The DOI matches its Crossref record; 143 of the 143 references it cites were found in a registry or an index; 48 of the 184 sources its claims cite were checked for support.
A Systematic Review of Data Quality in CPS and IoT for Industry 4.0
Open accessAbstract
The Internet of Things (IoT) and Cyber-Physical Systems (CPS) are the backbones of Industry 4.0, where data quality is crucial for decision support. Data quality in these systems can deteriorate due to sensor failures or uncertain operating environments. Our objective is to summarize and assess the research efforts that address data quality in data-centric CPS/IoT industrial applications. We systematically review the state-of-the-art data quality techniques for CPS and IoT in Industry 4.0 through a systematic literature review (SLR) study. We pose three research questions, define selection and exclusion criteria for primary studies, and extract and synthesize data from these studies to answer our research questions. Our most significant results are (i) the list of data quality issues, their sources, and application domains, (ii) the best practices and metrics for managing data quality, (iii) the software engineering solutions employed to manage data quality, and (iv) the state of the data quality techniques (data repair, cleaning, and monitoring) in the application domains. The results of our SLR can help researchers obtain an overview of existing data quality issues, techniques, metrics, and best practices. We suggest research directions that require attention from the research community for follow-up work.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
31 Valid · 16 Not valid · 34 Not checked · 134 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“For instance, Zhang et al. [156] and Liu et al. [110] study the literature on data quality based on quality issues, dimensions, and measures but exclude the data quality techniques (e.g., data repair) and their solution domain (i.e., the abstract environment where the data quality technique is developed).”
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > 1 INTRODUCTION
What the sources say
- Disputedcites [156] sourceExperimental — accuracy not yet measured
The paper does review data-quality issues, dimensions, and metrics (Section 4). But its Abstract says it surveys data-quality frameworks and methodologies to help choose management techniques, and Section 3 reviews those techniques and screens frameworks by their applicability to the IoT domain. That contradicts the claim that Zhang et al. exclude techniques and their solution domain; this verdict does not assess Liu et al. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
- Not checked — no full text of the sourcecites [110] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Two techniques [9,18] employ the principal component analysis [53] to filter out irrelevant attributes.”
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > Noise Sample Reduction
What the sources say
- Disputedcites [9] sourceExperimental — accuracy not yet measured
Our copy shows this paper does not employ PCA to filter out irrelevant attributes: Section 4.2.4 states 'we recommend using two methods of filter approach based on the absolute correlation... Chi-squared and Information Gain were the methods used', and the concluding bullet says 'the filter methods were used in DC-RM (due their fast and low computational cost)'. PCA appears only twice: as an example of the 'Projection' approach in a taxonomy of four dimensionality-reduction approaches (Section 3.3, citing Blum & Langley), and in Section 4.2.2 where the first two principal components were plotted merely to verify LOF-detected outliers. Thus the attribution that this technique uses PCA to remove irrelevant attributes is contrary to what the paper reports. (LLM, conf=0.75)
Checked by a reasoning model — may be wrong.
- Not checked — no full text of the sourcecites [18] source
- Not checked — no full text of the sourcecites [53] source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Four of these papers [7,11,19,31] investigate how data security solutions can improve data quality (in particular, data accuracy).”
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > 4.1.3 RQ1.3: What is the Tradeoff between Data Quality and Data Security?
What the sources say
- Not matchedcites [7]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites [11] source
The Security Analysis section explains that the proposed data-trust module assigns low trust to tampered sensor observations when other observations do not support them. Section 5.1 evaluates its ability to distinguish honest observations from malicious ones that deviate from the true target path. This supports citing the paper as an investigation of how a security-oriented trust mechanism can protect data accuracy; the count of four refers to the citing document’s group of papers, not to this source alone. (LLM, conf=0.88)
- Not matchedcites [19]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites [31] source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, we revealed only two studies [12,27] applying ML to data repair.”
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > Sensory Substitution -Fog based Analytics
What the sources say
- Not matchedcites [12]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites [27] source
The Introduction says the study applies models to correct sensor-output errors, and §5.6 describes using an artificial neural network to calibrate sensor data. This supports citing the paper as one study applying machine learning to data repair; the count of two is the citing authors’ own finding. (LLM, conf=0.91)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“They provide only offline repair.”
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > 4.2.2 RQ2.2: What Are the Data Repair Techniques?
What the sources say
- Could not verifycites [44] sourceExperimental — accuracy not yet measured
Our copy of 10.1145/3145623 contains only the institutional-repository metadata record (title/author listing, Abstract-section blocks holding BIBTEX/RIS citation exports, Scopus links and PlumX metrics such as '352 Downloads (Pure)' and 'Citation Indexes: 43'); no body text of the article is present. Searches for 'offline repair', 'data repair / missing value recovery', 'online real-time imputation versus offline batch', and 'framework architecture anomaly detection smart grid' returned nothing but these bibliographic passages, so nothing addresses whether the authors' framework provides only offline repair. Absence here is not contrary evidence, hence unverifiable rather than disputed. (LLM, conf=0.75)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
126 more claims · 25 with their cited sources checked
Create a free account to see all 215 claims and to verify the 2 references still open.
