scholarly journals Recognition of Blinks Activity Patterns during Stress Conditions Using CNN and Markovian Analysis

Signals ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 55-71
Author(s):  
Alexandra I. Korda ◽  
Giorgos Giannakakis ◽  
Errikos Ventouras ◽  
Pantelis A. Asvestas ◽  
Nikolaos Smyrnis ◽  
...  

This paper investigates eye behaviour through blinks activity during stress conditions. Although eye blinking is a semi-voluntary action, it is considered to be affected by one’s emotional states such as arousal or stress. The blinking rate provides information towards this direction, however, the analysis on the entire eye aperture timeseries and the corresponding blinking patterns provide enhanced information on eye behaviour during stress conditions. Thus, two experimental protocols were established to induce affective states (neutral, relaxed and stress) systematically through a variety of external and internal stressors. The study populations included 24 and 58 participants respectively performing 12 experimental affective trials. After the preprocessing phase, the eye aperture timeseries and the corresponding features were extracted. The behaviour of inter-blink intervals (IBI) was investigated using the Markovian Analysis to quantify incidence dynamics in sequences of blinks. Moreover, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) network models were employed to discriminate stressed versus neutral tasks per cognitive process using the sequence of IBI. The classification accuracy reached a percentage of 81.3% which is very promising considering the unimodal analysis and the noninvasiveness modality used.

Author(s):  
Farshid Rahmani ◽  
Chaopeng Shen ◽  
Samantha Oliver ◽  
Kathryn Lawson ◽  
Alison Appling

Basin-centric long short-term memory (LSTM) network models have recently been shown to be an exceptionally powerful tool for simulating stream temperature (Ts, temperature measured in rivers), among other hydrological variables. However, spatial extrapolation is a well-known challenge to modeling Ts and it is uncertain how an LSTM-based daily Ts model will perform in unmonitored or dammed basins. Here we compiled a new benchmark dataset consisting of >400 basins for across the contiguous United States in different data availability groups (DAG, meaning the daily sampling frequency) with or without major dams and study how to assemble suitable training datasets for predictions in monitored or unmonitored situations. For temporal generalization, CONUS-median best root-mean-square error (RMSE) values for sites with extensive (99%), intermediate (60%), scarce (10%) and absent (0%, unmonitored) data for training were 0.75, 0.83, 0.88, and 1.59°C, representing the state of the art. For prediction in unmonitored basins (PUB), LSTM’s results surpassed those reported in the literature. Even for unmonitored basins with major reservoirs, we obtained a median RMSE of 1.492°C and an R2 of 0.966. The most suitable training set was the matching DAG that the basin could be grouped into, e.g., the 60% DAG for a basin with 61% data availability. However, for PUB, a training dataset including all basins with data is preferred. An input-selection ensemble moderately mitigated attribute overfitting. Our results suggest there are influential latent processes not sufficiently described by the inputs (e.g., geology, wetland covers), but temporal fluctuations are well predictable, and LSTM appears to be the more accurate Ts modeling tool when sufficient training data are available.


2021 ◽  
Vol 13 (12) ◽  
pp. 6953
Author(s):  
Yixing Du ◽  
Zhijian Hu

Data-driven methods using synchrophasor measurements have a broad application prospect in Transient Stability Assessment (TSA). Most previous studies only focused on predicting whether the power system is stable or not after disturbance, which lacked a quantitative analysis of the risk of transient stability. Therefore, this paper proposes a two-stage power system TSA method based on snapshot ensemble long short-term memory (LSTM) network. This method can efficiently build an ensemble model through a single training process, and employ the disturbed trajectory measurements as the inputs, which can realize rapid end-to-end TSA. In the first stage, dynamic hierarchical assessment is carried out through the classifier, so as to screen out credible samples step by step. In the second stage, the regressor is used to predict the transient stability margin of the credible stable samples and the undetermined samples, and combined with the built risk function to realize the risk quantification of transient angle stability. Furthermore, by modifying the loss function of the model, it effectively overcomes sample imbalance and overlapping. The simulation results show that the proposed method can not only accurately predict binary information representing transient stability status of samples, but also reasonably reflect the transient safety risk level of power systems, providing reliable reference for the subsequent control.


