scholarly journals Hands-Free User Interface for AR/VR Devices Exploiting Wearer’s Facial Gestures Using Unsupervised Deep Learning

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4441
Author(s):  
Jaekwang Cha ◽  
Jinhyuk Kim ◽  
Shiho Kim
Keyword(s):  
User Interface ◽  
Clustering Algorithm ◽  
Sensor Data ◽  
User Input ◽  
Skin Deformation ◽  
User Intentions ◽  
Average Accuracy ◽  
Online Sensor ◽  
Facial Gestures ◽  
Unsupervised Deep Learning

Developing a user interface (UI) suitable for headset environments is one of the challenges in the field of augmented reality (AR) technologies. This study proposes a hands-free UI for an AR headset that exploits facial gestures of the wearer to recognize user intentions. The facial gestures of the headset wearer are detected by a custom-designed sensor that detects skin deformation based on infrared diffusion characteristics of human skin. We designed a deep neural network classifier to determine the user’s intended gestures from skin-deformation data, which are exploited as user input commands for the proposed UI system. The proposed classifier is composed of a spatiotemporal autoencoder and deep embedded clustering algorithm, trained in an unsupervised manner. The UI device was embedded in a commercial AR headset, and several experiments were performed on the online sensor data to verify operation of the device. We achieved implementation of a hands-free UI for an AR headset with average accuracy of 95.4% user-command recognition, as determined through tests by participants.

Semi-Automatic Online Tagging with K-Medoid Clustering

2014 ◽  
Vol 24 (08) ◽  
pp. 1115-1130 ◽  
Author(s):  
He Hu ◽  
Xiaoyong Du
Keyword(s):  
Clustering Algorithm ◽  
Prototype System ◽  
Web Pages ◽  
Web Page ◽  
Web Browser ◽  
User Input ◽  
Browser Extension ◽  
Annotation Process ◽  
Efficiency And Effectiveness ◽  
Automatic Mechanism

Online tagging is crucial for the acquisition and organization of web knowledge. We present TYG (Tag-as-You-Go) in this paper, a web browser extension for online tagging of personal knowledge on standard web pages. We investigate an approach to combine a K-Medoid-style clustering algorithm with the user input to achieve semi-automatic web page annotation. The annotation process supports user-defined tagging schema and comprises an automatic mechanism that is built upon clustering techniques, which can automatically group similar HTML DOM nodes into clusters corresponding to the user specification. TYG is a prototype system illustrating the proposed approach. Experiments with TYG show that our approach can achieve both efficiency and effectiveness in real world annotation scenarios.

Extracting Medical Information from Paper COVID-19 Assessment Forms

2021 ◽  
Vol 12 (01) ◽  
pp. 170-178
Author(s):  
Jacob D. Schultz ◽  
Colin G. White-Dzuro ◽  
Cheng Ye ◽  
Joseph R. Coco ◽  
Janet M. Myers ◽  
...  
Keyword(s):  
User Interface ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Medical Information ◽  
Medical Center ◽  
Data Validation ◽  
Average Accuracy ◽  
Medical Documents ◽  
Optical Mark Recognition ◽  
The Right

Abstract Objective This study examines the validity of optical mark recognition, a novel user interface, and crowdsourced data validation to rapidly digitize and extract data from paper COVID-19 assessment forms at a large medical center. Methods An optical mark recognition/optical character recognition (OMR/OCR) system was developed to identify fields that were selected on 2,814 paper assessment forms, each with 141 fields which were used to assess potential COVID-19 infections. A novel user interface (UI) displayed mirrored forms showing the scanned assessment forms with OMR results superimposed on the left and an editable web form on the right to improve ease of data validation. Crowdsourced participants validated the results of the OMR system. Overall error rate and time taken to validate were calculated. A subset of forms was validated by multiple participants to calculate agreement between participants. Results The OMR/OCR tools correctly extracted data from scanned forms fields with an average accuracy of 70% and median accuracy of 78% when the OMR/OCR results were compared with the results from crowd validation. Scanned forms were crowd-validated at a mean rate of 157 seconds per document and a volume of approximately 108 documents per day. A randomly selected subset of documents was reviewed by multiple participants, producing an interobserver agreement of 97% for documents when narrative-text fields were included and 98% when only Boolean and multiple-choice fields were considered. Conclusion Due to the COVID-19 pandemic, it may be challenging for health care workers wearing personal protective equipment to interact with electronic health records. The combination of OMR/OCR technology, a novel UI, and crowdsourcing data-validation processes allowed for the efficient extraction of a large volume of paper medical documents produced during the COVID-19 pandemic.

