scholarly journals Eye movements and human face perception: An holistic analysis and proficiency classification based on frontal 2D face images

2018 ◽  
Author(s):  
Victor P. L. Varela ◽  
Estela Ribeiro ◽  
Pedro A. S. S. Orona ◽  
Carlos E. Thomaz
Keyword(s):  
Eye Movements ◽  
Cognitive Task ◽  
Machine Learning Techniques ◽  
Superior Performance ◽  
Emotional States ◽  
Face Images ◽  
Benchmark Tests ◽  
Learning Techniques ◽  
Proficiency Classification ◽  
Human Faces

Human faces convey a collection of information, such as gender, identity, and emotional states. Therefore, understanding the differences between volunteers’ eye movements on benchmark tests of face recognition and perception can explicitly indicate the most discriminating regions to improve performance in this visual cognitive task. The aim of this work is to qualify and classify these eye strategies using multivariate statistics and machine learning techniques, achieving up to 94.8% accuracy. Our experimental results show that volunteers have focused their visual attention, on average, at the eyes, but those with superior performance in the tests carried out have looked at the nose region more closely.

scholarly journals Detection of duplicate and non-face images in the eRecruitment applications using machine learning techniques

2021 ◽  
Vol 10 (2) ◽  
pp. 114
Author(s):  
Manjunath K. E. ◽  
Yogeen S. Honnavar ◽  
Rakesh Pritmani ◽  
Sethuraman K.
Keyword(s):  
Machine Learning ◽  
Detection Algorithm ◽  
Similarity Score ◽  
Machine Learning Techniques ◽  
Human Face ◽  
Face Images ◽  
Research Organisation ◽  
Learning Techniques ◽  
Satellite Centre ◽  
Recruitment Activities

The objective of this work is to develop methodologies to detect, and report the noncompliant images with respect to indian space research organisation (ISRO) recruitment requirements. The recruitment software hosted at U. R. rao satellite centre (URSC) is responsible for handling recruitment activities of ISRO. Large number of online applications are received for each post advertised. In many cases, it is observed that the candidates are uploading either wrong or non-compliant images of the required documents. By non-compliant images, we mean images which do not have faces or there is not enough clarity in the faces present in the images uploaded. In this work, we attempt to address two specific problems namely: 1) To recognise image uploaded to recruitment portal contains a human face or not. This is addressed using a face detection algorithm. 2) To check whether images uploaded by two or more applications are same or not. This is achieved by using machine learning (ML) algorithms to generate similarity score between two images, and then identify the duplicate images. Screening of valid applications becomes very challenging as the verification of such images using a manual process is very time consuming and requires large human efforts. Hence, we propose novel ML techniques to determine duplicate and non-face images in the applications received by the recruitment portal.

scholarly journals Reaction Wheels Fault Isolation Onboard 3-Axis Controlled Satel-lite using Enhanced Random Forest with Multidomain Features

2021 ◽  
Vol 12 (2) ◽  
Author(s):  
Afshin Rahimi ◽  
Mofiyinoluwa O. Folami
Keyword(s):  
Machine Learning ◽  
Fault Isolation ◽  
Data Driven ◽  
Machine Learning Techniques ◽  
Superior Performance ◽  
Alternative Methods ◽  
Model Parameters ◽  
High Fidelity ◽  
Novel Approach ◽  
Learning Techniques

As the number of satellite launches increases each year, it is only natural that an interest in the safety and monitoring of these systems would increase as well. However, as a system becomes more complex, generating a high-fidelity model that accurately describes the system becomes complicated. Therefore, imploring a data-driven method can provide to be more beneficial for such applications. This research proposes a novel approach for data-driven machine learning techniques on the detection and isolation of nonlinear systems, with a case-study for an in-orbit closed loop-controlled satellite with reaction wheels as actuators. High-fidelity models of the 3-axis controlled satellite are employed to generate data for both nominal and faulty conditions of the reaction wheels. The generated simulation data is used as input for the isolation method, after which the data is pre-processed through feature extraction from a temporal, statistical, and spectral domain. The pre-processed features are then fed into various machine learning classifiers. Isolation results are validated with cross-validation, and model parameters are tuned using hyperparameter optimization. To validate the robustness of the proposed method, it is tested on three characterized datasets and three reaction wheel configurations, including standard four-wheel, three-orthogonal, and pyramid. The results prove superior performance isolation accuracy for the system under study compared to previous studies using alternative methods (Rahimi & Saadat, 2019, 2020).

