ALL Metrics
-
Views
-
Downloads
Get PDF
Get XML
Cite
Export
Track
Research Article
Revised

MSTCN: A multiscale temporal convolutional network for user independent human activity recognition

[version 2; peer review: 2 approved, 1 approved with reservations]
PUBLISHED 18 May 2022
Author details Author details
OPEN PEER REVIEW
REVIEWER STATUS

This article is included in the Research Synergy Foundation gateway.

Abstract

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.

Keywords

human activity recognition, smartphone, temporal convolutional network, dilated convolution, one-dimensional inertial sensor

Revised Amendments from Version 1

In the revised version, the work's problem statement and contributions have been revised to ensure a clearer description. We have also revised Figures 1, 2, 3, 4 and 5 to provide more details. In addition, the authors have included another literature work in the Related Work section. Further, the Methods and Results sections have been separated into two sections. The Method section has been revised to include a detailed explanation regarding the architecture of the proposed model, mainly the justification of the use of the Inception model, 1x1 convolution, dilated convolution, feature concatenation, global average pooling, causality, regularisation, softmax equation and categorical cross-entropy function. Besides, the Experiment and Results section has been revised to include input dimensionality and hyperparameter values (optimizer, learning rate, batch size, etc.) used in the proposed model. Finally, the Discussion section was revised and written in a paragraph.

See the authors' detailed response to the review by Cheng-Yaw Low
See the authors' detailed response to the review by Sultan Daud Khan

Introduction

Human activity recognition (HAR) is extensively applied in various applications such as personal health monitoring,1,2 geriatric patient monitoring,3 ambient assisted living,4 etc. The widespread use of smartphone-based HAR is due to the ubiquity of smartphones and low-cost sensors. Additionally, sensor-based HAR provides a non-intrusive solution.

Over the years, numerous algorithms have been proposed, including handcrafted feature (HCF) methods5-7 and deep learning (DL) methods.8,9 HCF methods require complex signal pre-processing and manual feature engineering to extract essential features. In contrast, DL methods, such as convolutional neural network (CNN),8,9 recurrent neural network (RNN), and long-short term memory network (LSTM),10,11 can automatically extract crucial discriminative features from input signals without manual feature engineering. Besides, the architecture is adaptable to different applications.

Though the existing methods produce satisfactory performances, there are several challenges which hinder the HAR models from achieving potential performance:

  • - HCF methods require manual feature extraction where the extracted features are highly dependent on prior knowledge. This may lead to high bias and missing of essential implicit patterns.

  • - CNN is good at extracting spatial features. It is suboptimal in learning temporal features. Temporal features are crucial in motion analysis.

  • - Although recurrent models are feasible for time-series data, RNN is prone to short-term memory problems, leaving out important information at the beginning if the input sequence is too long.

  • - LSTM prevails over RNN. LSTM has a longer-term dependency and is less susceptible to vanishing gradient. However, LSTM requires higher computation due to multiple gate operations and more memory to store partial results throughout the training phase.

To address the aforementioned challenges, this work proposes a multiscale temporal convolutional network (MSTCN) for HAR. As illustrated in Figure 1, MSTCN is constituted by multiscale dilation (MSD) blocks, global average pooling and softmax. The details of the components will be described in the later section. The contributions of this work are:

  • - A deep analytic model, amalgamating Inception model and Temporal Convolutional Network (TCN), is developed to extract spatial-temporal features from inertial data. MSTCN requires minimal data pre-processing and no manual feature engineering.

  • - MSTCN incorporates multiple different-sized convolutions to perform multiscale feature extraction. These multiscale features provide richer information for data analysis.

  • - To retain longer effective history, dilated convolution is implemented to increase the receptive field without raising the overall parameters.

  • - A comprehensive experimental analysis is conducted using two popular public databases, UCI5 and WISDM.12 Subject independent protocol is implemented where different subjects are used for training and testing. In other words, there is no overlap in subject in the training and test sets.

a5e2cfd0-397c-45c0-b99e-84e9806fa863_figure1.gif

Figure 1. Architecture of MSTCN.

