An interpretable coupled model (SWAT-STFT) for multispatial-multistep evapotranspiration prediction in the river basin by Zhonghui Guo, Chang Feng, Liu Yang, Qing Liu

“…Additionally, the coupled model's SSTI leveraged model-internal attention weights to provide new insights into further understanding watershed ET spatiotemporal mechanisms. The feature global interpretation results revealed that meteorological features served as ET dominant drivers in time-varying features (48 % importance), followed by land use features (35 %), while soil features (64 %) dominated static features. …”
Get full text

Exploring the potential of deep learning models integrating transformer and LSTM in predicting blood glucose levels for T1D patients by Xin Xiong, XinLiang Yang, Yunying Cai, Yuxin Xue, JianFeng He, Heng Su

“…The Transformer Encoder captures long-range dependencies, while the LSTM models short-term patterns. To improve feature extraction, we integrate Bidirectional LSTM and Transformer Encoder layers at multiple stages. …”
Get full text

Fine-Tuning Retrieval-Augmented Generation with an Auto-Regressive Language Model for Sentiment Analysis in Financial Reviews by Miehleketo Mathebula, Abiodun Modupe, Vukosi Marivate

“…Additionally, the pre-training of a larger language model (PTLM) struggles to capture bidirectional contextual knowledge learnt through word dependency because the sentence-level representation fails to take broad features into account. We develop a novel structure called language feature extraction and adaptation for reviews (LFEAR), an advanced natural language model that amalgamates retrieval-augmented generation (RAG) with a conversation format for an auto-regressive fine-tuning model (ARFT). …”
Get full text

SYNESTHESIA IN THE NOVEL BY M. PAVIĆ: “LANDSCAPE PAINTED WITH TEA” by Nataliya L. Bilyk

“…The specific nature of certain components of the mechanism and the patterns of functioning inherent in synesthesia, and above all, meaning-making, should be accepted in a generalized aspect. …”
Get full text

Multi-scale machine learning model predicts muscle and functional disease progression by Silvia S. Blemker, Lara Riem, Olivia DuCharme, Megan Pinette, Kathryn Eve Costanzo, Emma Weatherley, Jeff Statland, Stephen J. Tapscott, Leo H. Wang, Dennis W. W. Shaw, Xing Song, Doris Leung, Seth D. Friedman

“…A three-stage random forest model was developed to predict annualized changes in muscle composition and a functional outcome (timed up-and-go (TUG)). …”
Get full text

Antibiotic stories: a mixed-methods, multi-country analysis of household antibiotic use in Malawi, Uganda and Zimbabwe by Justin Dixon, Shunmay Yeung, John Bradley, Laurie Denyer Willis, Susan Nayiga, Clare I R Chandler, Rashida Abbas Ferrand, Sham Lal, Miriam Kayendeke, Christine Nabirye, Sarah G Staedke, Eleanor Elizabeth MacPherson, Edward Green, Salome Manyau, Esnart Sanudi, Alex Nkaombe, Portia Mareke, Kenny Sitole, Coll de Lima Hutchison, Chrissy Roberts

Get full text

Label efficient phenotyping for Long COVID using electronic health records by Chuan Hong, Jun Wen, Harrison G. Zhang, Vidul Ayakulangara Panickan, Doris Y. Yang, Alicia W. Chen, Xin Xiong, Xuan Wang, Michele Morris, Sara Morini, Rahul Sangar, Andrew Dey, Malarkodi J. Samayamuthu, Katherine Liao, Clara-Lea Bonzel, Vidisha Tanukonda, Monika Maripuri, Jacqueline Honerlaw, Yuk-Lam Ho, Shyam Visweswaran, Isaac S. Kohane, Kelly Cho, Gabriel Brat, Zongqi Xia, Tianxi Cai

“…Our downstream analysis revealed a pattern of elevated healthcare utilization due to Long COVID, peaking at and continuing beyond the fourth month following COVID infection. …”
Get full text

Design of an intelligent optimization system for high-altitude photovoltaic power plant output power prediction and enhancement using GVSAO-CNN-BiGRU-Attention by Shuai Yuan, Hui Zhou, Kai Zhao

“…The CNN extracts spatial features, while the BiGRU enhances temporal dependency modeling, effectively capturing short- and long-term patterns. …”
Get full text

Measuring place rather than space: integrating landscape qualities for the urban–rural gradient using people’s perceptions and machine learning by Michal Switalski, Maarten Van Strien, Adrienne Grêt-Regamey

Get full text

Pure pancreatic hepatoid carcinoma: a surgical case report and literature review by Takahiro Tomino, Mizuki Ninomiya, Rumi Matono, Fumiya Narutomi, Yumi Oshiro, Kenji Watanabe, Daisuke Taniguchi, Sho Nishimura, Yoko Zaitsu, Yuichiro Kajiwara, Tomoyuki Yokota, Kazuhito Minami, Takashi Nishizaki

