scholarly journals Automating areas of interest analysis in mobile eye tracking experiments based on machine learning

2018 ◽  
Vol 11 (6) ◽  
Author(s):  
Julian Wolf ◽  
Stephan Hess ◽  
David Bachmann ◽  
Quentin Lohmeyer ◽  
Mirko Meboldt
Keyword(s):  
Machine Learning ◽  
Eye Tracking ◽  
Ground Truth ◽  
True Positive Rate ◽  
True Negative ◽  
Art Object ◽  
Positive Rate ◽  
Mapping Process ◽  
Break Even Point ◽  
Mobile Eye Tracking

For an in-depth, AOI-based analysis of mobile eye tracking data, a preceding gaze assignment step is inevitable. Current solutions such as manual gaze mapping or marker-based approaches are tedious and not suitable for applications manipulating tangible objects. This makes mobile eye tracking studies with several hours of recording difficult to analyse quantitatively. We introduce a new machine learning-based algorithm, the computational Gaze-Object Mapping (cGOM), that automatically maps gaze data onto respective AOIs. cGOM extends state-of-the-art object detection and segmentation by mask R-CNN with a gaze mapping feature. The new algorithm’s performance is validated against a manual fixation-by-fixation mapping, which is considered as ground truth, in terms of true positive rate (TPR), true negative rate (TNR) and efficiency. Using only 72 training images with 264 labelled object representations, cGOM is able to reach a TPR of approx. 80% and a TNR of 85% compared to the manual mapping. The break-even point is reached at 2 hours of eye tracking recording for the total procedure, respectively 1 hour considering human working time only. Together with a real-time capability of the mapping process after completed training, even hours of eye tracking recording can be evaluated efficiently. (Code and video examples have been made available at: https://gitlab.ethz.ch/pdz/cgom.git)

scholarly journals STUDI KOMPARASI METODE SEGMENTASI PARU-PARU PADA CITRA CT-SCAN AKSIAL

2019 ◽  
Vol 7 (3) ◽  
pp. 283
Author(s):  
Made Satria Wibawa
Keyword(s):  
Ground Truth ◽  
True Positive Rate ◽  
Computer Assisted ◽  
True Positive ◽  
Ct Diagnosis ◽  
True Negative ◽  
Fuzzy C Means ◽  
True Negative Rate ◽  
Positive Rate ◽  
Assisted Diagnosis

Kanker paru dapat diobati jika diagnosis dini dilakukan. Diagnosis dapat dilakukan menggunakan modalitas citra Computed Tomography (CT). Diagnosis kanker paru melalui citra CT dilakukan oleh tenaga medis. Untuk membantu diagnosis kanker, tenaga medis dapat dibantu dengan Computer Assisted Diagnosis (CAD). Dalam CAD, tahapan pertama yang paling penting adalah segmentasi citra paru-paru. Penelitian ini melakukan studi komparasi metode segmentasi citra CT paru-paru. Terdapat tiga metode segmentasi yang digunakan, yaitu Otsu, K-Means dan Fuzzy C-Means. Proses evaluasi menggunakan metrik akurasi, true negative rate dan true positive rate. Berdasarkan nilai yang diperoleh dari ketiga parameter evaluasi tersebut, ketiga metode segmentasi dapat memberikan hasil segmentasi yang mendekati citra ground truth. Namun, dilihat dari sebaran hasil nilai ketiga parameter evaluasi yang didapatkan dari seluruh citra, metode Otsu sedikit lebih unggul dibandingkan metode K-Means dan Fuzzy C-Means.

Watch For Failing Objects: What Inappropriate Compliance Reveals About Shared Mental Models In Autonomous Cars

2021 ◽  
Vol 65 (1) ◽  
pp. 643-647
Author(s):  
Yosef S. Razin ◽  
Jack Gale ◽  
Jiaojiao Fan ◽  
Jaznae’ Smith ◽  
Karen M. Feigh
Keyword(s):  
Mental Models ◽  
Mental Model ◽  
False Positive Rate ◽  
Ground Truth ◽  
True Positive Rate ◽  
Shared Mental Models ◽  
Shared Mental Model ◽  
Autonomous Cars ◽  
Positive Rate ◽  
Dispositional Factors

This paper evaluates Banks et al.’s Human-AI Shared Mental Model theory by examining how a self-driving vehicle’s hazard assessment facilitates shared mental models. Participants were asked to affirm the vehicle’s assessment of road objects as either hazards or mistakes in real-time as behavioral and subjective measures were collected. The baseline performance of the AI was purposefully low (<50%) to examine how the human’s shared mental model might lead to inappropriate compliance. Results indicated that while the participant true positive rate was high, overall performance was reduced by the large false positive rate, indicating that participants were indeed being influenced by the Al’s faulty assessments, despite full transparency as to the ground-truth. Both performance and compliance were directly affected by frustration, mental, and even physical demands. Dispositional factors such as faith in other people’s cooperativeness and in technology companies were also significant. Thus, our findings strongly supported the theory that shared mental models play a measurable role in performance and compliance, in a complex interplay with trust.

