Automatic detection, identification and counting of deep-water snappers on underwater baited video using deep learning by Florian Baletaud, Florian Baletaud, Florian Baletaud, Sébastien Villon, Antoine Gilbert, Jean-Marie Côme, Sylvie Fiat, Corina Iovan, Laurent Vigliola

“…Videos were collected in New Caledonia (South Pacific) at depths ranging from 47 to 552 m. Using a dataset of 12,100 annotations from 11 deep-water snapper species observed in 6,364 images, we obtained good model performance for the 6 species with sufficient annotations (F-measures >0.7, up to 0.87). …”
Get full text

Individualized resting-state functional connectivity abnormalities unveil two major depressive disorder subtypes with contrasting abnormal patterns of abnormality by Keke Fang, Lianjie Niu, Baohong Wen, Liang Liu, Ya Tian, Huiting Yang, Ying Hou, Shaoqiang Han, Xianfu Sun, Wenzhou Zhang

“…In this study, we sought to identify potential MDD subtypes from subject-level abnormalities in functional connectivity, leveraging a large multi-site dataset of resting-state MRI from 1276 MDD patients and 1104 matched healthy controls. …”
Get full text

Ethnic inequalities in mental and physical multimorbidity in women of reproductive age: a data linkage cohort study by Amelia Jewell, Matthew Broadbent, Stephani Hatch, Mark Ashworth, Megan Pritchard, Sarah Dorrington, Louise Howard, Raquel Catalao

“…Objectives Explore inequalities in risk factors, mental and physical health morbidity in non-pregnant women of reproductive age in contact with mental health services and how these vary per ethnicity.Design Retrospective cohort study.Setting Data from Lambeth DataNet, anonymised primary care records of this ethnically diverse London borough, linked to anonymised electronic mental health records (‘CRIS secondary care database’).Participants Women aged 15–40 years with an episode of secondary mental health care between January 2008 and December 2018 and no antenatal or postnatal Read codes (n=3817) and a 4:1 age-matched comparison cohort (n=14 532).Main outcome measures Preconception risk factors including low/high body mass index, smoking, alcohol, substance misuse, micronutrient deficiencies and physical diagnoses.Results Women in contact with mental health services (whether with or without severe mental illness (SMI)) had a higher prevalence of all risk factors and physical health diagnoses studied. …”
Get full text

Shear Wave Velocity Prediction with Hyperparameter Optimization by Gebrail Bekdaş, Yaren Aydın, Umit Işıkdağ, Sinan Melih Nigdeli, Dara Hajebi, Tae-Hyung Kim, Zong Woo Geem

“…This dataset was extracted, and a 494-line dataset was created. …”
Get full text

Enhancing pediatric congenital heart disease detection using customized 1D CNN algorithm and phonocardiogram signals by Ihtisham Ul Haq, Ghassan Husnain, Yazeed Yasin Ghadi, Nisreen Innab, Masoud Alajmi, Hanan Aljuaid

“…The model was trained on a composite dataset consisting of local pediatric PCG signals and publicly accessible dataset. …”
Get full text

Data on hydrodynamic flow and aspiration mechanisms in a patient-specific pharyngolaryngeal model with variable epiglottis anglesMendeley Data by Amr Seifelnasr, Chen Sun, Peng Ding, Xiuhua April Si, Jinxiang Xi

“…This dataset comprises a comprehensive collection of videos and images illustrating the fluid dynamics of swallowing and aspiration in a patient-specific pharyngolaryngeal model with varying epiglottis angles. …”
Get full text

Sequencing of game complexes in women’s volleyball: are there differences according to the set played? by Pedro Henrique Cavalcante Vieira, Lorenzo Laporta, Gustavo Ferreira Pedrosa, Augusto Faria de Paula Santana, Auro Barreiros Freire, Crislaine Couto Rangel, Claudio Andre Barbosa de Lira, Filipe Manuel Clemente, Thiago José Leonardi, Gustavo De Conti Teixeira Costa

Get full text

Rapid Detection of Astaxanthin in Antarctic Krill Meal by Computer Vision Combined with Convolutional Neural Network by Quantong ZHANG, Yao ZHENG, Liu YANG, Shuaishuai ZHANG, Quanyou GUO

“…The optimal parameter model was evaluated by randomly dividing the dataset, and 30 images from the dataset were randomly selected for model validation. …”
Get full text

