EXPRESSION OF CONCERN FOR: H. A. Hussain, M. A. Subhi, A. S. Al Tmeme, A. D. Radhi, and M. A. Albahar, ``Improving Road Safety Through Multimodal Deep Learning for Driver Drowsiness Detection,'' Iraqi Journal for Computer Science and Mathematics, vol. 6, no. 4, Article 12, 2025. DOI: https://doi.org/10.52866/2788-7421.1330. Available at: https://ijcsm.researchcommons.org/ijcsm/vol6/iss4/12. Reason for Expression of Concern: The Editors wish to alert readers to potential concerns regarding the reliability of the findings reported in “Improving Road Safety Through Multimodal Deep Learning for Driver Drowsiness Detection (Manuscript 1330)”. The journal has initiated an additional editorial assessment of the article’s methodology, data provenance, and reported outcomes to confirm their reliability and reproducibility. This notice is issued to ensure transparency while the review is ongoing. The Expression of Concern does not constitute a final determination regarding the validity of the work. The journal will update readers once the assessment is completed and will take any necessary editorial action in accordance with the journal’s policies and COPE guidance. Available online Editor's Note: The Expression of Concern (DOI: https://doi.org/10.52866/2788-7421.1384) regarding the Original Article (DOI: https://doi.org/10.52866/2788-7421.1330) has been resolved. The publication timeline is as follows: Original Article → Expression of Concern → Resolution.
EXPRESSION OF CONCERN FOR: M. H. Al-Adhaileh, M. I. Ahmed Al-mashhadani, E. M. Alzahrani, and T. H. H. Aldhyani, ``Improving Heart Attack Prediction Accuracy Performance Using Machine Learning and Deep Learning Algorithms,'' Iraqi Journal for Computer Science and Mathematics, vol. 6, no. 2, 2025, Article~3. DOI:~https://doi.org/10.52866/2788-7421.1239. Available at: https://ijcsm.researchcommons.org/ijcsm/vol6/iss2/3. Reason for Expression of Concern: The Editors wish to alert readers to potential concerns regarding the reliability of the findings reported in “Improving Heart Attack Prediction Accuracy Performance Using Machine Learning and Deep Learning Algorithms (Manuscript 1239)”. The journal has initiated an additional editorial assessment of the article’s methodology, data provenance, and reported outcomes to confirm their reliability and reproducibility. This notice is issued to ensure transparency while the review is ongoing. The Expression of Concern does not constitute a final determination regarding the validity of the work. The journal will update readers once the assessment is completed and will take any necessary editorial action in accordance with the journal’s policies and COPE guidance.
NOTICE OF CORRIGENDUM FOR: Almulla, Hussein K.; Mohammed, Hussam J.; Al-Waisy, Alaa S.; Al-Fahdawi, Shumoos; Had, Ahmed Adnan; and AL-Attar, Bourair (2025) ``MotionFusion: A Robust Ensemble Learning Framework for Accurate Sensor-Based Human Activity Recognition,'' Iraqi Journal for Computer Science and Mathematics: Vol. 6: Iss. 3, Article 14. DOI: https://doi.org/10.52866/2788-7421.1289. Available at: https://ijcsm.researchcommons.org/ijcsm/vol6/iss3/14. Reason for Corrigendum: In the published version of the above article, a number of typographical and formatting errors were identified. These corrections do not affect the study design, results, or conclusions, and are provided below to ensure accuracy and consistency. 1) Feature subset sizes (text–table inconsistency) Error: The manuscript contains inconsistent feature subset sizes. While the feature-selection setup defines subsets as 420 / 280 / 140 (≈ 75% / 50% / 25% of 561), another sentence incorrectly reports 300 and 100 for 50% and 25%. Correction: The correct subset sizes are: 75%: 420 features 50%: 280 features 25%: 140 features Accordingly, the sentence reporting ``50% (300)'' and ``25% (100)'' should be corrected to ``50% (280)'' and ``25% (140)''. 2) Table 2 formatting merge error (Class weight row) Error: Table 2 contains a layout/line-break merge where page/footer text appears inside a cell (e.g., ``Balanced220 ...''). Correction: Table 2 should display the SVC class weight as ``Balanced'' only, and the footer/page text must be removed from the table content. 3) Incorrect unit/format for F1-score Error: The paper states: ``highest F1-score value of 0.81% ...'', which is a unit-formatting error. Correction: The correct representation is F1-score = 0.81 (or equivalently 81% if the journal uses percent formatting). The ``%'' symbol after 0.81 must be removed (or the value reformatted consistently as 81%). 4) Reference typography issue (invalid symbol) Error: In Reference [1], the title includes an unintended symbol (e.g., ``human° activity''). Correction: The reference title should be corrected to ``human activity recognition dataset ...'' (removing the unintended symbol). 5) Minor table label typo Error: A table label uses ``Matric''. Correction: Replace ``Matric'' with ``Metric'' and standardize ``Features'' capitalization for consistency. The authors apologize for these errors and any inconvenience caused.
