Displaying publications 1 - 20 of 280 in total

Abstract:
Sort:
  1. Should brain chip implants for memory and cognitive enhancement be banned in competitive national examinations?
    Chin AHB, Alsomali N, Muhsin SM
    Neurosurg Rev, 2024 May 25;47(1):234.
    PMID: 38795179 DOI: 10.1007/s10143-024-02471-4
    In a recent medical breakthrough, Elon Musk's startup company Neuralink implanted the first brain chip in a human patient, purportedly for aiding paralysis. While certainly representing a significant medical milestone for many patients afflicted with debilitating brain and spinal cord injuries, as well as devastating neurodegenerative diseases such as Parkinson's and Alzheimer's, it must be noted that this very same technology can also be manipulated for human memory or cognitive enhancement. What happens if a brain chip were to be developed that can significantly improve either IQ (intelligence quotient) or memory, and these were then implanted in people to enhance their performance in highly competitive national examinations for college entrance or gaining employment in civil service positions? This article therefore discusses the ethical implications of this nascent technology platform, and whether its use in competitive national examinations should be banned.
    Matched MeSH terms: Memory/physiology
  2. Fulltext Examining the roles of visual imagery and working memory in the retrieval of autobiographical memories using a dual-task paradigm
    Anthony K, Wong HK, Lim A, Sow F, Janssen SM
    Q J Exp Psychol (Hove), 2024 Mar;77(3):447-460.
    PMID: 37649149 DOI: 10.1177/17470218231200724
    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.
    Matched MeSH terms: Memory, Short-Term; Memory, Episodic*
  3. Recollecting positive and negative autobiographical memories disrupts working memory
    Allen RJ, Schaefer A, Falcon T
    Acta Psychol (Amst), 2014 Sep;151:237-43.
    PMID: 25086225 DOI: 10.1016/j.actpsy.2014.07.003
    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).
    Matched MeSH terms: Memory, Short-Term*; Memory, Episodic*
  4. Chronic disease profiles of subjective memory complaints: a latent class analysis of older people in a rural Malaysian community
    Yap KH, Warren N, Allotey P, Reidpath DD
    Aging Ment Health, 2020 05;24(5):709-716.
    PMID: 30588848 DOI: 10.1080/13607863.2018.1550632
    Background: Subjective memory complaints (SMC) are common in the elderly and have been suggested as the first subtle sign of decline which can predict dementia. Cognitive decline is thought to be related to inflammatory processes similarly found in other chronic diseases and conditions such as stroke, heart disease and arthritis. This study aimed to examine the association of SMC with chronic diseases and the profile of these health conditions reported by a group of older adults.Methods: Data from a cross-sectional survey conducted from August 2013 and March 2014 was drawn from 6179 individuals aged 56 years and above. Multivariable logistic regression analyses were used to examine SMC's relationship with individual chronic diseases (asthma, kidney disease, heart disease, stroke, arthritis, hypertension and diabetes) and multimorbidity. Latent class analysis (LCA) was used to identify the profile of health conditions. The effect of SMC was estimated in a multinomial logistic regression as part of the latent class model.Results: SMC was statistically significant in its association with asthma, stroke, heart disease, arthritis and multimorbidity in the fully controlled multivariable logistic regression models. Three health profiles were identified: low comorbidity (n = 4136, low rates in all health conditions), arthritis group (n = 860) and diabetes and hypertension group (n = 1183). SMC was associated with arthritis group (OR = 2.04, 95% CI = 1.51-2.75) and diabetes and hypertension group (OR = 1.22, 95% CI = 1.03-1.46).Conclusion: Adapting a combination of analytical approaches allows a better understanding in the assessment of SMC's relationship with chronic diseases and the patterns of distribution of these health conditions.
    Matched MeSH terms: Memory*
  5. The eyes of the past: larger pupil size for autobiographical memories retrieved from field perspective
    El Haj M, Janssen SMJ, Lenoble Q, Robin F, Gallouj K
    Neurol Sci, 2022 Jan;43(1):661-666.
