Article
Environmental Sciences
Xu He, Shiping Ma, Linyuan He, Le Ru, Chen Wang
Summary: The paper proposes a novel multi-sector oriented object detection framework called MSO2-Det, which quantizes the scales and orientation prediction of targets in optical remote sensing images through an anchor-free classification-to-regression approach. It achieves more accurate localization information by dividing the scales and angle space into multiple discrete sectors and using a coarse-granularity classification to fine-grained regression strategy. To decrease angular-sector classification loss and accelerate network convergence, a smooth angular-sector label (SASL) and a localization-aided detection score (LADS) are designed.
Article
Geochemistry & Geophysics
Kunye Shen, Xiaofei Zhou, Bin Wan, Ran Shi, Jiyong Zhang
Summary: Salient object detection in optical remote-sensing images has gained increasing attention with the proposal of cutting-edge CNN-based models. An innovative fully squeezed multiscale module has been introduced to enhance the network, achieving a balance between computational cost and detection performance.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Environmental Sciences
Liqiong Chen, Wenxuan Shi, Dexiang Deng
Summary: Ship detection is crucial in computer vision, and improving detection speed is essential for timely ocean rescue and maritime surveillance. The proposed ImYOLOv3 based on attention mechanism achieves a balance between detection accuracy and speed by enhancing the performance of YOLOv3 and introducing a novel dilated attention module.
Article
Engineering, Biomedical
Y. Mrad, Y. Elloumi, M. Akil, M. H. Bedoui
Summary: This study presents an automated method for glaucoma screening using smartphone captured fundus images. By analyzing the vessel displacement inside the optic disk, glaucoma can be inferred. The method achieves high accuracy and robustness, making it a cost-effective and widely accessible platform for early screening of glaucoma.
Article
Engineering, Electrical & Electronic
Li Linhui, Jing Weipeng, Wang Huihui
Summary: Identifying forest types and their distribution using remote sensing imagery is crucial for forest resource monitoring and management. This study proposed a method based on GF-2 remote sensing images and other data sources that can enhance the accuracy of forest type classification.
IEEE SENSORS JOURNAL
(2021)
Article
Chemistry, Analytical
Lei Lang, Ke Xu, Qian Zhang, Dong Wang
Summary: The study introduces a lightweight object detection method for remote sensing images, achieving high-speed and high-accuracy detection through efficient channel attention layers and differential evolution algorithm. Experimental results show that the network outperforms existing lightweight models in accuracy and performs well on embedded boards.
Article
Remote Sensing
Wei Zhang, Ping Tang, Lijun Zhao
Summary: Traditional CNN methods for land-cover classification have issues with high computation cost and low efficiency, while methods based on FCN have opened up new possibilities for efficient land-cover classification.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2021)
Article
Geochemistry & Geophysics
Xueli Geng, Licheng Jiao, Lingling Li, Fang Liu, Xu Liu, Shuyuan Yang, Xiangrong Zhang
Summary: This study proposes a novel multisource remote sensing image fusion classification method called Multisource Information Bottleneck Fusion Network (MIBF-Net). Based on the information bottleneck principle, MIBF-Net effectively integrates multisource information by using mutual information constraints, generating comprehensive and nonredundant multisource representations. Experimental results demonstrate that the proposed model significantly outperforms existing methods on three heterogeneous multisource remote sensing data benchmarks.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Biochemical Research Methods
Arun Das, Michael C. Schatz
Summary: In modern sequencing experiments, accurately identifying the sources of the reads is crucial. This study investigates several sampling and sketching-based approaches for read classification. These approaches require limited preprocessing and are able to perform classification with high accuracy.
BMC BIOINFORMATICS
(2022)
Article
Geochemistry & Geophysics
Baokai Lin, Guang Yang, Qian Zhang, Guixu Zhang
Summary: In this study, a novel upsampling method based on local relations was proposed to replace traditional bilinear interpolation for semantic segmentation, improving the integration of local and global information. By using ResNet101 as the backbone network, our proposed method achieved a 2.69% increase in average F-1 score and a 1.31% increase in overall accuracy on the Vaihingen dataset, with fewer parameters and shorter inference time.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Environmental Sciences
Tianyi Xie, Wen Han, Sheng Xu
Summary: This paper proposes YOLO-RS, an optimized object detection algorithm based on YOLOv4, which improves the detection accuracy and speed by introducing the ASFF structure, optimizing the SPP structure in YOLOv4, and introducing Lightnet.
