Emotion recognition based on multi-channel electroencephalograph (EEG) signals is becoming increasingly attractive. However, the conventional methods ignore the spatial characteristics of EEG ...signals, which also contain salient information related to emotion states. In this paper, a deep learning framework based on a multiband feature matrix (MFM) and a capsule network (CapsNet) is proposed. In the framework, the frequency domain, spatial characteristics, and frequency band characteristics of the multi-channel EEG signals are combined to construct the MFM. Then, the CapsNet model is introduced to recognize emotion states according to the input MFM. Experiments conducted on the dataset for emotion analysis using EEG, physiological, and video signals (DEAP) indicate that the proposed method outperforms most of the common models. The experimental results demonstrate that the three characteristics contained in the MFM were complementary and the capsule network was more suitable for mining and utilizing the three correlation characteristics.
This work describes a novel fluorescent chemoprobe that uses carbon dots and silver nanoparticles (AgNPs) to monitor mercury ions in aqueous samples attributed to the principle of inner filter ...effect. The fluorescent response signal of the carbon dots is diminished by AgNPs, attributed to inner filter effect, and is restored with the addition of Hg2+. The fluorescent chemoprobe was specific over the range from 0.01 to 2.5 μM and a high sensitivity of 3.6 nM. The chemoprobe was validated using real local aqueous samples, and the spike recoveries of 97.4%–103% were excellent and satisfied. The data indicated that the developed fluorescent chemoprobe was sensitive, selective, stable and reliable. This fluorescent chemoprobe provides a sensitive tool with broad prospects for mercury detection in aqueous samples and the work will offer ideas for designing and constructing novel fluorescent probes.
•Carbon dots were prepared with citric acid and polyacrylamide by hydrothermal method.•Sensitive chemoprobe was developed with carbon dots and silver nanoparticles.•Proposed chemoprobe earned high sensitivity and selectivity for sensing Hg2+.•Proposed chemoprobe provided limit of detection of 3.6 nM.•Proposed probe possessed good application prospect and opens new approaches.
This paper expounds the emergency disposal technology based on mapping knowledge domain, dynamically integrates the mapping knowledge domain and emergency disposal plan, and uses data fusion ...technology to integrate multi-source heterogeneous data to construct the mapping knowledge domain of fire and coupling disasters, disaster management graph and supervision department graph. The mapping knowledge domain technology is used to establish a multi-department emergency response plan generation model with dynamic injection of data and process, realizes the cross-department and multi-agent efficient dynamic collaborative emergency response method, and provides data basis and auxiliary decision support for the generation of emergency plans.
Recently, much attention has been attracted to automatic emotion recognition based on multi-channel electroencephalogram (EEG) signals, with the rapid development of machine learning methods. ...However, traditional methods ignore the correlation information between different channels, and cannot fully capture the long-term dependencies and contextual information of EEG signals. To address the problems, this paper proposes a deep belief-conditional random field (DBN-CRF) framework which integrates the improved deep belief networks with glia chains (DBN-GC) and conditional random field. In the framework, the raw feature vector sequence is firstly extracted from the multi-channel EEG signals by a sliding window. Then, parallel DBN-GC models are utilized to obtain the high-level feature sequence of the multi-channel EEG signals. And the conditional random field (CRF) model generates the predicted emotion label sequence according to the high-level feature sequence. Finally, the decision merge layer based on K-nearest neighbor algorithm is employed to estimate the emotion state. According to our best knowledge, this is the first attempt that applies the conditional random field methodology to deep belief networks for emotion recognition. Experiments are conducted on three publicly available emotional datasets which include AMIGOS, SEED and DEAP. The results demonstrate that the proposed framework can mine inter correlation information of multiple-channel by the glia chains and catch inter channel correlation information and contextual information of EEG signals for emotion recognition. In addition, the classification accuracy of the proposed method is compared with several classical techniques. The results indicate that the proposed method outperforms most of the other deep classifiers. Thus, potential of the proposed framework is demonstrated.
