetic and transcriptional profiles, and gene silencing experiments. Through systematic integration of these data sets, we built various machine learning models to predict the difference between cell viability upon drug treatment and the silencing of its target across the same cell lines. More than 50% of the models built with the same data set or with independent data sets successfully predicted the testing set with significant correlation to the ground truth data. Features selected by our models were also significantly enriched in known drug transporters annotated in DrugBank for more than 60% of the models. Novel drug-transporter interactions were discovered, such as lapatinib and gefitinib with ABCA1, olaparib and NVPADW742 with ABCC3, and gefitinib and AZ628 with SLC4A4. Furthermore, we identified ABCC3, SLC12A7, SLCO4A1, SERPINA1, and SLC22A3 as potential transporters for erlotinib, three of which are also significantly more highly expressed in patients who were resistant to therapy in a clinical trial.

Chemical Proportionality within Molecular Networks

2021 ◽  
Author(s):  
Daniel Petras ◽  
Andrés Mauricio Caraballo-Rodríguez ◽  
Alan K. Jarmusch ◽  
Carlos Molina-Santiago ◽  
Julia M. Gauglitz ◽  
...  
Keyword(s):  
Natural Products ◽  
Ground Truth ◽  
Mass Spectrometry Data ◽  
Molecular Networks ◽  
Data Series ◽  
Sequential Data ◽  
Chemical Transformations ◽  
Data Set ◽  
Molecular Networking ◽  
Ground Truth Data

Molecular networking of non-targeted tandem mass spectrometry data connects structurally related molecules based on similar fragmentation spectra. Here we report the Chemical Proportionality contextualization of molecular networks. ChemProp scores the changes of abundance between two connected nodes over sequential data series which can be displayed as a direction within the network to prioritize potential biological and chemical transformations or proportional changes of related compounds. We tested the ChemProp workflow on a ground truth data set of defined mixture and highlighted the utility of the tool to prioritize specific molecules within biological samples, including bacterial transformations of bile acids, human drug metabolism and bacterial natural products biosynthesis. The ChemProp workflow is freely available through the Global Natural Products Social Molecular Networking environment.<br><b> </b>

INTERDISCOURSE SWITCHING IN DRAMA TEXT. GAZE PATTERNS AND COMPREHENSION CHECK RESULTS

2021 ◽  
pp. 55-66
Author(s):  
M.I. Kiose ◽  
◽  
A.A. Rzheshevskaya ◽  
Keyword(s):  
Eye Movement ◽  
Significant Influence ◽  
Cognitive Process ◽  
Event Type ◽  
The Gaze ◽  
Gaze Patterns ◽  
Discourse Interpretation ◽  
Areas Of Interest ◽  
Interpretation Patterns ◽  
Event Construal

The study explores the cognitive process of interdiscourse switching which occurs in reading drama plays with the author’s discourse fragments incorporated (Areas of Interest). The oculographic experiment reveals the gaze patterns and the discourse interpretation patterns, more and less typical of the process. The experiment is preceded by the parametric and annotation analysis of interdiscourse switching construal. Interestingly, there exist several construal parameter groups contingent with eye movement load redistribution, among them are Participant construal, Event construal, and Perspective construal. The results sufficed to show that construal effects also affect mentioning Areas of Interest in the subjects’ responses, the most significant influence is displayed by Participant Agentivity and Complexity parameters as well as by Event Type parameters.

Regularization strategies for deep-learning-based salt model building

2019 ◽  
Vol 7 (4) ◽  
pp. T911-T922
Author(s):  
Satyakee Sen ◽  
Sribharath Kainkaryam ◽  
Cen Ong ◽  
Arvind Sharma
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Model Building ◽  
Ground Truth ◽  
Real Data ◽  
Test Time ◽  
Generalization Error ◽  
Training Set ◽  
Production Scale ◽  
Ensemble Strategy

