Search results

The aim of this study is to investigate subject independent emotion recognition capabilities of EEG and peripheral physiological signals namely: electroocoulogram (EOG), electromyography (EMG), electrodermal activity (EDA), temperature, plethysmograph and respiration. The experiments are conducted on both modalities independently and in combination. This study arranges the physiological signals in order based on the prediction accuracy obtained on test data using time and frequency domain features.

DEAP dataset is used in this experiment. Time and frequency domain features of EEG and physiological signals are extracted, followed by correlation-based feature selection. Classifiers namely – Naïve Bayes, logistic regression, linear discriminant analysis, quadratic discriminant analysis, logit boost and stacking are trained on the selected features. Based on the performance of the classifiers on the test set, the best modality for each dimension of emotion is identified.

 The experimental results with EEG as one modality and all physiological signals as another modality indicate that EEG signals are better at arousal prediction compared to physiological signals by 7.18%, while physiological signals are better at valence prediction compared to EEG signals by 3.51%. The valence prediction accuracy of EOG is superior to zygomaticus electromyography (zEMG) and EDA by 1.75% at the cost of higher number of electrodes. This paper concludes that valence can be measured from the eyes (EOG) while arousal can be measured from the changes in blood volume (plethysmograph). The sorted order of physiological signals based on arousal prediction accuracy is plethysmograph, EOG (hEOG + vEOG), vEOG, hEOG, zEMG, tEMG, temperature, EMG (tEMG + zEMG), respiration, EDA, while based on valence prediction accuracy the sorted order is EOG (hEOG + vEOG), EDA, zEMG, hEOG, respiration, tEMG, vEOG, EMG (tEMG + zEMG), temperature and plethysmograph.

Many of the emotion recognition studies in literature are subject dependent and the limited subject independent emotion recognition studies in the literature report an average of leave one subject out (LOSO) validation result as accuracy. The work reported in this paper sets the baseline for subject independent emotion recognition using DEAP dataset by clearly specifying the subjects used in training and test set. In addition, this work specifies the cut-off score used to classify the scale as low or high in arousal and valence dimensions. Generally, statistical features are used for emotion recognition using physiological signals as a modality, whereas in this work, time and frequency domain features of physiological signals and EEG are used. This paper concludes that valence can be identified from EOG while arousal can be predicted from plethysmograph.

Depression is a mental health problem characterized by a persistent sense of sadness and loss of interest. EEG signals are regarded as the most appropriate instruments for diagnosing depression because they reflect the operating status of the human brain. The purpose of this study is the early detection of depression among people using EEG signals.

(i) Artifacts are removed by filtering and linear and non-linear features are extracted; (ii) feature scaling is done using a standard scalar while principal component analysis (PCA) is used for feature reduction; (iii) the linear, non-linear and combination of both (only for those whose accuracy is highest) are taken for further analysis where some ML and DL classifiers are applied for the classification of depression; and (iv) in this study, total 15 distinct ML and DL methods, including KNN, SVM, bagging SVM, RF, GB, Extreme Gradient Boosting, MNB, Adaboost, Bagging RF, BootAgg, Gaussian NB, RNN, 1DCNN, RBFNN and LSTM, that have been effectively utilized as classifiers to handle a variety of real-world issues.

1. Among all, alpha, alpha asymmetry, gamma and gamma asymmetry give the best results in linear features, while RWE, DFA, CD and AE give the best results in non-linear feature. 2. In the linear features, gamma and alpha asymmetry have given 99.98% accuracy for Bagging RF, while gamma asymmetry has given 99.98% accuracy for BootAgg. 3. For non-linear features, it has been shown 99.84% of accuracy for RWE and DFA in RF, 99.97% accuracy for DFA in XGBoost and 99.94% accuracy for RWE in BootAgg. 4. By using DL, in linear features, gamma asymmetry has given more than 96% accuracy in RNN and 91% accuracy in LSTM and for non-linear features, 89% accuracy has been achieved for CD and AE in LSTM. 5. By combining linear and non-linear features, the highest accuracy was achieved in Bagging RF (98.50%) gamma asymmetry + RWE. In DL, Alpha + RWE, Gamma asymmetry + CD and gamma asymmetry + RWE have achieved 98% accuracy in LSTM.

