Ghulam Mujtaba^1,2,#, Wenbiao Liu^1,#, Mohammed Alshehri³, Yahya AlQahtani⁴, Nouf Abdullah Almujally⁵, Hui Liu^1,6,7,*

CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-19, 2026, DOI:10.32604/cmc.2025.067895 - 10 November 2025

Abstract As urban landscapes evolve and vehicular volumes soar, traditional traffic monitoring systems struggle to scale, often failing under the complexities of dense, dynamic, and occluded environments. This paper introduces a novel, unified deep learning framework for vehicle detection, tracking, counting, and classification in aerial imagery designed explicitly for modern smart city infrastructure demands. Our approach begins with adaptive histogram equalization to optimize aerial image clarity, followed by a cutting-edge scene parsing technique using Mask2Former, enabling robust segmentation even in visually congested settings. Vehicle detection leverages the latest YOLOv11 architecture, delivering superior accuracy in aerial contexts… More >

Ye Tao^*, Ilyana Jalaluddin, Zalina Mohd Kasim

Journal of Psychology in Africa, Vol.35, No.5, pp. 671-679, 2025, DOI:10.32604/jpa.2025.066530 - 24 October 2025

Abstract This study investigated the role of self-efficacy and motivation in the relationship between perfectionism and writing performance. Participants were 500 Chinese EFL (English as a Foreign Language) undergraduates (females = 34%, Mage = 21.56 years, SD = 2.27). The students completed the Self-Reported Writing Proficiency Scale, the Frost Multidimensional Perfectionism Scale for Chinese, the Second Language Writer Self-Efficacy Scale, and the English Writing Motivation Questionnaire. Results from Structural Equation Modeling (SEM, Amos 29.0) revealed that perfectionism predicted writing performance positively for students with positive (adaptive) perfectionism, but negatively for those with negative (maladaptive) perfectionism. Self-efficacy and More >

Naif Al Mudawi^1,*, Muhammad Hanzla², Abdulwahab Alazeb¹, Mohammed Alshehri¹, Haifa F. Alhasson³, Dina Abdulaziz AlHammadi⁴, Ahmad Jalal^2,5

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 4491-4509, 2025, DOI:10.32604/cmc.2025.065490 - 30 July 2025

Abstract Unmanned Aerial Vehicles (UAVs) are increasingly employed in traffic surveillance, urban planning, and infrastructure monitoring due to their cost-effectiveness, flexibility, and high-resolution imaging. However, vehicle detection and classification in aerial imagery remain challenging due to scale variations from fluctuating UAV altitudes, frequent occlusions in dense traffic, and environmental noise, such as shadows and lighting inconsistencies. Traditional methods, including sliding-window searches and shallow learning techniques, struggle with computational inefficiency and robustness under dynamic conditions. To address these limitations, this study proposes a six-stage hierarchical framework integrating radiometric calibration, deep learning, and classical feature engineering. The workflow… More >

Ruijun Song^*, Xichen Qin, Xiaomei Yang, Mei Wu, Jinyu Hong, Youping Cao, Yuting Ning

Journal of Psychology in Africa, Vol.35, No.2, pp. 265-270, 2025, DOI:10.32604/jpa.2025.065778 - 30 June 2025

Abstract The current study conducted the psychological capital profiles and the relation between profile memberships and learning burnout among undergraduates. Participants were 541 Chinese undergraduates ranging from 18 to 21 years old (48.2% male; Mean years = 19.54, SD = 1.09 years). Latent profile analysis revealed three categories of psychological capital profile consistent high psychological capital profile (50.5%), consistent low psychological capital profile (38.1%), and dominate loss-orientated psychological capital profile (11.4%). The undergraduates in consistent high profile reported high self-efficacy, resilience, hope, and optimism. Consistent low profile characterized by a little low (~0.50 SD below the M) self-efficacy, resilience, More >

Xinyi Song¹, Haixiang Zhang^1,*, Shaohua Li²

CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 2735-2750, 2025, DOI:10.32604/cmc.2025.059006 - 16 April 2025

