Recognition Cues Research Articles

The Long-Term Transferability of Clinical Judgment Via In-Class Simulations to Nursing Practice: A Qualitative Descriptive Study

BackgroundThe transferability of clinical judgment developed through in-class simulations to clinical practice is understudied. MethodsThis qualitative descriptive study utilized semi-structured interviews to determine to what extent new-to-practice nurses transfer active learning that occurred during observation of in-class simulations during their traditional pre-licensure nursing program to their nursing practice three years later. ResultsThree major themes emerged: cue recognition through visual recall, increased confidence in decision-making, and new cognitive frameworks for nursing practice. ConclusionUsing in-class simulations may improve transferability of clinical judgment through contextualizing student learning and promoting long-term retention as learners transition to practice.

Conserved and divergent signals in 5' splice site sequences across fungi, metazoa and plants.

In eukaryotic organisms the ensemble of 5' splice site sequences reflects the balance between natural nucleotide variability and minimal molecular constraints necessary to ensure splicing fidelity. This compromise shapes the underlying statistical patterns in the composition of donor splice site sequences. The scope of this study was to mine conserved and divergent signals in the composition of 5' splice site sequences. Because 5' donor sequences are a major cue for proper recognition of splice sites, we reasoned that statistical regularities in their composition could reflect the biological functionality and evolutionary history associated with splicing mechanisms. Results: We considered a regularized maximum entropy modeling framework to mine for non-trivial two-site correlations in donor sequence datasets corresponding to 30 different eukaryotes. For each analyzed species, we identified minimal sets of two-site coupling patterns that were able to replicate, at a given regularization level, the observed one-site and two-site frequencies in donor sequences. By performing a systematic and comparative analysis of 5'splice sites we showed that lineage information could be traced from joint di-nucleotide probabilities. We were able to identify characteristic two-site coupling patterns for plants and animals, and propose that they may echo differences in splicing regulation previously reported between these groups.

The Role of Auditory and Visual Cues in the Perception of Mandarin Emotional Speech in Male Drug Addicts

Evidence from previous neurological studies has revealed that drugs can cause severe damage to the human brain structure, leading to significant cognitive disorders in emotion processing, such as psychotic-like symptoms (e.g., speech illusion: reporting positive/negative responses when hearing white noise) and negative reinforcement. Due to these emotion processing disorders, drug addicts may experience difficulties in emotion recognition and speech illusion, which are essential for interpersonal communication and a healthy life experience. However, previous research has yielded divergent results regarding whether drug addicts are more attracted to negative stimuli or positive stimuli. Additionally, little attention has been paid to the speech illusion experienced by drug addicts. Therefore, the current study aimed to investigate the effect of drugs on patterns of emotion recognition through two basic channels: auditory (speech) and visual (facial expression), as well as the speech illusions of drug addicts. The current study conducted a perceptual experiment in which 52 stimuli of four emotions (happy, angry, sad, and neutral) in three modalities (auditory, visual, auditory + visual [congruent & incongruent]) were presented to address Question 1 regarding the multi-modal emotional speech perception of drug addicts. Additionally, 26 stimuli of white noise and speech of three emotions in two noise conditions were presented to investigate Question 2 concerning the speech illusion of drug addicts. A total of thirty-five male drug addicts (25 heroin addicts and 10 ketamine addicts) and thirty-five male healthy controls were recruited for the perception experiment. The results, with heroin and ketamine addicts as examples, revealed that drug addicts exhibited lower accuracies in multi-modal emotional speech perception and relied more on visual cues for emotion recognition, especially when auditory and visual inputs were incongruent. Furthermore, both heroin and ketamine addicts showed a higher incidence of emotional responses when only exposed to white noise, suggesting the presence of psychotic-like symptoms (i.e., speech illusion) in drug addicts. Our results preliminarily indicate a disorder or deficit in multi-modal emotional speech processing among drug addicts, and the use of visual cues (e.g., facial expressions) may be recommended to improve their interpretation of emotional expressions. Moreover, the speech illusions experienced by drug addicts warrant greater attention and awareness. This paper not only fills the research gap in understanding multi-modal emotion processing and speech illusion in drug addicts but also contributes to a deeper understanding of the effects of drugs on human behavior and provides insights for the theoretical foundations of detoxification and speech rehabilitation for drug addicts.

Color and luminance processing in V1 complex cells and artificial neural networks.

