LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 385

Search options

  1. Article ; Online: SMOTE-CD: SMOTE for compositional data.

    Nguyen, Teo / Mengersen, Kerrie / Sous, Damien / Liquet, Benoit

    PloS one

    2023  Volume 18, Issue 6, Page(s) e0287705

    Abstract: Compositional data are a special kind of data, represented as a proportion carrying relative information. Although this type of data is widely spread, no solution exists to deal with the cases where the classes are not well balanced. After describing ... ...

    Abstract Compositional data are a special kind of data, represented as a proportion carrying relative information. Although this type of data is widely spread, no solution exists to deal with the cases where the classes are not well balanced. After describing compositional data imbalance, this paper proposes an adaptation of the original Synthetic Minority Oversampling TEchnique (SMOTE) to deal with compositional data imbalance. The new approach, called SMOTE for Compositional Data (SMOTE-CD), generates synthetic examples by computing a linear combination of selected existing data points, using compositional data operations. The performance of the SMOTE-CD is tested with three different regressors (Gradient Boosting tree, Neural Networks, Dirichlet regressor) applied to two real datasets and to synthetic generated data, and the performance is evaluated using accuracy, cross-entropy, F1-score, R2 score and RMSE. The results show improvements across all metrics, but the impact of oversampling on performance varies depending on the model and the data. In some cases, oversampling may lead to a decrease in performance for the majority class. However, for the real data, the best performance across all models is achieved when oversampling is used. Notably, the F1-score is consistently increased with oversampling. Unlike the original technique, the performance is not improved when combining oversampling of the minority classes and undersampling of the majority class. The Python package smote-cd implements the method and is available online.
    MeSH term(s) Acclimatization ; Benchmarking ; Entropy ; Minority Groups ; Neural Networks, Computer
    Language English
    Publishing date 2023-06-29
    Publishing country United States
    Document type Journal Article ; Research Support, Non-U.S. Gov't
    ZDB-ID 2267670-3
    ISSN 1932-6203 ; 1932-6203
    ISSN (online) 1932-6203
    ISSN 1932-6203
    DOI 10.1371/journal.pone.0287705
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  2. Article ; Online: SMOTE-CD

    Teo Nguyen / Kerrie Mengersen / Damien Sous / Benoit Liquet

    PLoS ONE, Vol 18, Iss 6, p e

    SMOTE for compositional data.

    2023  Volume 0287705

    Abstract: Compositional data are a special kind of data, represented as a proportion carrying relative information. Although this type of data is widely spread, no solution exists to deal with the cases where the classes are not well balanced. After describing ... ...

    Abstract Compositional data are a special kind of data, represented as a proportion carrying relative information. Although this type of data is widely spread, no solution exists to deal with the cases where the classes are not well balanced. After describing compositional data imbalance, this paper proposes an adaptation of the original Synthetic Minority Oversampling TEchnique (SMOTE) to deal with compositional data imbalance. The new approach, called SMOTE for Compositional Data (SMOTE-CD), generates synthetic examples by computing a linear combination of selected existing data points, using compositional data operations. The performance of the SMOTE-CD is tested with three different regressors (Gradient Boosting tree, Neural Networks, Dirichlet regressor) applied to two real datasets and to synthetic generated data, and the performance is evaluated using accuracy, cross-entropy, F1-score, R2 score and RMSE. The results show improvements across all metrics, but the impact of oversampling on performance varies depending on the model and the data. In some cases, oversampling may lead to a decrease in performance for the majority class. However, for the real data, the best performance across all models is achieved when oversampling is used. Notably, the F1-score is consistently increased with oversampling. Unlike the original technique, the performance is not improved when combining oversampling of the minority classes and undersampling of the majority class. The Python package smote-cd implements the method and is available online.
    Keywords Medicine ; R ; Science ; Q
    Subject code 780
    Language English
    Publishing date 2023-01-01T00:00:00Z
    Publisher Public Library of Science (PLoS)
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  3. Article ; Online: "The flying thymus sign".

