Development of an Intelligent System for Processing Semistructured Data: Industry Structuring and Advanced Analysis of Information Extracted from Comments to Video Clips in Social... by A. A. Poguda, H. Tape

“…The aim of this research is to develop an intelligent system for processing semistructured data from comments on social media videos using structuring algorithms targeting different industries. The research aims to create an efficient method to analyze tone, clustering and extract key themes from comments in order to evaluate the impact of video content on the audience. …”
Get full text

Research Progress and Prospect of Green Infrastructure with Public Health Promotion Function by Tongyu LI, Junyi LIXU, Binxia XUE, Yan (USA) SONG

“…To manage the multidimensionality of GI research, cluster analysis is performed using a Word2Vec model combined with a K-means algorithm to integrate different GI forms into a coherent classification system.ResultsThe results show that GI can be clearly divided into different categories, such as urban green spaces and parks, high-interaction spaces, trees in built-up areas, water management and biofiltration systems, community and residential greening, green roofs and facades, linear green networks, and broader macro-GI strategies. …”
Get full text

Human Action Recognition Method Based on Multi-channel Fusion by Zhiyong TAO, Xijun GUO, Xiaokui REN, Ying LIU, Zemin WANG

“…This result highlights the model’s effectiveness in distinguishing different actions in controlled settings. Tests are also conducted in various natural settings to validate the model’s adaptability to real-world environments, including self-built laboratories, classrooms, and corridors. …”
Get full text

SpectralEarth: Training Hyperspectral Foundation Models at Scale by Nassim Ait Ali Braham, Conrad M. Albrecht, Julien Mairal, Jocelyn Chanussot, Yi Wang, Xiao Xiang Zhu

“…Utilizing state-of-the-art self-supervised learning algorithms, we pretrain a series of foundation models on SpectralEarth, integrating a spectral adapter into classical vision backbones to accommodate the unique characteristics of HSI. …”
Get full text

Recognition of pepper plant and ridge characteristics using an ultrasonic sensor for smart upland crop production by Mohammod Ali, Md Rejaul Karim, Md Sazzadul Kabir, Md Asrakul Haque, Kyu-Ho Lee, Sun-Ok Chung

“…The developed system shows the potential of ultrasonic sensors to develop automatic crop monitoring systems and support smart crop production and be adaptable to greenhouses, open fields or on-farm vehicles to identify different types of plants and land features. …”
Get full text

A scalable framework for soil property mapping tested across a highly diverse tropical data-scarce regionZENODO by Rodrigo de Q. Miranda, Rodolfo L.B. Nóbrega, Anne Verhoef, Estevão L.R. da Silva, Jadson F. da Silva, José C. de Araújo Filho, Magna S.B. de Moura, Alexandre H.C. Barros, Alzira G.S.S. Souza, Wanhong Yang, Hui Shao, Raghavan Srinivasan, Feras Ziadat, Suzana M.G.L. Montenegro, Maria do S.B. Araújo, Josiclêda D. Galvíncio

“…We developed a machine learning framework that integrates the Soil-Landscape Estimation and Evaluation Program (SLEEP) with gradient boosting to predict soil properties at regional scales and multiple depths. …”
Get full text

Enhancing Port Energy Autonomy Through Hybrid Renewables and Optimized Energy Storage Management by Dimitrios Cholidis, Nikolaos Sifakis, Nikolaos Savvakis, George Tsinarakis, Avraam Kartalidis, George Arampatzis

“…Hybrid renewable energy systems (HRESs) are being incorporated and evaluated within seaports to realize efficiencies, reduce dependence on grid electricity, and reduce operating costs. …”
Get full text

Improving health-promoting workplaces through interdisciplinary approaches. The example of WISEWORK-C, a cluster of five work and health projects within Horizon-Europe by Deborah De Moortel, Michelle C Turner, Ella Arensman, Alex Binh Vinh Duc Nguyen, Víctor Gonzalez

“…These shifts are giving rise to new forms of work (eg, hybrid work, gig economy jobs) and reshaping management and work organization practices (eg, through algorithmic decision-making or digital monitoring of worker performance). …”
Get full text