Interestingness Improvement of Face Images by Learning Visual Saliency

2020 ◽  
Vol 24 (5) ◽  
pp. 630-637
Author(s):  
Dao Nam Anh ◽  
Keyword(s):  
Saliency Detection ◽  
Personal Characteristics ◽  
Visual Saliency ◽  
Image Features ◽  
Machine Learning Techniques ◽  
Consistent Estimation ◽  
Detection Techniques ◽  
Face Images ◽  
Learning Techniques ◽  
Machine Communication

Connecting features of face images with the interestingness of a face may assist in a range of applications such as intelligent visual human-machine communication. To enable the connection, we use interestingness and image features in combination with machine learning techniques. In this paper, we use visual saliency of face images as learning features to classify the interestingness of the images. Applying multiple saliency detection techniques specifically to objects in the images allows us to create a database of saliency-based features. Consistent estimation of facial interestingness and using multiple saliency methods contribute to estimate, and exclusively, to modify the interestingness of the image. To investigate interestingness – one of the personal characteristics in a face image, a large benchmark face database is tested using our method. Taken together, the method may advance prospects for further research incorporating other personal characteristics and visual attention related to face images.

scholarly journals Emotion Detection for Social Robots Based on NLP Transformers and an Emotion Ontology

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1322
Author(s):  
Wilfredo Graterol ◽  
Jose Diaz-Amado ◽  
Yudith Cardinale ◽  
Irvin Dongo ◽  
Edmundo Lopes-Silva ◽  
...  
Keyword(s):  
Language Processing ◽  
Application Programming Interface ◽  
Social Robots ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Emotional States ◽  
Emotion Detection ◽  
Learning Techniques ◽  
Wide Range ◽  
Application Programming

For social robots, knowledge regarding human emotional states is an essential part of adapting their behavior or associating emotions to other entities. Robots gather the information from which emotion detection is processed via different media, such as text, speech, images, or videos. The multimedia content is then properly processed to recognize emotions/sentiments, for example, by analyzing faces and postures in images/videos based on machine learning techniques or by converting speech into text to perform emotion detection with natural language processing (NLP) techniques. Keeping this information in semantic repositories offers a wide range of possibilities for implementing smart applications. We propose a framework to allow social robots to detect emotions and to store this information in a semantic repository, based on EMONTO (an EMotion ONTOlogy), and in the first figure or table caption. Please define if appropriate. an ontology to represent emotions. As a proof-of-concept, we develop a first version of this framework focused on emotion detection in text, which can be obtained directly as text or by converting speech to text. We tested the implementation with a case study of tour-guide robots for museums that rely on a speech-to-text converter based on the Google Application Programming Interface (API) and a Python library, a neural network to label the emotions in texts based on NLP transformers, and EMONTO integrated with an ontology for museums; thus, it is possible to register the emotions that artworks produce in visitors. We evaluate the classification model, obtaining equivalent results compared with a state-of-the-art transformer-based model and with a clear roadmap for improvement.

Quantifying Emotional States Based on Body Language Data Using Non Invasive Sensors

2014 ◽  
Author(s):  
Ishan Behoora ◽  
Conrad S. Tucker
Keyword(s):  
Real Time ◽  
Body Language ◽  
Machine Learning Techniques ◽  
Emotional States ◽  
Participant Engagement ◽  
Non Invasive ◽  
Learning Techniques ◽  
Language Data ◽  
Position Data ◽  
Human Participants

Determining participant engagement is an important issue across a large number of fields, ranging from entertainment to education. Traditionally, feedback from participants is taken after the activity has been completed. Alternately, continuous observation by trained humans is needed. Thus, there is a need for an automated real time solution. In this paper, the authors propose a data mining driven approach that models a participant’s engagement, based on body language data acquired in real time using non-invasive sensors. Skeletal position data, that approximates human body motions, is acquired from participants using off the shelf, non-invasive sensors. Thereafter, machine learning techniques are employed to detect body language patterns representing emotions such as delight, interest, boredom, frustration, and confusion. The methodology proposed in this paper enables researchers to predict the participants’ engagement levels in real time with high accuracy above 98%. A case study involving human participants enacting eight body language poses, is used to illustrate the effectiveness of the methodology. Finally, this methodology highlights the potential of a real time, automated engagement detection using non-invasive sensors which can ultimately have applications in a large variety of areas such as lectures, gaming and classroom learning.

scholarly journals Estimating Biomechanical Time-Series with Wearable Sensors: A Systematic Review of Machine Learning Techniques

2019 ◽  
Author(s):  
Reed D. Gurchiek ◽  
Nicholas Cheney ◽  
Ryan S. McGinnis
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Wearable Sensors ◽  
Sensor Data ◽  
Machine Learning Techniques ◽  
Superior Performance ◽  
Estimation Accuracy ◽  
Accurate Estimation ◽  
Practical Implementation ◽  
Learning Techniques

Wearable sensors have the potential to enable comprehensive patient characterization and optimized clinical intervention. Critical to realizing this vision is accurate estimation of biomechanical time-series in daily-life, including joint, segment, and muscle kinetics and kinematics, from wearable sensor data. The use of physical models for estimation of these quantities often requires many wearable devices making practical implementation more difficult. However, regression techniques may provide a viable alternative by allowing the use of a reduced number of sensors for estimating biomechanical time-series. Herein, we review 46 articles that used regression algorithms to estimate joint, segment, and muscle kinematics and kinetics. We present a high-level comparison of the many different techniques identified and discuss the implications of our findings concerning practical implementation and further improving estimation accuracy. In particular, we found that several studies report the incorporation of domain knowledge often yielded superior performance. Further, most models were trained on small datasets in which case nonparametric regression often performed best. No models were open-sourced, and most were subject-specific and not validated on impaired populations. Future research should focus on developing open-source algorithms using complementary physics-based and machine learning techniques that are validated in clinically impaired populations. This approach may further improve estimation performance and reduce barriers to clinical adoption.