Author(s):  
Sahinya Susindar ◽  
Harrison Wissel-Littmann ◽  
Terry Ho ◽  
Thomas K. Ferris

In studying naturalistic human decision-making, it is important to understand how emotional states shape decision-making processes and outcomes. Emotion regulation techniques can improve the quality of decisions, but there are several challenges to evaluating these techniques in a controlled research context. Determining the effectiveness of emotion regulation techniques requires methodology that can: 1) reliably elicit desired emotions in decision-makers; 2) include decision tasks with response measures that are sensitive to emotional loading; and 3) support repeated exposures/trials with relatively-consistent emotional loading and response sensitivity. The current study investigates one common method, the Balloon Analog Risk Task (BART), for its consistency and reliability in measuring the risk-propensity of decision-makers, and specifically how the method’s effectiveness might change over the course of repeated exposures. With the PANASX subjective assessment serving for comparison, results suggest the BART assessment method, when applied over repeated exposures, is reduced in its sensitivity to emotional stimuli and exhibits decision task-related learning effects which influence the observed trends in response data in complex ways. This work is valuable for researchers in decision-making and to guide design for humans with consideration for their affective states.


Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1181
Author(s):  
Chenhao Zhu ◽  
Sheng Cai ◽  
Yifan Yang ◽  
Wei Xu ◽  
Honghai Shen ◽  
...  

In applications such as carrier attitude control and mobile device navigation, a micro-electro-mechanical-system (MEMS) gyroscope will inevitably be affected by random vibration, which significantly affects the performance of the MEMS gyroscope. In order to solve the degradation of MEMS gyroscope performance in random vibration environments, in this paper, a combined method of a long short-term memory (LSTM) network and Kalman filter (KF) is proposed for error compensation, where Kalman filter parameters are iteratively optimized using the Kalman smoother and expectation-maximization (EM) algorithm. In order to verify the effectiveness of the proposed method, we performed a linear random vibration test to acquire MEMS gyroscope data. Subsequently, an analysis of the effects of input data step size and network topology on gyroscope error compensation performance is presented. Furthermore, the autoregressive moving average-Kalman filter (ARMA-KF) model, which is commonly used in gyroscope error compensation, was also combined with the LSTM network as a comparison method. The results show that, for the x-axis data, the proposed combined method reduces the standard deviation (STD) by 51.58% and 31.92% compared to the bidirectional LSTM (BiLSTM) network, and EM-KF method, respectively. For the z-axis data, the proposed combined method reduces the standard deviation by 29.19% and 12.75% compared to the BiLSTM network and EM-KF method, respectively. Furthermore, for x-axis data and z-axis data, the proposed combined method reduces the standard deviation by 46.54% and 22.30% compared to the BiLSTM-ARMA-KF method, respectively, and the output is smoother, proving the effectiveness of the proposed method.


2021 ◽  
Vol 2 (2) ◽  
Author(s):  
Kate Highnam ◽  
Domenic Puzio ◽  
Song Luo ◽  
Nicholas R. Jennings

AbstractBotnets and malware continue to avoid detection by static rule engines when using domain generation algorithms (DGAs) for callouts to unique, dynamically generated web addresses. Common DGA detection techniques fail to reliably detect DGA variants that combine random dictionary words to create domain names that closely mirror legitimate domains. To combat this, we created a novel hybrid neural network, Bilbo the “bagging” model, that analyses domains and scores the likelihood they are generated by such algorithms and therefore are potentially malicious. Bilbo is the first parallel usage of a convolutional neural network (CNN) and a long short-term memory (LSTM) network for DGA detection. Our unique architecture is found to be the most consistent in performance in terms of AUC, $$F_1$$ F 1 score, and accuracy when generalising across different dictionary DGA classification tasks compared to current state-of-the-art deep learning architectures. We validate using reverse-engineered dictionary DGA domains and detail our real-time implementation strategy for scoring real-world network logs within a large enterprise. In 4 h of actual network traffic, the model discovered at least five potential command-and-control networks that commercial vendor tools did not flag.


