Previous experiments investigating visual search have shown that distractors that are semantically related to a search target can capture attention and slow the search process. In two experiments, we examine if distractors exactly matching, or semantically related to, search-irrelevant information held in working memory (WM) can also influence visual search while ruling out potential effects of color similarity. Participants first viewed and memorized an image of an everyday object, then they determined if a target item was present or absent in a two-object search array. On exact-match trials, the memorized object appeared as a distractor; on semantic-match trials, an object semantically related to the memorized object appeared as a distractor. Both exact-match and semantic-match distractors slowed search when the target was present in the search array. Our findings extend previous findings by demonstrating WM-driven attentional guidance by complex objects rather than simple features. The results also suggest that visual search can be influenced by distractors sharing only semantic features with a search-irrelevant, but active, WM representation.
Background: In recent years, human activity recognition (HAR) has been an active research topic due to its widespread application in various fields such as healthcare, sports, patient monitoring, etc. HAR approaches can be categorised as handcrafted feature methods (HCF) and deep learning methods (DL). HCF involves complex data pre-processing and manual feature extraction in which the models may be exposed to high bias and crucial implicit pattern loss. Hence, DL approaches are introduced due to their exceptional recognition performance. Convolutional Neural Network (CNN) extracts spatial features while preserving localisation. However, it hardly captures temporal features. Recurrent Neural Network (RNN) learns temporal features, but it is susceptible to gradient vanishing and suffers from short-term memory problems. Unlike RNN, Long-Short Term Memory network has a relatively longer-term dependency. However, it consumes higher computation and memory because it computes and stores partial results at each level. Methods: This work proposes a novel multiscale temporal convolutional network (MSTCN) based on the Inception model with a temporal convolutional architecture. Unlike HCF methods, MSTCN requires minimal pre-processing and no manual feature engineering. Further, multiple separable convolutions with different-sized kernels are used in MSTCN for multiscale feature extraction. Dilations are applied to each separable convolution to enlarge the receptive fields without increasing the model parameters. Moreover, residual connections are utilised to prevent information loss and gradient vanishing. These features enable MSTCN to possess a longer effective history while maintaining a relatively low in-network computation. Results: The performance of MSTCN is evaluated on UCI and WISDM datasets using a subject independent protocol with no overlapping subjects between the training and testing sets. MSTCN achieves accuracies of 97.42 on UCI and 96.09 on WISDM. Conclusion: The proposed MSTCN dominates the other state-of-the-art methods by acquiring high recognition accuracies without requiring any manual feature engineering.
This research proposes a 'temporal attention' addition for long-short term memory (LSTM) models for dengue prediction. The number of monthly dengue cases was collected for each of five Malaysian states i.e. Selangor, Kelantan, Johor, Pulau Pinang, and Melaka from 2011 to 2016. Climatic, demographic, geographic and temporal attributes were used as covariates. The proposed LSTM models with temporal attention was compared with several benchmark models including a linear support vector machine (LSVM), a radial basis function support vector machine (RBFSVM), a decision tree (DT), a shallow neural network (SANN) and a deep neural network (D-ANN). In addition, experiments were conducted to analyze the impact of look-back settings on each model performance. The results showed that the attention LSTM (A-LSTM) model performed best, with the stacked, attention LSTM (SA-LSTM) one in second place. The LSTM and stacked LSTM (S-LSTM) models performed almost identically but with the accuracy improved by the attention mechanism was added. Indeed, they were both found to be superior to the benchmark models mentioned above. The best results were obtained when all attributes were included in the model. The four models (LSTM, S-LSTM, A-LSTM and SA-LSTM) were able to accurately predict dengue presence 1-6 months ahead. Our findings provide a more accurate dengue prediction model than previously used, with the prospect of also applying this approach in other geographic areas.
The present article reports two experiments examining the impact of recollecting emotionally valenced autobiographical memories on subsequent working memory (WM) task performance. Experiment 1 found that negatively valenced recollection significantly disrupted performance on a supra-span spatial WM task. Experiment 2 replicated and extended these findings to a verbal WM task (digit recall), and found that both negative and positive autobiographical recollections had a detrimental effect on verbal WM. In addition, we observed that these disruptive effects were more apparent on early trials, immediately following autobiographical recollection. Overall, these findings show that both positive and negative affect can disrupt WM when the mood-eliciting context is based on autobiographical memories. Furthermore, these results indicate that the emotional disruption of WM can take place across different modalities of WM (verbal and visuo-spatial).