Salt model building has long been considered a severe bottleneck for large-scale 3D seismic imaging projects. It is one of the most time-consuming, labor-intensive, and difficult-to-automate processes in the entire depth imaging workflow requiring significant intervention by domain experts to manually interpret the salt bodies on noisy, low-frequency, and low-resolution seismic images at each iteration of the salt model building process. The difficulty and need for automating this task is well-recognized by the imaging community and has propelled the use of deep-learning-based convolutional neural network (CNN) architectures to carry out this task. However, significant challenges remain for reliable production-scale deployment of CNN-based methods for salt model building. This is mainly due to the poor generalization capabilities of these networks. When used on new surveys, never seen by the CNN models during the training stage, the interpretation accuracy of these models drops significantly. To remediate this key problem, we have introduced a U-shaped encoder-decoder type CNN architecture trained using a specialized regularization strategy aimed at reducing the generalization error of the network. Our regularization scheme perturbs the ground truth labels in the training set. Two different perturbations are discussed: one that randomly changes the labels of the training set, flipping salt labels to sediments and vice versa and the second that smooths the labels. We have determined that such perturbations act as a strong regularizer preventing the network from making highly confident predictions on the training set and thus reducing overfitting. An ensemble strategy is also used for test time augmentation that is shown to further improve the accuracy. The robustness of our CNN models, in terms of reduced generalization error and improved interpretation accuracy is demonstrated with real data examples from the Gulf of Mexico.

scholarly journals Comparative Analysis of Supervised and Unsupervised Approaches Applied to Large-Scale “In The Wild” Face Verification

Symmetry ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 1832
Author(s):  
Tomasz Hachaj ◽  
Patryk Mazurek
Keyword(s):  
Pattern Recognition ◽  
Large Scale ◽  
Statistical Significance ◽  
Ground Truth ◽  
Classification Algorithm ◽  
Adjusted Rand Index ◽  
Face Verification ◽  
Data Set ◽  
In The Wild ◽  
Unsupervised Approaches

Deep learning-based feature extraction methods and transfer learning have become common approaches in the field of pattern recognition. Deep convolutional neural networks trained using tripled-based loss functions allow for the generation of face embeddings, which can be directly applied to face verification and clustering. Knowledge about the ground truth of face identities might improve the effectiveness of the final classification algorithm; however, it is also possible to use ground truth clusters previously discovered using an unsupervised approach. The aim of this paper is to evaluate the potential improvement of classification results of state-of-the-art supervised classification methods trained with and without ground truth knowledge. In this study, we use two sufficiently large data sets containing more than 200,000 “taken in the wild” images, each with various resolutions, visual quality, and face poses which, in our opinion, guarantee the statistical significance of the results. We examine several clustering and supervised pattern recognition algorithms and find that knowledge about the ground truth has a very small influence on the Fowlkes–Mallows score (FMS) of the classification algorithm. In the case of the classification algorithm that obtained the highest accuracy in our experiment, the FMS improved by only 5.3% (from 0.749 to 0.791) in the first data set and by 6.6% (from 0.652 to 0.718) in the second data set. Our results show that, beside highly secure systems in which face verification is a key component, face identities discovered by unsupervised approaches can be safely used for training supervised classifiers. We also found that the Silhouette Coefficient (SC) of unsupervised clustering is positively correlated with the Adjusted Rand Index, V-measure score, and Fowlkes–Mallows score and, so, we can use the SC as an indicator of clustering performance when the ground truth of face identities is not known. All of these conclusions are important findings for large-scale face verification problems. The reason for this is the fact that skipping the verification of people’s identities before supervised training saves a lot of time and resources.

SaltSeg: Automatic 3D salt segmentation using a deep convolutional neural network

2019 ◽  
Vol 7 (3) ◽  
pp. SE113-SE122 ◽  
Author(s):  
Yunzhi Shi ◽  
Xinming Wu ◽  
Sergey Fomel
Keyword(s):  
Large Scale ◽  
Model Building ◽  
Ground Truth ◽  
Velocity Model ◽  
Training Data ◽  
Data Sets ◽  
Validation Data ◽  
Data Set ◽  
Seismic Image ◽  
Data Generator

Salt boundary interpretation is important for the understanding of salt tectonics and velocity model building for seismic migration. Conventional methods consist of computing salt attributes and extracting salt boundaries. We have formulated the problem as 3D image segmentation and evaluated an efficient approach based on deep convolutional neural networks (CNNs) with an encoder-decoder architecture. To train the model, we design a data generator that extracts randomly positioned subvolumes from large-scale 3D training data set followed by data augmentation, then feed a large number of subvolumes into the network while using salt/nonsalt binary labels generated by thresholding the velocity model as ground truth labels. We test the model on validation data sets and compare the blind test predictions with the ground truth. Our results indicate that our method is capable of automatically capturing subtle salt features from the 3D seismic image with less or no need for manual input. We further test the model on a field example to indicate the generalization of this deep CNN method across different data sets.

scholarly journals A Product Feature Inference Model for Mining Implicit Customer Preferences Within Large Scale Social Media Networks