Dual-hybrid intrusion detection system to detect False Data Injection in smart grids. by Saad Hammood Mohammed, Mandeep S Jit Singh, Abdulmajeed Al-Jumaily, Mohammad Tariqul Islam, Md Shabiul Islam, Abdulmajeed M Alenezi, Mohamed S Soliman

“…Additionally, the IDS employs a hybrid deep learning classifier that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to capture the smart grid data's spatial and temporal features. The dataset used for evaluation, the Industrial Control System (ICS) Cyber Attack Dataset (Power System Dataset) consists of various FDIA scenarios simulated in a smart grid environment. …”
Get full text

A Deep Learning-Based Approach for Two-Phase Flow Pattern Classification Using Void Fraction Time Series Analysis by Jefferson Dos Santos Ambrosio, Marco Jose da Silva, Andre Eugenio Lazzaretti

“…We also present the generalization analysis of the models with cross-dataset experiments, training the model with one dataset and testing it with another dataset collected in another system for two datasets: HZDR (from the Helmholtz-Zentrum Dresden-Rossendorf research laboratory) and TUD (from Technische Universität Dresden). …”
Get full text

Costs and Outcomes of Clostridioides difficile Infections in Germany: A Retrospective Health Claims Data Analysis by Katharina Schley, Kirstin Heinrich, Jennifer C. Moïsi, Dennis Häckl, Dominik Obermüller, Gordon Brestrich, Christof von Eiff, Thomas Weinke

Get full text

Impact of a multiple oversampling technique-based assessment framework on shallow rockburst prediction models by Guozhu Rao, Guozhu Rao, Yunzhang Rao, Yunzhang Rao, Yangjun Xie, Qiang Huang, Jiazheng Wan, Jiyong Zhang

“…Initially, genuine rockburst incidents within a burial depth of 500 m were sourced from literature, revealing a small dataset imbalance issue. Utilizing various mainstream oversampling techniques, the dataset was expanded to generate six new datasets, subsequently subjected to 12 classifiers across 84 classification processes. …”
Get full text

Delayed Postoperative Ambulation Results in a Significant Increase in 90-Day Mortality in Surgically Treated Hip Fractures by Robert S. Wood DO, Maddie Vergun BS, Elizabeth Herrera MPH, Jacqueline Krumrey MD

Get full text

Effects of Dispersal for a Logistic Growth Population in Random Environments by Xiaoling Zou, Dejun Fan, Ke Wang

Get full text

45 years of directional wave recorded data at the Acqua Alta oceanographic tower by Luigi Cavaleri, Angela Pomaro, Luciana Bertotti, Andrea Bonometto, Luca De Nat, Alvise Papa, Valerio Volpe

“…Abstract The dataset comprises a 45-year-long directional wave time series recorded at the Acqua Alta Oceanographic research Tower (AAOT) since 1979. …”
Get full text

A Multidisciplinary Investigation to Determine the Structure and Source of Dimeric Impurities in AMG 517 Drug Substance by Maria Victoria Silva Elipe, Zhixin Jessica Tan, Michael Ronk, Tracy Bostick

Get full text

ResNet15: Weather Recognition on Traffic Road with Deep Convolutional Neural Network by Jingming Xia, Dawei Xuan, Ling Tan, Luping Xing

“…In addition, we build a medium-scale dataset of weather images on traffic road, called “WeatherDataset-4,” which consists of 4 categories and contains 4983 weather images covering most of the severe weather. …”
Get full text

The Influence of Domestic Players on the Success in National and International Competitions in Football by Michal Varmus, Pavol Boško, Roman Adámik, Dominika Toman, Zakaria Elkhwesky

Get full text

DR_PVNet: An Improved PVNet Network for Weakly Textured Object Pose Estimation in Indoor Complex Environments by Mengru Niu, Changyong Li

“…The 2D projection metric reached 94.95%, and the ADD(-S) metric reached 91.65 % for the self-made dataset.…”
Get full text

Metaphor recognition based on cross-modal multi-level information fusion by Qimeng Yang, Yuanbo Yan, Xiaoyu He, Shisong Guo

“…We conducted many experiments on the Met-Meme dataset. Compared with the strong baseline model in the experiment, the weighted F1 of our model on three data types of the MET-Meme dataset improved by 1.95%, 1.55%, and 1.72%, respectively. …”
Get full text