Droughts are slow-moving natural hazards that gradually spread over large areas and capable of extending to continental scales, leading to severe socio-economic damage. A key challenge is developing accurate drought forecast model and understanding a models' capability to examine different drought characteristics. Traditionally, forecasting techniques have used various time-series approaches and machine learning models. However, the use of deep learning methods have not been tested extensively despite its potential to improve our understanding of drought characteristics. The present study uses a deep learning approach, specifically the Long Short-Term Memory (LSTM) to predict a commonly used drought measure, the Standard Precipitation Evaporation Index (SPEI) at two different time scales (SPEI 1, SPEI 3). The model was compared with other common machine learning method, Random Forests, Artificial Neural Networks and applied over the New South Wales (NSW) region of Australia, using hydro-meteorological variables as predictors. The drought index and predictor data were collected from the Climatic Research Unit (CRU) dataset spanning from 1901 to 2018. We analysed the LSTM forecasted results in terms of several drought characteristics (drought intensity, drought category, or spatial variation) to better understand how drought forecasting was improved. Evaluation of the drought intensity forecasting capabilities of the model were based on three different statistical metrics, Coefficient of Determination (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The model achieved R2 value of more than 0.99 for both SPEI 1 and SPEI 3 cases. The variation in drought category forecasted results were studied using a multi-class Receiver Operating Characteristic based Area under Curves (ROC-AUC) approach. The analysis revealed an AUC value of 0.83 and 0.82 for SPEI 1 and SPEI 3 respectively. The spatial variation between observed and forecasted values were analysed for the summer months of 2016-2018. The findings from the study show an improvement relative to machine learning models for a lead time of 1 month in terms of different drought characteristics. The results from this work can be used for drought mitigation purposes and different models need to be tested to further enhance our capabilities.
Self-regulation is a widely studied construct, generally assumed to be cognitively supported by executive functions (EFs). There is a lack of clarity and consensus over the roles of specific components of EFs in self-regulation. The current study examines the relations between performance on (a) a self-regulation task (Heads, Toes, Knees Shoulders Task) and (b) two EF tasks (Knox Cube and Beads Tasks) that measure different components of updating: working memory and short-term memory, respectively. We compared 107 8- to 13-year-old children (64 females) across demographically-diverse populations in four low and middle-income countries, including: Tanna, Vanuatu; Keningau, Malaysia; Saltpond, Ghana; and Natal, Brazil. The communities we studied vary in market integration/urbanicity as well as level of access, structure, and quality of schooling. We found that performance on the visuospatial working memory task (Knox Cube) and the visuospatial short-term memory task (Beads) are each independently associated with performance on the self-regulation task, even when controlling for schooling and location effects. These effects were robust across demographically-diverse populations of children in low-and middle-income countries. We conclude that this study found evidence supporting visuospatial working memory and visuospatial short-term memory as distinct cognitive processes which each support the development of self-regulation.
This study introduces an augmented Long-Short Term Memory (LSTM) neural network architecture, integrating Symbolic Genetic Programming (SGP), with the objective of forecasting cross-sectional price returns across a comprehensive dataset comprising 4500 listed stocks in the Chinese market over the period from 2014 to 2022. Using the S&P Alpha Pool Dataset for China as basic input, this architecture incorporates data augmentation and feature extraction techniques. The result of this study demonstrates significant improvements in Rank Information coefficient (Rank IC) and IC information ratio (ICIR) by 1128% and 5360% respectively when it is applied to fundamental indicators. For technical indicators, the hybrid model achieves a 206% increase in Rank IC and an impressive surge of 2752% in ICIR. Furthermore, the proposed hybrid SGP-LSTM model outperforms major Chinese stock indexes, generating average annualized excess returns of 31.00%, 24.48%, and 16.38% compared to the CSI 300 index, CSI 500 index, and the average portfolio, respectively. These findings highlight the effectiveness of SGP-LSTM model in improving the accuracy of cross-sectional stock return predictions and provide valuable insights for fund managers, traders, and financial analysts.
