Yurong Guan

Yurong Guan

Auto-generated profile, based on publicly available information

Yurong Guan

Huanggang Normal University, China, Hubei

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 June 2020 in IEEE Access
Verified
Journal Article
Open access
ZRZiaur Rahman
Ziaur Rahman
Yi-Fei PuYi-Fei Pu
Yi-Fei Pu
Aamir MuhammadAamir Muhammad
Aamir Muhammad
DWDr. Samad Wali
Dr. Samad Wali
YGYurong Guan
Yurong Guan
Images captured under varying light conditions have deficient contrast, low brightness, latent colors, and high noise. Numerous methods have been developed for image enhancement. However, these methods are only suitable for enhancing specific type of images (e.g., over-exposed or underexposed), and also fail to restore artifact-free results for various other types of images. Therefore, to meet this goal, in this paper, we present an automatic image enhancement method, which is capable of producing quality results for all types of images captured under uneven exposure conditions (e.g., backlit, non-uniform, over-exposed, one-sided illumination and night-time images). Firstly, images are categorized using a convolutional neural network (CNN) to determine their class, and different values of weight coefficients are achieved for further processing. Then, images are converted into photonegative form to obtain an initial transmission map using a bright channel prior. Next, L1-norm regularization is adopted to refine scene transmission. Besides, environmental light is estimated based on an effective filter. Finally, the image degradation model is applied to achieve enhanced results. Furthermore, post-processing of the images is comprised of two steps, such as denoising and details enhancement. The denoised model is only applied when the images are captured in extreme low-light conditions. Whereas, a smooth layer is obtained using L1-norm regularization to enhance details in partially over-and under-exposed images. Extensive experiments reveal the effectives of the proposed approach as compared to other state-of-the-art algorithms.

30 June 2021 in Traitement du Signal
Verified
Journal Article
Open access
YGYurong Guan
Yurong Guan
Aamir MuhammadAamir Muhammad
Aamir Muhammad
ZHZhihua Hu
Zhihua Hu
Zaheer Ahmed DayoZaheer Ahmed Dayo
Zaheer Ahmed Dayo
ZRZiaur Rahman
Ziaur Rahman
PSPermanand Soothar
Permanand Soothar
Objection detection has long been a fundamental issue in computer vision. Despite being widely studied, it remains a challenging task in the current body of knowledge. Many researchers are eager to develop a more robust and efficient mechanism for object detection. In the extant literature, promising results are achieved by many novel approaches of object detection and classification. However, there is ample room to further enhance the detection efficiency. Therefore, this paper proposes an image object detection and classification, using a deep neural network (DNN) for based on high-quality object locations. The proposed method firstly derives high-quality class-independent object proposals (locations) through computing multiple hierarchical segments with super pixels. Next, the proposals were ranked by region score, i.e., several contours wholly enclosed in the proposed region. After that, the top-ranking object proposal was adopted for post-classification by the DNN. During the post-classification, the network extracts the eigenvectors from the proposals, and then maps the features with the softmax classifier, thereby determining the class of each object. The proposed method was found superior to traditional approaches through an evaluation on Pascal VOC 2007 Dataset.

