All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
I am pleased to inform you that your work has now been accepted for publication in PeerJ Computer Science.
Please be advised that you cannot add or remove authors or references post-acceptance, regardless of the reviewers' request(s).
Thank you for submitting your work to this journal. On behalf of the Editors of PeerJ Computer Science, we look forward to your continued contributions to the Journal.
With kind regards,
[# PeerJ Staff Note - this decision was reviewed and approved by Sedat Akleylek, a 'PeerJ Computer Science' Section Editor covering this Section #]
No comment
No comment
No comment
This paper can be accepted for publication.
All concerns raised by the reviewers have been addressed satisfactorily; however, the paper still needs some work on the introduction, methodology, and results sections as well as further proofreading by a native English speaker. These issues require a minor revision. If you are prepared to undertake the work required, I would be pleased to reconsider my decision. Please submit a list of changes or a rebuttal against each point that is being raised when you submit your revised manuscript.
[# PeerJ Staff Note: The review process has identified that the English language must be improved. PeerJ can provide language editing services if you wish - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title) #]
No
It is well designed
NO
The title is Hybrid Computing Framework Security in Dynamic
Offloading for IoT-Enabled Smart Home System.The authors needs to be address the below suggestion for improving the quality of the manuscript. The suggestion are provided below. This would helpful for improving the quality.
1.Abstract:In the Abstract and Conclusion sections, the percentage of
the improvement of the proposed method in comparison with other methods
should be expressed. Therefore, these sections should be rewritten.
2.The introduction seems too short. It is recommend to add more studies of the recent work in the introduction section to provide more information about the proposed model.
3.Discussing potential challenges and considerations for
implementing the system in real-world environments would provide
valuable insights for researchers and practitioners.
4.In the result and discussion, the analytical reasons for better results of the proposed model in comparison with other methods should be explained.
5.All the images in the article are of poor quality and the author is
advised to improve the quality of the images to make them more suitable
for publication.
6.The writing of the article should be improved. It is recommend to employ a fluent English speaker to revise the language of the article.
7.The equation variables need to be declared. It is necessary to ensure that all the variables are defined in the manuscript.
8.How the proposed model is secure and how the Digital Signatures are used in this research. Is there any specific method employed for generating the keys.
9.It is better to provide the real time case study of the proposed work.
10.Provide the security analysis of the method formally and theoretically.
11. The conclusion section must be in a manner unique contribution, limitation and future work.
Several concerns raised by the reviewers remain unanswered. The manuscript still needs further clarification regarding contributions to the body of knowledge, formal comparisons with previously reported approaches (more elaborated), and how the simulation parameters are determined. These issues require a minor revision. If you are prepared to undertake the work required, I would be pleased to reconsider my decision. Please submit a list of changes or a rebuttal against each point that is being raised when you submit your revised manuscript.
No comment
No comment
No comment
This article is about "Secure IoT enabled Smart Home System1 with Hybrid Computing Framework".The Internet of Things (IoT) has proliferated into numerous services and applications that permeate our
daily activities. Here are some comments for you.
1.I do not see anything interesting or new or brilliant enough that could advance
discovery and conversation in this specific sub-field of research. All the presented ideas seem to
be obsolete. How the proposed method is novel.
2.Enhance the proposed methods credibility by conducting a more comprehensive comparison
with state-of-the-art methods within the same research domain. This will provide a clearer
understanding of the proposed approaches strengths and weaknesses.
3.How are the simulation parameters determined?
4.Should provide the main contributions in the Introduction.
5.Some of the figures are inappropriate.So, the figures should be given with better accuracy
and described in the paper. Figures must be replaced with high resolution ones.
6.How the proposed methods overcome the challenges faced by existing methods.
7. The paper requires a serious improvement
in English grammar and spelling. The English should be improved and deep proofreading is
needed.
8.What is the motivation of the proposed method.
9.How the proposed model is secure.
10. In the conclusion section, explicitly state the limitations of the study. Acknowledge any
constraints or shortcomings in the proposed method, providing a well-rounded evaluation of its
applicability.
I have received reviews of your manuscript from scholars who are experts on the cited topic. They find the topic very interesting; however, several concerns must be addressed regarding experimental results, data privacy and confidentiality, formal specifications, simulation models, datasets, and comparisons with current approaches. These issues require a major revision. Please refer to the reviewers’ comments listed at the end of this letter, and you will see that they are advising that you revise your manuscript. If you are prepared to undertake the work required, I would be pleased to reconsider my decision. Please submit a list of changes or a rebuttal against each point that is being raised when you submit your revised manuscript.
Thank you for considering PeerJ Computer Science for the publication of your research.