Object recognition by natural and artificial visual systems benefits from the identification of object boundaries. A useful cue for the detection of object boundaries is the superposition of luminance and color edges. To gain insight into the suitability of this cue for object recognition, we examined convolutional neural network models that had been trained to recognize objects in natural images. We focused specifically on units in the second convolutional layer whose activations are invariant to the spatial phase of a sinusoidal grating. Some of these units were tuned for a nonlinear combination of color and luminance, which is broadly consistent with a role in object boundary detection. Others were tuned for luminance alone, but very few were tuned for color alone. A literature review reveals that V1 complex cells have a similar distribution of tuning. We speculate that this pattern of sensitivity provides an efficient basis for object recognition, perhaps by mitigating the effects of lighting on luminance contrast polarity. The absence of a contrast polarity-invariant representation of chromaticity alone suggests that it is redundant with other representations.

Recognition subtests of the Repeatable Battery for the Assessment of Neuropsychological Status: evidence for a cortical vs. subcortical distinction

ABSTRACT Introduction Within clinical neuropsychology, a classic diagnostic distinction is made between cortical and subcortical disorders, especially based on their memory profiles. Typically, this is based on the comparison of recall and recognition trials, where individuals with cortical conditions do not tend to benefit (i.e., score well) on recognition trials and individuals with subcortical conditions do. Although the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS) is a widely used brief cognitive battery, there is a lack of evidence to support this measure’s utility in distinguishing between the memory profiles of these conditions. Method Thirty-six mild Alzheimer’s disease (AD), 55 Parkinson’s disease (PD), and 105 essential tremor (ET) participants (N = 196) were administered the RBANS with additional Story and Figure Recognition subtests. Group differences on recall and recognition scores (Total Correct, Hits or True Positives, False Positive Errors, and discriminability index) were examined across the three groups, while controlling for the influence of age and gender. Results As expected, individuals with AD had poorer recognition scores compared to the other clinical groups across tasks (all p-values < .05), while the ET sample largely performed comparably to the PD sample. With the exception of comparable Figure Recognition and Recall in the PD sample, all groups exhibited significantly greater recognition Hit performance compared to Recall (all p-values < .05). Conclusions The group differences in performance across RBANS recognition subtests suggest support for traditional “cortical” and “subcortical” profiles. However, all groups, including the mild AD sample, demonstrated a benefit from recognition cues compared to free recall. Overall, these findings support the inclusion of the newly developed Story and Figure Recognition subtests in future clinical practice and research endeavors.

Red biases sex categorization of human bodies.

Color is associated with gender information (e.g., red-female). However, little has been known on the effect of color on sex recognition of human bodies. This study aimed to investigate whether the color red could influence the categorization of human bodies by sex, and the effect of contextual information. Visual stimuli were created using body silhouettes varying along the waist-to-hip ratio from female to male shapes. These stimuli were presented in conjunction with red, green, and gray colors, which were used either as body color (Experiment 1) or background color (Experiment 2). Participants were instructed to categorize the sex of the body stimuli as either male or female by pressing labeled keys. The results showed that when red was used as a body color, it induced a bias toward feminine body perception, while when used as a background color, it induced a bias toward masculine body perception. Thus, the color red influenced the sex categorization of human bodies, which being modulated by contextual information. These findings provided novel insights into the effect of contextual color cues in sex recognition of human bodies.

Widespread learned predator recognition to an alien predator across populations in an amphibian species

Alien predators are a major cause of decline and extinction of species worldwide, since native organisms are rarely equipped with specific antipredatory strategies to cope with them. However, phenotypic plasticity and learned predator recognition may help prey populations to survive novel predators. Here we examine geographical variation in the learning ability of larval spadefoot toads (Pelobates cultripes) to recognize invasive predatory crayfish (Procambarus clarkii). We compare the learning-mediated behavioural responses of tadpoles from six populations across two regions in Spain (central and southern), with different histories of exposure to the presence of the invasive species. Two of the populations showed innate recognition of chemical cues from the invasive crayfish, whereas three of them learned to recognize such cues as a threat after conditioning with conspecific alarm cues. Learning abilities did not differ among southern populations, but they did among central populations. We assessed patterns of genetic variation within and among these two regions through microsatellite markers and found low genetic divergence among the southern populations but greater differentiation among the central ones. We hypothesize that similar responses to the invasive crayfish in southern populations may have arisen from a combination of extended historical exposure to this introduced predator (~ 50 y) and higher levels of gene flow, as they inhabit a highly interconnected pond network. In contrast, populations from central Spain show lower connectivity, have been exposed to the invasive crayfish for a shorter period of time, and are more divergent in their plastic responses.