Multisensor Degradation Data Fusion and Remaining Life Prediction

2017 ◽  
Author(s):  
Changxi Wang ◽  
E. A. Elsayed ◽  
Kang Li ◽  
Javier Cabrera
Keyword(s):  
Data Fusion ◽  
Prediction Accuracy ◽  
Life Prediction ◽  
Clustering Algorithm ◽  
Partial Information ◽  
Degradation Process ◽  
Sensor Data ◽  
Multiple Sensors ◽  
Degradation Data ◽  
Degradation Monitoring

Multiple sensors are commonly used for degradation monitoring. Since different sensors may be sensitive at different stages of the degradation process and each sensor data contain only partial information of the degraded unit, data fusion approaches that integrate degradation data from multiple sensors can effectively improve degradation modeling and life prediction accuracy. We present a non-parametric approach that assigns weights to each sensor based on dynamic clustering of the sensors observations. A case study that involves a fatigue-crack-growth dataset is implemented in order evaluate the prognostic performance of the unit. Results show that the fused path obtained with the proposed approach outperforms any individual sensor data and other paths obtained with an adaptive threshold clustering algorithm in terms of life prediction accuracy.

Failure Modeling of a Propulsion Subsystem: Unsupervised and Semi-Supervised Approaches to Anomaly Detection

2019 ◽  
Vol 33 (11) ◽  
pp. 1940019 ◽  
Author(s):  
Catherine Cheung ◽  
Julio J. Valdés ◽  
Richard Salas Chavez ◽  
Srishti Sehgal
Keyword(s):  
Anomaly Detection ◽  
Clustering Algorithm ◽  
Operating Conditions ◽  
Sensor Data ◽  
Support Vector ◽  
Training Models ◽  
Detection Techniques ◽  
Failure Modeling ◽  
Supervised Classifiers ◽  
Unsupervised Anomaly Detection

In this work, the sensor data related to a diesel engine system and specifically its turbocharger subsystem were analyzed. An incident where the turbocharger seized was recorded by dozens of standard turbocharger-related sensors. By training models to distinguish between normal healthy operating conditions and deteriorated conditions, there is an opportunity to develop prognostic and predictive tools to ideally help prevent a similar occurrence in the future. Analysis of this event provides an opportunity to identify changes in equipment indicators with a known outcome. A number of data analysis tools were used to characterize the healthy and deteriorated states of the turbocharger system, including various supervised classification as well as semi-supervised and unsupervised anomaly detection techniques. The leader clustering algorithm was also implemented to reduce the amount of data to train and develop the models. This paper describes the results of this modeling process, validated by testing on healthy data from the same propulsion system and a second distinct one. Although this problem posed challenges due to the severely imbalanced class distribution, the supervised classifiers, in particular Support Vector Machine (SVM) and Random Forest (RF), performed very well in all metrics while the unsupervised anomaly detection models achieved near-perfect accuracy for identifying healthy turbocharger states.

scholarly journals Data Fusion Using a Multi-Sensor Sparse-Based Clustering Algorithm

2020 ◽  
Vol 12 (23) ◽  
pp. 4007
Author(s):  
Kasra Rafiezadeh Shahi ◽  
Pedram Ghamisi ◽  
Behnood Rasti ◽  
Robert Jackisch ◽  
Paul Scheunders ◽  
...  
Keyword(s):  
Clustering Algorithm ◽  
Spatial Information ◽  
Clustering Algorithms ◽  
Hyperspectral Data ◽  
Sensor Data ◽  
Data Sets ◽  
Data Types ◽  
Data Set ◽  
Multiple Data Sets ◽  
Imaging Sensors

The increasing amount of information acquired by imaging sensors in Earth Sciences results in the availability of a multitude of complementary data (e.g., spectral, spatial, elevation) for monitoring of the Earth’s surface. Many studies were devoted to investigating the usage of multi-sensor data sets in the performance of supervised learning-based approaches at various tasks (i.e., classification and regression) while unsupervised learning-based approaches have received less attention. In this paper, we propose a new approach to fuse multiple data sets from imaging sensors using a multi-sensor sparse-based clustering algorithm (Multi-SSC). A technique for the extraction of spatial features (i.e., morphological profiles (MPs) and invariant attribute profiles (IAPs)) is applied to high spatial-resolution data to derive the spatial and contextual information. This information is then fused with spectrally rich data such as multi- or hyperspectral data. In order to fuse multi-sensor data sets a hierarchical sparse subspace clustering approach is employed. More specifically, a lasso-based binary algorithm is used to fuse the spectral and spatial information prior to automatic clustering. The proposed framework ensures that the generated clustering map is smooth and preserves the spatial structures of the scene. In order to evaluate the generalization capability of the proposed approach, we investigate its performance not only on diverse scenes but also on different sensors and data types. The first two data sets are geological data sets, which consist of hyperspectral and RGB data. The third data set is the well-known benchmark Trento data set, including hyperspectral and LiDAR data. Experimental results indicate that this novel multi-sensor clustering algorithm can provide an accurate clustering map compared to the state-of-the-art sparse subspace-based clustering algorithms.