With kind regards,
**PeerJ Staff Note:** Please ensure that all review, editorial, and staff comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
**Language Note:** PeerJ staff have identified that the English language needs to be improved. When you prepare your next revision, please either (i) have a colleague who is proficient in English and familiar with the subject matter review your manuscript, or (ii) contact a professional editing service to review your manuscript. PeerJ can provide language editing services - you can contact us at [email protected] for pricing (be sure to provide your manuscript number and title). – PeerJ Staff
AI and ML approaches for securing IoT big data of smart home systems and dynamic offloading in Edge to Clou Computing framework
This paper presents the Trusted IoT Big Data Analitics (TIBDA) framework which incorporates robust trust mechanisms, prioritizing data privacy and reliability for secure processing and user information confidentiality within the smart home environment. Another contribution is the enhancement of data processing efficiency through dynamic offloading. A technique optimizing computational tasks among Edge, Fog, and Cloud resources based on real-time conditions. This strategic approach significantly amplifies operational efficiency, responsiveness, storage, and resource utilization in smart home data processing.
The authors claim their research contributions as follows:
a) Our research introduces an innovative framework for secure IoT data in smart homes. This novel approach addresses data privacy and reliability by embedding trust mechanisms, ensuring secure processing and user information confidentiality.
b) We comprehensively compared four prominent Artificial Intelligence anomaly detection algorithms: Isolation Forest, Local Outlier Factor, One-Class SVM, and Elliptic Envelope.
c) In this study, we have utilized Machine Learning classification algorithms such as Random Forest (RF), k-nearest Neighbors (KNN), Support Vector Machines (SVM), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA) for detecting malicious and non-malicious activities.
d) Our framework introduces dynamic offloading, a pioneering optimization technique that dynamically distributes computational tasks among Edge, Fog, and Cloud resources based on real-time conditions. This innovative feature ensures operational efficiency, responsiveness, and resource utilization, contributing significantly to the framework’s smart home data processing prowess.
Review
This paper presents an informal specification, using natural language, of the TIBDA framework; this kind of specification is based on the narrative, using natural language, of the operation of the framework shown in figure 2.
The informal specification tries to be formalized through the equations from 1 to 20, and by the presentation of the algorithms 1, 2, and 3.
Finally the specification is verified by means of a simulation model which includes the following simulations: anomalies detection (using the Isolation Forest, Local Outlier Factor, One-Class SVM, and Elliptic Envelope algorithms); Malicious and non-malicious detection (using random forest algorithm); Performance comparison of malicious and non-malicious classification (using the Random Forest, k-Nearest Neighbors, Support Vector Machines, Linear Discriminant Analysis, and Quadratic Discriminant Analysis algorithms); and using Artificial Neural Networks (ANN) for Offloading Decisions-Making.
However both the informal and formal specifications have serious inconsistencies that do not allow the verification of the simulation model.
1. With regard to data privacy and user information confidentiality
Examples of the informal specification are as follows: The authors propose to use the following:
a) Line 466. “We integrated robust encryption algorithms”. The paper should describe which encryption algorithms were proposed at each level, i.e., sensors, edge, fog, and cloud. As well as to report encryption and decryption times.
b) Line 469. “We also utilize secure communication protocols, such as HTTPS”. The paper should describe at what level this protocol was used. It must be noted that the sensors are constrained devices in terms of CPU processing, speed, memory and energy consumption and therefore the sensors do no support the execution of this protocol.
c) Line 472. “Fine-Grained Access Controls and Authorization”. The paper should describe at what level of the TIBDA architecture it was implemented.
d) Line 475. “Continuos monitoring system”. The paper should describe it.
e) Line 681. “Secure communication protocols, such as TLS/SSL, have been implemented to encrypt data during transmission between devices, fog, and the cloud”. Same remark as b)
f) Line 682. “Robust encryption has been applied to secure data during storage and processing, preventing unauthorized access”. Same remark as a)
g) Line 684. “Access control mechanisms were
monitored for data access and operations on offloaded data, ensuring that only authorized entities could
perform analytics”. The paper should describe these mechanisms.
2. With regard to the formal specification
a) The authors should explain the inclusion on the paper of the equations 1 through 11 since they are not used in the simulation models.
b) Equation 2 describing the communication process between sensors, devices, and appliances over time is a very simple way to specify the wireless communications, such Wi-Fi (lines 319, 381). It is recommended to consult specialized literature.
c) The Isolation Forest algorithm was published in 2008 by Liu et al. Nevertheless there is not reference in the paper. Also the authors should explain the presentation of this algorithm in the paper as Algorithm 1 if it was previously published.
d) The Random Forest algorithm has a long history; the authors should explain its inclusion in the article as Algorithm 2 and include the reference.
e) There are many Artificial Neural Network (ANN) algorithms for Dynamic Offloading in Edge, Fog, and Cloud. The authors should explain its inclusion in the article as Algorithm 3 and include the reference.
f) The formal specification has some inconsistencies, for example in the equation 16, where the binary offloading decision-making for a request is described as Ri but Ri does not appear in the equation 16.
g) Also, in line 433, “constraints for incoming requests are represented by R1, R2, and R3” that are not defined.
h) Finally, line 436, “The constraint for remote servers is represented by R4 in equation 16”, but R4 is not defined.
i) Nevertheless, with these inconsistencies equation 16 is included in the Algorithm 3.
j) The authors should explain what do the successive points in the equation 16 mean.