    PMID: 33959825 DOI: 10.1007/s10072-021-05297-w
    BACKGROUND: Visual perspective during memory retrieval has mainly been evaluated with methodologies based on introspection and subjective reports. The current study investigates whether visual perspective can be evaluated with a physiological measurement: pupil dilation.

    METHODS: While their pupil diameter was measured with an eye-tracker, forty-five participants retrieved one memory from a field perspective (i.e., as viewed through our own eyes) and one memory from an observer perspective (i.e., as viewed from a spectator's standpoint). After retrieval, participants rated the emotional intensity of the memories.

    RESULTS: Analysis demonstrated larger pupils during the retrieval of memories from a field perspective and higher emotional intensity for memories retrieved from a field perspective.

    DISCUSSION: The larger pupils for memories recalled from a field perspective could, however, not be attributed to their higher emotional intensity. These findings suggest that pupil dilation could be used as a physiological assessment of visual perspective during memory retrieval.

    Matched MeSH terms: Memory, Episodic*
  6. Views on Memory and Treatment of Cognitive Impairment in 17th-Century Spain: Juan Gutiérrez de Godoy's Work
    Palma JA, Palma F
    Neurology, 2022 Sep 05;99(10):424-427.
    PMID: 35794022 DOI: 10.1212/WNL.0000000000201025
    Memory and its care were significant sociocultural and scientific topics in early modern Spain. Although a major interest in memory was related to its legal and rhetorical implications, medical treatises discussing memory, cognitive impairment, and its treatment began to appear in the 16th and 17th century. Among these treatises, Disputationes phylosophicæ ac medicæ super libros Aristotelis de memoria, et reminiscentia (Philosophical and medical arguments on Aristotle's "De memoria et reminiscentia"), published in 1629 by the physician Juan Gutiérrez de Godoy, is unique in that it is entirely devoted to the medical aspects of memory. Although many of its concepts are now superseded, the treatise is valuable to understand the views on memory and cognitive impairment in 17th-century Spain and their sources, as Gutiérrez quoted many classical, medieval, and contemporary scholars and physicians. The book, written in Latin, is exclusively devoted to memory from a physiologic and medical point of view, with chapters on the classification of memory loss, a description of its causes (including old age, something not widely recognized before), and several chapters on its prevention and treatment, with a fascinating emphasis on confectio anacardina, or anacardium, an intranasal concoction made with the "marking nut," the fruit of the Semecarpus anacardium tree (also known as Malacca bean), with alleged memory-enhancing properties. We review Gutiérrez's Disputationes phylosophicæ, putting it into the wider intellectual and social context in the Europe of its time, and discuss the relevance and purported neuropharmacologic effects of anacardina.
    Matched MeSH terms: Memory Disorders/therapy
  7. The flashbulb-like nature of memory for the first COVID-19 case and the impact of the emergency. A cross-national survey
    Lanciano T, Alfeo F, Curci A, Marin C, D'Uggento AM, Decarolis D, et al.
    Memory, 2024 Feb;32(2):264-282.
    PMID: 38315731 DOI: 10.1080/09658211.2024.2310554
    Flashbulb memories (FBMs) refer to vivid and long-lasting autobiographical memories for the circumstances in which people learned of a shocking and consequential public event. A cross-national study across eleven countries aimed to investigate FBM formation following the first COVID-19 case news in each country and test the effect of pandemic-related variables on FBM. Participants had detailed memories of the date and others present when they heard the news, and had partially detailed memories of the place, activity, and news source. China had the highest FBM specificity. All countries considered the COVID-19 emergency as highly significant at both the individual and global level. The Classification and Regression Tree Analysis revealed that FBM specificity might be influenced by participants' age, subjective severity (assessment of COVID-19 impact in each country and relative to others), residing in an area with stringent COVID-19 protection measures, and expecting the pandemic effects. Hierarchical regression models demonstrated that age and subjective severity negatively predicted FBM specificity, whereas sex, pandemic impact expectedness, and rehearsal showed positive associations in the total sample. Subjective severity negatively affected FBM specificity in Turkey, whereas pandemic impact expectedness positively influenced FBM specificity in China and negatively in Denmark.