Autism ◽  
2021 ◽  
pp. 136236132098795
Author(s):  
Eleanor R Palser ◽  
Alejandro Galvez-Pol ◽  
Clare E Palmer ◽  
Ricci Hannah ◽  
Aikaterini Fotopoulou ◽  
...  

Differences in understanding emotion in autism are well-documented, although far more research has considered how being autistic impacts an understanding of other people’s emotions, compared to their own. In neurotypical adults and children, many emotions are associated with distinct bodily maps of experienced sensation, and the ability to report these maps is significantly related to the awareness of interoceptive signals. Here, in 100 children who either carry a clinical diagnosis of autism ( n = 45) or who have no history of autism ( n = 55), we investigated potential differences in differentiation across autistic children’s bodily maps of emotion, as well as how such differentiation relates to the processing of interoceptive signals. As such, we measured objective interoceptive performance using the heartbeat-counting task, and participants’ subjective experience of interoceptive signals using the child version of the Body Perception Questionnaire. We found less differentiation in the bodily maps of emotion in autistic children, but no association with either objective or subjective interoceptive processing. These findings suggest that, in addition to previously reported differences in detecting others’ emotional states, autistic children have a less differentiated bodily experience of emotion. This does not, however, relate to differences in interoceptive perception as measured here. Lay abstract More research has been conducted on how autistic people understand and interpret other people’s emotions, than on how autistic people experience their own emotions. The experience of emotion is important however, because it can relate to difficulties like anxiety and depression, which are common in autism. In neurotypical adults and children, different emotions have been associated with unique maps of activity patterns in the body. Whether these maps of emotion are comparable in autism is currently unknown. Here, we asked 100 children and adolescents, 45 of whom were autistic, to color in outlines of the body to indicate how they experienced seven emotions. Autistic adults and children sometimes report differences in how they experience their internal bodily states, termed interoception, and so we also investigated how this related to the bodily maps of emotion. In this study, the autistic children and adolescents had comparable interoception to the non-autistic children and adolescents, but there was less variability in their maps of emotion. In other words, they showed more similar patterns of activity across the different emotions. This was not related to interoception, however. This work suggests that there are differences in how autistic people experience emotion that are not explained by differences in interoception. In neurotypical people, less variability in emotional experiences is linked to anxiety and depression, and future work should seek to understand if this is a contributing factor to the increased prevalence of these difficulties in autism.


Author(s):  
Zhang Chao ◽  
Wang Wei-zhi ◽  
Zhang Chen ◽  
Fan Bin ◽  
Wang Jian-guo ◽  
...  

Accurate and reliable fault diagnosis is one of the key and difficult issues in mechanical condition monitoring. In recent years, Convolutional Neural Network (CNN) has been widely used in mechanical condition monitoring, which is also a great breakthrough in the field of bearing fault diagnosis. However, CNN can only extract local features of signals. The model accuracy and generalization of the original vibration signals are very low in the process of vibration signal processing only by CNN. Based on the above problems, this paper improves the traditional convolution layer of CNN, and builds the learning module (local feature learning block, LFLB) of the local characteristics. At the same time, the Long Short-Term Memory (LSTM) is introduced into the network, which is used to extract the global features. This paper proposes the new neural network—improved CNN-LSTM network. The extracted deep feature is used for fault classification. The improved CNN-LSTM network is applied to the processing of the vibration signal of the faulty bearing collected by the bearing failure laboratory of Inner Mongolia University of science and technology. The results show that the accuracy of the improved CNN-LSTM network on the same batch test set is 98.75%, which is about 24% higher than that of the traditional CNN. The proposed network is applied to the bearing data collection of Western Reserve University under the condition that the network parameters remain unchanged. The experiment shows that the improved CNN-LSTM network has better generalization than the traditional CNN.


