A Descriptive Survey on Face Emotion Recognition Techniques

Author(s):  
Bhagyashri Devi ◽  
M. Mary Synthuja Jain Preetha

Recognition of natural emotion from human faces has applications in Human–Computer Interaction, image and video retrieval, automated tutoring systems, smart environment as well as driver warning systems. It is also a significant indication of nonverbal communication among the individuals. The assignment of Face Emotion Recognition (FER) is predominantly complex for two reasons. The first reason is the nonexistence of a large database of training images, and the second one is about classifying the emotions, which can be complex based on the static input image. In addition, robust unbiased FER in real time remains the foremost challenge for various supervised learning-based techniques. This survey analyzes diverse techniques regarding the FER systems. It reviews a bunch of research papers and performs a significant analysis. Initially, the analysis depicts various techniques that are contributed in different research papers. In addition, this paper offers a comprehensive study regarding the chronological review and performance achievements in each contribution. The analytical review is also concerned about the measures for which the maximum performance was achieved in several contributions. Finally, the survey is extended with various research issues and gaps that can be useful for the researchers to promote improved future works on the FER models.

Author(s):  
Kishor Purushottam Jadhav ◽  
Amita Mahor ◽  
Anirban Bhowmick ◽  
Anveshkumar N.

Purpose Non-orthogonal multiple access (NOMA) is a much hopeful scheme, which is deployed to enhance the spectral efficiency (SE) significantly, and it also enhances the massive access that has attained substantial concern from industrial and academic domains. However, the deployment of superposition coding (SC) at the receiver side resulted in interference. For reducing this interference, “multi-antenna NOMA” seems to be an emerging solution. Particularly, by using the channel state information at the transmitter, spatial beam forming could be deployed that eliminates the interference in an effective manner. Design/methodology/approach This survey analyzes the literature review and diverse techniques regarding the NOMA-based spatial modulation (SM) environment. It reviews a bunch of research papers and states a significant analysis. Initially, the analysis depicts various transmit antenna selection techniques that are contributed in different papers. This survey offers a comprehensive study regarding the chronological review and performance achievements in each contribution. The analytical review also concerns on the amplitude phase modulation (APM) selection schemes adopted in several contributions. Moreover, the objective functions adopted in the reviewed works are also analyzed. Finally, the survey extends with various research issues and its gaps that can be useful for the researchers to promote improved future works on NOMA-based SM. Findings This paper contributes to a review related to NOMA-based SM systems. Various techniques and performance measures adopted in each paper are analyzed and described in this survey. More particularly, the selection of transmission antenna and APM are also examined in this review work. Moreover, the defined objective function of each paper is also observed and made a chronological review as well. Finally, the research challenges along with the gaps on NOMA-based SM systems are also elaborated. Originality/value This paper presents a brief analysis of NOMA-based SM systems. To the best of the authors’ knowledge, this is the first work that uses NOMA-based SM systems to enhance SE.


Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4496
Author(s):  
Vlad Pandelea ◽  
Edoardo Ragusa ◽  
Tommaso Apicella ◽  
Paolo Gastaldo ◽  
Erik Cambria

Emotion recognition, among other natural language processing tasks, has greatly benefited from the use of large transformer models. Deploying these models on resource-constrained devices, however, is a major challenge due to their computational cost. In this paper, we show that the combination of large transformers, as high-quality feature extractors, and simple hardware-friendly classifiers based on linear separators can achieve competitive performance while allowing real-time inference and fast training. Various solutions including batch and Online Sequential Learning are analyzed. Additionally, our experiments show that latency and performance can be further improved via dimensionality reduction and pre-training, respectively. The resulting system is implemented on two types of edge device, namely an edge accelerator and two smartphones.


Data ◽  
2021 ◽  
Vol 6 (6) ◽  
pp. 60
Author(s):  
Miguel A. Becerra ◽  
Catalina Tobón ◽  
Andrés Eduardo Castro-Ospina ◽  
Diego H. Peluffo-Ordóñez

This paper provides a comprehensive description of the current literature on data fusion, with an emphasis on Information Quality (IQ) and performance evaluation. This literature review highlights recent studies that reveal existing gaps, the need to find a synergy between data fusion and IQ, several research issues, and the challenges and pitfalls in this field. First, the main models, frameworks, architectures, algorithms, solutions, problems, and requirements are analyzed. Second, a general data fusion engineering process is presented to show how complex it is to design a framework for a specific application. Third, an IQ approach, as well as the different methodologies and frameworks used to assess IQ in information systems are addressed; in addition, data fusion systems are presented along with their related criteria. Furthermore, information on the context in data fusion systems and its IQ assessment are discussed. Subsequently, the issue of data fusion systems’ performance is reviewed. Finally, some key aspects and concluding remarks are outlined, and some future lines of work are gathered.