Related work

One-dimensional inertial data undergoes a complicated pre-processing in HCF methods to extract salient statistical feature vectors in time and/or frequency domains. The manually extracted features are then fed into standard machine learning classifiers, such as support vector machine (SVM),5,6 ADA Boost,7 Random Forest,13 C4.5 decision tree,14 etc., for activity classification. He and Jin15 proposed a discrete cosine transform method to extract features and classify the features using multiclass SVM. Lara et al.,16 developed an additive logistic regression, boosting with an ensemble of 10 decision stump classifiers. In the works of Ronao and Cho,17,18 the authors explored the Continuous Hidden Markov Model (HMM) to perform activity recognition in two stages, where the first stage is for static and dynamic classification and the second stage is for course classification. Although these methods produce satisfactory performances, they are highly dependent on the effectiveness of the manual feature engineering techniques.

Recently, researchers leaned towards DL methods since DL requires minimal to zero pre-processing and feature engineering. Ronao et al.,8 Yazdanbakhsh et al.,9 and Huang et al.,19 proposed a CNN-based deep learning system to perform HAR. The reported empirical results show the feasibility of the CNN-based method in analysing motion data. Besides, three-layer LSTM was proposed to classify human activities.20 In addition, Ullah et al. proposed a HAR algorithm that classified the normalised inertial data signals using stacked LSTM into respective classes.11 Further, LSTM variant, known as Bidirectional LSTM, was employed in HAR.10 This model uses richer information, i.e. previous and subsequent information, to perform activity recognition. Nair et al., proposed two variations of TCN, namely Dilated-TCN and Encoder-Decoder TCN in HAR.21 In addition, another two TCN-based models are proposed in Ref. 22, namely TCN-FullyConnectedNetwork and deepConvTCN. Both works of Nair et al.,21 and Garcia et al.,22 concluded that the TCN-based models achieved better performance than existing recurrent models in HAR application due to the longer-term dependencies in TCN.

Methods

In the proposed HAR, the raw inertial signals were firstly pre-processed to remove noise. Next, the pre-processed signals were segmented using sliding window technique. In specific, the signals were partitioned into fixed-sized time windows and each window did not intersect with another window. Then, the segmented data was fed into MSTCN for feature analysis and classification. MSTCN comprises of MSD blocks (green box in Figure 1), global average pooling and softmax classifier.

Figure 2 illustrates the structure of a MSD block, comprising convolution unit (CU), average pooling, residual connection, batch normalization etc. The design of MSD is inspired by Inception module23 in such a way that multiple kernels/filters are applied simultaneously to the input time series data, as shown in the CU in Figure 3. These kernels are in varying lengths which allow multiscale feature extraction, i.e. extracting features from short and long time series.24 In the subsequent MSD blocks, the input of CU is processed via one-by-one causal convolution for channel-wise pooling and dimensionality reduction.25 The padding preserves the input sequence’s length and order, preventing information leakage from the future into the past. Next, the produced feature maps are further processed parallelly by separable convolutions (SepConv) with three different-sized filters to extract features at multiple scales. The ordinary Inception module is using multiple standard convolutions with smaller kernel sizes, i.e., 3 and 5.23 However, bigger kernel sizes are required in HAR application in order to capture longer time series and preserve longer-term dependencies of the input.24 The authors also claimed that the increasing kernel size leads to the rise of the number of network parameters, which may cause overfitting of the model. Hence, SepConv was used since it reduces the number of parameters in convolution process, while demanding lesser memory compared to standard convolutions.26 Figure 4 shows the operation of SepConv through decoupling standard convolution.

a5e2cfd0-397c-45c0-b99e-84e9806fa863_figure2.gif

Figure 2. MSD block.

(concat = concatenation, conv = convolution and p = pooling factor).

a5e2cfd0-397c-45c0-b99e-84e9806fa863_figure3.gif

Figure 3. Convolutional unit in MSD block.

(concat = concatenation, conv = convolution, s = kernel size and d = dilation rate).

a5e2cfd0-397c-45c0-b99e-84e9806fa863_figure4.gif

Figure 4. Separable convolution.