One of the most critical parameters in concrete design is compressive strength. As the compressive strength of concrete is correctly measured, time and cost can be decreased. Concrete strength is relatively resilient to impacts on the environment. The production of concrete compressive strength is greatly influenced by severe weather conditions and increases in humidity rates. In this research, a model has been developed to predict concrete compressive strength utilizing a detailed dataset obtained from previously published studies based on a deep learning method, namely, long short-term memory (LSTM), and a conventional machine learning (ML) algorithm, namely, support vector machine (SVM). The input variables of the model include cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, and age of specimens. To demonstrate the efficiency of the proposed models, three statistical indices, namely, the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE), were used. Findings shows that LSTM outperformed SVM with R2=0.98, R2= 0.78, MAE=1.861, MAE=6.152, and RMSE=2.36, RMSE=7.93, respectively. The results of this study suggest that high-performance concrete (HPC) compressive strength can be reliably measured using the proposed LSTM model.
The retrieval of autobiographical memories involves the construction of mental representations of past personal events. Many researchers examining the processes underlying memory retrieval argue that visual imagery plays a fundamental role. Other researchers, however, have argued that working memory is an integral component involved in memory retrieval. The goal of this study was to resolve these conflicting arguments by comparing the relative contributions of visual imagery and working memory during the retrieval of autobiographical memories in a dual-task paradigm. While following a moving dot, viewing a dynamic visual noise (DVN), or viewing a blank screen, 95 participants recalled their memories and subsequently rated them on different memory characteristics. The results suggest that inhibiting visual imagery by having participants view DVN merely delayed memory retrieval but did not affect the phenomenological quality of the memories retrieved. Taxations to the working memory by having participants follow a moving dot, on the contrary, resulted in only longer retrieval latencies and no reductions in the specificity, vividness, or the emotional intensity of the memories retrieved. Whereas the role of visual imagery during retrieval is clear, future studies could further examine the role of working memory during retrieval by administering a task that is less difficult or by recruiting a larger sample than this study. The results of this study seem to suggest that both visual imagery and working memory play a role during the retrieval of autobiographical memory, but more research needs to be conducted to determine their exact roles.
Parkinson's disease (PD) is a progressively debilitating neurodegenerative disorder that primarily affects the dopaminergic system in the basal ganglia, impacting millions of individuals globally. The clinical manifestations of the disease include resting tremors, muscle rigidity, bradykinesia, and postural instability. Diagnosis relies mainly on clinical evaluation, lacking reliable diagnostic tests and being inherently imprecise and subjective. Early detection of PD is crucial for initiating treatments that, while unable to cure the chronic condition, can enhance the life quality of patients and alleviate symptoms. This study explores the potential of utilizing long-short term memory neural networks (LSTM) with attention mechanisms to detect Parkinson's disease based on dual-task walking test data. Given that the performance of networks is significantly inductance by architecture and training parameter choices, a modified version of the recently introduced crayfish optimization algorithm (COA) is proposed, specifically tailored to the requirements of this investigation. The proposed optimizer is assessed on a publicly accessible real-world clinical gait in Parkinson's disease dataset, and the results demonstrate its promise, achieving an accuracy of 87.4187 % for the best-constructed models.
In spite of extensive research conducted to study how human brain works, little is known about a special function of the brain that stores and manipulates information-the working memory-and how noise influences this special ability. In this study, Functional magnetic resonance imaging (fMRI) was used to investigate brain responses to arithmetic problems solved in noisy and quiet backgrounds.
Regular aerobic exercise and milk consumption have been found to have positive effects on certain cognitive functions such as short-term memory and sustained attention. However, aggregated effects of combining these modalities have not been explored. This study examined the combined effects of milk supplementation and aerobic exercise on the short-term memory and sustained attention of female students aged 16 yr. (N = 81). The intervention involved serving of 250 ml of regular milk during school days and/or a 1-hr. aerobic exercise period twice per week for 6 weeks. The Digit Span Test and Digit Vigilance Test were used to measure short-term memory and sustained attention, respectively. The combination group (milk and exercise) and exercise group performed significantly better than did the milk and control groups in terms of short-term memory. No significant interaction or group differences were found for sustained attention. The results suggest benefits of regular exercise for students' short-term memory.
Previous studies on individual differences in mathematical abilities have shown that working memory contributes to early arithmetic performance. In this study, we extended the investigation to algebraic word problem solving. A total of 151 10-year-olds were administered algebraic word problems and measures of working memory, intelligence quotient (IQ), and reading ability. Regression results were consistent with findings from the arithmetic literature showing that a literacy composite measure provided greater contribution than did executive function capacity. However, a series of path analyses showed that the overall contribution of executive function was comparable to that of literacy; the effect of executive function was mediated by that of literacy. Both the phonological loop and the visual spatial sketchpad failed to contribute directly; they contributed only indirectly by way of literacy and performance IQ, respectively.
