This article contains several tortured phrases that make some passages hard to parse. These typically result from an attempt to avoid plagiarism detection using a paraphrasing software. So far, the following have been spotted:
Tortured Phrases (found) | Established Phrases (expected) |
---|---|
Parkinson's infection | Parkinson's disease |
Parkinson's sickness | Parkinson's disease |
back proliferation AND neural | back propagation |
calculated relapse | logistic regression |
counterfeit neural | artificial neural (network) |
crude information | raw data |
disarray network | confusion matrix |
discourse acknowledgement OR discourse acknowledgment | voice recognition |
fake neural | artificial neural (network) |
head part examination | principal component analysis (PCA) |
head part investigation | principal component analysis (PCA) |
inclination plummet | gradient descent |
mechanized tomography | computed tomography (CT) |
random timberland | random forest |
relapse tree | regression tree |
yield layer AND neural | output layer |
A paragraph in particular in the introduction stands out as containing many different tortured phrases, making it quite difficult to read:
Can the authors explain why they used these unusual phrases?
The article also contains a full repetition of two paragraphs:
Flagged by the Problematic Paper Screener.
Additionally, some of the references in the paper appear to be made up by combining the bibliographic data of two different papers and paraphrasing the title.
For example,
in "L. Berus, S. Klancnik, M. Brezocnik, M. Ficko, Novel discourse signal preparing calculations for high accuracy grouping of Parkinson’s illness. Biomed. Design. IEEE Trans. 59(5), 1264–1271 (2018)",
the title and publication venue actually refer to "Novel Speech Signal Processing Algorithms for High-Accuracy Classification of Parkinson's Disease" by Athanasios Tsanas et al., published in IEEE Transactions on Biomedical Engineering (Volume: 59, Issue: 5, May 2012) (https://doi.org/10.1109/TBME.2012.2183367)
the names of the authors and the publication year, on the other hand, are from "Classifying Parkinson’s Disease Based on Acoustic Measures Using Artificial Neural Networks" by Lucijano Berus, Simon Klancnik, Miran Brezocnik and Mirko Ficko (2018) (https://doi.org/10.3390/s19010016)
in "H. Gunduz (2019). Determination of Parkinson's illness utilizing head part examination and boosting advisory group machines." (no journal/conference given)
the title likely refers to "Diagnosis of Parkinson’s Disease using Principal Component Analysis and Boosting Committee Machines" by Indira Rustempasic and Mehmet Can (http://dx.doi.org/10.21533/scjournal.v2i1.52)
and the name of the author and the year likely refer to "Deep learning-based Parkinson’s disease classification using vocal feature sets" by H. Gunduz (2019) (https://doi.org/10.1109/ACCESS.2019.2936564)
"S. Akshay, K. Vincent (2019). Component determination in Parkinson's illness: A harsh sets approach, In: Software engineering and Information Technology, 2009. IMCSIT'09. Global Multiconference on (pp. 425–428). IEEE."
the title and publication venue refer to "Feature selection in Parkinson's disease: A rough sets approach" by Kenneth Revett et al. , 2009(https://doi.org/10.1109/IMCSIT.2009.5352688)
the names of the authors and the publication year refer to "Identification of Parkinson disease patients classification using feed forward technique based on speech signals", by S Akshay, K Vincent - Int. J. Eng. Adv. Technol, 2019
There are likely more - these are the only three I checked.
Can the authors explain what happened here?
And how come the conference editors and reviewers did not notice these issues?
(Found while investigating another paper, which copied these references.)
Attach files by dragging & dropping, selecting them, or pasting from the clipboard. Uploading your files… We don’t support that file type. with a PNG, GIF, or JPG. Yowza, that’s a big file. with a file smaller than 1MB. This file is empty. with a file that’s not empty. Something went really wrong, and we can’t process that file.
Comment must be at least 15 characters.