-
PloS One 2024In this study, we used unidirectional and bidirectional long short-term memory (LSTM) deep learning networks for Chinese news classification and characterized the...
In this study, we used unidirectional and bidirectional long short-term memory (LSTM) deep learning networks for Chinese news classification and characterized the effects of contextual information on text classification, achieving a high level of accuracy. A Chinese glossary was created using jieba-a word segmentation tool-stop-word removal, and word frequency analysis. Next, word2vec was used to map the processed words into word vectors, creating a convenient lookup table for word vectors that could be used as feature inputs for the LSTM model. A bidirectional LSTM (BiLSTM) network was used for feature extraction from word vectors to facilitate the transfer of information in both the backward and forward directions to the hidden layer. Subsequently, an LSTM network was used to perform feature integration on all the outputs of the BiLSTM network, with the output from the last layer of the LSTM being treated as the mapping of the text into a feature vector. The output feature vectors were then connected to a fully connected layer to construct a feature classifier using the integrated features, finally classifying the news articles. The hyperparameters of the model were optimized based on the loss between the true and predicted values using the adaptive moment estimation (Adam) optimizer. Additionally, multiple dropout layers were added to the model to reduce overfitting. As text classification models for Chinese news articles, the Bi-LSTM and unidirectional LSTM models obtained f1-scores of 94.15% and 93.16%, respectively, with the former outperforming the latter in terms of feature extraction.
Topics: Humans; Memory, Short-Term; Deep Learning; Neural Networks, Computer; Memory, Long-Term; China
PubMed: 38814925
DOI: 10.1371/journal.pone.0301835 -
Frontiers in Rehabilitation Sciences 2024Employment is recognized as a fundamental human right, which correlates with better physical and mental health. Importantly, well-designed work, which considers the...
INTRODUCTION
Employment is recognized as a fundamental human right, which correlates with better physical and mental health. Importantly, well-designed work, which considers the physical, social, and psychological impacts of work, can serve to enhance the cognitive abilities of workers. Although often overlooked, work for individuals with disabilities, including cognitive impairments, is equally important for their physical and mental well-being. What has not been established, however, is whether well-designed work can also enhance the cognitive abilities of individuals with cognitive impairments.
METHODS
Using a longitudinal study design, we investigated the impact of well-designed work on the cognitive abilities of 60 participants (operators) at the AMIPI Foundation factories, which employ individuals with cognitive impairments to produce electrical cables and harnesses for the automobile industry. The same operators were assessed at three different time points: upon hiring ( = 60), and after working in the factory for 1 year ( = 41, since 19 left the factory) and 2 years ( = 28, since 13 more left the factory). We used five cognitive tests evaluating: (1) finger and manual dexterity, bimanual dexterity, and procedural memory using the Purdue Pegboard; (2) sustained and selective attention using the Symbol Cancellation Task; (3) short- and long-term declarative verbal memory and long-term verbal recognition memory using Rey's Audio-Verbal Learning Test; (4) short- and long-term visual recognition memory using the Continuous Visual Memory Test; and (5) abstract reasoning using Raven's Standard Progressive Matrices.
RESULTS
We observed improvements in procedural memory, sustained and selective attention, and short- and long-term visual recognition memory after working in the factory for 1 or 2 years. We did not observe improvements in finger or manual dexterity or bimanual dexterity, nor short- or long-term declarative verbal memory or verbal recognition memory, nor abstract reasoning.
DISCUSSION
We conclude that, in addition to improving physical and mental well-being, well-designed manufacturing work can serve as a training intervention improving some types of cognitive functioning in individuals with cognitive impairments.
PubMed: 38813372
DOI: 10.3389/fresc.2024.1377133 -
Frontiers in Physiology 2024Eye movement is one of the cues used in human-machine interface technologies for predicting the intention of users. The developing application in eye movement event...