Does Deliberately Going Beyond Alarms in Stall Recovery Exercises Lead to Negative Training?

Abstract: We investigated whether deliberately going beyond alarms during aerodynamic stall recovery exercises may result in negative training. Two groups of 20 airline pilots received stall recovery training in a moving-base simulator. The “delayed-response” group induced the stall themselves. The “immediate-response” group was presented with paused situations and had to recover immediately after unpausing. In a surprising transfer test, the pilots in the delayed-response group showed less aggressive unloading, and experienced significantly more time pressure compared to the pilots in the immediate-response group. In a stall cue recognition test, the delayed-response group performed nearly significantly better. We conclude that experiencing the progression of an aerodynamic stall during training has positive effects on pilot performance, even if this requires unprocedural behavior.

Discrimination of facial identity based on simple contrast patterns generated by shading and shadows

The pattern of shadows and shading across a face is determined partly by face shape and may therefore provide a cue for facial recognition. In this study, we measured the ability of human observers to discriminate facial identity based simply on the coarse pattern of contrast produced by the interaction between facial geometry and lighting direction. We used highly realistic 3D models of human heads to create images of faces illuminated from different horizontal and vertical directions, which were then converted to two-tone images (‘Mooney faces’) to isolate the coarse pattern of contrast. Participants were presented with pairs of two-tone faces and judged whether it was the same person in both images. Participants could discriminate facial identity based on the minimal cues within the two-tone images, though sensitivity depended on the horizontal and vertical lighting direction. Performance on the Mooney recognition task correlated with general facial recognition ability, though the role of face-specific processing in this relationship was not significant. Our results demonstrate that shading information in the form of simple contrast cues is sufficient for discriminating facial identity, and support the idea that visual processing is somewhat optimised for overhead lighting – here, in the relatively high-level context of face identity recognition.

Tropical rock lobster (Panulirus ornatus) uses chemoreception via the antennular lateral flagellum to identify conspecific ecdysis

The tropical rock lobster, Panulirus ornatus, is a commercially important aquaculture species exhibiting complex social interactions in laboratory culture, including cannibalism of moulting conspecifics. Cannibalism of soft-shelled post-moult stage individuals is a major limitation during the juvenile stage of culture. Not limited to P. ornatus, cannibalism is widespread across farmed decapods, limiting stocking densities in crab, freshwater crayfish, and prawn species. To understand the mechanisms driving this behaviour and reduce its prevalence, we have investigated the role of chemoreception via the aesthetasc-bearing region of the lateral antennular flagellum, in the recognition of conspecific moulting cues. Differential expression analysis of several tissues in P. ornatus shows an upregulation of 70 ionotropic receptor isoforms, including co-receptors (IR25a and IR93a) and divergent receptors (IR4, IR7, and IR21a) in the aesthetasc-bearing region of the antennules. Deafferentation of the aesthetascs via deionised water exposure prevents juveniles from responding to conspecific moulting cues in a two-current choice flume, suggesting chemoreception, possibly olfaction, plays a role in identifying moulting juveniles. This is the first step in understanding the mechanisms via which cannibalism is triggered in juvenile P. ornatus culture. Further work in this area will help discover means to limit cannibalism in laboratory and commercial culture.

Trusted emotion recognition based on multiple signals captured from video

Emotion recognition based on facial expressions has low accuracy and doubtful reliability because of the existence of fake expressions. In this paper, a method is proposed to recognize fake emotions based on multivisual information generated from single information sources, including facial expressions, eye states and physiological signals captured from video. An algorithm based on a graph neural network is used to extract spatial and spectral domain features from facial images for facial expression recognition. A model-based method is used for decomposing RGB signals into heart rates. A deep model trained by a labeled dataset that we created is used to segment the eye region. After obtaining the signals extracted from video, different fusion strategies are applied to evaluate emotion recognition performance based on multiple signals. In the experiment, the CK+, TFEID, JAFFE, RAF, PURE, and ESLD datasets are used to measure the accuracy of facial expression recognition, heart rate detection and eye region segmentation. The results show that multimodality is effective in improving accuracy and that eye state can be considered a cue for trusted emotion recognition. Compared with the method based on the eye state and noncontact physiological signal, the accuracy of multimodality can be improved by 26.19% and 9.52%, respectively.