One of the ways to capture longer time dependent features is by introducing dilations to the convolutions for improving the receptive fields without drastically increasing the model’s parameters.27 The difference between dilated and standard convolution is shown in Figure 5. Receptive field, or field of view, is the region of an input space which is visible to a convolution kernel at a time. A model can capture longer underlying patterns from input data using a convolution kernel with a larger receptive field. The receptive field size of a kernel can be enlarged by increasing the dilation rate. Hence, dilated convolutions were applied in this work to enlarge the receptive field without requiring extra parameters. After the parallel convolutions, the produced feature maps of each SepConv are concatenated by stacking them together, see Figure 3.

a5e2cfd0-397c-45c0-b99e-84e9806fa863_figure5.gif

Figure 5. Comparison between standard and dilated convolution.

In the MSD block, average pooling (in Figure 2) down-samples the feature map to reduce noise and dimensionality. Additionally, it also preserves localisation. The pooling’s output is fed into a one-by-one convolution. Next, the features of CU are stacked with the one-by-one convolution output. As illustrated in Figure 2, a residual connection is formed by passing the input into a one-by-one convolution, followed by a batch normalisation. This residual connection ensures longer-term dependencies and prevents information loss. Further, it also reduces the vanishing gradient effects. On the other hand, batch normalisations in MSD block are to reduce the internal covariate shift in the model during training. Furthermore, ReLU activation is chosen for its non-linearity, and the gradient vanishing is minimised.

The features extracted from the series of MSD blocks are further fed into the global average pooling (GAP) for feature pooling. Next, softmax classifier is implemented for data classification. The softmax activation formula for the ith input vector, σ(z)i, is defined:

(1)
σzi=ezij=1Kezj
where zi is the ith input vector, e(zi) is the exponential function of the ith input vector, K is the number of classes and e(zj) is the exponential function of the jth output vector. This function outputs a probability of each human activity class, ranging from zero to one, and the target/predicted class will have the highest probability. Then, softmax loss is computed by implementing categorical cross-entropy loss function to the softmax output.
(2)
CEgeneral=iKtilogzi
where ti are the ground truths and zi are the predicted values for ith class in classes K
(3)
CEsoftmax=logezpjKezj
where zp is the softmax score for the positive class p. The details can be referred to Ref. 28.

Experiments and results

Model configuration and experimental setup

The proposed MSTCN was implemented using Tensorflow, an open-source machine learning platform, with Keras library (a high-level deep learning API written in Python). MSTCN is learned for 100 epochs according to the parameter settings in Table 1. These parameters were fine-tuned based on the validation data from the training set with 10% random data of the training samples.

Table 1. Parameter settings of the proposed model.

UCIWISDM
Input dimension(128,9)(128,3)
Batch size6464
Number of MSD blocks77
Number of filters6464
Filter size8, 16 and 208, 16 and 20
Dilation rate1, 2, 4 and 51, 2, 4 and 5
Stride11
RegularisationL1 and L2L1 and L2
Number of epoch100100
Initial learning rate0.0010.001
Reduce learning rate on plateau functionPatience: 5
Minimum learning rate: 0.0001
Factor: 0.5
Mode: Validation loss
Patience: 5
Minimum learning rate: 0.0001
Factor: 0.5
Mode: Validation loss
OptimizerAdamAdam
Loss functionCategorical cross-entropyCategorical cross-entropy

The experiments were conducted on a desktop with Intel® Core™ i7-8750H CPU with 2.20 GHz, 16GB RAM and NVIDIA GeForce GTX 1050 Ti with Max-Q Design and 4GB memory. Two public databases, UCI5 and WISDM12 were used to assess the reliability of the proposed model. In this work, subject independent protocol was implemented to facilitate impersonal solution. There is no overlap in subject between the training and testing sets. This protocol is relatively challenging since there are some extent of discrepancies of gaits towards the motion patterns in same activities. Details of the databases are recorded in Table 2. The evaluation metrics used in this work include precision, recall, F1 score and classification accuracy.

Table 2. Description of UCI and WISDM datasets.