Article
Geochemistry & Geophysics
Jianqi Chen, Keyan Chen, Hao Chen, Wenyuan Li, Zhengxia Zou, Zhenwei Shi
Summary: The article introduces an asynchronous contrastive learning-based method for effective fine-grained ship classification in remote sensing images. The method, called Push-and-Pull Network (P(2)Net), separates images using a dual-branch network and aggregates them into subclasses using an integration module. Experimental results demonstrate the effectiveness of the proposed method.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Chemistry, Analytical
Boyang Wu, Jianyong Cui, Wenkai Cui, Yirong Yuan, Xiancong Ren
Summary: Researchers proposed Fast-GLNet, which enhances feature fusion and segmentation processes by incorporating the DFPA module and IFS module. Compared to GLNet, Fast-GLNet achieves a higher mIoU of 72.1% and reduces GPU memory usage from 1865 MB to 1639 MB on the Deepglobe dataset.
Article
Engineering, Electrical & Electronic
Nanqing Liu, Turgay Celik, Tingyu Zhao, Chao Zhang, Heng-Chao Li
Summary: In this article, a more accurate and faster detector named AFDet is proposed for object detection in remote sensing imagery. AFDet consists of a backbone pretrained on ImageNet and a head that includes a center prediction branch, semantic supervision branch, and boundary estimation branch, achieving state-of-the-art results on widely used optical remote sensing object detection datasets.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Yanghua Di, Zhiguo Jiang, Haopeng Zhang
Summary: The paper investigates fine-grained ship classification in remote sensing images, determines 42 common categories, and creates the FGSCR-42 dataset. Researchers collect remote sensing images containing warships and civilian ships of various scales from multiple datasets, and make the dataset publicly available for use.
Article
Multidisciplinary Sciences
Mireia Valles-Colomer, Aitor Blanco-Miguez, Paolo Manghi, Francesco Asnicar, Leonard Dubois, Davide Golzato, Federica Pinto, Fabio Cumbo, Kun D. Huang, Serena Manara, Giulia Masetti, Federica Pinto, Elisa Piperni, Michal Puncochar, Liviana Ricci, Moreno Zolfo, Olivia Farrant, Adriana Goncalves, Marta Selma-Royo, Ana G. Binetti, Jimmy E. Becerra, Bei Han, John Lusingu, John Amuasi, Loredana Amoroso, Alessia Visconti, Claire M. Steves, Mario Falchi, Michele Filosi, Adrian Tett, Anna Last, Qian Xu, Nan Qin, Huanlong Qin, Juergen May, Daniel Eibach, Maria Valeria Corrias, Mirco Ponzoni, Edoardo Pasolli, Tim D. Spector, Enrico Domenici, Maria Carmen Collado, Nicola Segata
Summary: The human microbiome is an essential part of the human body and plays a role in various health conditions. However, we still have limited understanding of the genetic differences in the microbiome between individuals and how it spreads within and across populations.
Article
Virology
Giulia Mencattelli, Andrea Silverj, Federica Iapaolo, Carla Ippoliti, Liana Teodori, Annapia Di Gennaro, Valentina Curini, Luca Candeloro, Annamaria Conte, Andrea Polci, Daniela Morelli, Maria Gabriella Perrotta, Giovanni Marini, Roberto Rosa, Federica Monaco, Nicola Segata, Annapaola Rizzoli, Omar Rota-Stabelli, Giovanni Savini
Summary: This paper provides an overview of the epidemiological and genetic features of West Nile virus (WNV) Lineage 2 (L2) in Italy. The study reveals a progressive increase in WNV L2 in Italy and predicts a wider spread in the future. The findings emphasize the importance of using quantitative models for early warning detection of WNV outbreaks.