The impact of shift work on pain recognition, a robust ability among intensive care nurses.

Pain empathy is essential for high-quality of care. The cognitive ability to identify and understand the pain in others remains underexplored in the context of hospital shift work. This study aimed to observe the early subliminal ability to detect pain in other faces and to investigate pain intensity evaluations during day and night shifts. Twenty-one nurses (31 ± 7 years, 20 women) from cardio-paediatric intensive care participated in this study. Eighteen nurses completed all testing in the morning and evening hours, before and after the 12-hour day and night shift. In the first test, the nurses had to decide if facial stimuli presented subliminally showed pain or not. During the second test, they consciously determined the intensity of the painful faces on a numerical scale. Sleep, sleepiness and empathy were also measured. Recognition accuracy and pain sensitivity remained stable over time, only sensitivity increased following the work shift (F(1,15) = 7.10, p = 0.018). Intensity ratings remained stable. Sleepiness at the end of the night shift was negatively correlated with accuracy (ρ = -0.51, p = 0.018) and positively correlated with prior night shifts (ρ = -0.50, p = 0.022). The judgement of facial pain expressions seems robust across shift types, only individual factors such as sleepiness interfere with pain recognition. Pain sensitivity may be enhanced during working hours. Some professions need to know how to assess pain 24/7 and a lack of sleep can disrupt the cognitive processes necessary for this assessment. Night shifts provoke a bias in pain management, and sleep deprivation, a decrease in pain evaluation. By conducting a repeated measure study in the field that applied a different paradigm (subliminal recognition of facial cues) we add evidence to the understanding of pain recognition and the impact of sleep deprivation on the early processing of pain in others.

Humans recognize affective cues in primate vocalizations: acoustic and phylogenetic perspectives

Humans are adept at extracting affective information from vocalizations of humans and other animals. However, the extent to which human recognition of vocal affective cues of other species is due to cross-taxa similarities in acoustic parameters or the phylogenetic closeness between species is currently unclear. To address this, we first analyzed acoustic variation in 96 affective vocalizations, taken from agonistic and affiliative contexts, of humans and three other primates—rhesus macaques (Macaca mulatta), chimpanzees and bonobos (Pan troglodytes and Pan paniscus). Acoustic analyses revealed that agonistic chimpanzee and bonobo vocalizations were similarly distant from agonistic human voices, but chimpanzee affiliative vocalizations were significantly closer to human affiliative vocalizations, than those of bonobos, indicating a potential derived vocal evolution in the bonobo lineage. Second, we asked 68 human participants to categorize and also discriminate vocalizations based on their presumed affective content. Results showed that participants reliably categorized human and chimpanzee vocalizations according to affective content, but not bonobo threat vocalizations nor any macaque vocalizations. Participants discriminated all species calls above chance level except for threat calls by bonobos and macaques. Our results highlight the importance of both phylogenetic and acoustic parameter level explanations in cross-species affective perception, drawing a more complex picture to the origin of vocal emotions.

Assessing the exploratory profile of two zebrafish populations: Influence of anxiety-like phenotypes and independent trials on homebase-related parameters and exploration

Anxiety is a protective behavior when animals face aversive conditions. The open field test (OFT) is used to assess the spatio-temporal dynamics of exploration, in which both homebase formation and recognition of environmental cues may reflect habituation to unfamiliar conditions. Because emotional- and affective-like states influence exploration patterns and mnemonic aspects, we aimed to verify whether the exploratory behaviors of two zebrafish populations showing distinct baselines of anxiety differ in two OFT sessions. Firstly, we assessed the baseline anxiety-like responses of short fin (SF) and leopard (LEO) populations using the novel tank test (NTT) and light-dark test (LDT) in 6-min trials. Fish were later tested in two consecutive days in the OFT, where the spatial occupancy and exploratory profile were analyzed for 30 min. In general, LEO showed pronounced diving behavior and scototaxis in the NTT and LDT, respectively, in which an “anxiety index” corroborated their exacerbated anxiety-like behavior. In the OFT, the SF population spent less time to establish the homebase in the 1st trial, while only LEO showed a markedly reduction in the latency to homebase formation in the 2nd trial. Both locomotion and homebase-related activities were decreased in the 2nd trial, in which animals also revealed increased occupancy in the center area of the apparatus. Moreover, we verified a significant percentage of homebase conservation for both populations, while only SF showed reduced the number of trips and increased the average length of trips. Principal component analyses revealed that distinct factors accounted for total variances between trials for each population tested. While homebase exploration was reduced in the 2nd trial for SF, an increased occupancy in the center area and hypolocomotion were the main factors that contribute to the effects observed in LEO during re-exposure to the OFT. In conclusion, our novel data support the homebase conservation in zebrafish subjected to independent OFT sessions, as well as corroborate a population-dependent effect on specific behavioral parameters related to exploration.

