Mapping Peatlands Combing Deep Learning With Sparse Spectral Unmixing Based on Zhuhai-1 Hyperspectral Images by Yulin Xu, Xiaodong Na

“…A multihead attention mechanism based on the transformer encoder captures global contextual information by correlating patches in the image, facilitating precise hyperspectral data reconstruction. …”
Get full text

An evaluation of traceability dynamics in dairy supply chains through causal modeling in emerging economies by Shahab Bayatzadeh, Hamidreza Talaie

“…The results highlight food safety and quality, supply chain process management, data analysis and forecasting, and data integration as the most influential drivers of traceability. …”
Get full text

Perspectives of undergraduate module convenors at a South African academic institution on medical student training in evidence-based health care: a qualitative study by Taryn Young, Anke Rohwer, Jimmy Volmink, Mike Clarke

“…Faculty convening medical undergraduate teaching modules were purposively sampled. Data collection was done using focus-group or individual interviews. …”
Get full text

Leveraging Machine Learning for Enhanced Bug Triaging in Open-Source Software Projects by Nitanta Adhikari, Rabindra Bista, Joao Carlos Ferreira

“…Our primary contribution is the development of an Augmented Bidirectional LSTM model that integrates enriched textual features and contextual metadata. …”
Get full text

Research on a denoising model for entity-relation extraction using hierarchical contrastive learning with distant supervision by Ayiguli Halike, Aishan Wumaier, Kahaerjiang Abiderexiti, Tuergen Yibulayin

“…Specifically, a three-layer learning architecture is designed, which incorporates interactions at different levels and employs a multi-head self-attention mechanism to generate denoised context-aware representations, referred to as multi-granular re-contextualization. Additionally, a dynamic gradient adversarial perturbation data augmentation strategy is introduced to provide pseudo-positive samples for contrastive learning, further enhancing the model’s capabilities in recognizing rare relations. …”
Get full text

Semi-Supervised Salient Object Detection for Side-Scan Sonar Images via Entropy-Based Uncertainty and Contrastive Learning by Shenao Yuan, Zhen Wang, Fu-Lin He, Shan-Wen Zhang

“…Our method aims to improve the quality of pseudo-labels and the overall performance of the model using a small amount of labeled data. Specifically, we design an uncertainty map evaluation module that effectively extracts global contextual information through an entropy-based partition loss and a contrastive learning mechanism, integrated with the uncertainty map to handle the complex underwater background. …”
Get full text

Unitary patent system and innovation dynamics in the European Union: The role of economic resources and R&D investments by Radka MacGregor Pelikánová, Martin Hála, Marek Beneš

“…On 1st June 2023, the EU launched the Unitary Patent System (UPS) with the Unitary Patent as a universal innovation protection tool. The data regarding its first 20 months of operations offers indices about innovation and patenting trends. …”
Get full text

Scientific Illustration: from Informational Support to a Culture of Participation by D. K. Lisovsky

“…This is due to constantly changing technical and technological means of presenting scientific data, as well as a change in the communicative space of science itself. …”
Get full text

Urban walkability through different lenses: A comparative study of GPT-4o and human perceptions. by Musab Wedyan, Yu-Chen Yeh, Fatemeh Saeidi-Rizi, Tai-Quan Peng, Chun-Yen Chang

“…However, these approaches often fail to capture the subjective and emotional dimensions of walkability, due to their limited ability to integrate human-centered perceptions and contextual understanding. …”
Get full text

The lived experiences of pediatric nursing students following high-fidelity simulations and problem-based learning sessions by Sadeg Aldolaim, Latifa Abdullah Aldossary, Ibtihal Abdulhadial Almomin, Areej Abdulghani Haitham

“…Results Four themes emerged from the data: (1) Benefits of HFS and PBL, describing enhanced clinical confidence, decision-making, and practical skills; (2) Effect of Integrative Learning, highlighting the meaningful connection between theory and practice through guided reflection and teamwork; (3) Challenge to Respond to the Real Child, reflecting students’ concerns about applying simulation-learned skills in emotionally demanding pediatric settings; and (4) Necessity of Collaboration, underscoring the importance of interdisciplinary engagement and broader clinical exposure. …”
Get full text

A Participatory Governance Model for Comprehensive Conservation of Historical Buildings and Urban Fabric: A Grounded Theory Approach by Somayyeh Ghadimzadeh, Elnaz Abizadeh, Mahdiyeh Rahnemay Toori

“…In the selective coding phase, these subcategories were integrated to form 26 main categories, which were then structured into 5 sections within the paradigm model: causal conditions (4 categories), contextual conditions (5 categories), intervening conditions (5 categories), strategies (7 categories), and consequences (5 categories).   …”
Get full text