Article
Biochemistry & Molecular Biology
Serena Manara, Marta Selma-Royo, Kun D. Huang, Francesco Asnicar, Federica Armanini, Aitor Blanco-Miguez, Fabio Cumbo, Davide Golzato, Paolo Manghi, Federica Pinto, Mireia Valles-Colomer, Loredana Amoroso, Maria Valeria Corrias, Mirco Ponzoni, Roberta Raffaeta, Raul Cabrera-Rubio, Mari Olcina, Edoardo Pasolli, Maria Carmen Collado, Nicola Segata
Summary: Findings reveal that modern westernized lifestyles have an impact on mother-infant microbiome sharing, with differences in composition and diversity observed in newborns compared to non-westernized populations.
Editorial Material
Biotechnology & Applied Microbiology
Marta Selma-Royo, Nicola Segata, Liviana Ricci
NATURE BIOTECHNOLOGY
(2023)
Article
Biotechnology & Applied Microbiology
Aitor Blanco-Miguez, Francesco Beghini, Fabio Cumbo, Lauren J. McIver, Kelsey N. Thompson, Moreno Zolfo, Paolo Manghi, Leonard Dubois, Kun D. Huang, Andrew Maltez Thomas, William A. Nickols, Gianmarco Piccinno, Elisa Piperni, Michal Puncochar, Mireia Valles-Colomer, Adrian Tett, Francesca Giordano, Richard Davies, Jonathan Wolf, Sarah E. Berry, Tim D. Spector, Eric A. Franzosa, Edoardo Pasolli, Francesco Asnicar, Curtis Huttenhower, Nicola Segata
Summary: MetaPhlAn 4 integrates information from metagenome assemblies and microbial isolate genomes for more comprehensive metagenomic taxonomic profiling.
NATURE BIOTECHNOLOGY
(2023)
Review
Biochemistry & Molecular Biology
Mireia Valles-Colomer, Cristina Menni, Sarah E. Berry, Ana M. Valdes, Tim D. Spector, Nicola Segata
Summary: Cardiometabolic diseases are closely related to the gut microbiome and diet, and high-throughput meta-omics techniques have the potential to reveal their intricate links. However, effective integration of these techniques and their application on large cohorts is still a challenge. This review discusses the potential of meta-omics technologies in improving cardiometabolic health and highlights recent large-scale efforts and insights provided.
Article
Multidisciplinary Sciences
Kihyun Lee, Sebastien Raguideau, Kimmo Siren, Francesco Asnicar, Fabio Cumbo, Falk Hildebrand, Nicola Segata, Chang-Jun Cha, Christopher Quince
Summary: The authors investigate the population-level impact of antimicrobial resistance genes (ARGs). By analyzing 8972 metagenomes and 3096 gut microbiomes from healthy individuals not taking antibiotics, they find significant correlations between the total ARG abundance and diversity and per capita antibiotic usage rates across ten countries spanning three continents. Using a collection of 154,723 human-associated metagenome assembled genomes (MAGs), they link these ARGs to microbial taxa and detect horizontal gene transfer.
NATURE COMMUNICATIONS
(2023)
Article
Cell Biology
Paolo Manghi, Aitor Blanco-Miguez, Serena Manara, Amir NabiNejad, Fabio Cumbo, Francesco Beghini, Federica Armanini, Davide Golzato, Kun D. Huang, Andrew M. Thomas, Gianmarco Piccinno, Michal Puncochar, Moreno Zolfo, Till R. Lesker, Marius Bredon, Julien Planchais, Jeremy Glodt, Mireia Valles-Colomer, Omry Koren, Edoardo Pasolli, Francesco Asnicar, Till Strowig, Harry Sokol, Nicola Segata
Summary: In this study, the researchers used MetaPhlAn 4, a metagenomic profiling method, to improve the analysis of the mouse gut microbiome. By combining multiple datasets and additional samples, they were able to identify several diet-related microbial biomarkers, including previously unknown ones.