Eye movement is one of the cues used in human-machine interface technologies for predicting the intention of users. The developing application in eye movement event detection is the creation of assistive technologies for paralyzed patients. However, developing an effective classifier is one of the main issues in eye movement event detection. In this paper, bidirectional long short-term memory (BILSTM) is proposed along with hyperparameter tuning for achieving effective eye movement event classification. The Lévy flight and interactive crossover-based reptile search algorithm (LICRSA) is used for optimizing the hyperparameters of BILSTM. The issues related to overfitting are avoided by using fuzzy data augmentation (FDA), and a deep neural network, namely, VGG-19, is used for extracting features from eye movements. Therefore, the optimization of hyperparameters using LICRSA enhances the classification of eye movement events using BILSTM. The proposed BILSTM-LICRSA is evaluated by using accuracy, precision, sensitivity, F1-score, area under the receiver operating characteristic (AUROC) curve measure, and area under the precision-recall curve (AUPRC) measure for four datasets, namely, Lund2013, collected dataset, GazeBaseR, and UTMultiView. The gazeNet, human manual classification (HMC), and multi-source information-embedded approach (MSIEA) are used for comparison with the BILSTM-LICRSA. The F1-score of BILSTM-LICRSA for the GazeBaseR dataset is 98.99%, which is higher than that of the MSIEA.
PubMed: 38812881
DOI: 10.3389/fphys.2024.1366910 -
Journal of Integrative Neuroscience Apr 2024In our modern world we are exposed to a steady stream of information containing important as well as irrelevant information. Therefore, our brains have to constantly...
BACKGROUND
In our modern world we are exposed to a steady stream of information containing important as well as irrelevant information. Therefore, our brains have to constantly select relevant over distracting items and further process the selected information. Whereas there is good evidence that even in rapid serial streams of presented information relevant targets can be actively selected, it is less clear whether and how distracting information is de-selected and suppressed in such scenarios.
METHODS
To address this issue we recorded electroencephalographic activity during a rapid serial visual presentation paradigm in which healthy, young human volunteers had to encode visual targets into short-term memory while salient visual distractors and neutral filler items needed to be ignored. Event-related potentials were analyzed in 3D source space and compared between stimulus types.
RESULTS
A negative wave between around 170 and 230 ms after stimulus onset resembling the N2pc component was identified that dissociated between target stimuli and distractors as well as filler items. This wave appears to reflect target selection processes. However, there was no electrophysiological signature identified that would indicate an active distractor suppression mechanism.
CONCLUSIONS
The obtained results suggest that unlike in situations where target stimuli and distractors are presented simultaneously, targets can be selected without the need for active suppression of distracting information in serial presentations with a clear and regular temporal structure. It is assumed that temporal expectation supports efficient target selection by the brain.
Topics: Humans; Young Adult; Male; Electroencephalography; Female; Adult; Attention; Evoked Potentials; Brain; Visual Perception; Memory, Short-Term; Photic Stimulation
PubMed: 38812398
DOI: 10.31083/j.jin2305088 -
Psychiatry Investigation May 2024Early detection and intervention of developmental disabilities (DDs) are critical to improving the long-term outcomes of afflicted children. In this study, our objective...
OBJECTIVE
Early detection and intervention of developmental disabilities (DDs) are critical to improving the long-term outcomes of afflicted children. In this study, our objective was to utilize facial landmark features from mobile application to distinguish between children with DDs and typically developing (TD) children.
METHODS
The present study recruited 89 children, including 33 diagnosed with DD, and 56 TD children. The aim was to examine the effectiveness of a deep learning classification model using facial video collected from children through mobile-based application. The study participants underwent comprehensive developmental assessments, which included the child completion of the Korean Psychoeducational Profile-Revised and caregiver completing the Korean versions of Vineland Adaptive Behavior Scale, Korean version of the Childhood Autism Rating Scale, Social Responsiveness Scale, and Child Behavior Checklist. We extracted facial landmarks from recorded videos using mobile application and performed DDs classification using long short-term memory with stratified 5-fold cross-validation.
RESULTS
The classification model shows an average accuracy of 0.88 (range: 0.78-1.00), an average precision of 0.91 (range: 0.75-1.00), and an average F1-score of 0.80 (range: 0.60-1.00). Upon interpreting prediction results using SHapley Additive exPlanations (SHAP), we verified that the most crucial variable was the nodding head angle variable, with a median SHAP score of 2.6. All the top 10 contributing variables exhibited significant differences in distribution between children with DD and TD (p<0.05).
CONCLUSION
The results of this study provide evidence that facial landmarks, utilizing readily available mobile-based video data, can be used to detect DD at an early stage.
PubMed: 38810998
DOI: 10.30773/pi.2023.0315 -
Social Cognitive and Affective... May 2024Elevated arousal in anxiety is thought to affect attention control. To test this, we designed a visual short-term memory (VSTM) task to examine distractor suppression...