    Matched MeSH terms: Memory, Episodic*
  8. Eye movements of recent and remote autobiographical memories: fewer and longer lasting fixations during the retrieval of childhood memories
    El Haj M, Boutoleau-Bretonnière C, Janssen SMJ
    Psychol Res, 2021 Sep;85(6):2466-2473.
    PMID: 32862309 DOI: 10.1007/s00426-020-01403-3
    There is an increased interest in the study of eye movements during the retrieval of autobiographical memories. Following this trend, the aim of the current study was to evaluate eye movements during the retrieval of remote and recent autobiographical memories. We instructed 71 participants to retrieve memories of personal events from early childhood (6-10 years), late childhood/early adolescence (11-14 years), late adolescence (15-18 years), and the last month. During the retrieval of these memories, participants wore eye-tracking glasses. Analyses showed that early childhood memories triggered fewer fixations and fixations with longer durations than memories from the last month. However, no significant differences were observed for the number of saccades, saccade durations, or total amplitude of the saccades. The fewer and longer lasting fixations during the retrieval of early childhood memories can be attributed either to the visual system reconstructing remote memories from an observer perspective or to difficulties when reconstructing remote memories.
    Matched MeSH terms: Memory, Long-Term; Memory, Episodic*
  9. Fulltext Forecasting stock prices changes using long-short term memory neural network with symbolic genetic programming
    Li Q, Kamaruddin N, Yuhaniz SS, Al-Jaifi HAA
    Sci Rep, 2024 Jan 03;14(1):422.
    PMID: 38172568 DOI: 10.1038/s41598-023-50783-0
    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.
    Matched MeSH terms: Memory, Short-Term*; Memory, Long-Term
  10. Fulltext Diagonal preconditioned conjugate gradient algorithm for unconstrained optimization
    Choong Boon Ng, Wah June Leong, Mansor Monsi
    Pertanika Journal of Science & Technology, 2014;22(1):213-224.
    MyJurnal
    The nonlinear conjugate gradient (CG) methods have widely been used in solving unconstrained optimization problems. They are well-suited for large-scale optimization problems due to their low memory requirements and least computational costs. In this paper, a new diagonal preconditioned conjugate gradient (PRECG) algorithm is designed, and this is motivated by the fact that a pre-conditioner can greatly enhance the performance of the CG method. Under mild conditions, it is shown that the algorithm is globally convergent for strongly convex functions. Numerical results are presented to show that the new diagonal PRECG method works better than the standard CG method.
    Matched MeSH terms: Memory
  11. Fulltext Does talking about emotion help eyewitness memory? The role of emotional and factual retelling in memory accuracy
    Kartini Abdul Ghani, Lau, Choon Ning
    Journal of Cognitive Sciences & Human Development, 2016;1(2):1-10.
    MyJurnal
    Eyewitnesses typically talk about the traumatic events that they have experienced based on their memory. This research aimed to investigate differences between emotional and factual retelling of eyewitness in terms of memory accuracy and error. Participants watched a traumatic robbery video and were instructed to recall the events in detail. Participants were divided into three retelling conditions where they: a) discussed the robbery in a factual way, b) focused on discussing their emotional response, and c) performed unrelated tasks. Results showed that eyewitnesses who talked about their emotion recalled less detailed memories and made more errors in free recall while eyewitnesses who focused on factual detail seem to be able to maintain their memory accuracy of the event.
    Matched MeSH terms: Memory
  12. Fulltext An improved memory-based collaborative filtering method based on the TOPSIS technique
    Al-Bashiri H, Abdulgabber MA, Romli A, Kahtan H
    PLoS One, 2018;13(10):e0204434.