Article
Microbiology
Marta Selma-Royo, Liviana Ricci, Davide Golzato, Charlotte Servais, Federica Armanini, Francesco Asnicar, Federica Pinto, Nicola Segata
Summary: In this study, we isolated and sequenced the genome of a strictly anaerobic bacterium belonging to a previously unidentified species in the Oscillospiraceae family. The bacterium was obtained from a fecal sample of a healthy adult human. We propose the name Neopoerus faecalis gen. nov., sp. nov.
MICROBIOLOGY RESOURCE ANNOUNCEMENTS
(2023)
Article
Nutrition & Dietetics
Kate M. M. Bermingham, Sophie Stensrud, Francesco Asnicar, Ana M. Valdes, Paul W. W. Franks, Jonathan Wolf, George Hadjigeorgiou, Richard Davies, Tim D. D. Spector, Nicola Segata, Sarah E. E. Berry, Wendy L. L. Hall
Summary: This study explores the relationship between social jetlag (SJL), gut microbial composition, diet, and cardiometabolic health. The results show a negative association between SJL and gut microbial composition, as well as unhealthy dietary habits and slight inflammation markers.
EUROPEAN JOURNAL OF NUTRITION
(2023)
Article
Multidisciplinary Sciences
Marc F. Osterdahl, Ronan Whiston, Carole H. Sudre, Francesco Asnicar, Nathan J. Cheetham, Aitor Blanco Miguez, Vicky Bowyer, Michela Antonelli, Olivia Snell, Liane dos Santos Canas, Christina Hu, Jonathan Wolf, Cristina Menni, Michael Malim, Deborah Hart, Tim Spector, Sarah Berry, Nicola Segata, Katie Doores, Sebastien Ourselin, Emma L. Duncan, Claire J. Steves
Summary: A study found that longer duration of symptoms after SARS-CoV-2 infection is associated with an atherogenic-dyslipidaemic metabolic profile, including biomarkers such as fatty acids and cholesterol. A pre-existing metabolomic biomarker score is also associated with longer illness duration.
SCIENTIFIC REPORTS
(2023)
Article
Gastroenterology & Hepatology
Yiqing Wang, Wenjie Ma, Raaj Mehta, Long H. Nguyen, Mingyang Song, David A. Drew, Francesco Asnicar, Curtis Huttenhower, Nicola Segata, Jonathan Wolf, Tim Spector, Sarah Berry, Kyle Staller, Andrew T. Chan
Summary: This study investigated the interaction between diet and gut microbiota in different subtypes of irritable bowel syndrome (IBS). The results showed that individuals with IBS-D consumed more healthy plant-based foods and fiber, while those with IBS-C tended to consume more unhealthy plant-based foods. Microbial diversity was lower in IBS-D patients, and specific variations in microbiota were found in different IBS subtypes.
Article
Dermatology
Serena Manara, Francesco Beghini, Giulia Masetti, Federica Armanini, Davide Geat, Giulia Galligioni, Nicola Segata, Stefania Farina, Mario Cristofolini
Summary: This study investigated the effects of thermal treatments on the skin and gut microbiome of patients with psoriasis. The results showed that thermal treatment improved the microbiome composition of affected skin areas, making it similar to that of healthy skin. Additionally, drinking thermal water was found to affect the gut microbiome, promoting the presence of species associated with favorable metabolic health.
DERMATOLOGY AND THERAPY
(2023)
Review
Microbiology
Francesco Asnicar, Andrew Maltez Thomas, Andrea Passerini, Levi Waldron, Nicola Segata
Summary: This article reviews the importance and applications of machine learning in microbiology, including tasks such as predicting antibiotic resistance and associating with host diseases. It provides a basic toolbox for microbiologists to understand and apply machine learning.
NATURE REVIEWS MICROBIOLOGY
(2023)
Meeting Abstract
Biotechnology & Applied Microbiology
Laura Pezze, Matteo Ciciani, Sally Bertolini, Kalina Badowska, Eleonora Pedrazzoli, Elisabetta Visentin, Michele Demozzi, Nicola Segata, Anna Cereseto, Antonio Casini