Facial and Vocal Emotion Recognition in Adolescence: A Systematic Review

AbstractThe ability to recognize emotion is important to wellbeing and building relationships with others, making this skill important in adolescence. Research investigating adolescents’ ability to recognize facial and vocal emotion expressions has reported differing conclusions about the pattern of emotion recognition across this developmental period. This systematic review aimed to clarify the pattern of recognition for facial and vocal emotion expressions, and the relationship of performance to different task and emotion expression characteristics. A comprehensive and systematic search of the literature was conducted using six databases. To be eligible for inclusion, studies had to report data for adolescents between 11 and 18 years of age and measure accuracy of the recognition of emotion cues in either the face or voice. A total of 2333 studies were identified and 47 met inclusion criteria. The majority of studies focused on facial emotion recognition. Overall, early, mid-, and late-adolescents showed a similar pattern of recognition for both facial and vocal emotion expressions with the exception of Sad facial expressions. Sex of the participant also had minimal impact on the overall recognition of different emotions. However, analysis showed considerable variability according to task and emotion expression characteristics. Future research needs to increase focus on recognition of complex emotions, and low-intensity emotion expressions as well as the influence of the inclusion of Neutral as a response option.

African jewel fish (Hemichromis bimaculatus) distinguish individual faces based on their unique iridophore patterns

Previous research has shown that African jewel fish (Hemichromis bimaculatus) recognize pair-bonded mates during their exchanges of egg-guarding duties. The current research examined the perceptual cues for face recognition by comparing two face models displaying anatomically realistic arrangements of blue iridophores derived from discriminant function analysis of distinct sibling groups. Four groups each consisting of 9 subadults were examined using a narrow compartment restraining lateral movement where face models were presented at eye level for eight trials. Because respiratory movement of the operculum can mechanically displace the eye thereby shifting the retinal image, jewel fish reduce their respiration rate during increased attention. When two experimental groups were presented with the same face models on four trials following initial model presentations, both groups exhibited stable respiration rates indicative of model habituation. When the habituated face models were switched to novel face models on the fifth trial, the rates of respiration decreased as measured by reliable increases in the elapsed times of opercular beats. Switching the models back to the habituated models on the sixth trial caused reliable decreases in the elapsed times of opercular beats, resembling the earlier trials for the habituated models. Switching the face models again to the formerly novel models on the seventh trial produced respiration rates that resembled those of the habituated models. The two control groups viewing the same models for all eight trials exhibited no substantial change in respiration rates. Together, these findings indicate that jewel fish can learn to recognize novel faces displaying unique arrangements of iridorphores after one trial of exposure.

Effects of emotion and sex difference on item-method directed forgetting

It is crucial to remember or forget others' faces in daily life. People can intentionally forget things they wish to forget, a phenomenon called directed forgetting (DF). This study examined the effects of stimuli's emotions and sex differences in participants and stimuli on DF. We used happy and angry faces as the items in a typical item-method paradigm and conducted three behavioral experiments. In Experiment 1, we recruited 60 participants to examine how emotions of stimuli and sex differences in participants and stimuli affected DF. In Experiment 2, we recruited 60 female participants and manipulated the durations of items presented during the study phase to examine whether the selective rehearsal theory was held. In Experiment 3, we recruited 50 female participants and attached recognition cues to the items presented during the test phase to examine whether the inhibitory control theory was held. We treated the sex of participants in Experiment 1, the durations of items presented during the study phase in Experiment 2 as the between-subject factors, and emotion and sex of stimuli as the with-subject factors. We conducted the mixed-design ANOVA for corrected hit rate, sensitivity, and bias based on the signal detection theory. As a result, we found that DF occurred easily for male participants, whereas not for female participants because of females' superior memorial performances and stronger sensitivities. Furthermore, we found that female participants owned the best and worst recognition rates for angry female faces and happy male faces, respectively. Our results supported the selective rehearsal theory, suggesting manipulations during the study phase had the potential to help females forget what they wished to forget. We presumed that psychologists and therapists should pay attention to the roles of sex difference in twofold, self and others, when studying people's memory and forgetting. Furthermore, the sensitivity of self and the emotion of others should be considered as well.