2015 ◽  
Author(s):  
Suppawong Tuarob ◽  
Conrad S. Tucker
Keyword(s):  
Social Media ◽  
Large Scale ◽  
Ground Truth ◽  
Inference Model ◽  
Underlying Assumption ◽  
Ground Truth Data ◽  
Social Media Networks ◽  
Customer Preferences ◽  
Product Features ◽  
Online Sources

The acquisition and mining of product feature data from online sources such as customer review websites and large scale social media networks is an emerging area of research. In many existing design methodologies that acquire product feature preferences form online sources, the underlying assumption is that product features expressed by customers are explicitly stated and readily observable to be mined using product feature extraction tools. In many scenarios however, product feature preferences expressed by customers are implicit in nature and do not directly map to engineering design targets. For example, a customer may implicitly state “wow I have to squint to read this on the screen”, when the explicit product feature may be a larger screen. The authors of this work propose an inference model that automatically assigns the most probable explicit product feature desired by a customer, given an implicit preference expressed. The algorithm iteratively refines its inference model by presenting a hypothesis and using ground truth data, determining its statistical validity. A case study involving smartphone product features expressed through Twitter networks is presented to demonstrate the effectiveness of the proposed methodology.

scholarly journals Terrestrial Laser Scanning and Ground Truth Data for Characterizing Downed Dead Wood

2020 ◽  
Author(s):  
Tuomas Yrttimaa ◽  
Ninni Saarinen ◽  
Ville Luoma ◽  
Topi Tanhuanpää ◽  
Ville Kankare ◽  
...  
Keyword(s):  
Boreal Forests ◽  
Laser Scanning ◽  
Dead Wood ◽  
Terrestrial Laser Scanning ◽  
Ground Truth ◽  
Point Clouds ◽  
Data Set ◽  
Ground Truth Data ◽  
Standing Trees ◽  
Downed Dead Wood

The feasibility of terrestrial laser scanning (TLS) in characterizing standing trees has been frequently investigated, while less effort has been put in quantifying downed dead wood using TLS. To advance dead wood characterization using TLS, we collected TLS point clouds and downed dead wood information from 20 sample plots (32 m x 32 m in size) located in southern Finland. This data set can be used in developing new algorithms for downed dead wood detection and characterization as well as for understanding spatial patterns of downed dead wood in boreal forests.

scholarly journals Assignment Flow for Order-Constrained OCT Segmentation

2021 ◽  
Author(s):  
Dmitrij Sitenko ◽  
Bastian Boll ◽  
Christoph Schnörr
Keyword(s):  
Geometric Approach ◽  
Ground Truth ◽  
Retinal Cell ◽  
Dice Similarity Coefficient ◽  
Retinal Layer ◽  
Healthy Human ◽  
Data Set ◽  
Ground Truth Data ◽  
Global Shape ◽  
Layer Segmentation

AbstractAt the present time optical coherence tomography (OCT) is among the most commonly used non-invasive imaging methods for the acquisition of large volumetric scans of human retinal tissues and vasculature. The substantial increase of accessible highly resolved 3D samples at the optic nerve head and the macula is directly linked to medical advancements in early detection of eye diseases. To resolve decisive information from extracted OCT volumes and to make it applicable for further diagnostic analysis, the exact measurement of retinal layer thicknesses serves as an essential task be done for each patient separately. However, manual examination of OCT scans is a demanding and time consuming task, which is typically made difficult by the presence of tissue-dependent speckle noise. Therefore, the elaboration of automated segmentation models has become an important task in the field of medical image processing. We propose a novel, purely data driven geometric approach to order-constrained 3D OCT retinal cell layer segmentation which takes as input data in any metric space and can be implemented using only simple, highly parallelizable operations. As opposed to many established retinal layer segmentation methods, we use only locally extracted features as input and do not employ any global shape prior. The physiological order of retinal cell layers and membranes is achieved through the introduction of a smoothed energy term. This is combined with additional regularization of local smoothness to yield highly accurate 3D segmentations. The approach thereby systematically avoid bias pertaining to global shape and is hence suited for the detection of anatomical changes of retinal tissue structure. To demonstrate its robustness, we compare two different choices of features on a data set of manually annotated 3D OCT volumes of healthy human retina. The quality of computed segmentations is compared to the state of the art in automatic retinal layer segmention as well as to manually annotated ground truth data in terms of mean absolute error and Dice similarity coefficient. Visualizations of segmented volumes are also provided.

Sign in / Sign up

Export Citation Format

Share Document