The proliferation of unmanned aerial vehicles (UAVs) has necessitated the development of sophisticated object detection algorithms capable of handling the unique challenges posed by aerial imagery. Traditional detection methods often struggle with small object sizes, dense distributions, and complex backgrounds characteristic of UAV-captured scenes. This research presents EYOLOv8-MSAFF (Enhanced YOLOv8 with Multi-Scale Attention and Feature Fusion), a novel deep learning architecture specifically engineered for superior performance in UAV-based object detection tasks. The proposed methodology integrates four innovative components: a Hybrid Spatial-Channel Attention Mechanism (HSCAM) that processes attention information in parallel rather than sequentially, an Adaptive Multi-Scale Feature Fusion Module (AMSFFM) that dynamically weights multi-scale features based on contextual relevance, a Dilated Convolutional Block Attention Module (DCBAM) that captures multi-scale contextual information through varying dilation rates, and a Progressive Feature Refinement Network (PFRN) that iteratively enhances feature representations through multiple refinement stages. Extensive experimental validation conducted on two challenging datasets demonstrates the exceptional performance of the proposed approach. On the VisDrone2019 dataset, EYOLOv8-MSAFF achieves 87.3% mAP@0.5 and 64.2% mAP@0.5:0.95, representing substantial improvements of 6.1% and 7.1% respectively over the baseline YOLOv8l architecture. The method exhibits particularly remarkable performance in small object detection, achieving 52.7% AP_S, which constitutes an 18.2% improvement over the baseline. Similarly, on the DOTA v2.0 dataset, the proposed method attains 85.7% mAP@0.5 and 58.9% mAP@0.5:0.95, surpassing existing state-of-the-art approaches by significant margins. Comprehensive ablation studies validate the effectiveness of each proposed component, while computational analysis demonstrates that the method maintains practical inference speeds of 33.4 FPS despite the incorporation of sophisticated attention mechanisms.
Editor's Note: This Resolution notice concludes the investigation initiated by the Expression of Concern (DOI: https://doi.org/10.52866/2788-7421.1385) regarding the Original Article (DOI: https://doi.org/10.52866/2788-7421.1275). The publication timeline is as follows: Original Article → Expression of Concern → Resolution. Resolution of Expression of Concern: The editorial team of the Iraqi Journal for Computer Science and Mathematics has completed a thorough post-publication review of the above-mentioned article, the supporting data, and the authors’ responses to the queries raised. Upon careful assessment, we have determined that the concerns have been addressed and clarified to the satisfaction of the editors. We have found no evidence of misconduct or invalidity in the research. The gindings presented in the original article are considered robust and accurate. This notice formally resolves the previously published Expression of Concern. The original article stands as published, and we affirm the integrity of the research.