UCIWISDM
SensorAccelerometer and GyroscopeAccelerometer
Segment size128 ms-2128 ms-2
Segment interval50 ms-220 ms-2
Channel size93
Activities (class labels)Walking, Upstairs, Downstairs, Sitting, Standing and LayingWalking, Jogging, Upstairs, Downstairs, Sitting and Standing
Training testing split21 training users: 9 testing users31 training users: 5 testing users
Validation split10% of the training set10% of the training set

Experiments

Experiments were conducted on UCI dataset to study the effects of (1) convolution, (2) pooling and (3) regularisation on MSTCN's performance. Table 3 shows the proposed model's performances using dilated one-dimensional (1D) causal convolution (CC) and dilated 1D separable convolution (SC). From the empirical results, it was observed that the parameters of SC are approximately half of the parameters of CC. Usually, models with more parameters perform better since maximal data patterns are captured and learned. However, when the training sample size is limited, these models might tend to overfit and not generalise properly to the unseen data, leading to poor performance. In this study, SC obtains ~4% higher accuracy than CC.

Table 3. Performance of MSTCN using different convolutions.

Dilated 1D
causal convolution
Dilated 1D
separable convolution
Number of parameters6 062 0863 750 406
Precision0.93570.9764
Recall0.93750.9744
F1 score0.93560.9747
Accuracy93.6297.42

Next, the performances of max-pooling and average pooling were studied. From Table 4, average pooling excels max-pooling with ~3% higher accuracy. Average pooling performs better in this domain because it takes every value into account. With this, the information leakage is prevented, and feature localisation is preserved.

Table 4. Performance of MSTCN using different pooling layers.

Max poolingAverage pooling
Precision0.94780.9764
Recall0.94680.9744
F1 score0.94630.9747
Accuracy94.6797.42

Table 5 shows the performance of MSTCN with different regularisation settings. The regularisation is performed at the one-by-one causal convolution in MSTCN. L1 is good at dealing with outliers since it takes the absolute values of all the weight instead of squared value.35 On the other hand, L2 forces weights toward zero, but never exactly zero. The non-sparseness of L2 is useful as a prediction performance. By combining the usage of L1 and L2, we can leverage the benefits of both with achieving ~97.5% accuracy.

Table 5. Performance of MSTCN using different regularisation settings.

L1L2L1 and L2Without regularisation
Precision0.94850.96660.97640.9529
Recall0.94640.96500.97440.9521
F1 score0.94590.96490.97470.9517
Accuracy94.6096.4497.4295.28

Further, we also conducted the performance comparison between the proposed MSTCN and the other state-of-the-art methods. Tables 6 and 7 records the classification accuracy performance of the methods on UCI and WISDM datasets, respectively.

Table 6. Accuracy for user independent UCI dataset.

TypeAccuracy (%)
Statistical features + SVM5HCF96.00
Statistical features + Continuous HMM17HCF91.76
Statistical features + HMM Ensemble29HCF83.51
Statistical features + RF13HCF78.00
Statistical features + Linear SVM6HCF86.00
Statistical features + Hierarchical Continuous HMM18HCF93.18
Statistical features + Dropout Classifiers30DL~76.00
Statistical features + Data Centering + CNN31DL97.63
CNN8DL94.79
Frequency features + CNN8DL95.75
Bidirectional LSTM10DL93.79
Dilated TCN21DL93.80
Encoder-Decoder TCN21DL94.60
Statistical features + MLP32DL95.00
Frequency and Power features + Multichannel CNN33DL95.25
Statistical features + InnoHAR25DL94.50
Stacked LSTM11DL93.13
MSTCN (Proposed Method)DL97.42

Table 7. Accuracy for user independent WISDM dataset.

MethodsTypeAccuracy (%)
Statistical features + RF30HCF83.46
Statistical features + RF13HCF83.35
Statistical features + Dropout Classifiers30DL85.36
Statistical features + CNN31DL93.32
Dilated and Strided CNN9DL88.27
Data Augmentation + Two Stage End-to-End CNN19DL84.60
Statistical features + CNN34DL94.18
MSTCN (Proposed Method)DL96.09

