Rethinking composite quantification by capturing biological and ecological diversity across multiple dimensions by Ioan Sîrbu, Ana-Maria Benedek, Monica Sîrbu

“…We defined and measured overall biodiversity by integrating taxonomic, functional, genetic-, and niche-based diversity, lambda diversity, which expresses the cumulative sequential differences in communities along a gradient, and xi ecological integrative diversity combining community, spatial, and environmental heterogeneity. …”
Get full text

A hybrid framework of generative deep learning for antiviral peptide discovery by Huynh Anh Duy, Tarapong Srisongkram

“…The performance of the WGAN-GP model was comprehensively evaluated, confirming its ability to produce diverse and functional peptide sequences. The model successfully generated and identified 815 novel AVPs, demonstrating its effectiveness in peptide generation and classification. …”
Get full text

An Efficient Explainability of Deep Models on Medical Images by Salim Khiat, Sidi Ahmed Mahmoudi, Sédrick Stassin, Lillia Boukerroui, Besma Senaï, Saïd Mahmoudi

“…Then, the visual explainability methods (GradCAM, LIME, Vanilla Gradient, Gradient Integrated Gradient and SmoothGrad) are performed to understand and explain the decisions made by these models. …”
Get full text

Physiological and molecular responses of juvenile silver crucian carp (Carassius gibelio) to long-term high alkaline stress: Growth performance, histopathology, and transcriptomic... by Kemeng Jiang, Wenqian Wang, Jianlin Li, Wenrong Feng, Ezra Martini Kamunga, Zhihua Zhang, Yongkai Tang

“…Meanwhile, histopathology of the gills showed structural changes, indicating that the physiological functions of juvenile silver crucian carp were impaired under alkaline conditions. …”
Get full text

Combining rapid evaporative ionization mass spectrometry and chemometrics for the differentiation of cocoa bean quality by Julie Lestang, Susanne Miescher Schwenninger, Laura Nyström

“…Further analysis of the six classification models demonstrated the strong performance of gradient boosting machines, random forests, and neural networks in differentiating metabolite fingerprints based on the functionality of microbial co-cultures, with accuracy estimates of 85 %, 84 %, and 81 %, respectively. …”
Get full text

Host species and temperature drive beech and Scots pine phyllosphere microbiota across European forests by Daniela Sangiorgio, Joan Cáliz, Stefania Mattana, Anna Barceló, Bruno De Cinti, David Elustondo, Sofie Hellsten, Federico Magnani, Giorgio Matteucci, Päivi Merilä, Manuel Nicolas, Dario Ravaioli, Anne Thimonier, Elena Vanguelova, Arne Verstraeten, Peter Waldner, Emilio O. Casamayor, Josep Peñuelas, Maurizio Mencuccini, Rossella Guerrieri

“…We characterized taxonomical and functional composition of epiphytic bacteria in the phyllosphere of beech and Scots pine across an environmental gradient from Fennoscandia to the Mediterranean area, with major changes in temperature and nitrogen deposition. …”
Get full text

Enhanced rotator cuff tendon-bone interface regeneration with injectable manganese-based mesoporous silica nanoparticle-loaded dual crosslinked hydrogels by Zihang Chen, Youjie Liu, Tianxiang Liang, Zhaoyuan Du, Liming Deng, Zhiwen Wu, Ye Li, Haobo Zhong, JinJin Ma, Riwang Li, Huajun Wang, Qiu Dong, Tao Yu, Xiaofei Zheng

“…IntroductionDuring the healing process, the functional gradient attachment of the rotator cuff (RC) tendon-bone interface fails to regenerate, which severely impedes load transfer and stress dissipation, thereby increasing the risk of retears. …”
Get full text

Benthic Community Metrics Track Hydrologically Stressed Mangrove Systems by Amanda W. J. Demopoulos, Jill R. Bourque, Jennifer P. McClain-Counts, Nicole Cormier, Ken W. Krauss

“…Our results suggest that stable isotope niche metrics provide a useful tool for tracking mangrove degradation gradients. These baseline data provide critical information on the ecosystem functioning in mangrove habitats following hydrological restoration.…”
Get full text

Establishing a novel model to assess exercise capacity in chronic heart failure based on stress echocardiography by Huan Cen, Sinan Chen, Shen Feng, Xiankun Chen, Huiying Zhu, Wei Jiang, Han Zhang, Hongmei Liu, Bo Liu, Weihui Lu, Pengtao Sun

“…The analytical features of all patients in the four phases (rest, warm‐up, peak and recovery phases) of ESE included the following parameters: left ventricular (LV) systolic function, LV systolic function reserve, LV diastolic function, LV diastolic function reserve and right ventricular function. …”
Get full text

Flow Topology of Three-Dimensional Spherical Flame in Shock Accelerated Flows by Yuejin Zhu, Lei Yu, Gang Dong, Jianfeng Pan, Zhenhua Pan