- It may state two separate claims as one. 43
- Probably not a substantial claim. 53
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Noise , which is another topmost issue affecting sensor data [6,7].”
From Case-Based Data Quality Management for IoT Logs: A Case Study Focusing on Detection of Data Quality Issues (2025) · cites this paper as [7]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Missing Data , which are widely regarded as the most prevalent issue in sensor data-excluding outliers, which are frequent but represent intrinsically valid observations [6,7].”
From Case-Based Data Quality Management for IoT Logs: A Case Study Focusing on Detection of Data Quality Issues (2025) · cites this paper as [7]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“which is known to suffer from many Data Quality Issues (DQIs), such as missing data due to faulty sensors or noise due to difficult environmental conditions [5-7].”
From Case-Based Data Quality Management for IoT Logs: A Case Study Focusing on Detection of Data Quality Issues (2025) · cites this paper as [7]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > 4.3.2 RQ3.2: What Data Storage Solutions Are Used to Manage Data Quality?
“Three papers [1,7,11] employ the blockchain to ensure data security, such as the trustworthiness of sensor observations, while the blockchain is also a storage medium.”
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > 4.3.2 RQ3.2: What Data Storage Solutions Are Used to Manage Data Quality?
“There is an explicit dependency between the data storage solution and the data quality support (i.e., ensuring data security) in these two works.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > 1 INTRODUCTION
“Number of primary studies 14 NA 57 45 NA 60 57”
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > 2.4 Data Synthesis and Extraction Method
“We included 51 primary studies in our study.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > IoT Architecture Perception Network Application L1
“Nine primary studies [4,8,10,16,23,24,31,40,49] cover edge-Cloud orchestration for data processing (not necessarily data quality management).”
§ A Systematic Review of Data Quality in CPS and IoT for Industry 4.0 > IoT Architecture Perception Network Application L1
“Villalobos et al. [42] Wang et al. [44] Hui et al. [14] Mohammed et al. [26] Ahmed et al. [1] Tham et al. [41] Kufner et al. [21] Casado-vara et al. [7] Dedeoglu et al. [11] Guo et al. [13] Buschjager et al. [5] Yu et al. [49] Liu et al. [24] Cerquitelli et al. [8] Bamgboye et al. [4] Lin et al. [23] Syafrudin et al. [40] Jeong et al. [16] Cui et al. [10] Sanyal et al. [33] Total ( ): 20”
Citations
Cites
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
The WEKA data mining software: an update
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1656274.1656278 · Cited by 17,750
Learning the parts of objects by non-negative matrix factorization
Lee, D. D., & Seung, H. S. (1999) · Nature · doi:10.1038/44565 · Cited by 13,868
TensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
Abdi, H., & Williams, L. J. (2010) · WIREs Computational Statistics · doi:10.1002/wics.101 · Cited by 11,104
LOF: identifying density-based local outliers
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000) · ACM SIGMOD Record · doi:10.1145/335191.335388 · Cited by 5,207
Internet of Things in industries: A survey
Xu, L. D., He, W., & Li, S. (2014) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2014.2300753 · Cited by 5,172 · cited 1×
“…issues [57, 61, 73, 78, 107, 123, 137], IoT applications in blockchain systems [105], applications of blockchain technologies to IoT [158], IoT big data [63], data analytics for IoT [141], IoT-based smart cities [60], IoT for agriculture [80], IoT for healthcare [101], and IoT in industries [76].”
BackgroundBeyond Accuracy: What Data Quality Means to Data Consumers
Wang, R. Y., & Strong, D. M. (1996) · Journal of Management Information Systems · doi:10.1080/07421222.1996.11518099 · Cited by 4,672
Wohlin, C. (2014) · Proceedings of the 18th International Conference on Evaluation and Assessment in Software Engineering · doi:10.1145/2601248.2601268 · Cited by 4,234
Industry 4.0: state of the art and future trends
Xu, L. D., Xu, E. L., & Li, L. (2018) · International Journal of Production Research · doi:10.1080/00207543.2018.1444806 · Cited by 3,221
Research works printed but not linked: 12
- Daniel Kuemper, Thorben Iggena, Ralf Toenjes, and Elke Pulvermueller. 2018. Valid.IoT: A framework for sensor data quality analysis and interpolation. In MMSys’18. 294–303.
- Fei Li, Stefan Nastic, and Schahram Dustdar. 2012. Data quality observation in pervasive environments. In ICCSE’12. 602–609.
- Wei-Tsung Lin, Fatih Bakir, Chandra Krintz, Rich Wolski, and Markus Mock. 2019. Data repair for distributed, event-based IoT applications. In DEBS’19. 139–150.
- Leon Wu and Gail Kaiser. 2012. An autonomic reliability improvement system for cyber-physical systems. In HASE’12. 56–61.