A novel dataset was collected from the Central Institute of Psychiatry (CIP), Ranchi which was recorded using a 128-channels whereas major previous studies used fewer channels; the details of the study participants are summarized and a model is developed for statistical analysis using N-way ANOVA; artifacts are removed by high and low pass filtering of epoch data followed by re-referencing and independent component analysis for noise removal; linear features, namely, band power and interhemispheric asymmetry and non-linear features, namely, relative wavelet energy, wavelet entropy, Approximate entropy, sample entropy, detrended fluctuation analysis and correlation dimension are extracted; this model utilizes Epoch (213,072) for 5 s EEG data, which allows the model to train for longer, thereby increasing the efficiency of classifiers. Features scaling is done using a standard scalar rather than normalization because it helps increase the accuracy of the models (especially for deep learning algorithms) while PCA is used for feature reduction; the linear, non-linear and combination of both features are taken for extensive analysis in conjunction with ML and DL classifiers for the classification of depression. The combination of linear and non-linear features (only for those whose accuracy is highest) is used for the best detection results.

The purpose of this study is to propose an alternative efficient 3D emotion recognition model for variable-length electroencephalogram (EEG) data.

Classical AMIGOS data set which comprises of multimodal records of varying lengths on mood, personality and other physiological aspects on emotional response is used for empirical assessment of the proposed overlapping sliding window (OSW) modelling framework. Two features are extracted using Fourier and Wavelet transforms: normalised band power (NBP) and normalised wavelet energy (NWE), respectively. The arousal, valence and dominance (AVD) emotions are predicted using one-dimension (1D) and two-dimensional (2D) convolution neural network (CNN) for both single and combined features.

The two-dimensional convolution neural network (2D CNN) outcomes on EEG signals of AMIGOS data set are observed to yield the highest accuracy, that is 96.63%, 95.87% and 96.30% for AVD, respectively, which is evidenced to be at least 6% higher as compared to the other available competitive approaches.

The present work is focussed on the less explored, complex AMIGOS (2018) data set which is imbalanced and of variable length. EEG emotion recognition-based work is widely available on simpler data sets. The following are the challenges of the AMIGOS data set addressed in the present work: handling of tensor form data; proposing an efficient method for generating sufficient equal-length samples corresponding to imbalanced and variable-length data.; selecting a suitable machine learning/deep learning model; improving the accuracy of the applied model.

Residing in a densely populated urban area possesses its allure; nonetheless, it can significantly impact physical and mental well-being owing to the persistent stress and information overload inherent in urban settings. This study aims to introduce a neuro-urbanism framework that can guide urban planners and designers in quantitatively evaluating individuals' responses to virtual simulated environments.

Our study consisted of two phases after randomly selecting six locations representing three types of urban areas in Bratislava, Slovakia: urban spaces, urban streets, and public parks. First, we conducted a Mentimeter live polling (dialogic survey fusion), followed by an experiment involving volunteer participants from the Slovak University of Technology. This experiment employed an electroencephalogram (EEG) with virtual reality headsets to virtually explore participants' responses to the selected locations.

The EEG signal analysis revealed significant differences in relaxation levels across the selected locations in this study. Urban streets with commercial activities promote mental well-being more effectively than public parks, challenging the preconception that restorative environments are exclusively confined to public parks.

The results demonstrate a replicable neuro-urbanism framework comprising three distinct stages: problem-based technology rooted in neuroscience, experimental setup and deliverables, and identification of restorative environments.

Social recommendation has been recognized as a kind of e-commerce with large potential, but how social recommendations influence consumer decisions is still unclear. This paper aims to investigate how recommendations from different social ties influence consumers’ purchase intentions through both behavior and brain activity.

Utilizing behavioral (N = 70) and electroencephalogram (EEG) (N = 49) experiments, this study explored participants’ behavior and brain responses after being recommended by different social ties. The data were analyzed using statistical inference and event-related potential (ERP) analysis.

Behavioral results show that social tie strength positively impacts purchase intention, which can be fitted by a logarithmic model. Moreover, recommender-to-customer similarity and product affect mediate the effect of tie strength on purchase intention serially. EEG findings show that recommendations from weak tie strength elicit larger N100, N200 and P300 amplitudes than those from strong tie strength. These results imply that weak tie strength may motivate individuals to recruit more mental resources in social recommendation, including unconscious processing of consumer attention and conscious processing of cognitive conflict and negative emotion.

