Wearable Sensor-Based Behavioral User Authentication Using a Hybrid Deep Learning Approach with Squeeze-and-Excitation Mechanism by Sakorn Mekruksavanich, Anuchit Jitpattanakul

“…The suggested network design integrates convolutional neural networks for spatial feature extraction, while the SE blocks improve feature identification by flexibly recalibrating channel-wise feature responses. …”
Get full text

Cells Grouping Detection and Confusing Labels Correction on Cervical Pathology Images by Wenbo Pang, Yi Ma, Huiyan Jiang, Qiming Yu

“…To address this issue, we perform a labels correction module with feature similarity by constructing feature centers for typical cells in each category. …”
Get full text

Single-nucleus RNA sequencing reveals the specific molecular signatures of myeloid cells responding to brain injury after microglial replacement by Xiao-Yi Xiong, Xiao-Yi Xiong, Xiao-Yi Xiong, Haicheng Yuan, Ying Mu, Yi He, Fang Xie, Xiao-Shuang Feng, Jia-Xin Xie, Xin-Ru Pan, Yu-Fei Wang, Jian Gong, Xiaoming Zheng, Peng-Fei Wang

“…Aged microglial replacement is protective against brain injury in aged mice; however, whether/how the molecular changes in myeloid cells are affected by this replacement in injured brains remains unclear.MethodsAged microglia in mice were eliminated by PLX3397 for 21 consecutive days and repopulated following withdrawal for 21 days; then, intracerebral hemorrhage (ICH) models were constructed. Then, a single-nucleus transcriptomic analysis of acutely injured brains in aged mice with microglial replacement was performed.ResultsWe observed similarities but strong divergence in the composition and molecular change features of myeloid cells between the replacement (Rep) and control (Con) groups, indicating retention of the core transcriptome and development of differential genes in myeloid cells after microglial replacement in response to brain injury. …”
Get full text

A Multi-Class Intrusion Detection System for DDoS Attacks in IoT Networks Using Deep Learning and Transformers by Sheikh Abdul Wahab, Saira Sultana, Noshina Tariq, Maleeha Mujahid, Javed Ali Khan, Alexios Mylonas

“…In three-class classification (benign, DDoS, and non-DDoS), all models attained near-perfect performance (approximately 99.9–100%). …”
Get full text

Knockdown of eIF3a alleviates pulmonary arterial hypertension by inhibiting endothelial-to-mesenchymal transition via TGFβ1/SMAD pathway by Qiuhong Jiao, Xiufeng Xu, Longwu Xu, Yuying Wang, Shulan Pang, Jie Hao, Xiaohong Liu, Yudan Zhao, Wanpeng Qi, Limin Qin, Tao Huang, Jingtian Li, Tao Wang

“…The eIF3a-knockdown rat model was constructed by adeno-associated virus type-1 (AAV1) infection, PAH was evaluated according to hemodynamic alteration, right heart hypertrophy and histopathological changes in the lung tissue. …”
Get full text

Recent advances in machine learning for defects detection and prediction in laser cladding process by X.C. Ji, R.S. Chen, C.X. Lu, J. Zhou, M.Q. Zhang, T. Zhang, H.L. Yu, Y.L. Yin, P.J. Shi, W. Zhang

“…Additionally, it synthesizes advancements in machine learning methodologies for signal feature extraction, defect classification, and predictive modeling within the laser cladding process. …”
Get full text

Longitudinal multi-omics analysis of convalescent individuals with respiratory sequelae 6–36 months after COVID-19 by Huqin Yang, Lujia Guan, Yi Xue, Xuyan Li, Leyi Gao, Zhijin Zhang, Haifan Zhang, Haomiao Ma, Fengjiao Liu, Xuan Huang, Zhaohui Tong, Jieqiong Li

“…Pulmonary and molecular abnormalities persisted for 3 years in COVID-19 convalescents; impaired diffusing capacity for carbon monoxide (DLco) was the most prominent feature. We used this multi-omics profile to develop a model involving one protein (heterogeneous nuclear ribonucleoprotein K (HNRNPK)) and two metabolites (arachidonoyl-EA and 1-O-(2r-hydroxy-pentadecyl)-sn-glycerol)) for identification of COVID-19 convalescents with abnormal DLco. …”
Get full text

A mini review on AI-driven thermal treatment of solid waste: Emission control and process optimization by Dongjie Pang, Cristina Moliner, Tao Wang, Jin Sun, Xinyan Zhang, Yingping Pang, Xiqiang Zhao, Zhanlong Song, Ziliang Wang, Yanpeng Mao, Wenlong Wang

“…The application of machine learning models, including linear regression (LR), genetic algorithm (GA), support vector machine (SVM), artificial neural networks (ANN), decision trees (DT), and Extreme Gradient Boosting (XGBoost), enables real-time monitoring of performance and dynamic adjustment of parameters to enhance energy recovery and minimize pollution. …”
Get full text

Comparative analysis of machine learning algorithms for predicting depression among individuals with diabetes by Hind Bourkhime, Noura Qarmiche, Soumaya Benmaamar, Nada Lazar, Mohammed Omari, Mohamed Berraho, Nabil Tachfouti, Samira El Fakir, Hanan El Ouahabi, Nada Otmani