“…We herein report the case of a 56-year-old man who developed pure pancreatic HC treated with surgical resection. …”
Get full text

Urban change detection with airborne LiDAR for hostilities’ impact estimation: a case study of Kharkiv by Sergiy V. Kostrikov, Denys S. Serohin

“…This research demonstrates the application of LiDAR for urban change detection (CD), focusing on distinguishing between CD-patterns of normal urban development and from those caused by military hostilities. …”
Get full text

Shaping towns through time: geology and urbanization in the historical context of Woldia, Ethiopia by Fentaw Baye

“…The study also contrasts growth patterns under various political regimes and evaluates the ecological consequences of settlement practices. …”
Get full text

Coastal Storm – Surge Combination Risk Identification and Resilience Planning Based on Supply and Demand Assessment of Flood Regulation Ecosystem Services: A Case Study of Fujian D... by Jian TIAN, Tianyu XIU, Suiping ZENG

“…For medium risk–ecological improvement zones (e.g., Jimei District, Xiangcheng District), the focus should be on harmonizing urban – rural ecological patterns through the strategic use of natural topographical features as buffer barriers, adopting mixed land-use approaches to curb urban sprawl, and upgrading eco-oriented infrastructure networks. …”
Get full text

Dermoscopy and Pathological Correlation in Different Grades of Actinic Keratosis and Squamous Cell Carcinoma by Li X, Sun J, Zhang H, Zhang C, Li W

“…Dermoscopic grading significantly correlated with both pathological grading systems (P < 0.05). Dermoscopic features such as pigmentation, white fine scaling, erosions, ulceration, white structureless areas, white lines, and vessel patterns were pathologically validated, corresponding to changes related to epidermal basal cells, along with increased inflammatory cell infiltration and fibroblast content in the dermis.Conclusion: Dermoscopy offers a non-invasive and effective method for assessing lesion malignancy across various grades of AK and SCC, reflecting their pathological features and aiding clinical diagnosis while potentially reducing unnecessary biopsies.Keywords: actinic keratosis, squamous cell carcinoma, dermatological imaging, tumor microenvironment…”
Get full text

RES complex is associated with intron definition and required for zebrafish early embryogenesis. by Juan Pablo Fernandez, Miguel Angel Moreno-Mateos, Andre Gohr, Liyun Miao, Shun Hang Chan, Manuel Irimia, Antonio J Giraldez

“…However, the importance of the RES complex for vertebrate splicing, the intronic features associated with its activity, and its role in development are unknown. …”
Get full text

The Role of Metaphorical and Ironic Structures in Representing Hidden Behavioral and Verbal Ideologies of Shahad Al-Rawi’s Novel The Baghdad Clock using Andrew Goatly’s Speech Act... by Ali sayadani, yazdan Heydarpour Marand

“…Introduction Speech act theory is among the theories that have played a role in the development and expansion of critical discourse analysis (CDA). …”
Get full text

XGBoost-based machine learning model combining clinical and ultrasound data for personalized prediction of thyroid nodule malignancy by Wenhan Li, Wenhan Li, Yajing Zhou, Ziyu Luo, Ziyu Luo, Miao Tan, Miao Tan, Rui Yin, Jianhui Li, Jianhui Li

“…Nowadays, machine learning (ML) offers advanced capabilities to handle high-dimensional data and complex patterns. This study aimed to develop an ML model integrating clinical data and ultrasound features to improve personalized prediction of TN malignancy.MethodsData from 2,014 patients with TNs (2018.01–2024.01) were retrospectively analyzed, with 1,612 in the training set and 402 in the test set. …”
Get full text

Enhancing sustainable agriculture through innovative packaging: consumer preferences and willingness to pay in the Nepalese market by Anisha Giri, Tilak Raj Chaulagai

Get full text

A cartographic generalization method for 3D visualization of trajectories in space–time cubes: case study of epidemic spread by Fei Yang, Jie Shen, Fengzhen Zhu, Junrui Zhang

Get full text

Mitigating malicious denial of wallet attack using attribute reduction with deep learning approach for serverless computing on next generation applications by Amal K. Alkhalifa, Mohammed Aljebreen, Rakan Alanazi, Nazir Ahmad, Sultan Alahmari, Othman Alrusaini, Ali Alqazzaz, Hassan Alkhiri

“…The deep learning (DL) model, a part of the machine learning (ML) technique, has developed as an effectual device in cybersecurity, permitting more effectual recognition of anomalous behaviour and classifying patterns indicative of threats. …”
Get full text