Retraction Watch

Tracking retractions as a window into the scientific process

Archive for the ‘Neural Comput Applications’ Category

Author surprised when publisher pulls three of her papers

with 13 comments

A researcher is strongly objecting to a publisher’s decision to retract three of her papers from two computing journals without informing her first.

The reason: Self-plagiarism, which the author said stemmed from her PhD student using similar descriptions for the background sections of the papers. She argued that if the reviewers had flagged the duplication, she would have been happy to revise the papers before publication. A representative of the publisher, Springer, told us the overlap was extensive enough for the journal to determine the papers should be retracted.

We spoke with Sameem Abdul Kareem from the Department Of Artificial Intelligence at the University of Malaya in Malaysia, last author on all three papers, which she co-authored with her former PhD student Haitham Badi (also referred to as Haitham Hasan in several papers). She explained how the duplication occurred:

Read the rest of this entry »

Plagiarism detected in two papers on improving detection of cancer by mammograms

without comments

8 (1)

A group of computer scientists has a pair of retractions for duplicating “substantial parts” of other articles written by different authors. Both papers, published in Neural Computing and Applications, are on ways to screen for breast cancer more effectively.

According to the abstract of  “An improved data mining technique for classification and detection of breast cancer from mammograms,” computers make the process of identifying cancer in lesions detected by mammograms faster and more accurate:

Although general rules for the differentiation between benign and malignant breast lesion exist, only 15–30% of masses referred for surgical biopsy are actually malignant. Physician experience of detecting breast cancer can be assisted by using some computerized feature extraction and classification algorithms. Computer-aided classification system was used to help in diagnosing abnormalities faster than traditional screening program without the drawback attribute to human factors.

The article has been cited four times, according to Thomson Scientific’s Web of Knowledge.  The retraction note reveals where “substantial parts” of the article came from:

Read the rest of this entry »