Performance of Fineneedle Aspiration Cytology of the Breast. Clinical Experience in Ravenna (Italy)

1993 ◽  
Vol 79 (6) ◽  
pp. 413-417
Author(s):  
Lauro Bucchi ◽  
Patrizia Schincaglia ◽  
Giangiuseppe Melandri ◽  
Nori Morini ◽  
Carlo Naldoni ◽  
...  
Keyword(s):  
Predictive Value ◽  
Breast Cancer Case ◽  
True Positive Rate ◽  
Cancer Case ◽  
Breast Lesions ◽  
Additional Contribution ◽  
True Positive ◽  
Aspiration Cytology ◽  
True Negative ◽  
Positive Rate

Aims and background Fineneedle aspiration cytology (FNAC) is a routine test in the evaluation of breast lesions. We assessed the diagnostic accuracy of mammography (MG), physical examination (PE), ultrasonography (US) and FNAC in 1064 histologically confirmed breast lesions (638 malignant, 426 benign) observed consecutively at the Cancer Prevention Center of Ravenna (Italy). Methods The performance of each test and the additional contribution of FNAC were determined. Results FNAC was done in 69.6 % of cancers and 39.7 % of benign lesions (P = 0.00000), the frequency of aspiration being significantly associated with severity at MG, PE, and US. For FNAC, the true positive rate was 95.1 % and the true negative rate 67.4 %. Only one breast cancer case was detected by FNAC alone (additional true positive rate 0.2 %). The positive predictive value of FNAC in the absence of other abnormalities was 5 %. The negative predictive value of a benign report at MG, PE, US and FNAC was 100 %. Conclusions All breast lesions should be evaluated by all available techniques, especially FNAC, and open biopsy should be avoided for those reported as benign at all tests.

scholarly journals The Validity of the Tool “statcheck” in Discovering Statistical Reporting Inconsistencies

2017 ◽  
Author(s):  
Michele B. Nuijten ◽  
Marcel A. L. M. van Assen ◽  
Chris Hubertus Joseph Hartgerink ◽  
Sacha Epskamp ◽  
Jelte M. Wicherts
Keyword(s):  
Multiple Testing ◽  
Degrees Of Freedom ◽  
R Package ◽  
True Positive Rate ◽  
P Value ◽  
True Positive ◽  
Test Statistic ◽  
True Negative ◽  
True Negative Rate ◽  
Positive Rate

The R package “statcheck” (Epskamp &amp; Nuijten, 2016) is a tool to extract statistical results from articles and check whether the reported p-value matches the accompanying test statistic and degrees of freedom. A previous study showed high interrater reliabilities (between .76 and .89) between statcheck and manual coding of inconsistencies (.76 - .89; Nuijten, Hartgerink, Van Assen, Epskamp, &amp; Wicherts, 2016). Here we present an additional, detailed study of the validity of statcheck. In Study 1, we calculated its sensitivity and specificity. We found that statcheck’s sensitivity (true positive rate) and specificity (true negative rate) were high: between 85.3% and 100%, and between 96.0% and 100%, respectively, depending on the assumptions and settings. The overall accuracy of statcheck ranged from 96.2% to 99.9%. In Study 2, we investigated statcheck’s ability to deal with statistical corrections for multiple testing or violations of assumptions in articles. We found that the prevalence of corrections for multiple testing or violations of assumptions in psychology was higher than we initially estimated in Nuijten et al. (2016). Although we found numerous reporting inconsistencies in results corrected for violations of the sphericity assumption, we demonstrate that inconsistencies associated with statistical corrections are not what is causing the high estimates of the prevalence of statistical reporting inconsistencies in psychology.

scholarly journals Spectral features and optimal Hierarchical Attention Networks for Pulmonary abnormality detection from the Respiratory Sound signals

2021 ◽  
Author(s):  
JAWAD AHMAD DAR ◽  
sajaad Ahmad lone ◽  
Kamal Kr Srivast
Keyword(s):  
Water Cycle ◽  
Optimization Technique ◽  
True Positive Rate ◽  
Respiratory Sounds ◽  
Training Procedure ◽  
True Negative ◽  
Important Concern ◽  
Efficient Performance ◽  
Positive Rate ◽  
Pulmonary Abnormalities