The high turnover rate of kindergarten teachers has become a global problem. Job satisfaction is regarded as a contributing factor that can reduce turnover intention. We sought to examine the ...relationship between work-related use of information and communication technologies after hours (W_ICTs) and kindergarten teachers' job satisfaction, as well as the mediating role of emotional exhaustion and the moderating role of perceived organizational support in the link between W_ICTs and emotional exhaustion. A sample of 434 participants of kindergarten teachers completed questionnaires on W_ICTs, job satisfaction, perceived organizational support and emotional exhaustion. Results indicated that kindergarten teachers' emotional exhaustion played a partial mediating role in the relationship between W_ICTs and job satisfaction. In addition, perceived organizational support moderated the association between W_ICTs and emotional exhaustion. Specifically, W_ICTs had a greater impact on emotional exhaustion for kindergarten teachers with low perceived organizational support.
In order to probe the seasonal variation, formation mechanisms as well as geographical origins of fine particles and its chemical components in two cities (Zhengzhou, ZZ and Xinxiang, XX) in Central ...Plains Urban Agglomeration, daily PM2.5 aerosol samples were collected for four consecutive seasons during 2017–2018. The annual average concentrations of PM2.5 (particulate matter with an aerodynamic diameter smaller than 2.5 μm) were calculated at 70.5 ± 50.8 and 69.0 ± 46.3 μg m−3 at ZZ and XX, respectively. Daily ambient PM2.5 concentrations ranged from 18.2 to 303.0 μg m−3, among which >81% of the total sampling days exceeded the National Ambient Air Quality Standard of China (NAAQS, 35 μg m−3 as an annual average). Additionally, concentrations of PM2.5 and its major chemical components were seasonally dependent, usually with the highest mass concentration in winter. Compared with previous studies, higher NO3−/SO42− were observed in this study depicted that air pollution caused by motor vehicle exhaust cannot be ignored. OC concentration was higher at ZZ than XX during sampling campaign likely partially caused by larger number of motor vehicles, chemical pesticide and solvent used in ZZ. Both homogeneous and heterogeneous reactions played an important role in the formation of nitrate, while heterogeneous reactions dominated the formation of sulfate. We also found a faster increase in nitrate than in sulfate during the evolution of haze. The characteristics of long-range transportation of PM2.5 and its major chemical components and gaseous precursors were observed at both sites through back trajectories and WPSCF analysis, suggesting the complexity of air pollution and the multi-influence among cities.
Display omitted
•Seasonal variation characteristics of PM2.5 and its chemical components are explored.•A faster increase in nitrate than in sulfate during the evolution of haze periods.•Severe pollution in winter has alleviated obviously compared with previous years.•Discrepancies of individual compositions of PM2.5 at both sites are significant.•Long-range transportation of PM2.5 is observed at both sites with WPSCF analysis.
Growing competition in tight job market and academic excellence as a social norm in Asian culture have made Chinese college students burdened with immense academic stress.
This study aimed to explore ...the associations between academic stress and depression, and the mediating roles of negative affect and sleep quality, as well as the moderating role of social support in the relationship between negative affect and sleep quality.
A convenience sample of 221 male and 479 female college students aged between 17 and 25 completed questionnaires on academic stress, depression, negative affect, sleep quality and social support.
Results indicated that academic stress could not only directly affect depression (b = 0.31, p < 001), but also affect depression through the mediation role of negative affect and sleep quality. The chain mediating effects includes three paths, namely, the mediating role of negative affect (indirect effect = 0.21, percentage of total effect = 69.58 %), the mediating role of sleep quality (indirect effect = 0.06, percentage of total effect = 21.03 %), and the chain mediating role of negative affect and sleep quality (indirect effect = 0.06, percentage of total effect = 19.86 %). Social support moderated the adverse influence of negative affect on sleep quality. Social support decreases the impact of negative affect on sleep quality. Specifically, the association between negative affect and sleep quality was stronger for college students with low (bsimple = 0.44, p < 0.001) social support than those with high (bsimple = 0.32, p < 0.001) social support.