Abstract In recent years, Transformer has achieved remarkable results in the field of computer vision, with its built-in attention layers effectively modeling global dependencies in images by transforming image features into token forms. However, Transformers often face high computational costs when processing large-scale image data, which limits their feasibility in real-time applications. To address this issue, we propose Token Masked Pose Transformers (TMPose), constructing an efficient Transformer network for pose estimation. This network applies semantic-level masking to tokens and employs three different masking strategies to optimize model performance, aiming to reduce computational complexity. Experimental results show More >

Chunjuan Bo^1,*, Xin Chen², Junxing Zhang¹

CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 1105-1122, 2024, DOI:10.32604/cmc.2024.052329 - 18 July 2024

Abstract Significant advancements have been witnessed in visual tracking applications leveraging ViT in recent years, mainly due to the formidable modeling capabilities of Vision Transformer (ViT). However, the strong performance of such trackers heavily relies on ViT models pretrained for long periods, limiting more flexible model designs for tracking tasks. To address this issue, we propose an efficient unsupervised ViT pretraining method for the tracking task based on masked autoencoders, called TrackMAE. During pretraining, we employ two shared-parameter ViTs, serving as the appearance encoder and motion encoder, respectively. The appearance encoder encodes randomly masked image data,… More >

Chili Li¹, Xinxin Zhao², Ziwen Pan³, Ting Yi⁴, Long Qian^5,6,*

International Journal of Mental Health Promotion, Vol.26, No.2, pp. 161-175, 2024, DOI:10.32604/ijmhp.2023.029896 - 08 March 2024

Abstract While a plethora of studies has been conducted to explore demotivation and its impact on mental health in second language (L2) education, scanty research focuses on demotivation in L2 speaking learning. Particularly, little research explores the measures to quantify L2 speaking demotivation. The present two-phase study attempts to develop and validate an English Speaking Demotivation Scale (ESDS). To this end, an independent sample of 207 Chinese tertiary learners of English as a Foreign Language (EFL) participated in the development phase, and another group of 188 Chinese EFL learners was recruited for the validation of the… More >

Ali Derakhshan¹, Yongliang Wang^2,*, Yongxiang Wang^2,*, José Luis Ortega-Martín³

International Journal of Mental Health Promotion, Vol.25, No.7, pp. 823-832, 2023, DOI:10.32604/ijmhp.2023.029877 - 01 June 2023

Abstract The adequacy of language education largely depends on the favorable and unfavorable emotions that teachers and students experience throughout the education process. Simply said, emotional factors play a key role in improving the quality of language teaching and learning. Furthermore, these emotional factors also promote the well-being of language teachers and learners and place them in a suitable mental condition. In view of the favorable impact of emotional factors on the mental health of language teachers and learners, many educational scholars around the world have studied these factors, their background, and their pedagogical consequences. Nonetheless,… More >

Sait Can Yucebas^*

Intelligent Automation & Soft Computing, Vol.37, No.1, pp. 49-71, 2023, DOI:10.32604/iasc.2023.036871 - 29 April 2023

Abstract The number of studies in the literature that diagnose cancer with machine learning using genome data is quite limited. These studies focus on the prediction performance, and the extraction of genomic factors that cause disease is often overlooked. However, finding underlying genetic causes is very important in terms of early diagnosis, development of diagnostic kits, preventive medicine, etc. The motivation of our study was to diagnose bladder cancer (BCa) based on genetic data and to reveal underlying genetic factors by using machine-learning models. In addition, conducting hyper-parameter optimization to get the best performance from different… More >

I. Mettildha Mary^1,*, K. Karuppasamy²

Computer Systems Science and Engineering, Vol.46, No.3, pp. 2667-2685, 2023, DOI:10.32604/csse.2023.031114 - 03 April 2023

Abstract CC’s (Cloud Computing) networks are distributed and dynamic as signals appear/disappear or lose significance. MLTs (Machine learning Techniques) train datasets which sometime are inadequate in terms of sample for inferring information. A dynamic strategy, DevMLOps (Development Machine Learning Operations) used in automatic selections and tunings of MLTs result in significant performance differences. But, the scheme has many disadvantages including continuity in training, more samples and training time in feature selections and increased classification execution times. RFEs (Recursive Feature Eliminations) are computationally very expensive in its operations as it traverses through each feature without considering correlations More >