Memory plays an important role in human life. Memory can be divided into two categories, i.e., long term memory and short term memory (STM). STM or working memory (WM) stores information for a short span of time and it is used for information manipulations and fast response activities. WM is generally involved in the higher cognitive functions of the brain. Different studies have been carried out by researchers to understand the WM process. Most of these studies were based on neuroimaging modalities like fMRI, EEG, MEG etc., which use standalone processes. Each neuroimaging modality has some pros and cons. For example, EEG gives high temporal resolution but poor spatial resolution. On the other hand, the fMRI results have a high spatial resolution but poor temporal resolution. For a more in depth understanding and insight of what is happening inside the human brain during the WM process or during cognitive tasks, high spatial as well as high temporal resolution is desirable. Over the past decade, researchers have been working to combine different modalities to achieve a high spatial and temporal resolution at the same time. Developments of MRI compatible EEG equipment in recent times have enabled researchers to combine EEG-fMRI successfully. The research publications in simultaneous EEG-fMRI have been increasing tremendously. This review is focused on the WM research involving simultaneous EEG-fMRI data acquisition and analysis. We have covered the simultaneous EEG-fMRI application in WM and data processing. Also, it adds to potential fusion methods which can be used for simultaneous EEG-fMRI for WM and cognitive tasks.
Recent evidence has exhibited dietary influence on the manifestation of different types of behavior induced by stressor tasks. The present study examined the effects of Tualang honey supplement administered with the goal of preventing or attenuating the occurrence of stress-related behaviors in male rats subjected to noise stress. Forty-eight adult male rats were randomly divided into the following four groups: i) nonstressed with vehicle, ii) nonstressed with Tualang honey, iii) stressed with vehicle, and iv) stressed with honey. The supplement was given once daily via oral gavage at 0.2 g/kg body weight. Two types of behavioral tests were performed, namely, the novel object recognition test to evaluate working memory and the forced swimming test to evaluate depressive-like behavior. Data were analyzed by a two-way analysis of variance (ANOVA) using IBM SPSS 18.0. It was observed that the rats subjected to noise stress expressed higher levels of depressive-like behavior and lower memory functions compared to the unexposed control rats. In addition, our results indicated that the supplementation regimen successfully counteracted the effects of noise stress. The forced swimming test indicated that climbing and swimming times were significantly increased and immobility times significantly decreased in honey-supplemented rats, thereby demonstrating an antidepressant-like effect. Furthermore, cognitive function was shown to be intensely affected by noise stress, but the effects were counteracted by the honey supplement. These findings suggest that subchronic exposure to noise stress induces depressive-like behavior and reduces cognitive functions, and that these effects can be attenuated by Tualang honey supplementation. This warrants further studies to examine the role of Tulang honey in mediating such effects.
Working memory training has been proven effective for improving cognitive functioning in patients with Attention Deficit/Hyperactivity Disorder (ADHD). However, the feasibility of this type of training for children in Saudi Arabia has not been previously explored. We investigated the feasibility of implementing Cogmed Working Memory Training (CWMT) in a sample of 29 Saudi children with ADHD. We found no significant demographic or clinical differences between compliant and noncompliant children. Although compliant children were initially better at following instructions and reported better improvements in working memory and math skills compared to those who did not complete the CWMT, all children who participated in the program showed improvements in performing the CWMT tasks. Most parents found the Cogmed training feasible for their children, were satisfied and keen to continue with the program, and felt the training helped them to address their problems. Most children did not encounter any difficulties in using the software, and many families were, therefore, likely to continue using the techniques from the program. We conclude that CWMT for children with ADHD is feasible in Saudi Arabia. Larger case-controlled studies are needed to thoroughly investigate the effects of CWMT compared to other interventions in Saudi children with ADHD.
