A Dataset of Real and Synthetic Speech in Ukrainian by Khrystyna Lipianina-Honcharenko, Hennadii Bohuta, Adam Ivaniush, Mariana Soia

“…Abstract This work is dedicated to the analysis and evaluation of the DRSSU dataset: A Dataset of Real and Synthetic Speech in Ukrainian, created to support research in the field of natural language processing and speech recognition. …”
Get full text

Selection of suitable reference lncRNAs for gene expression analysis in Osmanthus fragrans under abiotic stresses, hormone treatments, and metal ion treatments by Yingting Zhang, Yingting Zhang, Qingyu Yan, Hui Xia, Xiangling Zeng, Xiangling Zeng, Xiangling Zeng, Jie Yang, Jie Yang, Jie Yang, Xuan Cai, Xuan Cai, Xuan Cai, Zeqing Li, Zeqing Li, Hongguo Chen, Hongguo Chen, Hongguo Chen, Jingjing Zou, Jingjing Zou, Jingjing Zou

“…Despite its importance, research on long non-coding RNAs (lncRNAs) in O. fragrans has been constrained by the absence of reliable reference genes (RGs).MethodsWe employed five distinct algorithms, i.e., delta-Ct, NormFinder, geNorm, BestKeeper, and RefFinder, to evaluate the expression stability of 17 candidate RGs across various experimental conditions.Results and discussionThe results indicated the most stable RG combinations under different conditions as follows: cold stress: lnc00249739 and lnc00042194; drought stress: lnc00042194 and lnc00174850; salt stress: lnc00239991 and lnc00042194; abiotic stress: lnc00239991, lnc00042194, lnc00067193, and lnc00265419; ABA treatment: lnc00239991 and 18S; MeJA treatment: lnc00265419 and lnc00249739; ethephon treatment: lnc00229717 and lnc00044331; hormone treatments: lnc00265419 and lnc00239991; Al3+ treatment: lnc00087780 and lnc00265419; Cu2+ treatment: lnc00067193 and 18S; Fe2+ treatment: lnc00229717 and ACT7; metal ion treatment: lnc00239991 and lnc00067193; flowering stage: lnc00229717 and RAN1; different tissues: lnc00239991, lnc00042194, lnc00067193, TUA5, UBQ4, and RAN1; and across all samples: lnc00239991, lnc00042194, lnc00265419 and UBQ4. …”
Get full text

The future of critical care: AI-powered mortality prediction for acute variceal gastrointestinal bleeding and acute non-variceal gastrointestinal bleeding patients by Zhou Liu, Guijun Jiang, Liang Zhang, Palpasa Shrestha, Yugang Hu, Yi Zhu, Guang Li, Yuanguo Xiong, Liying Zhan

“…The model performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). …”
Get full text

The superiority of feasible solutions-moth flame optimizer using valve point loading by Mohammad Khurshed Alam, Herwan Sulaiman, Asma Ferdowsi, Md Shaoran Sayem, Md Mahfuzer Akter Ringku, Md. Foysal

“…The MFO, Grey Wolf Optimizer (GWO), Success-history-based Parameter Adaptation Technique of Differential Evolution - Superiority of Feasible Solutions (SHADE-SF), and Superiority of Feasible Solutions-Moth Flame Optimizer (SF-MFO) algorithms are applied to address the OPF problem with two objective functions: (1) reducing energy production costs and (2) minimizing power losses. …”
Get full text

Development and validation of interpretable machine learning models for postoperative pneumonia prediction by Bingbing Xiang, Yiran Liu, Shulan Jiao, Wensheng Zhang, Shun Wang, Mingliang Yi

“…This study aimed to develop and validate a predictive model for postoperative pneumonia in surgical patients using nine machine learning methods.ObjectiveOur study aims to develop and validate a predictive model for POP in surgical patients using nine machine learning algorithms. By evaluating the performance differences among these machine learning models, this study aims to assist clinicians in early prediction and diagnosis of POP, providing optimal interventions and treatments.MethodsRetrospective data from electronic medical records was collected for 264 patients diagnosed with postoperative pneumonia and 264 healthy control surgical patients. …”
Get full text

Integrating Fine-Grained Classification and Motion Relation Analysis for Face Anti-Spoofing by Ziyang Cheng, Xiafen Zhang

“…By introducing an attention mechanism, the MCAN uses the RAFT optical flow algorithm to adaptively focus on the direction and intensity of micro-movements in key face regions, distinguishing the natural movement of real faces from the static or repetitive motion patterns in spoofing attacks. …”
Get full text

dmQAR: Mapping Metacognition in Digital Spaces onto Question–Answer Relationship by Brittany Adams, Nance S. Wilson, Gillian E. Mertens

“…In response to the nonlinear, multimodal, and algorithmically curated nature of online texts, the dmQAR Framework scaffolds purposeful metacognitive questioning to support comprehension, evaluation, and critical engagement. …”
Get full text

Robust Vessel Segmentation in Fundus Images by A. Budai, R. Bock, A. Maier, J. Hornegger, G. Michelson

“…The proposed method is evaluated using the STARE and DRIVE databases and we propose a new high resolution fundus database to compare it to the state-of-the-art algorithms. …”
Get full text

