Lesion classification and diabetic retinopathy grading by integrating softmax and pooling operators into vision transformer by Chong Liu, Weiguang Wang, Jian Lian, Wanzhen Jiao

“…In practice, this task mainly relies on manual inspection using human visual system. …”
Get full text

Fractal Cross-Layer Service with Integration and Interaction in Internet of Things by Bing Jia, Shuai Liu, Yongjian Yang

“…Then, some of the key foundational models and algorithms are presented, such as IoT service ontology model, semantic-based IoT service description language OWL-S iot , and service management strategy both in registry mode and self-organization by subcluster. …”
Get full text

A Gaussian Process Latent Variable Model for Subspace Clustering by Shangfang Li

“…However, most of the existing GPLVMs are mainly designed for classification and regression tasks, thus cannot be used in data clustering task. …”
Get full text

Exploiter un corpus de données textuelles sans post-traitement : l’écriture burlesque de la Fronde by Karine Abiven, Jean-Baptiste Tanguy, Gaël Lejeune

“…The texts printed during the Fronde (“mazarinades”) and written in “burlesque” style are a set of documents well known to literary and historical scholars but little studied in a systematical way, mainly because they are difficult to access and turn into a corpus. …”
Get full text

L’efficacité visuelle des cartogrammes animés en question. Une piste d’amélioration à travers l’exemple de la ségrégation à Bogotá (1993-2005) by Florent Demoraes, Mégane Bouquet, Boris Mericskay

“…Over the past twenty or so years, the benefits of adding movement to this type of map–mainly to assess changes over time and space–have been discussed. …”
Get full text

Research on Random Access Technology of Inter-Frame Interference Cancellation for 6G Satellite Internet of Things by Yu XU, Qing GUO

“…In 6G, one of the important application scenarios is ultra-massive machinetype communications, which is mainly oriented to the application scenarios of concurrent access of massive terminals such as the satellite Internet of Things.How to design an access mechanism that can meet the concurrent access service requirements of large-scale users in machine communication scenarios for the future 6G satellite communication network is an important problem to be solved.A random access protocol based on intra-frame interference cancellation was proposed.In this protocol, each access user who needs to transmit data sends multiple packet copies in one frame, and the receiver can successfully receive packets from multiple users in confl icting time slots by using interference cancellation algorithms in the frame.Compared with the traditional random access mechanism, this mechanism can greatly improve the throughput performance in the scenario of multi-user concurrent access.…”
Get full text

Distinguishing Human From Machine: A Review of Advances and Challenges in AI-Generated Text Detection by Serena Fariello, Giuseppe Fenza, Flavia Forte, Mariacristina Gallo, Martina Marotta

“…This advancement offers benefits in various domains, including medicine, education, law, coding, and journalism, but also has negative implications, mainly related to ethical concerns. Preventing measures to mitigate negative implications pass through solutions that distinguish machine-generated text from humanwritten text. …”
Get full text

Adaptative Pressure Estimation and Control Architecture for Integrated Electro-Hydraulic Brake System by Zhenhai Gao, Yi Yang, Guoying Chen, Liang Yuan, Jianguang Zhou, Jie Zhang

“…The fusion strategy is mainly based on the prediction performance of two algorithms under different vehicle speeds, pressures, and ABS states. …”
Get full text

Defending CNN Against FGSM Attacks Using Beta-Based Personalized Activation Functions and Adversarial Training by Hanen Issaoui, Asma Eladel, Ahmed Zouinkhi, Mourad Zaied, Lazhar Khriji, Sarvar Hussain Nengroo

“…Machine learning algorithms based on deep neural networks have been widely used in many fields especially in computer vision, with impressive results. …”
Get full text

LIO-SAM++: A Lidar-Inertial Semantic SLAM with Association Optimization and Keyframe Selection by Bingke Shen, Wenming Xie, Xiaodong Peng, Xiaoning Qiao, Zhiyuan Guo

“…Current lidar-inertial SLAM algorithms mainly rely on the geometric features of the lidar for point cloud alignment. …”
Get full text

Daily Measurements from Cardiac Implantable Electronic Devices to Assess Health Status by Eva Roseboom, Fenna Daniëls, Michiel Rienstra, Alexander H. Maass

“…Modern CIEDs perform daily measurements, mainly aimed at discovering early signs of battery depletion or electrode dysfunction. …”
Get full text

The application of machine learning in clinical microbiology and infectious diseases by Cheng Xu, Ling-Yun Zhao, Cun-Si Ye, Ke-Chen Xu, Ke-Chen Xu, Ke-Yang Xu

“…Machine learning in the field of microbiology mainly adopts supervised learning and unsupervised learning, involving algorithms from classification and regression to clustering and dimensionality reduction. …”
Get full text

Metabolomics and lipidomics of plasma biomarkers for tuberculosis diagnostics using UHPLC-HRMS by Gaofeng Sun, Quan Wang, Xinjie Shan, Maierheba Kuerbanjiang, Ruiying Ma, Wensi Zhou, Lin Sun, Qifeng Li

“…KEGG pathway enrichment analysis showed that the differential metabolites were mainly enriched in lipid metabolism. Seven core differential metabolites were identified by the three machine learning algorithms. …”
Get full text

Enhancing face recognition in native low-resolution images using deep learning and bicubic interpolati by Ngoan Chi Le

“…This paper addresses the challenge of face recognition in Low-Resolution (LR) images, mainly when the resolution is below 48x48 pixels, which is common in surveillance systems. …”
Get full text

Detecting and Explaining Postpartum Depression in Real-Time with Generative Artificial Intelligence by Silvia García-Méndez, Francisco de Arriba-Pérez

“…Moreover, it addresses the black box problem since the predictions are described to the end users thanks to the combination of LLMS with interpretable ML models (i.e. tree-based algorithms) using feature importance and natural language. …”
Get full text

Ecological niche models as a tool for estimating the distribution of plant communities by Mayra Flores-Tolentino, Enrique Ortiz, José Luis Villaseñor

“… Ecological niche models allow inferences about the distribution of species and communities, facilitating the identification of priority areas for conservation, mainly in threatened environments such as the seasonally dry tropical forest (SDTF). …”
Get full text

Research on implementation of interventions in tuberculosis control in low- and middle-income countries: a systematic review. by Frank Cobelens, Sanne van Kampen, Eleanor Ochodo, Rifat Atun, Christian Lienhardt

“…Evaluations of diagnostic and screening algorithms were more frequent (n = 19) but geographically clustered and mainly of non-comparative design. …”
Get full text

Review of Maglev Train Dynamics Research by WEN Yanfeng, ZHANG Weifeng, CAI Wenfeng, XU Hao

“…Active suspension control algorithms and passive suspension fitting models significantly impact dynamics simulation performance. …”
Get full text

Solving Minimum Cost Three-Dimensional Localization Problem in Ocean Sensor Networks by Chao Zhang, Yingjian Liu, Zhongwen Guo, Yu Wang

“…Current localization algorithms mainly focus on how to localize as many sensors as possible given a set of mobile or static anchor nodes and distance measurements. …”
Get full text

Dense Crowd Dynamics and Pedestrian Trajectories: A Multiscale Field Dataset from the Festival of Lights in Lyon by Oscar Dufour, Huu-Tu Dang, Jakob Cordes, Raphael Korbmacher, Mohcine Chraibi, Benoit Gaudou, Alexandre Nicolas, Antoine Tordeux

“…Abstract The dynamics of dense crowds have received considerable attention from researchers seeking fundamental understanding or aiming to develop data-driven algorithms to predict pedestrian trajectories. However, current research mainly relies on data collected in controlled settings. …”
Get full text