Planning ability is important in everyday functioning, and a key measure to assess the preparation and execution of plans is the Tower of London (ToL) task. Previous studies indicate that older adults are often less accurate than the young on the ToL and that there may be cultural differences in performance on the task. However, potential interactions between age and culture have not previously been explored. In the current study we examined the effects of age on ToL performance in an Asian culture (Malaysia) and a Western culture (British) (n = 191). We also explored whether working memory, age, education, and socioeconomic status explained variance in ToL performance across these two cultures. Results indicated that age effects on ToL performance were greater in the Malaysian sample. Subsequent moderated mediation analysis revealed differences between the two cultures (British vs Malaysians), in that the age-related variance in ToL accuracy was accounted for by WM capacity at low and medium education levels only in the Malaysian sample. Demographic variables could not explain additional variance in ToL speed or accuracy. These results may reflect cultural differences in the familiarity and cognitive load of carrying out complex planning tasks.
Given the excessive foul language identified in audio and video files and the detrimental consequences to an individual's character and behaviour, content censorship is crucial to filter profanities from young viewers with higher exposure to uncensored content. Although manual detection and censorship were implemented, the methods proved tedious. Inevitably, misidentifications involving foul language owing to human weariness and the low performance in human visual systems concerning long screening time occurred. As such, this paper proposed an intelligent system for foul language censorship through a mechanized and strong detection method using advanced deep Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) through Long Short-Term Memory (LSTM) cells. Data on foul language were collected, annotated, augmented, and analysed for the development and evaluation of both CNN and RNN configurations. Hence, the results indicated the feasibility of the suggested systems by reporting a high volume of curse word identifications with only 2.53% to 5.92% of False Negative Rate (FNR). The proposed system outperformed state-of-the-art pre-trained neural networks on the novel foul language dataset and proved to reduce the computational cost with minimal trainable parameters.
The atmospheric particulate matter (PM) with a diameter of 2.5 μm or less (PM2.5) is one of the key indicators of air pollutants. Accurate prediction of PM2.5 concentration is very important for air pollution monitoring and public health management. However, the presence of noise in PM2.5 data series is a major challenge of its accurate prediction. A novel hybrid PM2.5 concentration prediction model is proposed in this study by combining complete ensemble empirical mode decomposition (CEEMD) method, Pearson's correlation analysis, and a deep long short-term memory (LSTM) method. CEEMD was employed to decompose historical PM2.5 concentration data to different frequencies in order to enhance the timing characteristics of data. Pearson's correlation was used to screen the different frequency intrinsic-mode functions of decomposed data. Finally, the filtered enhancement data were inputted to a deep LSTM network with multiple hidden layers for training and prediction. The results evidenced the potential of the CEEMD-LSTM hybrid model with a prediction accuracy of approximately 80% and model convergence after 700 training epochs. The secondary screening of Pearson's correlation test improved the model (CEEMD-Pearson) accuracy up to 87% but model convergence after 800 epochs. The hybrid model combining CEEMD-Pearson with the deep LSTM neural network showed a prediction accuracy of nearly 90% and model convergence after 650 interactions. The results provide a clear indication of higher prediction accuracy of PM2.5 with less computation time through hybridization of CEEMD-Pearson with deep LSTM models and its potential to be employed for air pollution monitoring.
The human respiratory system is affected when an individual is infected with COVID-19, which became a global pandemic in 2020 and affected millions of people worldwide. However, accurate diagnosis of COVID-19 can be challenging due to small variations in typical and COVID-19 pneumonia, as well as the complexities involved in classifying infection regions. Currently, various deep learning (DL)-based methods are being introduced for the automatic detection of COVID-19 using computerized tomography (CT) scan images. In this paper, we propose the pelican optimization algorithm-based long short-term memory (POA-LSTM) method for classifying coronavirus using CT scan images. The data preprocessing technique is used to convert raw image data into a suitable format for subsequent steps. Here, we develop a general framework called no new U-Net (nnU-Net) for region of interest (ROI) segmentation in medical images. We apply a set of heuristic guidelines derived from the domain to systematically optimize the ROI segmentation task, which represents the dataset's key properties. Furthermore, high-resolution net (HRNet) is a standard neural network design developed for feature extraction. HRNet chooses the top-down strategy over the bottom-up method after considering the two options. It first detects the subject, generates a bounding box around the object and then estimates the relevant feature. The POA is used to minimize the subjective influence of manually selected parameters and enhance the LSTM's parameters. Thus, the POA-LSTM is used for the classification process, achieving higher performance for each performance metric such as accuracy, sensitivity, F1-score, precision, and specificity of 99%, 98.67%, 98.88%, 98.72%, and 98.43%, respectively.