Elevated arousal in anxiety is thought to affect attention control. To test this, we designed a visual short-term memory (VSTM) task to examine distractor suppression during periods of threat and no-threat. We hypothesized that threat would impair performance when subjects had to filter out large numbers of distractors. The VSTM task required subjects to attend to one array of squares while ignoring a separate array. The number of target and distractor squares varied systematically, with high (4 squares) and low (2 squares) target and distractor conditions. This study comprised two separate experiments. Experiment 1 used startle responses and white noise as to directly measure threat-induced anxiety. Experiment 2 used BOLD to measure brain responses. For Experiment 1, subjects showed significantly larger startle responses during threat compared to safe period, supporting the validity of the threat manipulation. For Experiment 2, we found that accuracy was affected by threat, such that distractor load negatively impacted accuracy only in the threat condition. We also found threat related differences in parietal cortex activity. Overall, these findings suggest that threat affects distractor susceptibility, impairing filtering of distracting information. This effect is possibly mediated by hyperarousal of parietal cortex during threat.
PubMed: 38809714
DOI: 10.1093/scan/nsae036 -
Microbiology Spectrum May 2024The host immune responses play a pivotal role in the establishment of long-term memory responses, which effectively aids in infection clearance. However, the prevailing...
The host immune responses play a pivotal role in the establishment of long-term memory responses, which effectively aids in infection clearance. However, the prevailing anti-tuberculosis therapy, while aiming to combat tuberculosis (TB), also debilitates innate and adaptive immune components of the host. In this study, we explored how the front-line anti-TB drugs impact the host immune cells by modulating multiple signaling pathways and subsequently leading to disease relapse. Administration of these drugs led to a reduction in innate immune activation and also the cytokines required to trigger protective T cell responses. Moreover, these drugs led to activation-induced cell death in the mycobacterial-specific T cell leading to a reduced killing capacity. Furthermore, these drugs stalled the T cell differentiation into memory subsets by modulating the activation of STAT3, STAT4, FOXO1, and NFκB transcription factors and hampering the Th1 and Th17-mediated long-term host protective memory responses. These findings suggest the urgent need to augment directly observed treatment, short-course (DOTS) therapy with immunomodulatory agents to mitigate the adverse effects linked to the treatment.IMPORTANCEAs a central component of TB eradication initiatives, directly observed treatment, short-course (DOTS) therapy imparts immune-dampening effects during the course of treatment. This approach undermines the host immune system by delaying the activation process and lowering the immune response. In our investigation, we have unveiled the impact of DOTS on specific immune cell populations. Notably, the signaling pathways involving STAT3 and STAT4 critical for memory responses and NFκβ associated with pro-inflammation were substantially declined due to the therapy. Consequently, these drugs exhibit limited effectiveness in preventing recurrence of the disease. These observations highlight the imperative integration of immunomodulators to manage TB infection.
PubMed: 38809023
DOI: 10.1128/spectrum.00412-24 -
Scientific Reports May 2024Understanding water saturation levels in tight gas carbonate reservoirs is vital for optimizing hydrocarbon production and mitigating challenges such as reduced...
Understanding water saturation levels in tight gas carbonate reservoirs is vital for optimizing hydrocarbon production and mitigating challenges such as reduced permeability due to water saturation (Sw) and pore throat blockages, given its critical role in managing capillary pressure in water drive mechanisms reservoirs. Traditional sediment characterization methods such as core analysis, are often costly, invasive, and lack comprehensive spatial information. In recent years, several classical machine learning models have been developed to address these shortcomings. Traditional machine learning methods utilized in reservoir characterization encounter various challenges, including the ability to capture intricate relationships, potential overfitting, and handling extensive, multi-dimensional datasets. Moreover, these methods often face difficulties in dealing with temporal dependencies and subtle patterns within geological formations, particularly evident in heterogeneous carbonate reservoirs. Consequently, despite technological advancements, enhancing the reliability, interpretability, and applicability of predictive models remains imperative for effectively characterizing tight gas carbonate reservoirs. This study employs a novel data-driven strategy to prediction of water saturation in tight gas reservoir powered by three recurrent neural network type deep/shallow learning algorithms-Gated Recurrent Unit (GRU), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Support Vector Machine (SVM), K-nearest neighbor (KNN) and Decision tree (DT)-customized to accurately forecast sequential sedimentary structure data. These models, optimized using Adam's optimizer algorithm, demonstrated impressive performance in predicting water saturation levels using conventional petrophysical data. Particularly, the GRU model stood out, achieving remarkable accuracy (an R-squared value of 0.9973) with minimal errors (RMSE of 0.0198) compared to LSTM, RNN, SVM, KNN and, DT algorithms, thus showcasing its proficiency in processing extensive datasets and effectively identifying patterns. By achieving unprecedented accuracy levels, this study not only enhances the understanding of sediment properties and fluid saturation dynamics but also offers practical implications for reservoir management and hydrocarbon exploration in complex geological settings. These insights pave the way for more reliable and efficient decision-making processes, thereby advancing the forefront of reservoir engineering and petroleum geoscience.