scholarly journals HybridDTA: Hybrid Data Fusion through Pairwise Training for Drug-Target Affinity Prediction

2021 ◽  
Author(s):  
Hongyu Luo ◽  
Yingfei Xiang ◽  
Xiaomin Fang ◽  
Wei Lin ◽  
Fan Wang ◽  
...  
Keyword(s):  
Drug Target ◽  
Drug Repurposing ◽  
Machine Learning Techniques ◽  
Superior Performance ◽  
Experimental Conditions ◽  
Training Paradigm ◽  
Data Inconsistency ◽  
Learning Techniques ◽  
Hybrid Data ◽  
Target Binding

Estimating drug-target binding affinity (DTA) is crucial for various tasks, including drug design, drug repurposing, and lead optimization. Advanced works adopt machine learning techniques, especially deep learning, to DTA estimation by utilizing the existing assay data. These powerful techniques make it possible to screen a massive amount of potential drugs with limited computation cost. However, a typical DNN-based training paradigm directly minimizes the distances between the estimated scores and the ground truths, suffering from the issue of data inconsistency. The data inconsistency caused by various measurements, e.g., Kd, Ki, and IC50, as well as experimental conditions, e.g., reactant concentration and temperature, severely hinders the effective utilization of existing data, thus deteriorating the performance of DTA prediction. We propose a novel paradigm for effective training on hybrid DTA data to alleviate the data inconsistency issue. Since the ranking orders of the affinity scores with respect to measurements and experimental batches are more consistent, we adopt a pairwise paradigm to enable the DNNs to learn from ranking orders instead. We expect this paradigm can effectively blend datasets with various measurements and experimental batches to achieve better performances. For the sake of verifying the proposed paradigm, we compare it with the previous paradigm for various model backbones on multiple DTA datasets. The experimental results demonstrate the superior performance of our proposed paradigm. The ablation studies also show the effectiveness of the design of the proposed training paradigm.

scholarly journals A Survey on Emotion Recognition for Human Robot Interaction

2021 ◽  
Vol 28 (2) ◽  
pp. 125-146
Keyword(s):  
Machine Learning ◽  
Emotion Recognition ◽  
Human Robot Interaction ◽  
Machine Learning Techniques ◽  
Emotional States ◽  
Robot Interaction ◽  
Artificial Intelligent ◽  
Learning Techniques ◽  
Human Counterpart ◽  
Recent Developments

With the recent developments of technology and the advances in artificial intelligent and machine learning techniques, it becomes possible for the robot to acquire and show the emotions as a part of Human-Robot Interaction (HRI). An emotional robot can recognize the emotional states of humans so that it will be able to interact more naturally with its human counterpart in different environments. In this article, a survey on emotion recognition for HRI systems has been presented. The survey aims to achieve two objectives. Firstly, it aims to discuss the main challenges that face researchers when building emotional HRI systems. Secondly, it seeks to identify sensing channels that can be used to detect emotions and provides a literature review about recent researches published within each channel, along with the used methodologies and achieved results. Finally, some of the existing emotion recognition issues and recommendations for future works have been outlined.

scholarly journals Natural Gaze Data-Driven Wheelchair

2018 ◽  
Author(s):  
Lou-Ann Raymond ◽  
Margherita Piccini ◽  
Mahendran Subramanian ◽  
Orlov Pavel ◽  
Giuseppe Zito ◽  
...  
Keyword(s):  
Eye Movements ◽  
User Interfaces ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Camera System ◽  
Learning Techniques ◽  
Short Time Span ◽  
Planning Processes ◽  
Short Time ◽  
Action Intention

AbstractNatural eye movements during navigation have long been considered to reflect planning processes and link to user’s future action intention. We investigate here whether natural eye movements during joystick-based navigation of wheel-chairs follow identifiable patterns that are predictive of joystick actions. To place eye movements in context with driving intentions, we combine our eye tracking with a 3D depth camera system, which allows us to identify which eye movements have the floor as gaze target and distinguish them from other non-navigation related eye movements. We find consistent patterns of eye movements on the floor predictive of steering commands issued by the driver in all subjects. Based on this empirical data we developed two gaze decoders using supervised machine learning techniques and enabled each of these drivers to then steer the wheelchair by imagining they were using a joystick to trigger appropriate natural eye movements via motor imagery. We show that all subjects are able to navigate their wheelchair “by eye” learning it within a short time span of minutes. Our work shows that simple gaze-based decoding without need for artificial user interfaces suffices to restore mobility and increasing participation in daily life.

Sign in / Sign up

Export Citation Format

Share Document