Abstract The most important concern in the medical field is to consider the analysis of data and perform accurate diagnosis. However, the analysis of pulmonary abnormalities may depend on the diagnostic experience and the medical skills of the physicians, and is a time-consuming practice. In order to solve such issues, an efficient Water Cycle Swarm Optimizer-based Hierarchical Attention Network (WCSO-based HAN) is developed for detecting the pulmonary abnormalities from the respiratory sounds signals. However, the developed optimization technique named WCSO is devised by incorporating the Water Cycle Algorithm (WCA) with Competitive Swarm Optimizer (CSO). Here, the pre-processing is performed using the Hanning window and Spectral gating-based noise reduction method in order to remove the falsifications or noises from the signal. Thereafter, the process of feature extraction is carried out to extract the significant features, such as Bark frequency Cepstral coefficient (BFCC) and the short term features, such asspectral flux and spectral centroid. Once the significant features are extracted, classification is performed using HAN where the training procedure of HAN is carried out using WCSO. Furthermore, the developed WCSO-based HAN obtained efficient performance using True Positive Rate (TPR), True Negative Rate (TNR) and accuracy with the values of 0.943, 0.913, and 0.923 using dataset 1, respectively.

scholarly journals genuMet: distinguish genuine untargeted metabolic features without quality control samples

2019 ◽  
Author(s):  
L Cao ◽  
C Clish ◽  
FB Hu ◽  
MA Martínez-González ◽  
C Razquin ◽  
...  
Keyword(s):  
Quality Control ◽  
Large Scale ◽  
Control Method ◽  
R Package ◽  
True Positive Rate ◽  
Supplementary Information ◽  
True Negative ◽  
True Negative Rate ◽  
Positive Rate ◽  
Measurement Artifacts

AbstractMotivationLarge-scale untargeted metabolomics experiments lead to detection of thousands of novel metabolic features as well as false positive artifacts. With the incorporation of pooled QC samples and corresponding bioinformatics algorithms, those measurement artifacts can be well quality controlled. However, it is impracticable for all the studies to apply such experimental design.ResultsWe introduce a post-alignment quality control method called genuMet, which is solely based on injection order of biological samples to identify potential false metabolic features. In terms of the missing pattern of metabolic signals, genuMet can reach over 95% true negative rate and 85% true positive rate with suitable parameters, compared with the algorithm utilizing pooled QC samples. genu-Met makes it possible for studies without pooled QC samples to reduce false metabolic signals and perform robust statistical analysis.Availability and implementationgenuMet is implemented in a R package and available on https://github.com/liucaomics/genuMet under GPL-v2 license.ContactLiming Liang: [email protected] informationSupplementary data are available at ….

scholarly journals Online asynchronous decoding of error-related potentials during the continuous control of a robot

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Catarina Lopes-Dias ◽  
Andreea I. Sburlea ◽  
Gernot R. Müller-Putz
Keyword(s):  
True Positive Rate ◽  
Robotic Arm ◽  
Continuous Control ◽  
True Positive ◽  
True Negative ◽  
Computer Interfaces ◽  
True Negative Rate ◽  
Positive Rate ◽  
Related Potentials ◽  
Neural Signature

AbstractError-related potentials (ErrPs) are the neural signature of error processing. Therefore, the detection of ErrPs is an intuitive approach to improve the performance of brain-computer interfaces (BCIs). The incorporation of ErrPs in discrete BCIs is well established but the study of asynchronous detection of ErrPs is still in its early stages. Here we show the feasibility of asynchronously decoding ErrPs in an online scenario. For that, we measured EEG in 15 participants while they controlled a robotic arm towards a target using their right hand. In 30% of the trials, the control of the robotic arm was halted at an unexpected moment (error onset) in order to trigger error-related potentials. When an ErrP was detected after the error onset, participants regained the control of the robot and could finish the trial. Regarding the asynchronous classification in the online scenario, we obtained an average true positive rate (TPR) of 70% and an average true negative rate (TNR) of 86.8%. These results indicate that the online asynchronous decoding of ErrPs was, on average, reliable, showing the feasibility of the asynchronous decoding of ErrPs in an online scenario.