PubMed: 38806579
DOI: 10.1038/s41598-024-63168-8 -
Nature Communications May 2024The mechanisms by which the number of memory CD8 T cells is stably maintained remains incompletely understood. It has been postulated that maintaining them requires help...
The mechanisms by which the number of memory CD8 T cells is stably maintained remains incompletely understood. It has been postulated that maintaining them requires help from CD4 T cells, because adoptively transferred memory CD8 T cells persist poorly in MHC class II (MHCII)-deficient mice. Here we show that chronic interferon-γ signals, not CD4 T cell-deficiency, are responsible for their attrition in MHCII-deficient environments. Excess IFN-γ is produced primarily by endogenous colonic CD8 T cells in MHCII-deficient mice. IFN-γ neutralization restores the number of memory CD8 T cells in MHCII-deficient mice, whereas repeated IFN-γ administration or transduction of a gain-of-function STAT1 mutant reduces their number in wild-type mice. CD127 memory cells proliferate actively in response to IFN-γ signals, but are more susceptible to attrition than CD127 terminally differentiated effector memory cells. Furthermore, single-cell RNA-sequencing of memory CD8 T cells reveals proliferating cells that resemble short-lived, terminal effector cells and documents global downregulation of gene signatures of long-lived memory cells in MHCII-deficient environments. We propose that chronic IFN-γ signals deplete memory CD8 T cells by compromising their long-term survival and by diverting self-renewing CD127 cells toward terminal differentiation.
Topics: Animals; CD8-Positive T-Lymphocytes; Interferon-gamma; CD4-Positive T-Lymphocytes; Mice; Immunologic Memory; STAT1 Transcription Factor; Mice, Inbred C57BL; Histocompatibility Antigens Class II; Signal Transduction; Mice, Knockout; Memory T Cells; Interleukin-7 Receptor alpha Subunit; Cell Proliferation; Adoptive Transfer
PubMed: 38806459
DOI: 10.1038/s41467-024-48704-4 -
Scientific Reports May 2024Cervical cancer (CC) ranks as the fourth most common form of cancer affecting women, manifesting in the cervix. CC is caused by the Human papillomavirus (HPV) infection...
Cervical cancer (CC) ranks as the fourth most common form of cancer affecting women, manifesting in the cervix. CC is caused by the Human papillomavirus (HPV) infection and is eradicated by vaccinating women from an early age. However, limited medical facilities present a significant challenge in mid- or low-income countries. It can improve the survivability rate and be successfully treated if the CC is detected at earlier stages. Current technological improvements allow for cost-effective, more sensitive, and rapid screening and treatment measures for CC. DL techniques are widely adopted for the automated detection of CC. DL techniques and architectures are used to detect CC and provide higher detection performance. This study offers the design of Enhanced Cervical Precancerous Lesions Detection and Classification using the Archimedes Optimization Algorithm with Transfer Learning (CPLDC-AOATL) algorithm. The CPLDC-AOATL algorithm aims to diagnose cervical cancer using medical images. At the preliminary stage, the CPLDC-AOATL technique involves a bilateral filtering (BF) technique to eliminate the noise in the input images. Besides, the CPLDC-AOATL technique applies the Inception-ResNetv2 model for the feature extraction process, and the use of AOA chose the hyperparameters. The CPLDC-AOATL technique involves a bidirectional long short-term memory (BiLSTM) model for the cancer detection process. The experimental outcome of the CPLDC-AOATL technique emphasized the superior accuracy outcome of 99.53% over other existing approaches under a benchmark dataset.
Topics: Humans; Female; Uterine Cervical Neoplasms; Algorithms; Precancerous Conditions; Early Detection of Cancer; Machine Learning
PubMed: 38802525
DOI: 10.1038/s41598-024-62773-x