    Nguyen, Damien / Nguyen, Thomas / Castro Rodriguez, José

    Internal and emergency medicine

    2021  Volume 16, Issue 6, Page(s) 1701–1702

    MeSH term(s) Adolescent ; Chest Pain/etiology ; Humans ; Male ; Mediastinal Emphysema/diagnosis ; Mediastinal Emphysema/diagnostic imaging ; Radiography/methods ; Thymus Gland/abnormalities ; Thymus Gland/diagnostic imaging
    Language English
    Publishing date 2021-01-16
    Publishing country Italy
    Document type Case Reports ; Journal Article
    ZDB-ID 2454173-4
    ISSN 1970-9366 ; 1828-0447
    ISSN (online) 1970-9366
    ISSN 1828-0447
    DOI 10.1007/s11739-020-02626-3
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  4. Article ; Online: Brockenbrough-Braunwald-Morrow sign and Valsalva manoeuvre: how to unmask dynamic left ventricular outflow tract obstruction.

    Mabalukwa, Junior / Nguyen, Damien / Briki, Rachid / Audiat, Charles / Unger, Philippe

    European heart journal. Cardiovascular Imaging

    2022  Volume 23, Issue 4, Page(s) e169

    MeSH term(s) Cardiomyopathy, Hypertrophic ; Heart Defects, Congenital ; Humans ; Valsalva Maneuver ; Ventricular Dysfunction, Left ; Ventricular Outflow Obstruction/diagnostic imaging ; Ventricular Outflow Obstruction/etiology
    Language English
    Publishing date 2022-01-20
    Publishing country England
    Document type Journal Article
    ZDB-ID 2638345-7
    ISSN 2047-2412 ; 2047-2404
    ISSN (online) 2047-2412
    ISSN 2047-2404
    DOI 10.1093/ehjci/jeac008
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  5. Article ; Online: A Smart Home Digital Twin to Support the Recognition of Activities of Daily Living.

    Bouchabou, Damien / Grosset, Juliette / Nguyen, Sao Mai / Lohr, Christophe / Puig, Xavier

    Sensors (Basel, Switzerland)

    2023  Volume 23, Issue 17

    Abstract: One of the challenges in the field of human activity recognition in smart homes based on IoT sensors is the variability in the recorded data. This variability arises from differences in home configurations, sensor network setups, and the number and ... ...

    Abstract One of the challenges in the field of human activity recognition in smart homes based on IoT sensors is the variability in the recorded data. This variability arises from differences in home configurations, sensor network setups, and the number and habits of inhabitants, resulting in a lack of data that accurately represent the application environment. Although simulators have been proposed in the literature to generate data, they fail to bridge the gap between training and field data or produce diverse datasets. In this article, we propose a solution to address this issue by leveraging the concept of digital twins to reduce the disparity between training and real-world data and generate more varied datasets. We introduce the Virtual Smart Home, a simulator specifically designed for modeling daily life activities in smart homes, which is adapted from the Virtual Home simulator. To assess its realism, we compare a set of activity data recorded in a real-life smart apartment with its replication in the VirtualSmartHome simulator. Additionally, we demonstrate that an activity recognition algorithm trained on the data generated by the VirtualSmartHome simulator can be successfully validated using real-life field data.
    MeSH term(s) Humans ; Activities of Daily Living ; Pattern Recognition, Automated ; Algorithms ; Records ; Habits
    Language English
    Publishing date 2023-09-01
    Publishing country Switzerland
    Document type Dataset ; Journal Article
    ZDB-ID 2052857-7
    ISSN 1424-8220 ; 1424-8220
    ISSN (online) 1424-8220
    ISSN 1424-8220
    DOI 10.3390/s23177586
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  6. Article ; Online: Mapping of Coral Reefs with Multispectral Satellites

    Teo Nguyen / Benoît Liquet / Kerrie Mengersen / Damien Sous

    Remote Sensing, Vol 13, Iss 4470, p

    A Review of Recent Papers

    2021  Volume 4470

    Abstract: Coral reefs are an essential source of marine biodiversity, but they are declining at an alarming rate under the combined effects of global change and human pressure. A precise mapping of coral reef habitat with high spatial and time resolutions has ... ...