Vectorized Highly Parallel Density-Based Clustering for Applications With Noise by Joseph Arnold Xavier, Juan Pedro Gutierrez Hermosillo Muriedas, Stepan Nassyr, Rocco Sedona, Markus Gotz, Achim Streit, Morris Riedel, Gabriele Cavallaro

“…To fully harness a processor’s SIMD capabilities and achieve optimal performance, adapting algorithms for better compatibility with vector operations is necessary. …”
Get full text

A comprehensive review of data analytics and storage methods in geothermal energy operations by Ali Basem, Ahmed Kateb Jumaah Al-Nussairi, Dana Mohammad Khidhir, Narinderjit Singh Sawaran Singh, Mohammadreza Baghoolizadeh, Mohammad Ali Fazilati, Soheil Salahshour, S. Mohammad Sajadi, Ali Mohammadi Hasanabad

“…The ATES, with the advantage of large storage capacity and low operating costs has could be employed in regions with suitable aquifers. The adaptability of BTES to different ground conditions and its small land footprint made it a spotlight for the researchers. …”
Get full text

LLM in the Loop: A Framework for Contextualizing Counterfactual Segment Perturbations in Point Clouds by Veljka Kocic, Niko Lukac, Dzemail Rozajac, Stefan Schweng, Christoph Gollob, Arne Nothdurft, Karl Stampfer, Javier del Ser, Andreas Holzinger

“…The proposed framework undergoes rigorous evaluation, combining human inspection of LLM-generated suggestions with quantitative analysis of semantic classification model performance across different LLM variants. …”
Get full text

Toward Digital Twin of Off-Road Vehicles Using Robot Simulation Frameworks by Arianna Rana, Antonio Petitti, Angelo Ugenti, Rocco Galati, Giulio Reina, Annalisa Milella

“…Research presented in this paper deals with the development of the digital version of off-road vehicles. Two different robot simulation frameworks are investigated. …”
Get full text

Interpersonal counselling for adolescent depression delivered by youth mental health workers without core professional training: the ICALM feasibility RCT by Jon Wilson, Viktoria Cestaro, Eirini Charami-Roupa, Timothy Clarke, Aoife Dunne, Brioney Gee, Sharon Jarrett, Thando Katangwe-Chigamba, Andrew Laphan, Susie McIvor, Richard Meiser-Stedman, Jamie Murdoch, Thomas Rhodes, Carys Seeley, Lee Shepstone, David Turner, Paul Wilkinson

“…Aims The aims of this feasibility study were to (1) assess the feasibility and acceptability of trial procedures, (2) explore the delivery of IPC-A and treatment as usual (TAU) and how and why intervention delivery varies across differing service contexts, (3) evaluate the extent of contamination of the control arm and if it should be mitigated against in a future trial and (4) investigate if the interval estimate of benefit of IPC over TAU in depression scores post treatment includes a clinically significant effect. …”
Get full text

Phosphate transporter gene families in rye (Secale cereale L.) – genome-wide identification, characterization and sequence diversity assessment via DArTreseq by David Chan-Rodriguez, Brian Wakimwayi Koboyi, Sirine Werghi, Bradley J. Till, Julia Maksymiuk, Fatemeh Shoormij, Abuya Hilderlith, Anna Hawliczek, Maksymilian Królik, Hanna Bolibok-Brągoszewska

“…Our findings point to multiple layers of adaptation to local environments, ranging from gene copy number variation to differences in level of polymorphism across Pht family members. …”
Get full text

The implementation of the situational control concept of information security in automated training systems by A. M. Chernih, S. V. Fedoseev

“…Developed method of situational control of information security in automated learning systems, involves the participation of the operator in the development and decision-making (dialogue procedures statement of objectives situational control, the formation of the base of alternative sets of control actions, etc.).Another important feature of this technique is the necessity of using previously developed models (models of decision-making situation, a model of coordination and planning of operation of a subsystem of the control and protection of information, models of information processing about the status of the subsystem analysis models and evaluation of results) and the database obtained on the basis of operating experience of information protection systems in the automated learning systems.The implementation of the concept of situational control of information security ensures the timely adaptation of the algorithms and parameters of the information security system to changes in the external environment and the nature of tasks within the education systems and on this basis allows to improve the characteristics of the information protection system in the automated learning systems.…”
Get full text

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

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