Étudier l’appropriation des TIC à l’école en combinant l’examen des usages et des représentations sociales des utilisateurs. by Emmanuel BÉCHÉ

“…It uses three data collection methods: interview, network of association and direct observation. …”
Get full text

ModFus-PD: synergizing cross-modal attention and contrastive learning for enhanced multimodal diagnosis of Parkinson’s disease by Xiangze Teng, Xiangze Teng, Xiangze Teng, Xiang Li, Xiang Li, Xiang Li, Benzheng Wei, Benzheng Wei, Benzheng Wei

“…The framework comprises three key components: (1) a contrastive learning-based feature alignment module that projects MRI data and clinical text prompts into a unified embedding space via pretrained image and text encoders; (2) a bidirectional cross-modal attention module in which textual semantics guide MRI feature refinement for improved sensitivity to PD-related brain regions, while MRI features simultaneously enhance the contextual understanding of clinical text; (3) a hierarchical classification module that integrates the fused representations through two fully connected layers to produce final PD classification probabilities. …”
Get full text

Changes in food quality and habits in urban Ghana: evidence from a mixed-methods study by Sandra Boatemaa Kushitor, Lydia Okoibhole, Megan Vaughan, Kafui Adjaye-Gbewonyo, Irene Akwo Kretchy, Olutobi Adekunle Sanuade, Leonard Baatiema, Samuel Amon, Kojo Mensah Sedzro, Mawuli Komla Kushitor, Akanksha Abhay Marphatia, Emeline Rougeaux, Ann Blandford, Publa Antwi, Hannah Jennings, Vida Asah-Ayeh, Raphael Baffour Awuah, Edward Fottrell, Carlos Salvador Grijalva-Eternod

“…Focus group discussions were held to discuss current and past food habits, and data were analysed thematically (n = 30). The qualitative and quantitative data were integrated during the analysis. …”
Get full text

NSTP-CWTS of the Higher Education System: The Philippine Experience by Edna Liza Victoria

“…Using Stake's Responsive Model of evaluation, the triangulated data from survey questionnaire, interview, and focus group discussion revealed that the HEI respondents demonstrate great extent of contextualized CWTS practice under the CHED standards. …”
Get full text

SmartTrust: a hybrid deep learning framework for real-time threat detection in cloud environments using Zero-Trust Architecture by Umesh Kumar Lilhore, Sarita Simaiya, Roobaea Alroobaea, Abdullah M. Baqasah, Majed Alsafyani, Afnan Alhazmi, Md Monish Khan

“…SmartTrust integrates CNN, LSTM, and Transformer models to analyze spatial and temporal patterns in network traffic and user behaviours. …”
Get full text

DMSA-Net: a deformable multiscale adaptive classroom behavior recognition network by Chunyu Dong, Jing Liu, Shenglong Xie

“…Extensive experimentation reveals that our proposed method outperforms rival algorithms on two widely adopted benchmark datasets: SCB-Dataset3-S (the Student Classroom Behavior Dataset–https://github.com/Whiffe/SCB-dataset) and we created object detection dataset DataMountainSCB (https://github.com/Chunyu-Dong/DataFountainSCB1) containing six types of behaviors.…”
Get full text

Subjective social status among young working women in Sweden: how is it established and how does it affect health and well-being? A qualitative interview study by Ylva Lindberg, Åsa Andersén, Anna Nyberg, Ulrika Winblad, Ingrid Demmelmaier

“…Maximum variation purposeful sampling was employed to achieve rich information in the data. Data were collected through individual semi-structured interviews and analysed using thematic analysis. …”
Get full text

Analysis of Teaching Speaking Through Audio-Visual Methods at Jitjongrak School, Krabi, Thailand by Angeli Shela Rossa, Ikhfi Imaniah, Asep Suhendar

“…This research provides practical implications for educators aiming to integrate technology to improve speaking proficiency.…”
Get full text

INNOVATIVE SOLUTION FOR BIPA: ENHANCING READING SKILLS AND CULTURAL UNDERSTANDING THROUGH INTERACTIVE MULTIMEDIA by Yoga Karuniawan, Herman Dwi Surjono

“…This research addresses the low reading ability of beginner-level BIPA students in understanding Indonesian cultural materials, attributed to complex vocabulary, grammar, and contextual themes. It analyzes the feasibility, practicality, and effectiveness of interactive multimedia integrated with a self-directed learning model to enhance reading skills and cultural understanding. …”
Get full text