Discussion

MSTCN prevails over HCF methods on both datasets because the proposed model can better capture discriminating features from the motion data. Unlike handcrafted features, these deep features are less biased as they are not dependent on prior knowledge. This is crucial, especially for a subject independent solution. Furthermore, MSTCN outperforms most CNN-based approaches, with accuracy scores of ~97% in UCI and ~96% in WISDM. This performance exhibits that the competence of MSTCN in extracting features from the data at assorted scales via the application of different convolutional filter sizes. Besides, GAP in MSTCN not only performing feature pooling, but also minimizes overfitting since there is no parameter to be learned in the GAP.36 This is relatively suitable for subject independent HAR solution since testing data is new/unseen data. Moreover, MSTCN dominates the recurrent model10,11 due to its ability in modelling longer-term dependencies via dilated convolution. Further, residual connections and ReLU activations in MSTCN allow the model to be less susceptible to gradient vanishing and exploding. MSTCN is a TCN-variant model. The obtained empirical results demonstrate that MSTCN outperforms the ordinary TCNs (Dilated TCN and Encoder-Decoder TCN).21 MSTCN learns features at multiple scales via different convolutions with differently sized filters. These multiscale features provide richer information for data analysis.

Conclusions

A new deep analytic model, known as MSTCN, is proposed for subject independent HAR. MSTCN is based on the architectures of the Inception network and temporal convolutional network. In MSTCN, different-sized filters are adopted in dilated separable convolutions to extract multiscale features with the enlarged receptive field of each kernel for longer-term dependencies modelling. Besides, average pooling is performed for dimensionality reduction and locality preservation. The inclusion of residual connections in MSTCN prevents information leakage throughout the network. The efficiency of MSTCN is evaluated using UCI and WISDM datasets. The empirical results demonstrate the superiority of MSTCN over other state-of-the-art solutions by achieving ~97% and ~96% accuracy scores, respectively, in UCI and WISDM.

Data availability

All data underlying the results are available as part of the article and no additional source data are required.

Comments on this article Comments (0)

Version 2
VERSION 2 PUBLISHED 08 Dec 2021
Comment
Author details Author details
Competing interests
Grant information
Copyright
Download
 
Export To
metrics
Views Downloads
F1000Research - -
PubMed Central
Data from PMC are received and updated monthly.
- -
Citations
CITE
how to cite this article
Raja Sekaran S, Pang YH, Ling GF and Yin OS. MSTCN: A multiscale temporal convolutional network for user independent human activity recognition [version 2; peer review: 2 approved, 1 approved with reservations]. F1000Research 2022, 10:1261 (https://doi.org/10.12688/f1000research.73175.2)
NOTE: If applicable, it is important to ensure the information in square brackets after the title is included in all citations of this article.
track
receive updates on this article
Track an article to receive email alerts on any updates to this article.