    PMID: 30286123 DOI: 10.1371/journal.pone.0204434
    This paper describes an approach for improving the accuracy of memory-based collaborative filtering, based on the technique for order of preference by similarity to ideal solution (TOPSIS) method. Recommender systems are used to filter the huge amount of data available online based on user-defined preferences. Collaborative filtering (CF) is a commonly used recommendation approach that generates recommendations based on correlations among user preferences. Although several enhancements have increased the accuracy of memory-based CF through the development of improved similarity measures for finding successful neighbors, there has been less investigation into prediction score methods, in which rating/preference scores are assigned to items that have not yet been selected by a user. A TOPSIS solution for evaluating multiple alternatives based on more than one criterion is proposed as an alternative to prediction score methods for evaluating and ranking items based on the results from similar users. The recommendation accuracy of the proposed TOPSIS technique is evaluated by applying it to various common CF baseline methods, which are then used to analyze the MovieLens 100K and 1M benchmark datasets. The results show that CF based on the TOPSIS method is more accurate than baseline CF methods across a number of common evaluation metrics.
    Matched MeSH terms: Memory
  13. Existence of long memory in ozone time series
    Muzirah Musa, Kamarulzaman Ibrahim
    Sains Malaysiana, 2012;41:1367-1376.
    Long-memory is often observed in time series data. The existence of long-memory in a data set implies that the successive data points are strongly correlated i.e. they remain persistent for quite some time. A commonly used approach in modellingthe time series data such as the Box and Jenkins models are no longer appropriate since the assumption of stationary is not satisfied. Thus, the scaling analysis is particularly suitable to be used for identifying the existence of long-memory as well as the extent of persistent data. In this study, an analysis was carried out on the observed daily mean per hour of ozone concentration that were available at six monitoring stations located in the urban areas of Peninsular Malaysia from 1998 to 2006. In order to investigate the existence of long-memory, a preliminary analysis was done based on plots of autocorrelation function (ACF) of the observed data. Scaling analysis involving five methods which included rescaled range, rescaled variance, dispersional, linear and bridge detrending techniques of scaled windowed variance were applied to estimate the hurst coefficient (H) at each station. The results revealed that the ACF plots indicated a slow decay as the number lag increased. Based on the scaling analysis, the estimated H values lay within 0.7 and 0.9, indicating the existence of long-memory in the ozone time series data. In addition, it was also found that the data were persistent for the period of up to 150 days.
    Matched MeSH terms: Memory
  14. Improving Pipelined Time Stepping Algorithm for Distributed Memory Multicomputers
    Ng KF, Norhashidah Mohd Ali
    Sains Malaysiana, 2010;39.
    Time stepping algorithm with spatial parallelisation is commonly used to solve time dependent partial differential equations. Computation in each time step is carried out using all processors available before sequentially advancing to the next time step. In cases where few spatial components are involved and there are relatively many processors available for use, this will result in fine granularity and decreased scalability. Naturally one alternative is to parallelise the temporal domain. Several time parallelisation algorithms have been suggested for the past two decades. One of them is the pipelined iterations across time steps. In this pipelined time stepping method, communication however is extensive between time steps during the pipelining process. This causes a decrease in performance on distributed memory environment which often has high message latency. We present a modified pipelined time stepping algorithm based on delayed pipelining and reduced communication strategies to improve overall execution time on a distributed memory environment using MPI. Our goal is to reduce the inter-time step communications while providing adequate information for the next time step to converge. Numerical result confirms that the improved algorithm is faster than the original pipelined algorithm and sequential time stepping algorithm with spatial parallelisation alone. The improved algorithm is most beneficial for fine granularity time dependent problems with limited spatial parallelisation.
    Matched MeSH terms: Memory
  15. Financial risk evaluations in Malaysian stock exchange using extreme-value-theory and component-ARCH model
    Chin WC, Zaidi Isa, Abu Hassan Shaari Mohd Nor
    Sains Malaysiana, 2009;38.
    This study investigates the value-at-risk (VaR) using nonlinear time-varying volatility (ARCH model) and extreme-value-theory (EVT) methodologies. Similar VaR estimation and prediction are observes under the EVT and heavy-tailed long-memory ARCH approaches. The empirical results evidence the EVT-based VaR are more accurate but only at higher quantiles. It is also found that EVT approach is able to provide a convenient framework for asymmetric properties in both the lower and upper tails which implies that the risk and reward are not equally likely for the short- and long-trading positions in Malaysian stock market.