2011 ◽  
Vol 198 (4) ◽  
pp. 302-308 ◽  
Author(s):  
Ian M. Anderson ◽  
Clare Shippen ◽  
Gabriella Juhasz ◽  
Diana Chase ◽  
Emma Thomas ◽  
...  

BackgroundNegative biases in emotional processing are well recognised in people who are currently depressed but are less well described in those with a history of depression, where such biases may contribute to vulnerability to relapse.AimsTo compare accuracy, discrimination and bias in face emotion recognition in those with current and remitted depression.MethodThe sample comprised a control group (n = 101), a currently depressed group (n = 30) and a remitted depression group (n = 99). Participants provided valid data after receiving a computerised face emotion recognition task following standardised assessment of diagnosis and mood symptoms.ResultsIn the control group women were more accurate in recognising emotions than men owing to greater discrimination. Among participants with depression, those in remission correctly identified more emotions than controls owing to increased response bias, whereas those currently depressed recognised fewer emotions owing to decreased discrimination. These effects were most marked for anger, fear and sadness but there was no significant emotion × group interaction, and a similar pattern tended to be seen for happiness although not for surprise or disgust. These differences were confined to participants who were antidepressant-free, with those taking antidepressants having similar results to the control group.ConclusionsAbnormalities in face emotion recognition differ between people with current depression and those in remission. Reduced discrimination in depressed participants may reflect withdrawal from the emotions of others, whereas the increased bias in those with a history of depression could contribute to vulnerability to relapse. The normal face emotion recognition seen in those taking medication may relate to the known effects of antidepressants on emotional processing and could contribute to their ability to protect against depressive relapse.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Rajesh Pansare ◽  
Gunjan Yadav ◽  
Madhukar R. Nagare

Purpose Uncertainties in manufacturing and changing customer demands force manufacturing industries to adopt new strategies, such as the reconfigurable manufacturing system (RMS). To improve the implementation and performance of RMS, it is necessary to review the available literature and identify future trends in this field. This paper aims to analyze existing literature and to see trends in RMS-related research. Design/methodology/approach The systematic literature review and analysis of RMS-related research papers from 1999 to 2020 is carried out in this literature. The selected studies are analyzed based on the year of publication, journals, publishers, active authors, research design, countries, enablers, barriers, performance evaluation parameters and universities. Findings After the analysis of selected RMS-related research papers, the top countries, universities, journals, publishers and authors are identified in this domain. Research themes and trends in research are identified in this study. Besides, it has been noted that there is a need for further research in this domain and for the creation of a generalized framework that can guide researchers and practitioners to increase RMS adoption. Practical implications Research insights, guidance and observations from this paper are provided to RMS-related researchers and practitioners. Important research gaps are identified in this study, which can provide direction for future research and trends in RMS research. Originality/value The study presented focuses mainly on the method of collecting, organizing, capturing, interpreting and analyzing data to provide more insight into RMS to identify future trends in research.


2021 ◽  
Vol 17 (4) ◽  
pp. 28-51
Author(s):  
Ishita Batra ◽  
Preethi P. ◽  
Sanjay Dhir

The aim of the study is to conduct a structured review of literature on the antecedents of organizational ambidexterity by reconciling the mixed outcomes produced by the extant literature. This study offers some theoretical insights into the divergent views of authors on these factors by analysing the empirical studies done in the literature. This paper systematically analyses the extant literature on the factors affecting organizations' ambidexterity, using meta-analysis and the theory, context, characteristics, and methodology (TCCM) framework. Forty-three research papers across various journals that discussed the correlation of the variables with organizational ambidexterity were selected. The sample size was 17,383, and 20 variables were selected for the analysis. The results revealed that two variables showed high levels of heterogeneity. The implications of this study are relevant to the present business scenario and of substantial interest to scholars, as they provide a more detailed understanding of the very foundation of organizational ambidexterity.


2002 ◽  
Vol 124 (3) ◽  
pp. 441-450 ◽  
Author(s):  
R. Scott Erwin ◽  
Karl Schrader ◽  
Ruth L. Moser ◽  
Steven F. Griffin

This paper presents the development, design, and implementation of a precision control system for a large, sparse-aperture space-deployable telescope testbed. Aspects of the testbed and laboratory environment relevant to nanometer-level control and performance objectives are provided. There are four main objectives of the control system: 1) reduction of natural resonances of the supporting structure, 2) rejection of tonal disturbances, 3) tip, tilt, and piston set-point tracking for optical surfaces, and 4) reduction in settling time of optical surfaces after an impulsive slew-type disturbance. The development of a three-input, three-output, high-bandwidth structural control system for the testbed is presented, and experimental data demonstrating that all objectives were attained is provided. The paper concludes with a discussion of the results and a description of research issues remaining to be addressed.


Sign in / Sign up

Export Citation Format

Share Document