Open Peer Review

Current Reviewer Status: ?
Key to Reviewer Statuses VIEW
ApprovedThe paper is scientifically sound in its current form and only minor, if any, improvements are suggested
Approved with reservations A number of small changes, sometimes more significant revisions are required to address specific details and improve the papers academic merit.
Not approvedFundamental flaws in the paper seriously undermine the findings and conclusions
Version 2
VERSION 2
PUBLISHED 18 May 2022
Revised
Views
7
Cite
Reviewer Report 06 Mar 2023
Xinghua Li, School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China 
Approved
VIEWS 7
This work proposed a multiscale temporal convolutional network for human activity recognition. The contribution and innovation are satisfactory. The experiment's result is pleased. This work is meaningful in this field. The authors attempted to polish this manuscript after the first ... Continue reading
CITE
CITE
HOW TO CITE THIS REPORT
Li X. Reviewer Report For: MSTCN: A multiscale temporal convolutional network for user independent human activity recognition [version 2; peer review: 2 approved, 1 approved with reservations]. F1000Research 2022, 10:1261 (https://doi.org/10.5256/f1000research.133563.r165304)
NOTE: it is important to ensure the information in square brackets after the title is included in all citations of this article.
Views
14
Cite
Reviewer Report 13 Jun 2022
Cheng-Yaw Low, Institute for Basic Science, Seoul, South Korea 
Approved
VIEWS 14
The manuscript has been revised accordingly. Particularly, the experimental section has been included with the experimental setup and the important ... Continue reading
CITE
CITE
HOW TO CITE THIS REPORT
Low CY. Reviewer Report For: MSTCN: A multiscale temporal convolutional network for user independent human activity recognition [version 2; peer review: 2 approved, 1 approved with reservations]. F1000Research 2022, 10:1261 (https://doi.org/10.5256/f1000research.133563.r138230)
NOTE: it is important to ensure the information in square brackets after the title is included in all citations of this article.
Version 1
VERSION 1
PUBLISHED 08 Dec 2021
Views
24
Cite
Reviewer Report 02 Feb 2022
Sultan Daud Khan, Department of Computer Science, National University of Technology, Islamabad, Pakistan 
Approved with Reservations
VIEWS 24
In this work, the authors proposed a framework for human activities recognition. The authors proposed a multi-scale temporal convolutional network that constituted multi-scale dilations block to capture multi-scale information. Overall, the paper is not well-written and organized and I have ... Continue reading
CITE
CITE
HOW TO CITE THIS REPORT
Khan SD. Reviewer Report For: MSTCN: A multiscale temporal convolutional network for user independent human activity recognition [version 2; peer review: 2 approved, 1 approved with reservations]. F1000Research 2022, 10:1261 (https://doi.org/10.5256/f1000research.76807.r102276)
NOTE: it is important to ensure the information in square brackets after the title is included in all citations of this article.
  • Author Response 09 May 2022
    Sarmela Raja Sekaran, Faculty of Information Science and Technology, Multimedia University, Ayer Keroh, 75450, Malaysia
    09 May 2022
    Author Response
    First of all, we would like to convey our heartfelt thanks to the Editors and Reviewers who have provided us with constructive comments which allowed us to improve our work.
    ... Continue reading
COMMENTS ON THIS REPORT
  • Author Response 09 May 2022
    Sarmela Raja Sekaran, Faculty of Information Science and Technology, Multimedia University, Ayer Keroh, 75450, Malaysia
    09 May 2022
    Author Response
    First of all, we would like to convey our heartfelt thanks to the Editors and Reviewers who have provided us with constructive comments which allowed us to improve our work.
    ... Continue reading
Views
39
Cite
Reviewer Report 10 Jan 2022
Cheng-Yaw Low, Institute for Basic Science, Seoul, South Korea 
Approved with Reservations
VIEWS 39
This is a poorly written manuscript, as many sections are unclear and most of the important information is missing.
  1. The Inception model is recruited as the network backbone without any justifications. To be specific, why is
... Continue reading
CITE
CITE
HOW TO CITE THIS REPORT
Low CY. Reviewer Report For: MSTCN: A multiscale temporal convolutional network for user independent human activity recognition [version 2; peer review: 2 approved, 1 approved with reservations]. F1000Research 2022, 10:1261 (https://doi.org/10.5256/f1000research.76807.r102273)
NOTE: it is important to ensure the information in square brackets after the title is included in all citations of this article.
  • Author Response 09 May 2022
    Sarmela Raja Sekaran, Faculty of Information Science and Technology, Multimedia University, Ayer Keroh, 75450, Malaysia
    09 May 2022
    Author Response
    First of all, we would like to convey our heartfelt thanks to the Editors and Reviewers who have provided us with the constructive comments which allowed us to improve our ... Continue reading
COMMENTS ON THIS REPORT
  • Author Response 09 May 2022
    Sarmela Raja Sekaran, Faculty of Information Science and Technology, Multimedia University, Ayer Keroh, 75450, Malaysia
    09 May 2022
    Author Response
    First of all, we would like to convey our heartfelt thanks to the Editors and Reviewers who have provided us with the constructive comments which allowed us to improve our ... Continue reading

Comments on this article Comments (0)

Version 2
VERSION 2 PUBLISHED 08 Dec 2021
Comment
Alongside their report, reviewers assign a status to the article:
Approved - the paper is scientifically sound in its current form and only minor, if any, improvements are suggested
Approved with reservations - A number of small changes, sometimes more significant revisions are required to address specific details and improve the papers academic merit.
Not approved - fundamental flaws in the paper seriously undermine the findings and conclusions
Sign In
If you've forgotten your password, please enter your email address below and we'll send you instructions on how to reset your password.

The email address should be the one you originally registered with F1000.

Email address not valid, please try again

You registered with F1000 via Google, so we cannot reset your password.

To sign in, please click here.

If you still need help with your Google account password, please click here.

You registered with F1000 via Facebook, so we cannot reset your password.

To sign in, please click here.

If you still need help with your Facebook account password, please click here.

Code not correct, please try again
Email us for further assistance.
Server error, please try again.