    Matched MeSH terms: Memory
  16. Fulltext Leveraging transfer learning with deep learning for crime prediction
    Butt UM, Letchmunan S, Hassan FH, Koh TW
    PLoS One, 2024;19(4):e0296486.
    PMID: 38630687 DOI: 10.1371/journal.pone.0296486
    Crime remains a crucial concern regarding ensuring a safe and secure environment for the public. Numerous efforts have been made to predict crime, emphasizing the importance of employing deep learning approaches for precise predictions. However, sufficient crime data and resources for training state-of-the-art deep learning-based crime prediction systems pose a challenge. To address this issue, this study adopts the transfer learning paradigm. Moreover, this study fine-tunes state-of-the-art statistical and deep learning methods, including Simple Moving Averages (SMA), Weighted Moving Averages (WMA), Exponential Moving Averages (EMA), Long Short Term Memory (LSTM), Bi-directional Long Short Term Memory (BiLSTMs), and Convolutional Neural Networks and Long Short Term Memory (CNN-LSTM) for crime prediction. Primarily, this study proposed a BiLSTM based transfer learning architecture due to its high accuracy in predicting weekly and monthly crime trends. The transfer learning paradigm leverages the fine-tuned BiLSTM model to transfer crime knowledge from one neighbourhood to another. The proposed method is evaluated on Chicago, New York, and Lahore crime datasets. Experimental results demonstrate the superiority of transfer learning with BiLSTM, achieving low error values and reduced execution time. These prediction results can significantly enhance the efficiency of law enforcement agencies in controlling and preventing crime.
    Matched MeSH terms: Memory, Long-Term
  17. Fulltext Design and Implementation of Fast Spoken Foul Language Recognition with Different End-to-End Deep Neural Network Architectures
    Ba Wazir AS, Karim HA, Abdullah MHL, AlDahoul N, Mansor S, Fauzi MFA, et al.
    Sensors (Basel), 2021 Jan 21;21(3).
    PMID: 33494254 DOI: 10.3390/s21030710
    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.
    Matched MeSH terms: Memory, Short-Term; Memory, Long-Term
  18. Looking at remembering: Eye movements, pupil size, and autobiographical memory
    Janssen SMJ, Foo A, Johnson SN, Lim A, Satel J
    Conscious Cogn, 2021 03;89:103089.
    PMID: 33607423 DOI: 10.1016/j.concog.2021.103089
    To examine the relationship between visual imagery and autobiographical memory, eye position and pupil size were recorded while participants first searched for memories and then reconstructed the retrieved memories (Experiment 1), or only searched for memories (Experiment 2). In Experiment 1, we observed that, although recollective experience was not associated with the number of fixations per minute, memories that took longer to retrieve were linked to increased pupil size. In Experiment 2, we observed that directly retrieved memories were recalled more quickly and were accompanied by smaller pupils than generatively retrieved memories. After correcting for response time, retrieval mode also produced an effect, showing that decreased pupil size is not simply due to directly retrieved memories being recalled more quickly. These findings provide compelling evidence that objective measures, such as pupil size, can be used alongside subjective measures, such as self-reports, to distinguish between directly retrieved and generatively retrieved memories.
    Matched MeSH terms: Memory, Episodic*
  19. The effects of search-irrelevant working memory content on visual search
    Calleja MO, Willoughby AR
    Atten Percept Psychophys, 2023 Feb;85(2):293-300.
    PMID: 36596986 DOI: 10.3758/s13414-022-02634-9
    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.
    Matched MeSH terms: Memory, Short-Term*
  20. MSTCN: A multiscale temporal convolutional network for user independent human activity recognition
    Raja Sekaran S, Pang YH, Ling GF, Yin OS
    F1000Res, 2021;10:1261.
    PMID: 36896393 DOI: 10.12688/f1000research.73175.1
    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 subject independent protocol with no overlapping subjects between the training and testing sets. MSTCN achieves F1 scores of 0.9752 on UCI and 0.9470 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.
    Matched MeSH terms: Memory, Short-Term*
Related Terms
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links