The results advanced our understanding of how academic stress affects college students' depression. These findings provide implications on the cultivation of stress coping strategies, promotion of emotion regulation skills, exaltation of sleep quality, and improvement of the social support level aiming for future depression preventions and interventions. Specific measures include setting up psychological health courses, teaching emotion management strategies, and establishing web-based programme steming from acceptance and commitment therapy. It should be noted that the cross-sectional design means the causal associations among the variables could not be determined.
•Academic stress could affect depression through the chain mediation role of negative affect and sleep quality.•Social support moderated the adverse influence of negative affect on sleep quality.•The association between negative affect and sleep quality was stronger for college students with low social support.
In the process of working state perception and control, the intelligent boom-type roadheader interferes with the position of the boom and shovel table mechanism. However, the existing research on the ...prevention of interference and collision in boom-type roadheader is mainly based on a single control method. There are relatively few studies that integrate the prevention of interference and collision conditions into the control. In order to solve the above problems, a calculation model for associated position interference between the boom and shovel table mechanism is proposed. Based on the relative spatial position relationship between the boom and shovel table mechanism of a multi degree of freedom boom-type roadheader during the movement process, the boom mechanism is simplified as a segmented spatial straight line, and the shovel table mechanism is simplified as a spatial plane. Based on the distance between the specific points on the equivalent segmented spatial straight line of the boom boundary and the b
In this paper, a novel EEG emotion recognition method based on residual graph attention neural network is proposed. The method constructs a three-dimensional sparse feature matrix according to the ...relative position of electrode channels, and inputs it into the residual network to extract high-level abstract features containing electrode spatial position information. At the same time, the adjacency matrix representing the connection relationship of electrode channels is constructed, and the time-domain features of multi-channel EEG are modeled using graph. Then, the graph attention neural network is utilized to learn the intrinsic connection relationship between EEG channels located in different brain regions from the adjacency matrix and the constructed graph structure data. Finally, the high-level abstract features extracted from the two networks are fused to judge the emotional state. The experiment is carried out on DEAP data set. The experimental results show that the spatial domain information of electrode channels and the intrinsic connection relationship between different channels contain salient information related to emotional state, and the proposed model can effectively fuse these information to improve the performance of multi-channel EEG emotion recognition.
A landslide susceptibility assessment was accomplished in Huizhou, Guangdong province, by adopting the Statistical Index Method and the Analytic Hierarchy Process. Eight landslide causing factors ...were considered including elevation, slope, aspect, lithology, land cover, distance to a fault, distance to a road, distance to a river and precipitation. The Statistical Index Method was used to determine the weighted value (Si) for classes of every landslide causing factor, the Analytic Hierarchy Process was utilized to determine the weighted value (Wi) for every factor, and the summation of the product of Si by Wi represent the Landslide Susceptibility Index (LSI) value for every pixels. Based on the derived LSI, the study area was grouped into five susceptibility classes in the study area. The densities of landslide for five susceptibility classes from very high to very low show a linear increasing trend implying there is a satisfactory agreement between the susceptibility map and the actual landslide data. The ROC curves for training and prediction datasets suggest that the model could have a reasonably good predictive capability. The landslide susceptibility map derived in this study shows the settlement and sparse forest area with lithology of unit II (red layered moderate soft mixture of clastic rocks), unit III (layered moderate hard to hard mixture of clastic rocks) and unit V (massive moderate hard to hard mixture) at the elevation of 0–200m are the most susceptible to slope failure. The result could be very useful in identification of the most problematic areas, which is very critical for investigating landslide hazard and risk management and community & regional planning.
•Assessing landslide susceptibility in a mountainous city of Huizhou in south China•Integrating expert knowledge and existing landslide data for LSI•The major factors for landslide in Huizhou are land use, lithology and elevation.•The slope failure in Huizhou was affected by human activity seriously.•The model can include more slope instability factors and extend to other regions.