This study considers the effects of continuous social ties on purchase intention and models them mathematically, exploring the intrinsic mechanisms by which strong and weak ties influence purchase intentions through recommender-to-customer similarity and product affect, contributing to the applications of the stimulus-organism-response (SOR) model in the field of social recommendation. Furthermore, our study adopting EEG techniques bridges the gap of relying solely on self-report by providing an avenue to obtain relatively objective findings about the consumers’ early-occurred (unconscious) attentional responses and late-occurred (conscious) cognitive and emotional responses in purchase decisions.

Safety warnings remind construction workers about dangers and guide them to take necessary actions to avoid potential injuries, which could encourage their safe behavior. Workers’ behavior compliance with the safety warnings would be impacted by the risk perception levels induced by the warnings. This study aims to examine whether the design of safety warnings would impact the induced risk perception of workers

This study compared the risk perception levels of construction workers when processing two forms of safety warnings, i.e., safety signs and safety comics, which are commonly used in construction workplaces. Construction workers (n = 20) volunteered for an experiment with an implicit paradigm to probe how they perceive these safety warnings, using event-related potentials (ERPs) features collected by an electroencephalogram (EEG) sensor to indicate the risk perception level

The results demonstrated that the design of safety warnings would impact the induced risk perception. The safety signs and safety comics performed differently in inducing the workers’ risk perception. The safety signs representing prohibition and caution warnings induced significantly higher risk perception than the comics, and there were no significant differences regarding direction warnings

This is the first study to compare the risk perception levels between various forms of safety warnings presenting safety information in different ways. The findings would help to expand the knowledge of the relationship between the design of safety warnings and workers’ safety behavioral compliance

Sleep arousal detection is an important factor to monitor the sleep disorder.

Thus, a unique nth layer one-dimensional (1D) convolutional neural network-based U-Net model for automatic sleep arousal identification has been proposed.

The proposed method has achieved area under the precision–recall curve performance score of 0.498 and area under the receiver operating characteristics performance score of 0.946.

No other researchers have suggested U-Net-based detection of sleep arousal.

From the experimental results, it has been found that U-Net performs better accuracy as compared to the state-of-the-art methods.

Sleep arousal detection is an important factor to monitor the sleep disorder. Objective of the work is to detect the sleep arousal using different physiological channels of human body.

It will help in improving mental health by monitoring a person's sleep.

In the process of industrial growth, when existing industries go for technology upgradation and new modernised industries emerge, both capital intensity and energy demand of overall industry tend to rise steadily. This poses a serious challenge for sustainable development objectives. Towards this end, enhancing energy efficiency of individual industries is the only remedy. Against this backdrop, the study aims to probe the trends in capital intensities and energy efficiencies of individual industries in India.

This study uses panel data regression analysis on data of two-digit industries from 1980/1981–2016/2017. The statistical analysis includes relevant macroeconomic variables derived from the literature to ascertain the drivers of energy efficiency in industries.

The results brought out that capital deepening due to technology upgradation and modernisation and capital productivity growth are the decisive determinants of energy efficiency growth. Furthermore, the ever-increasing fuel price motivated industries to conserve energy on a steady basis, supplemented by energy conservation-specific policy interventions.

This study recommends policy initiatives to ascertain and address technology gaps industry-wise, so that its subsequent efficient capital utilisation, and energy conservation measures of industries would result in energy efficiency growth in industry. The policy must focus on energy-efficient capital intensification in fabricated metals, leather, textile and wood industries that are found less-energy-efficient despite being less-capital-intensive.

This study empirically explores the capital efficiency of industries by investigating the interaction between capital intensity and energy efficiency at a two-digit industry level. It explores the determinants of energy efficiency and proposes industry-specific policies for energy-efficiency-enhancement of the overall industry.

Construction organizations must maintain a productive workforce without sacrificing their health and safety. The global construction sector loses billions of dollars yearly to poor health and safety practices. This study aims to investigate benefits derivable from using wearable technologies to improve construction health and safety. The study also reports the challenges associated with adopting wearable technologies.

The study adopted a quantitative design, administering close-ended questions to professionals in the Nigerian construction industry. The research data were analysed using descriptive and inferential statistics.

The study found that the critical areas construction organizations can benefit from using WSDs include slips and trips, sensing environmental concerns, collision avoidance, falling from a high level and electrocution. However, key barriers preventing the organizations from adopting wearable technologies are related to cost, technology and human factors.

The time and cost lost to H&S incidents in the Nigerian construction sector can be reduced by implementing the report of this study.

Studies on WSDs have continued to increase in developed countries, but Nigeria is yet to experience a leap in the research area. This study provides insights into the Nigerian reality to provide directions for practice and theory.