3. With regard to the simulation models
a) The authors have used a dataset of 15 columns and almost 49,000 rows, spanning a simulated period of four years (2020-2023) in a real-world smart home in Xi’an, China. The parameters include voltage metrics, energy consumption, and temporal information, such as Month, Day of the Week, Hour of the Day.
b) It must be noted that the temporal information does no include real-time constraints, such as the bounded time intervals for sampling, transmitting, processing, and storing the data from sensors to Edge, Fog, and Cloud computing.
c) Figure 4 shows the comparison of the four anomaly detection algorithms and the authors justify the accuracy of the Isolation Forest algorithm by its linear complexity (line 557). It is recommended to document the complexity of the other algorithms.
d) According to the authors, the offlanding strategies can be categorized into Edge, Fog, and Cloud offlandings (line 642). Figure 7 shows the accuracy of offlanding decision making, but the authors do not specified which strategie is plotted.
e) The same remark is for Figure 8 that shows the loss of offlanding decision-making.
f) Algorithm 3 retuns the following: Predict delay latency, predict energy consumption, and predict bandwidth with test data. However, the bandwidth is not included in the dataset. The authors should explain how can the algorithm predicted it.
Minor remarks
1. Please insert a space between the punctuation marks in lines:
a) 43: (2018),Froiz-Míguez
b) 68: ,Mahor
c) 70: ,Sánchez
d) 71:.Smart
e) 78: ,Yang
f) 283: ,Dilraj
g) 284: ),Tang et al. (2019),Chithaluru et al. (2023),Kang
h) 320: ,Buil-Gil et al. (2023),Tanwar
i) 322: (2022),Andelic
j) 369: 3),Hossain et al. (2022),Joseph et al. (2019),Hoa et al. (2023),Mu
k) 370: (2022),Bajaj
2. The next references are missing the pages numbering:
a) Balasundaram et al. (2023)
b) Chithaluru et al. (2023)
c) Hoa et al. (2023)
d) Yang, J. and Sun, L. (2022)
1. The reason for developing this approach is not clear. Why AI and ML approaches are used?
2. The name of the proposed method is "Trusted IoT Big Data Analytics (TIBDA) framework". The name shows this work is something related to security. What are the security aspects considered in the proposed model.
3. Write the motivation clearly in the Introduction section.
4. What are the limitations of the existing methods are solved by the proposed method? How they are solved?
5. Improve the writing of the paper.
6. The text in figures are not clear.
7. Analyze your model with more publicly available dataset.
8. Define all variables in the equations.
9. Flowchart of the proposed method should be given.
10. The practical applications of the research should be provided.
11. What are the limitations and future work of the current study.
12. Compare your model with related works in Section 2 to show the superiority of your model.
no comment
no comment
no comment
The paper has clear, unambiguous, and professional English used throughout. It presents a well-structured presentation of research. The document gave proper citations and references to the background and literature review. It has adequate tables and the figures are properly labeled. The hypotheses are self contained. The paper proposed a theorems but the proof was not provided.
The experiment design of the paper "AI and ML Approaches for Securing IoT Big Data of Smart Home Systems and Dynamic Offloading in Edge to Cloud Computing Framework" aligns well with the journal's scope, presenting original primary research that is both relevant and meaningful. The research question is clearly defined, addressing the critical need for advanced data security solutions in smart home systems through the Trusted IoT Big Data Analytics (TIBDA) framework. This research fills a significant knowledge gap by offering a novel approach to enhancing data security, privacy, and processing efficiency in the context of the Internet of Things (IoT). The investigation is conducted rigorously, adhering to high technical and ethical standards. Methods are detailed comprehensively, providing sufficient information for replication, which is evident in the thorough explanation of the TIBDA framework, the dynamic offloading technique, and the use of advanced tools and machine-learning libraries for implementing algorithms. The paper's methodology section outlines the proposed approach, problem formulation, and algorithms with clarity, facilitating an understanding of how the research was conducted and how the results were obtained. Overall, the experiment design is robust, and well-structured, and might contribute significantly to the field of IoT and smart home security.
The validity of the findings in the paper "AI and ML Approaches for Securing IoT Big Data of Smart Home Systems and Dynamic Offloading in Edge to Cloud Computing Framework" is well-supported, with the authors providing comprehensive data and analyses that reinforce their conclusions. Although the impact and novelty of the research are not explicitly assessed within the reviewed excerpts, the findings contribute meaningfully to the literature by addressing significant gaps in data security and efficiency in IoT systems.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.