2017 ◽  
Vol 114 (32) ◽  
pp. 8505-8510 ◽  
Author(s):  
Francesco Bogliacino ◽  
Gianluca Grimalda ◽  
Pietro Ortoleva ◽  
Patrick Ring

Previous research has investigated the effects of violence and warfare on individuals' well-being, mental health, and individual prosociality and risk aversion. This study establishes the short- and long-term effects of exposure to violence on short-term memory and aspects of cognitive control. Short-term memory is the ability to store information. Cognitive control is the capacity to exert inhibition, working memory, and cognitive flexibility. Both have been shown to affect positively individual well-being and societal development. We sampled Colombian civilians who were exposed either to urban violence or to warfare more than a decade earlier. We assessed exposure to violence through either the urban district-level homicide rate or self-reported measures. Before undertaking cognitive tests, a randomly selected subset of our sample was asked to recall emotions of anxiety and fear connected to experiences of violence, whereas the rest recalled joyful or emotionally neutral experiences. We found that higher exposure to violence was associated with lower short-term memory abilities and lower cognitive control in the group recalling experiences of violence, whereas it had no effect in the other group. This finding demonstrates that exposure to violence, even if a decade earlier, can hamper cognitive functions, but only among individuals actively recalling emotional states linked with such experiences. A laboratory experiment conducted in Germany aimed to separate the effect of recalling violent events from the effect of emotions of fear and anxiety. Both factors had significant negative effects on cognitive functions and appeared to be independent from each other.


2021 ◽  
Author(s):  
Chonghua Xue ◽  
Cody Karjadi ◽  
Ioannis Ch. Paschalidis ◽  
Rhoda Au ◽  
Vijaya B. Kolachalama

AbstractBackgroundIdentification of reliable, affordable and easy-to-use strategies for detection of dementia are sorely needed. Digital technologies, such as individual voice recordings, offer an attractive modality to assess cognition but methods that could automatically analyze such data without any pre-processing are not readily available.MethodsWe used a subset of 1264 digital voice recordings of neuropsychological examinations administered to participants from the Framingham Heart Study (FHS), a community-based longitudinal observational study. The recordings were 73 minutes in duration, on average, and contained at least two speakers (participant and clinician). Of the total voice recordings, 483 were of participants with normal cognition (NC), 451 recordings were of participants with mild cognitive impairment (MCI), and 330 were of participants with dementia. We developed two deep learning models (a two-level long short-term memory (LSTM) network and a convolutional neural network (CNN)), which used the raw audio recordings to classify if the recording included a participant with only NC or only dementia, and also to differentiate between recordings corresponding to non-demented (NC+MCI) and demented participants.FindingsBased on 5-fold cross-validation, the LSTM model achieved a mean (±std) area under the sensitivity-specificity curve (AUC) of 0.744±0.038, mean accuracy of 0.680±0.032, mean sensitivity of 0.719±0.112, and mean specificity of 0.652±0.089 in predicting cases with dementia from those with normal cognition. The CNN model achieved a mean AUC of 0.805±0.027, mean accuracy of 0.740±0.033, mean sensitivity of 0.735±0.094, and mean specificity of 0.750±0.083 in predicting cases with only dementia from those with only NC. For the task related to classification of demented participants from non-demented ones, the LSTM model achieved a mean AUC of 0.659±0.043, mean accuracy of 0.701±0.057, mean sensitivity of 0.245±0.161 and mean specificity of 0.856±0.105. The CNN model achieved a mean AUC of 0.730±0.039, mean accuracy of 0.735±0.046, mean sensitivity of 0.443±0.113, and mean specificity of 0.840±0.076 in predicting cases with dementia from those who were not demented.InterpretationThis proof-of-concept study demonstrates the potential that raw audio recordings of neuropsychological testing performed on individuals recruited within a community cohort setting can provide a level of screening for dementia.


Sign in / Sign up

Export Citation Format

Share Document