MMAgentRec, a personalized multi-modal recommendation agent with large language model by Xiaochen Xiao

“…The system includes a recommendation module that seeks advice from different domain experts based on user requirements. …”
Get full text

Private Data Incrementalization: Data-Centric Model Development for Clinical Liver Segmentation by Stephanie Batista, Miguel Couceiro, Ricardo Filipe, Paulo Rachinhas, Jorge Isidoro, Inês Domingues

“…However, these models often face challenges in adapting to diverse clinical data sources as differences in dataset volume, resolution, and origin impact generalization and performance. …”
Get full text

Sound-Based Unsupervised Fault Diagnosis of Industrial Equipment Considering Environmental Noise by Jeong-Geun Lee, Kwang Sik Kim, Jang Hyun Lee

“…Moreover, applying DANN for fault diagnosis significantly improved diagnostic performance in noisy environments by overcoming environmental differences between the source and target domains. In particular, by adapting the model learned in the source domain to the target domain and considering the domain differences based on signal-to-noise ratio, high diagnostic accuracy was maintained regardless of the noise levels. …”
Get full text

Flash flood prediction modeling in the hilly regions of Southeastern Bangladesh: A machine learning attempt on present and future climate scenarios by Arifur Rahman Rifath, Md Golam Muktadir, Mahmudul Hasan, Md Ashraful Islam

“…To predict FFS, we evaluated twelve flood-influencing variables: elevation (EL), slope (SL), aspect (AS), drainage density (DD), distance to stream (DS), topography roughness index (TRI), stream power index (SPI), topographic wetness index (TWI), soil permeability (SP), precipitation (PR), land use and land cover (LULC) and normalized difference vegetation index (NDVI). …”
Get full text

Energy Efficient Heat Exchange Network for the Oil Vacuum Distillation Facility by Ved V.E., Ilchenko M.V., Myronov A.N.

“…The task is achieved by applying design algorithms of a pinch analysis. The most important result of the work is the proven possibility of reducing the external heat carriers’ energy by 1.87 MW and increasing the thermal energy recovery inside the system to 11.26 MW. …”
Get full text

Enhancing Corn Image Resolution Captured by Unmanned Aerial Vehicles With the Aid of Deep Learning by Emilia Alves Nogueira, Bruno Moraes Rocha, Gabriel da Silva Vieira, Afonso Ueslei da Fonseca, Juliana Paula Felix, Antonio Oliveira-Jr, Fabrizzio Soares

“…In future investigations, we hope to refine the accuracy of the proposed approaches, as well as expand the comparisons with other super-resolution algorithms. In addition, tests will be carried out with different datasets, including satellite images, to evaluate the specificity in apply these techniques in different scenarios. …”
Get full text

Continuous Real-Time Acoustic Monitoring of endangered bird species in Hawai‘i by Melissa Weidlich-Rau, Amanda K. Navine, Patrick T. Chaopricha, Felix Günther, Stefan Kahl, Thomas Wilhelm-Stein, Raymond C. Mack, Hendrik Reers, Aaron N. Rice, Maximilian Eibl, Patrick J. Hart, Patrick Wolff, Holger Klinck, Lena D. Schnell, Rogelio Doratt, Michael Loquet, Tiana Lackey

“…The system is based on the BirdNET algorithm and was evaluated with over 16,000 soundscape recordings from Hawai‘i. …”
Get full text

An Automatic Method for Powerline Extraction From ALS Point Cloud of Powerline Corridors by Di Cao, Cheng Wang, Haibo Liu, Su Zhang, Meng Du, Pu Wang, Sheng Nie, Sijin Cheng

“…The method was evaluated on nine datasets spanning 80.32 km, covering voltage levels of 220 kV, 500 kV, and 800 kV. …”
Get full text

An improved hybrid approach involving deep learning for urban greening tree species classification with Pléiades Neo 4 imagery—A case study from Nanjing, Eastern China by Min Sun, Stephane G.P. Debulois, Zhengnan Zhang, Xiaolei Cui, Zhili Chen, Mingshi Li

“…Future work will integrate multi-source data, multi-seasonal observations, and adaptive algorithms to further enhance classification performance and improve model robustness across diverse urban environments.…”
Get full text

A Hierarchical Machine Learning-Based Strategy for Mapping Grassland in Manitoba’s Diverse Ecoregions by Mirmajid Mousavi, James Kobina Mensah Biney, Barbara Kishchuk, Ali Youssef, Marcos R. C. Cordeiro, Glenn Friesen, Douglas Cattani, Mustapha Namous, Nasem Badreldin

Get full text

Comparing Machine Learning-Based Crime Hotspots Versus Police Districts: What’s the Best Approach for Crime Forecasting? by Eugenio Cesario, Paolo Lindia, Andrea Vinci

“…In contrast, machine learning-based approaches could dynamically adapt to areas with differing crime frequencies and densities, making them particularly effective in cities characterized by diverse population distributions and crime activity levels. …”
Get full text

Probing the Pitfalls: Understanding SVD’s Shortcomings in Language Model Compression by Сергей Александрович Плетенев

“…Then, we applied low-rank factorization to its transformer layers using various singular value decomposition algorithms at different compression rates. After that, we used probing tasks to analyze the changes in the internal representations and linguistic knowledge of the compressed models. …”
Get full text