- Wenjin Yu, Tharam Dillon, Fahed Mostafa, Wenny Rahayu, and Yuehua Liu. 2019. Implementation of industrial cyber physical system: Challenges and solutions. In ICPS’19. 173–178.
- Jeremy J. Carroll, Ian Dickinson, Chris Dollin, Dave Reynolds, Andy Seaborne, and Kevin Wilkinson. 2004. Jena: Implementing the semantic web recommendations. In WWW’04. 74–83.
- Martin Ester, Hans-Peter Kriegel, Jörg Sander, and Xiaowei Xu. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. In KDD’96, 226–231.
- Antonio Gulli and Sujit Pal. 2017. Deep Learning with Keras. Packt Publishing Ltd.
- DNV International. 2017. Data Quality Assessment Framework: DNV Recommended Practice-RP-0497. DNV.
- Barbara Ann Kitchenham and Stuart Charters. 2007. Guidelines for Performing Systematic Literature Reviews in Software Engineering. Technical Report EBSE 2007-001. https://www.elsevier.com/__data/promis_misc/525444systematicreviewsguide.pdf.
- Supavit Muangjaroen and Thaweesak Yingthawornsuk. 2012. A study of noise reduction in speech signal using fir filtering. In International Conference on Advances in Electrical and Electronics Engineering.
- Bruce Jay Nelson. 1981. Remote Procedure Call. Carnegie Mellon University.
Cited by
Ncube, M. M., & Ngulube, P. (2024) · Discover Sustainability · doi:10.1007/s43621-024-00510-0 · Cited by 98
“While studies like Goknil et al. [48] underscore the significance of robust data quality in domains such as Cyber-Physical Systems (CPS) and the Internet of Things (IoT), Bendre and Thool [37] emphasise the broader challenges inherent in big data environments.”
InfluentialBena, Y. A., Ibrahim, R. B., Mahmood, J., Al-Dhaqm, A., Alshammari, A., Nasser, M., Yusuf, M. N., & Ayemowa, M. O. (2025) · IEEE Access · doi:10.1109/access.2025.3528941 · Cited by 44
“This challenge arises due to the heterogeneity of data sources [6], generated by intelligent systems, which usually resulted in data errors, incompleteness, and inconsistency [33].”
InfluentialData Quality Assessment in Smart Manufacturing: A Review
Peixoto, T., Oliveira, B., Oliveira, Ó., & Ribeiro, F. (2025) · Systems · doi:10.3390/systems13040243 · Cited by 39
Odor-Based Molecular Communications: State-of-the-Art, Vision, Challenges, and Frontier Directions
Aktas, D., Ortlek, B. E., Civas, M., Baradari, E., Kilic, A. B., Bilgen, F. E., Okcu, A. S., Whitfield, M., Cetinkaya, O., & Akan, Ö. B. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3487472 · Cited by 37
“For instance, integrating Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Random Forest has been effective in monitoring sensor signals in an IoT-based automotive manufacturing system [210].”
Industrial data space application framework for semiconductor wafer manufacturing system scheduling
Chen, D., Zhang, J., Wu, L., Zhang, P., & Wang, M. (2024) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2024.09.013 · Cited by 13
Metadata
- Authors
- Goknil, A., Nguyen, P., Sen, S., Politaki, D., Niavis, H., Pedersen, K. J., Suyuthi, A., Anand, A., & Ziegenbein, A.
- Affiliations
- SINTEF, Norway
- SINTEF (NO)
- Inlecom Innovation, Greece
- DNV (Norway) (NO)
- Technische Universität Darmstadt (DE)
- ORCID
- Venue
- ACM Computing Surveys
- Published
- 2023-07-17
- Volume
- 55
- Issue
- 14s
- Pages
- 1-38
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4366407898
- Cited by
- 84
- References
- 114
- Citations by year
- 2026: 34 · 2025: 31 · 2024: 17 · 2023: 2
- FWCI
- 3.05
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM Computing Surveys (publishedVersion)
- NORA - Norwegian Open Research Archives (submittedVersion, other-oa)
- Funders
- European Union’s Horizon 2020 Research and Innovation programme (958357 (InterQ), and 958363 (DAT4.Zero))
- Topics
- Physical Sciences › Computer Science › Information Systems › Data Quality and Management
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Digital Transformation in Industry
- Physical Sciences › Computer Science › Information Systems › Technology and Data Analysis
- Keywords
- data quality, cyber-physical systems, Internet of Things, Industry 4.0, sensor faults, data repair, data cleaning, data quality monitoring, data quality metrics, data quality management, industrial applications
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A Systematic Review of Data Quality in CPS and IoT for Industry 4.0. https://app.cochat.ai/papers/10.1145/3593043
- The paper
- Goknil, A., Nguyen, P., Sen, S., Politaki, D., Niavis, H., Pedersen, K. J., Suyuthi, A., Anand, A., & Ziegenbein, A. (2023). A Systematic Review of Data Quality in CPS and IoT for Industry 4.0. ACM Computing Surveys. https://doi.org/10.1145/3593043
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.