    Abstract Coral reefs are an essential source of marine biodiversity, but they are declining at an alarming rate under the combined effects of global change and human pressure. A precise mapping of coral reef habitat with high spatial and time resolutions has become a necessary step for monitoring their health and evolution. This mapping can be achieved remotely thanks to satellite imagery coupled with machine-learning algorithms. In this paper, we review the different satellites used in recent literature, as well as the most common and efficient machine-learning methods. To account for the recent explosion of published research on coral reel mapping, we especially focus on the papers published between 2018 and 2020. Our review study indicates that object-based methods provide more accurate results than pixel-based ones, and that the most accurate methods are Support Vector Machine and Random Forest. We emphasize that the satellites with the highest spatial resolution provide the best images for benthic habitat mapping. We also highlight that preprocessing steps (water column correction, sunglint removal, etc.) and additional inputs (bathymetry data, aerial photographs, etc.) can significantly improve the mapping accuracy.
    Keywords coral mapping ; coral reefs ; machine learning ; remote sensing ; satellite imagery ; Science ; Q
    Subject code 333
    Language English
    Publishing date 2021-11-01T00:00:00Z
    Publisher MDPI AG
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  7. Article ; Online: Les CAR-NK allogéniques : une alternative prometteuse aux CAR-T autologues – État de la question, sources de cellules NK, limites et perspectives.

    Nguyen, Stéphanie / Lacan, Claire / Roos-Weil, Damien

    Bulletin du cancer

    2021  Volume 108, Issue 10S, Page(s) S81–S91

    Abstract: Immunotherapy with chimeric antigen receptor engineered-T cells (CAR-T) has revolutionized the landscape of treatment of relapsed or refractory B-cell. However, the use of autologous T cells has limitations: variable quality of collected effector T cells, ...

    Title translation Allogeneic CAR-NK cells: A promising alternative to autologous CAR-T cells - State of the art, sources of NK cells, limits and perspectives.
    Abstract Immunotherapy with chimeric antigen receptor engineered-T cells (CAR-T) has revolutionized the landscape of treatment of relapsed or refractory B-cell. However, the use of autologous T cells has limitations: variable quality of collected effector T cells, duration of the process sometimes incompatible with uncontrolled hemopathy, limited number of available CAR cells, sometimes fatal toxicities, extremely high cost. Natural Killer (NK) cells are an interesting alternative to T cells. NK cells are very powerful cytotoxic effectors that have demonstrated an anti-tumor effect after haploidentical hematopoietic stem cells transplantation or in adoptive cell therapy against a number of solid or hematological tumors. Mainly, they can be used in allogeneic situations without causing major toxic side effects. The sources of NK cells are multiple: cell line, cord blood, peripheral blood, induced pluripotent stem cells. Recent advances in manufacturing engineered CAR-NK cells make it possible to promote antibody-dependent cell-mediated cytotoxicity (ADCC), as well as the activation and persistence of these cells, notably via the cytokine Il-15. The majority of the reports on CAR-NK cells concern pre-clinical or early clinical trials. However, the many advantages of "off-the-shelf" allogeneic CAR-NK cells provide great potential in cancer treatments.
    MeSH term(s) Allogeneic Cells/cytology ; Allogeneic Cells/immunology ; Antibody-Dependent Cell Cytotoxicity ; Blood Cells ; Cell Engineering ; Cell Line ; Fetal Blood/cytology ; Hematologic Neoplasms/immunology ; Hematologic Neoplasms/therapy ; Hematopoietic Stem Cell Transplantation ; Humans ; Immunotherapy, Adoptive/methods ; Induced Pluripotent Stem Cells/cytology ; Killer Cells, Natural/cytology ; Killer Cells, Natural/immunology ; Killer Cells, Natural/transplantation ; Lymphocyte Activation ; Neoplasms/immunology ; Neoplasms/therapy ; Receptors, Chimeric Antigen/immunology ; T-Lymphocytes/cytology ; T-Lymphocytes/immunology ; T-Lymphocytes/transplantation
    Chemical Substances Receptors, Chimeric Antigen
    Language French
    Publishing date 2021-12-17
    Publishing country France
    Document type Journal Article ; Review
    ZDB-ID 213270-9
    ISSN 1769-6917 ; 0007-4551
    ISSN (online) 1769-6917
    ISSN 0007-4551
    DOI 10.1016/j.bulcan.2021.06.007
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  8. Article ; Online: Intracellular

    Malet, Karim / Faure, Emmanuel / Adam, Damien / Donner, Jannik / Liu, Lin / Pilon, Sarah-Jeanne / Fraser, Richard / Jorth, Peter / Newman, Dianne K / Brochiero, Emmanuelle / Rousseau, Simon / Nguyen, Dao

    American journal of respiratory and critical care medicine

    2024  

    Abstract: Rationale: Pseudomonas aeruginosa: Objectives: To detect and characterize intracellular : Methods: We sampled the lung explant tissues from CF patients undergoing lung transplantation and non-CF lung donor control. We analyzed lung tissue sections ...

