Research on Enhanced Dynamic Pig Counting Based on YOLOv8n and Deep SORT by Peng Shen, Keyu Mei, Haori Xue, Tenglong Li, Guoqing Zhang, Yongxiang Zhao, Wei Luo, Liang Mao

“…Finally, counting experiments were performed on videos of pigs traversing the farm passage using both the original and improved algorithms. …”
Get full text

An Efficient Encoding Spectral Information in Hyperspectral Images for Transfer Learning of Mask R-CNN for Instance Segmentation of Tomato Sepals by Zeljana Grbovic, Marko Panic, Vladan Filipovic, Sanja Brdar, Hendrik de Villiers, Manon Mensink, Aneesh Chauhan

“…A comparative analysis of three Mask Region-based Convolutional Neural Network (Mask R-CNN) backbone models is conducted: the Faster R-CNN, Deformable ConvNet, and Feature Pyramid Network (FPN) on spectral-encoded HSIs of the Brioso tomato variety. …”
Get full text

Genome-wide comparative analysis of clinical and environmental strains of the opportunistic pathogen Paracoccus yeei (Alphaproteobacteria) by Magdalena Szuplewska, Dorota Sentkowska, Robert Lasek, Przemysław Decewicz, Mateusz Hałucha, Łukasz Funk, Cora Chmielowska, Dariusz Bartosik

“…As a result, P. yeei strains provide a valuable model for exploring how bacteria shift from a saprophytic to a pathogenic lifestyle, as well as for investigating the role of horizontally transferred DNA in this transition. …”
Get full text

Environmental DNA Epigenetics Accurately Predicts the Age of Cultured Fish Larvae by Eliot Ruiz, Fabien Leprieur, Gérard Sposito, Martina Lüthi, Michel Schmidlin, Jacques Panfili, Loïc Pellissier, Camille Albouy

“…By considering qualitative and quantitative information about aging sites according to an objective model selection framework, our epigenetic clock reached a cross‐validated accuracy of 2.6 days (Median Absolute Error). …”
Get full text

Identification of neutrophil extracellular trap-related biomarkers in ulcerative colitis based on bioinformatics and machine learning by Jiao Li, Yupei Liu, Zhiyi Sun, Suqi Zeng, Caisong Zheng

“…To identify potential diagnostic biomarkers, we applied the Least Absolute Shrinkage and Selection Operator (LASSO), Support Vector Machine-Recursive Feature Elimination (SVM-RFE) model, and Random Forest (RF) algorithm, and constructed Receiver Operating Characteristic (ROC) curves to evaluate accuracy. …”
Get full text

Integration of Machine Learning and Wavelet Algorithms for Processing Probing Signals: An Example of Oil Wells by Zukhra Abdiakhmetova, Zhanerke Temirbekova

“…By integrating wavelet-based feature extraction with machine learning-driven analysis, this approach enhances the ability to detect complex wave propagation patterns, leading to more precise subsurface modeling. …”
Get full text

Improving the efficiency of the formation of professional competencies Masters in “Information Security” based on the use o CASE-technologies by A. V. Gavrilov, V. A. Sizov

“…For the formation of the register of enterprise information resources, it is proposed to build a structural-functional enterprise model using the IDEF0 notation. Business process modeling was performed in the Business Studio environment of «Modern Control Technologies». …”
Get full text

Replacing Gauges with Algorithms: Predicting Bottomhole Pressure in Hydraulic Fracturing Using Advanced Machine Learning by Samuel Nashed, Rouzbeh Moghanloo

“…The MSE and R² values of the best-performing machine learning predictors, primarily gradient boosting, decision trees, and neural network (L-BFGS) models, demonstrate a very low MSE value and high R² correlation coefficients when mapping the predictions of bottomhole pressure to actual downhole gauge measurements. …”
Get full text

Association between gut microbial diversity and technique failure in peritoneal dialysis patients by Shulan Guo, Huan Wu, Ji Ji, Zhaoxing Sun, Bo Xiang, Weiwei Wu, Jun Ji, Jie Teng, Xiaoqiang Ding, Xiaofang Yu

“…In addition, older age (HR, 1.034; 95% CI, 1.005–1.063; p = 0.020) and the history of diabetes (HR, 5.547; 95% CI, 2.218–13.876; p < 0.001) were also independent predictors for technique failure of PD patients. The prediction model constructed on the basis of three independent risk factors above performed well in predicting technique failure at 36 and 48 months (36 months: area under the curve [AUC] = 0.861; 95% CI, 0.836–0.886; 48 months: AUC = 0.815; 95% CI, 0.774–0.857).Conclusion Gut microbial diversity was independently correlated with technique failure in PD patients, and some specific microbial taxa may serve as a potential therapeutic target for decreasing PD technique failure.…”
Get full text

Date delivery scheme of delay-tolerant mobile sensor networks for high-voltage power transmission line inspection robot by FAN Fei, WU Gong-ping, WANG Man, XU Qing-shan, CAO Qi, YANG Song