“…And the joint probability density function (p.d.f.) of the Q-R diagram appears as a teardrop shape, which is a universal feature of turbulence. …”
Get full text

A Physics‐Informed Neural Network as a Digital Twin of Optically Turbid Media by Mohammadrahim Kazemzadeh, Liam Collard, Linda Piscopo, Massimo De Vittorio, Ferruccio Pisanello

“…Unlike previous approaches utilizing various deep neural network architectures that often function as black boxes, the method prioritizes interpretability, offering a clearer understanding of the underlying processes of light propagation through turbid media and estimating the transmission matrix. …”
Get full text

Facial Expression Recognition with Multi-perspective Feature Fusion Under Deep Residual Convolution by GUAN Xiaorui, GAO Lu, SONG Wenbo, LIN Kezheng

“…Then use the RReLu activation function to replace the original ReLu to avoid deactivation of some nodes when the gradient is large.Finally, the global average pooling layer is used instead of the fully connected layer to achieve dimensionality reduction, and the generated feature vector is sent to Softmax for classification Experiments show that the proposed method produces excellent results on the CK+ and RaFD datasets, which can effectively improve the accuracy of facial expression recognition.…”
Get full text

Machine learning algorithms can predict emotional valence across ungulate vocalizations by Romain A. Lefèvre, Ciara C.R. Sypherd, Élodie F. Briefer

“…Summary: Vocalizations can vary as a function of their context of production and provide an immediate measure of an animal’s affective states. …”
Get full text

Vehicle Lateral Control Based on Augmented Lagrangian DDPG Algorithm by Zhi Li, Meng Wang, Haitao Zhao

“…The actor-critic neural network based reinforcement learning framework is established and the environment of reinforcement learning is designed to include the vehicle model, tracking model, road model and reward function. Secondly, the augmented Lagrangian Deep Deterministic Policy Gradient (DDPG) method is proposed for updating, in which a replay separation buffer method is used to solve the problem of sample correlation, and a neural network with the same structure is copied to solve the update divergence problem. …”
Get full text

The role of land use in terrestrial support of boreal lake food webs by Ossi Keva, Matthew R. D. Cobain, Antti P. Eloranta, Heikki Hämäläinen, Mikko Kiljunen, Jos Schilder, Roger I. Jones

“…Our results demonstrate how cross-ecosystem transfer of organic matter can influence community dynamics in recipient ecosystems, with anthropogenic management of donor terrestrial ecosystems affecting the structure and function of food webs in recipient aquatic ecosystems.…”
Get full text

A model for shale gas well production prediction based on improved artificial neural network by LIN Hun, SUN Xinyi, SONG Xixiang, MENG Chun, XIONG Wenxin, HUANG Junhe, LIU Hongbo, LIU Cheng

“…To address these challenges, a novel approach is introduced, involving the construction of characteristic parameters based on physical meaning and random combination. The small batch gradient descent method（MBGD） is adopted as the training function to develop an improved artificial neural network prediction model for shale gas well production. …”
Get full text

Multitarget Tracking of Pedestrians in Video Sequences Based on Particle Filters by Hui Li, Shengwu Xiong, Pengfei Duan, Xiangzhen Kong

“…During the process of tracking, the algorithm uses the similarity between candidates and codebooks as observation likelihood function and processes severe occlusion condition to prevent drift and loss phenomenon caused by target occlusion. …”
Get full text

A machine learning framework for predictive electron density modelling to enhance 3D NAND flash memory performance by Dikendra Verma, Upendra Mohan Bhatt, Anurag Vidyarthi

“…The dataset, which was derived using TCAD simulations, has a sizable number of samples that show the electron density as a function of channel length. We assess their performance using R2 scores and RMSE values using regression models such as Linear Regression, Random Forest, K-Neighbour Regressor, Decision Tree, Gradient Boosting, XGBRegressor, CatBoosting Regressor, and AdaBoost Regressor. …”
Get full text

An Improved CO2-Crude Oil Minimum Miscibility Pressure Correlation by Hao Zhang, Dali Hou, Kai Li

“…On the basis of 210 groups of CO2-crude oil system minimum miscibility pressure data, an improved CO2-crude oil system minimum miscibility pressure correlation was built by modified conjugate gradient method and global optimizing method. The new correlation is a uniform empirical correlation to calculate the MMP for both thin oil and heavy oil and is expressed as a function of reservoir temperature, C7+ molecular weight of crude oil, and mole fractions of volatile components (CH4 and N2) and intermediate components (CO2, H2S, and C2~C6) of crude oil. …”
Get full text

Pressure Performance Analysis of Inclined Well under Multiple-Well Interference in Offshore Heavy Oil Reservoir by Kuiqian Ma, Gongchang Wang, Yue Gao, Meinan Wang, Jianguo Liu

“…In this paper, the threshold pressure gradient of heavy oil and the stress sensitive to permeability are considered comprehensively, and a well test model of inclined wells in dual-media reservoirs under multiwell interference is established. …”
Get full text