Natural and Pathological Aging Distinctively Impacts the Pheromone Detection System and Social Behavior

Normal aging and many age-related disorders such as Alzheimer’s disease cause deficits in olfaction; however, it is currently unknown how natural and pathological aging impacts the detection of social odors which might contribute to the impoverishment of social behavior at old age further worsening overall health. Analysis of the vomeronasal organ, the main gateway to pheromone-encoded information, indicated that natural and pathological aging distinctively affects the neurogenic ability of the vomeronasal sensory epithelium. Whereas cell proliferation remained majorly preserved in 1-year-old APP/PS1 mice, naturally aged animals exhibited significant deficiencies in the number of mature, proliferative, and progenitor cells. These alterations may support age-related deficits in the recognition of social cues and the display of social behavior. Our findings indicate that aging disrupts the processing of social olfactory cues decreasing social odor exploration, discrimination, and habituation in both wild-type senescent (2-year-old) mice and in 1-year-old double mutant model of Alzheimer’s disease (APP/PS1). Furthermore, social novelty was diminished in 1-year-old APP/PS1 mice, indicating that alterations in the processing of social cues are accelerated during pathological aging. This study reveals fundamental differences in the cellular processes by which natural and pathological aging disrupts the exploration of social information and social behavior.

Laser-Modified Ti Surface Improves Paracrine Osteogenesis by Modulating the Expression of DKK1 in Osteoblasts

Titanium surface modifications are widely used to modulate cellular behavior by recognition of topographical cues. However, how those modifications affect the expression of mediators that will influence neighboring cells is still elusive. This study aimed to evaluate the effects of conditioned media from osteoblasts cultured on laser-modified titanium surfaces on the differentiation of bone marrow cells in a paracrine manner and to analyze the expression of Wnt pathway inhibitors. Mice calvarial osteoblasts were seeded on polished (P) and Yb:YAG laser-irradiated (L) Ti surfaces. Osteoblast culture media were collected and filtered on alternate days to stimulate mice BMCs. Resazurin assay was performed every other day for 20 days to check BMC viability and proliferation. After 7 and 14 days of BMCs maintained with osteoblasts P and L-conditioned media, alkaline phosphatase activity, Alizarin Red staining, and RT-qPCR were performed. ELISA of conditioned media was conducted to investigate the expression of Wnt inhibitors Dickkopf-1 (DKK1) and Sclerostin (SOST). BMCs showed increased mineralized nodule formation and alkaline phosphatase activity. The L-conditioned media enhanced the BMC mRNA expression of bone-related markers Bglap, Alpl, and Sp7. L-conditioned media decreased the expression of DKK1 compared with P-conditioned media. The contact of osteoblasts with Yb:YAG laser-modified Ti surfaces induces the regulation of the expression of mediators that affect the osteoblastic differentiation of neighboring cells. DKK1 is among these regulated mediators.

Deep learning approach for recognizing cold and warm thermal discomfort cues from videos

Reducing building energy consumption while maintaining individual thermal comfort levels is a challenge. Energy-efficiency strategies that control indoor conditions, with the aim of reducing energy waste and increasing occupant comfort, require the capture of personal thermal comfort preferences in their feedback loop. However, direct feedback from surveys and invasive methods, which have been proposed to collect personal thermal comfort preferences, are impractical in real-world settings due to the decay of commitment, need for repeated feedback, and invasiveness. To address this challenge, this paper proposes a novel non-invasive approach for automated thermal discomfort detection using a deep learning-based model for thermal discomfort cue recognition. The model recognizes nine discomfort cues from video recordings of occupants in indoor work settings, which could be associated with the cold or warm thermal discomfort states. In developing the model, the architectures of two different residual neural networks (ResNets) that learn spatial and local information were tested using data augmentation and transfer learning techniques, and then compared with the performance of (1) traditional machine learning classifiers that used video frames mapped to the feature space of the ResNets; and (2) the ResNets extended with a long short-term memory (LSTM) layer that learns temporal information from the frame sequence. Approaches that accounted for temporal and spatial information outperformed those that only took spatial information into consideration. The final thermal discomfort cue recognition model achieved a weighted F1-measure of 85% in correctly classifying the cues. The proposed approach could help provide rapid and effortless feedback in building energy management systems to reduce building energy waste while providing comfortable indoor conditions towards increased occupant health and productivity.