    Abstract Rationale: Pseudomonas aeruginosa
    Objectives: To detect and characterize intracellular
    Methods: We sampled the lung explant tissues from CF patients undergoing lung transplantation and non-CF lung donor control. We analyzed lung tissue sections for the presence of intracellular
    Measurements and main results: P.a.
    Conclusion: This is the first study describing the presence of intracellular
    Language English
    Publishing date 2024-02-07
    Publishing country United States
    Document type Journal Article
    ZDB-ID 1180953-x
    ISSN 1535-4970 ; 0003-0805 ; 1073-449X
    ISSN (online) 1535-4970
    ISSN 0003-0805 ; 1073-449X
    DOI 10.1164/rccm.202308-1451OC
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  9. Article: Mapping of Coral Reefs with Multispectral Satellites: A Review of Recent Papers

    Nguyen, Teo / Liquet, Benoît / Mengersen, Kerrie / Sous, Damien

    Remote Sensing. 2021 Nov. 07, v. 13, no. 21

    2021  

    Abstract: Coral reefs are an essential source of marine biodiversity, but they are declining at an alarming rate under the combined effects of global change and human pressure. A precise mapping of coral reef habitat with high spatial and time resolutions has ... ...

    Abstract Coral reefs are an essential source of marine biodiversity, but they are declining at an alarming rate under the combined effects of global change and human pressure. A precise mapping of coral reef habitat with high spatial and time resolutions has become a necessary step for monitoring their health and evolution. This mapping can be achieved remotely thanks to satellite imagery coupled with machine-learning algorithms. In this paper, we review the different satellites used in recent literature, as well as the most common and efficient machine-learning methods. To account for the recent explosion of published research on coral reel mapping, we especially focus on the papers published between 2018 and 2020. Our review study indicates that object-based methods provide more accurate results than pixel-based ones, and that the most accurate methods are Support Vector Machine and Random Forest. We emphasize that the satellites with the highest spatial resolution provide the best images for benthic habitat mapping. We also highlight that preprocessing steps (water column correction, sunglint removal, etc.) and additional inputs (bathymetry data, aerial photographs, etc.) can significantly improve the mapping accuracy.
    Keywords benthic ecosystems ; biodiversity ; coral reefs ; corals ; evolution ; global change ; humans ; remote sensing ; support vector machines
    Language English
    Dates of publication 2021-1107
    Publishing place Multidisciplinary Digital Publishing Institute
    Document type Article
    ZDB-ID 2513863-7
    ISSN 2072-4292
    ISSN 2072-4292
    DOI 10.3390/rs13214470
    Database NAL-Catalogue (AGRICOLA)

    More links

    Kategorien

  10. Article ; Online: Proenkephalin A 119-159 (penKid) - a novel biomarker and its quantification on the Nexus IB10 POC system for assessing kidney function.

    Cobb, Jared / Szczesna, Karolina / Schulze, Axel / Ngo, Huy / Doyle, McKenna / Do, Tyler / Vu, Minh / Nguyen, John / Löffler, Julia / Borshchivska, Maryna / Bergmann, Deborah / Shin, Elizabeth / Hartmann, Tobias / Gruson, Damien

    Clinical chemistry and laboratory medicine

    2023  Volume 61, Issue 7, Page(s) e121–e125

    MeSH term(s) Humans ; Biomarkers ; Kidney ; Glomerular Filtration Rate
    Chemical Substances proenkephalin ; Biomarkers
    Language English
    Publishing date 2023-01-13
    Publishing country Germany
    Document type Letter
    ZDB-ID 1418007-8
    ISSN 1437-4331 ; 1434-6621 ; 1437-8523
    ISSN (online) 1437-4331
    ISSN 1434-6621 ; 1437-8523
    DOI 10.1515/cclm-2022-1187
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

To top