“…The study utilizes a dataset from Morocco, specifically curated for this purpose, and employs the Synthetic Minority Over-sampling Technique (SMOTE) to balance the dataset. Feature selection is performed using ExtraTreesClassifier, while hyperparameter tuning is accomplished through a grid search approach. …”
Get full text

Exploration of machine learning approaches for automated crop disease detection by Annu Singla, Ashima Nehra, Kamaldeep Joshi, Ajit Kumar, Narendra Tuteja, Rajeev K. Varshney, Sarvajeet Singh Gill, Ritu Gill

“…The review discusses the proposed models, techniques, accuracy, feature selection, extraction methods, the types of datasets used to perform experiments, and the sources of the datasets. …”
Get full text

A Human Tracking System for the Rocker-Bogie Mobile Robot Utilizing the YOLOv8 Network by Huy Anh Bui, Thi Thoa Mac, Xuan Thuan Nguyen

“…The stability and obstacle-climbing capability of this model are evaluated as suitable choices for mobile robots. …”
Get full text

The burden of rare cancers among adults in the Canton of Geneva, Switzerland, from 2011 to 2020 by Nathalie Bot, Evelyne Fournier, Marie-Laure Amram, Laura Botta, Alice Bernasconi, Elisabetta Rapiti

“…Survival differences between rare and common cancers were assessed using log-rank tests and Cox proportional hazards models adjusted for age and gender. Statistical analyses were performed using STATA software.ResultsBetween 2011 and 2020, 31,233 invasive cancers were diagnosed in adults in Geneva, of which 4,296 cases (13.75%) were classified as rare based on aforementioned thresholds. …”
Get full text

Pattern of changes in morpho-densitometric parameters of magnocellular neurons of the hypothalamic paraventricular nucleus under restraint stress of different duration by K. B. Romanova, O. V. Hancheva, Yu. M. Kolesnyk

“…Chronic stress condition modelled in rats for 6, 15, and 21 weeks (limited living space, inactivity, and complicated communications) resulted in a decrease in the area of cytoplasm and nuclei of magnocellular neurons of the hypothalamic PVN. …”
Get full text

Significant associations between high-risk sexual behaviors and enterotypes of gut microbiome in HIV-negative men who have sex with men by Kangjie Li, Xinjing Liu, Xiaohua Zhong, Haijiao Zeng, Tian Liu, Bing Lin, Pinyi Chen, Biao Xie, Xiaoni Zhong

“…A three-category random forest machine learning model was performed to further examine the correlation between abundant microbiome in each enterotype cluster and anal sex roles. …”
Get full text

A narrative review of nosology and the concept of schizophrenia: criticism and proposal by Ricardo Abreu Feijo de Mello, Ary Gadelha, Larissa Leal Freitas, Vitoria Fernandes Sant’Ana, Marcelo Feijó Mello

“…The central proposition was to adopt psychotic syndrome as a core feature instead of the current concept of schizophrenia. …”
Get full text

Leveraging Machine Learning Regression Algorithms to Predict Mechanical Properties of Evaporitic Rocks From Their Physical Attributes by Ayham Zaitouny, Hasan Arman, Anusuya Krishnan, Alaa Ahmed, Ahmed Gad

“…Nonlinear correlations demonstrated strong relationships between the mechanical properties and physical attributes, such as saturated density (s) and natural unit weight (n). After feature selection, random forest and XGBoost outperformed the other models with exceptional accuracy for UCS prediction (R<inline-formula> <tex-math notation="LaTeX">${}^{2} =0.95$ </tex-math></inline-formula>) and robust performance for ITS (R<inline-formula> <tex-math notation="LaTeX">${}^{2} =0.84$ </tex-math></inline-formula>) and SHV (R<inline-formula> <tex-math notation="LaTeX">${}^{2} =0.77$ </tex-math></inline-formula>). …”
Get full text

Gender Differences of Final Height Contributed by Parents’ Height Among Healthy Individuals by Pen-Hua Su, Shu-Li Wang, Jia-Yuh Chen

“…The current study was performed to characterize the feature of offsprings’ final heights by their parents’ heights by gender in Taiwan. …”
Get full text

The fate of artificial transgenes in Acanthamoeba castellanii by Morgan J. Colp, Cédric Blais, Bruce A. Curtis, John M. Archibald

“…Abstract Background The soil amoeba Acanthamoeba castellanii is an emerging model organism with which to study a wide range of biomedical, microbiological, and evolutionary phenomena. …”
Get full text

Damage Identification of a Derrick Steel Structure Based on the HHT Marginal Spectrum Amplitude Curvature Difference by Dongying Han, Shimin Wei, Peiming Shi, Ying Zhang, Kai Gao, Nengyuan Tian

“…Based on the technology of signal feature extraction, only using the low-order vibration information, taking the right front leg as an example, we analyzed the selection of HHT marginal spectrum amplitude and the calculation process of its curvature in practical application, designed the damage conditions of a derrick steel structure, used the index and intrinsic mode function (IMF) instantaneous energy curvature method to perform the damage simulation calculation and comparison, and verified the effect of identifying the damage location in a noisy environment. …”
Get full text

MPCNet: Improved MeshSegNet Based on Position Encoding and Channel Attention by Hanqing Hu, Zhengxun Li, Weichao Gao

“…Due to the limited variety of existing models, they are not well suited for different 3D segmentation scenarios, and the feature extraction capability and segmentation effect of these models still need to be improved. …”
Get full text