scholarly journals AI-Based Early Change Detection in Smart Living Environments

Sensors ◽  
2019 ◽  
Vol 19 (16) ◽  
pp. 3549
Author(s):  
Giovanni Diraco ◽  
Alessandro Leone ◽  
Pietro Siciliano
Keyword(s):  
Deep Learning ◽  
Vital Signs ◽  
Big Data Analytics ◽  
Synthetic Data ◽  
Value Added ◽  
Care Recipient ◽  
Sensor Data ◽  
Detection Accuracy ◽  
Learning Techniques ◽  
Unsupervised Deep Learning

In the smart environments we live today, a great variety of heterogeneous sensors are being increasingly deployed with the aim of providing more and more value-added services. This huge availability of sensor data, together with emerging Artificial Intelligence (AI) methods for Big Data analytics, can yield a wide array of actionable insights to help older adults continue to live independently with minimal support of caregivers. In this regard, there is a growing demand for technological solutions able to monitor human activities and vital signs in order to early detect abnormal conditions, avoiding the caregivers’ daily check of the care recipient. The aim of this study is to compare state-of-the-art machine and deep learning techniques suitable for detecting early changes in human behavior. At this purpose, specific synthetic data are generated, including activities of daily living, home locations in which such activities take place, and vital signs. The achieved results demonstrate the superiority of unsupervised deep-learning techniques over traditional supervised/semi-supervised ones in terms of detection accuracy and lead-time of prediction.

AUTOMATED DIAGNOSIS OF BRAIN TUMOURS ASTROCYTOMAS USING PROBABILISTIC NEURAL NETWORK CLUSTERING AND SUPPORT VECTOR MACHINES

2005 ◽  
Vol 15 (01n02) ◽  
pp. 1-11 ◽  
Author(s):  
DIMITRIS GLOTSOS ◽  
JUSSI TOHKA ◽  
PANAGIOTA RAVAZOULA ◽  
DIONISIS CAVOURAS ◽  
GEORGE NIKIFORIDIS
Keyword(s):  
Neural Network ◽  
Clustering Algorithm ◽  
Probabilistic Neural Network ◽  
Support Vector ◽  
Network Clustering ◽  
High Grade ◽  
Cell Nuclei ◽  
Decision Tree Classification ◽  
Average Accuracy ◽  
Malignancy Grading

A computer-aided diagnosis system was developed for assisting brain astrocytomas malignancy grading. Microscopy images from 140 astrocytic biopsies were digitized and cell nuclei were automatically segmented using a Probabilistic Neural Network pixel-based clustering algorithm. A decision tree classification scheme was constructed to discriminate low, intermediate and high-grade tumours by analyzing nuclear features extracted from segmented nuclei with a Support Vector Machine classifier. Nuclei were segmented with an average accuracy of 86.5%. Low, intermediate, and high-grade tumours were identified with 95%, 88.3%, and 91% accuracies respectively. The proposed algorithm could be used as a second opinion tool for the histopathologists.

A Parallel Local Search Algorithm for Clustering Large Biological Networks

2017 ◽  
Vol 27 (03n04) ◽  
pp. 1750007
Author(s):  
Gaetano Coccimiglio ◽  
Salimur Choudhury
Keyword(s):  
Local Search ◽  
Biological Networks ◽  
Clustering Algorithm ◽  
Search Algorithm ◽  
Local Search Algorithm ◽  
Effective Technique ◽  
User Input ◽  
Time Period ◽  
Cluster Quality

Clustering is an effective technique that can be used to analyze and extract useful information from large biological networks. Popular clustering solutions often require user input for several algorithm options that can seem very arbitrary without experimentation. These algorithms can provide good results in a reasonable time period but they are not above improvements. We present a local search based clustering algorithm free of such required input that can be used to improve the cluster quality of a set of given clusters taken from any existing algorithm or clusters produced via any arbitrary assignment. We implement this local search using a modern GPU based approach to allow for efficient runtime. The proposed algorithm shows promising results for improving the quality of clusters. With already high quality input clusters we can achieve cluster rating improvements upto to 33%.

Sign in / Sign up

Export Citation Format

Share Document