Credit-worthiness Prediction in Energy-Saving Finance Using Machine Learning Model

2021 ◽  
Vol 39 (10) ◽  
Author(s):  
Eka Sudarmaji ◽  
Noer Azam Achsani ◽  
Yandra Arkeman ◽  
Idqan Fahmi
Keyword(s):  
Machine Learning ◽  
Energy Saving ◽  
Test Data ◽  
Life Cycle Cost ◽  
Multinomial Logistic Regression ◽  
False Positive Rate ◽  
True Positive Rate ◽  
Factors Affecting ◽  
Positive Rate ◽  
Sensitivity Rate

Companies can form their own "ESCO model" with their capitals. Unfortunately, customer's creditworthiness was becoming more crucial for ESCO. Machine learning was used to predict the creditworthiness of clients in ESCO financing processes. This research aimed to develop a scoring model to leverage a machine learning and life cycle cost analysis (LCCA) to evaluate alternative financing for Energy Saving in Indonesia. The results of calculations using multinomial logistic regression showed that the accuracy value of prediction data with test data was 88.3562 %. The prediction rate result that refers to the percentage of correct predictions among all test data was 91.67%, and False Positive Rate (FPR) was 39.44%. The True Positive Rate was called Recall or 'Sensitivity Rate' as it was defined as several positive cases that were correctly identified (TPR) was 92.20%. We found the machine learning methods for creditworthiness prediction in retrofitting projects were fresh and worth a shot. It was hoped that this new practice would grow in popularity and become standard among ESCOs. Unfortunately, current machine-learning-based creditworthiness scoring practices lacked explain ability and interpretability. Unfortunately, ESCO must penalize the retrofitting project. As a result, since retrofitting was a new industry, the credit approval process was challenging to communicate to consumers. The most important thing for ESCO to deal with the project was to have a friendship and know-how with the client. Research from these case studies led to a clearer understanding of the factors affecting all parties' decisions to implement and continue with their ESCO project.

scholarly journals Temporal Filtering to Improve Single Molecule Identification in High Background Samples

Molecules ◽  
2018 ◽  
Vol 23 (12) ◽  
pp. 3338
Author(s):  
Alexander Reismann ◽  
Lea Atanasova ◽  
Lukas Schrangl ◽  
Susanne Zeilinger ◽  
Gerhard Schütz
Keyword(s):  
Single Molecule ◽  
Ground Truth ◽  
True Positive Rate ◽  
Full Potential ◽  
Statistical Parameters ◽  
High Background ◽  
Temporal Filtering ◽  
Localization Accuracy ◽  
Localization Algorithms ◽  
Positive Rate

Single molecule localization microscopy is currently revolutionizing the life sciences as it offers, for the first time, insights into the organization of biological samples below the classical diffraction limit of light microscopy. While there have been numerous examples of new biological findings reported in the last decade, the technique could not reach its full potential due to a set of limitations immanent to the samples themselves. Particularly, high background signals impede the proper performance of most single-molecule identification and localization algorithms. One option is to exploit the characteristic blinking of single molecule signals, which differs substantially from the residual brightness fluctuations of the fluorescence background. To pronounce single molecule signals, we used a temporal high-pass filtering in Fourier space on a pixel-by-pixel basis. We evaluated the performance of temporal filtering by assessing statistical parameters such as true positive rate and false discovery rate. For this, ground truth signals were generated by simulations and overlaid onto experimentally derived movies of samples with high background signals. Compared to the nonfiltered case, we found an improvement of the sensitivity by up to a factor 3.5 while no significant change in the localization accuracy was observable.

Mastoid, middle ear and inner ear analysis in CT scan – a possible contribution for the identification of remains

2020 ◽  
Vol 60 (2) ◽  
pp. 102-111
Author(s):  
Henrique Rodrigues ◽  
Rosa Ramos ◽  
Leoni Fagundes ◽  
Orlando Galego ◽  
David Navega ◽  
...  
Keyword(s):  
Positive Predictive Value ◽  
Predictive Value ◽  
Visual Assessment ◽  
True Positive Rate ◽  
Observer Agreement ◽  
True Positive ◽  
True Negative ◽  
True Negative Rate ◽  
Negative Rate ◽  
Positive Rate

Objective We aimed to evaluate whether the internal structures of the human ear have anatomical characteristics that are sufficiently distinctive to contribute to human identification and use in a forensic context. Materials and methods After data anonymisation, a dataset containing temporal bone CT scans of 100 subjects was processed by a radiologist who was not involved in the study. Four reference images were selected for each subject. Of the original sample, 10 examinations were used for visual comparison, case by case, against the dataset of 100 patients. This visual assessment was performed independently by four observers, who evaluated the anatomical agreement using a Likert scale (1–5). Inter-observer agreement, true positive rate, positive predictive value, true negative rate, negative predictive value, false positive rate, false negative rate and positive likelihood ratio (LR+) were evaluated. Results Inter-observer agreement obtained an overall Cohen’s Kappa = 99.59%. True positive rate, positive predictive value, true negative rate and negative predictive value were all 100%. Conclusion Visual assessment of the mastoid examinations was shown to be a robust and reliable approach to identify unique osseous features and contribute to human identification. The statistical analysis indicates that regardless of the examiner’s background and training, the approach has a high degree of accuracy.

Sign in / Sign up

Export Citation Format

Share Document