“…A path-constrained random motion model was established, in order to accurately calculate the network pose information of the inspection robot. …”
Get full text

Analysis of the overall development trends and hotspots in the research field of the human gut virome by Yidi Zhang, Ting Mei, Minhui Wang, Chunxia Huang, Hanzhi Yi, Yu Zhan, Sen Yang, Han Wang, Qiulong Yan, Ruochun Guo, Changming Chen

“…It is worth noting that the existing research shows a distinct feature of "imbalance between dry and wet experiments". …”
Get full text

A 50THz Ultra-Wideband Nano-Photonics Perfect Absorber Biosensor for Label-Free Detection of Circulating Cancer Exosomes: Advancing Early Cancer Diagnostics by Musa N. Hamza, Mohammad Tariqul Islam, Sunil Lavadiya, Iftikhar ud Din, Bruno Sanches, Slawomir Koziel, Syeda Iffat Naqvi, Abinash Panda, Mohammad Alibakhshikenari, Bal Virdee, D. Mariyanayagam, R. Jayanthi, S. Fernando, Md. Shabiul Islam

Get full text

Stochastic <i>H</i>_∞ Filtering of the Attitude Quaternion by Daniel Choukroun, Lotan Cooper, Nadav Berman

“…An essential advantage of this <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>H</mi><mo>∞</mo></msub></semantics></math></inline-formula> filter is that the gains are independent of the quaternion, which makes it insensitive to modeling errors. This desired feature is illustrated by comparing its performances against those of unmatched nonlinear optimal filters. …”
Get full text

Cattle welfare assessment based on adaptive fuzzy logic and multimodal data fusion by Lei Tong, Lei Tong, Lei Tong, Jiandong Fang, Jiandong Fang, Jiandong Fang, Xiuling Wang, Xiuling Wang, Xiuling Wang, Yudong Zhao, Yudong Zhao

“…By introducing a dynamic adaptive scoring mechanism, the model can automatically adjust evaluation parameters according to the actual application scenario, ensuring the practicality and reliability of the evaluation results. …”
Get full text

ECONOMIC AND LEGAL POLICY IN THE FIELD OF SECURITY ON THE MARKET OF NON-BANKING FINANCIAL SERVICES IN UKRAINE by Hanna Buha, Serhii Hermanov, Volodymyr Ihnatenko

“…Their characteristic feature is a clear definition of the scope of action (limits of legal regulation), which covers the subject area of work of public administration bodies and managerial social relations that arise in the process of their performance of power and organizational functions. …”
Get full text

Plot-scale peanut yield estimation using a phenotyping robot and transformer-based image analysis by Zhengkun Li, Rui Xu, Nino Brown, Barry L. Tillman, Changying Li

“…Additionally, the Real-Time Detection Transformer (RT-DETR) was customized for pod detection by integrating partial convolution into a lightweight ResNet-18 backbone and refining the up-sampling and down-sampling modules in cross-scale feature fusion. The customized detector achieved a mean Average Precision (mAP50) of 89.3% and a mAP95 of 55.0%, improving by 3.3% and 5.9% over the original RT-DETR model with lighter weights and less computation. …”
Get full text

A Multitask Network for the Diagnosis of Autoimmune Gastritis by Yuqi Cao, Yining Zhao, Xinao Jin, Jiayuan Zhang, Gangzhi Zhang, Pingjie Huang, Guangxin Zhang, Yuehua Han

“…Finally, we apply the RepLKNet model, which utilizes large-kernel convolution, to each image group to perform two tasks: anatomical region classification and lesion recognition. …”
Get full text

Evaluating Land use Mixed-ness on Street Level through Spatial Analyses and Gini Method by Hamid Motieyan, Mohammad Azmoodeh

“…Therefore, in the first step, the layers of streets and land uses of the Valiasr neighborhood, located in District 6 of Tehran, which have the ability to perform spatial analysis, have been collected. In the second step, in order to present the calculation model, the streets that have a length of more than 200 meters, which play higher importance in the distribution of land uses in the neighborhood, are selected and form the layer of analysis. …”
Get full text

Bioactive constituents from the edible seaweed Halymenia hawaiiana (Rhodophyta) by Achara Raksat, Md Samiul Huq Atanu, Karla J. McDermid, Marisa M. Wall, Boon Loong Chang, Supakit Wongwiwatthananukit, Leng Chee Chang

“…Furthermore, using a cell culture model, compounds 9, 10, and 11 exhibited significant anti-inflammatory effects as indicated by their inhibition of lipopolysaccharide (LPS)-induced nitric oxide (NO) production, with IC50 values ranging from 50.2 to 60.8 µM. …”
Get full text

Parallel Jacobian Computation Based on Distance-2 Algorithm and Its Application in Coupling Problems by LIU Lixun, ZHANG Han, PENG Xinru, DOU Qinrong, WU Yingjie, GUO Jiong, LI Fu

“…The Newton-Krylov method is an effective method for solving the multi-physics coupling problem, featuring strong stability and a high-order convergence rate. …”