29 June 2026 in Bulletin of Zhetysu University named after I.Zhansugurov
Verified
Journal Article
Closed access
BTBi. Tao
Bi. Tao
GYGuan. Yurong
Guan. Yurong
This study presents a comparative analysis of university teacher professional development centers in Kazakhstan and China based on a systematic review of peer-reviewed publications. Through thematic content analysis and frequency statistics, the research identifies similarities and differences between the two countries regarding organizational structures, functional positioning, service models, and digital transformation strategies. Quantitative analysis indicates that digital transformation and professional competency development are current focal points of research, while studies on inclusive development and evaluation mechanisms remain relatively insufficient. The findings reveal that Chinese teacher development centers exhibit greater institutionalization and policy orientation, whereas Kazakhstan demonstrates stronger characteristics of flexibility, practicality, and teacher identity cultivation. The results provide policy insights for both countries to optimize the governance of teacher development centers and foster teacher professional growth, suggesting future enhancements in transnational collaborative training programs, unified evaluation indicators, and the construction of inclusive support mechanisms. In addition, the study highlights the influence of national higher education reforms and sociocultural contexts on the strategic priorities of teacher professional development centers. The analysis demonstrates that differences in governance models and funding mechanisms significantly shape the scope and sustainability of professional development initiatives. Attention is also drawn to the growing role of digital platforms in expanding access to training resources and facilitating continuous professional learning. However, gaps persist in research addressing the long-term impact of professional development programs on teaching quality and student outcomes. These findings underscore the need for evidence-based policy alignment and cross-national knowledge exchange to enhance the effectiveness and inclusiveness of university teacher development systems. Данное исследование представляет сравнительный анализ центров профессионального развития университетских преподавателей в Казахстане и Китае на основе систематического обзора рецензируемых научных публикаций. С помощью тематического контент-анализа и статистики частот выявлены сходства и различия между двумя странами в отношении организационных структур, функциональной направленности, моделей предоставления услуг и стратегий цифровой трансформации. Количественный анализ показывает, что цифровая трансформация и развитие профессиональных компетенций являются актуальными направлениями исследований, тогда как работы, посвященные инклюзивному развитию и механизмам оценки, остаются относительно недостаточными. Результаты исследования показывают, что центры профессионального развития в Китае характеризуются более высокой институционализацией и ориентированностью на политику, тогда как в Казахстане преобладают гибкость, практическая направленность и формирование профессиональной идентичности преподавателя. Полученные выводы предоставляют рекомендации для обеих стран по оптимизации управления центрами развития преподавателей и поддержке профессионального роста, предлагая в будущем совершенствовать транснациональные совместные программы подготовки, внедрять единые показатели оценки и создавать инклюзивные механизмы поддержки. Кроме того, исследование подчеркивает влияние национальных реформ в сфере высшего образования и социокультурного контекста на стратегические приоритеты центров профессионального развития преподавателей. Анализ демонстрирует, что различия в моделях управления и механизмах финансирования существенно формируют масштаб и устойчивость инициатив профессионального развития. Особое внимание уделено возрастающей роли цифровых платформ в расширении доступа к учебным ресурсам и поддержке непрерывного профессионального обучения. Однако сохраняются пробелы в исследованиях, посвященных долгосрочному влиянию программ профессионального развития на качество преподавания и результаты обучения студентов. Эти выводы подчеркивают...

20 March 2026 in Journal of Educational Sciences
Verified
Journal Article
Open access
SXS. Xiu
S. Xiu
AAA. Akramova
A. Akramova
YGY. Guan
Y. Guan
ССС. Сюй
С. Сюй
ЮГЮ. Гуань
Ю. Гуань
This study examines the impact of technological platforms (Duolingo, Coursera, Quizlet) on the development of project thinking, cognitive skills, memorization, problem-solving, creativity, and engagement. A survey was conducted among 77 students majoring in “Pedagogy and Psychology” to analyze their understanding of the strengths of digital platforms, compare learning outcomes, and identify barriers to the implementation of digital education. Three hypotheses were tested: (1) Digital tools and teaching methods outperform conventional approaches in memorization efficiency and visual/creative thinking but are inferior in deep problem-solving and long-term knowledge retention; (2) Gamified platforms (e.g., Kahoot) enhance student engagement while both contributing to and helping manage distractions; (3) Digital tools (Coursera, Canva) are superior to conventional methods in structured task performance (e.g., following project templates), whereas conventional methods are more applicable for adaptive decision-making in unpredictable scenarios. The results confirmed that platforms such as Quizlet and Canva improve students’ memorization and creativity, while conventional instruction is preferable for complex problem-solving and teamwork; gamified tools correlate with higher motivation but also a greater number of distractions. Keywords: project-based thinking, educational psychologists, technologies, digital tools, education, cognitive skills.