LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 91

Search options

  1. Book ; Online ; E-Book: Digital Health in Focus of Predictive, Preventive and Personalised Medicine

    Chaari, Lotfi

    (Advances in Predictive, Preventive and Personalised Medicine, ; 12)

    2020  

    Abstract: ... Lotfi Chaari, professor at the University of Toulouse. This work comes after more than ten years ...

    Author's details edited by Lotfi Chaari
    Series title Advances in Predictive, Preventive and Personalised Medicine, ; 12
    Advances in predictive, preventive and personalised medicine
    Collection Advances in predictive, preventive and personalised medicine
    Abstract This collection, entitled Digital Health in Focus of Predictive, Preventive and Personalised Medicine contains the proceedings of the second International Conference on Digital Health Technologies (ICDHT 2019). Eighteen recent contributions are presented in the fields of Artificial Intelligence (AI), machine learning, Internet of Things (IoT), data analysis, optimization and health monitoring, all applied to digital health. This collection enables researchers to learn about recent advances in the above mentioned fields. It brings a technological viewpoint of PPP medicine and points out innovations and new applications. Readers will discover how advanced Information Technology (IT) tools can be used for healthcare. Most contributions are issue from collaborations between computer scientists and actors in the medical field. Participants from more than ten countries have contributed to enrich this content, either through original papers, keynote talks or discussions during the ICDHT 2019 conference. This work is edited by Prof. Lotfi Chaari, professor at the University of Toulouse. This work comes after more than ten years of expertise in the biomedical signal and image processing field. .
    Keywords Medicine/Research ; Biology/Research ; Medical informatics ; Biomedical engineering ; Biomedical Research ; Health Informatics ; Biomedical Engineering and Bioengineering
    Subject code 610.285
    Language English
    Size 1 online resource (XIX, 164 p. 67 illus., 51 illus. in color.)
    Edition 1st ed. 2020.
    Publisher Springer International Publishing ; Imprint: Springer
    Publishing place Cham
    Document type Book ; Online ; E-Book
    Remark Zugriff für angemeldete ZB MED-Nutzerinnen und -Nutzer
    ISBN 3-030-49815-8 ; 3-030-49814-X ; 978-3-030-49815-3 ; 978-3-030-49814-6
    DOI 10.1007/978-3-030-49815-3
    Database ZB MED Catalogue: Medicine, Health, Nutrition, Environment, Agriculture

    Full text online

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Article ; Online: Bayesian optimization for sparse neural networks with trainable activation functions.

    Fakhfakh, Mohamed / Chaari, Lotfi

    IEEE transactions on pattern analysis and machine intelligence

    2024  Volume PP

    Abstract: In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that ... ...

    Abstract In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that can be trained throughout the learning process, as they appear to improve network performance, especially by reducing overfitting. In this paper, we propose a trainable activation function whose parameters need to be estimated. A fully Bayesian model is developed to automatically estimate from the learning data both the model weights and activation function parameters. An MCMC-based optimization scheme is developed to build the inference. The proposed method aims to solve the aforementioned problems and improve convergence time by using an efficient sampling scheme that guarantees convergence to the global maximum. The proposed scheme has been tested across a diverse datasets, encompassing both classification and regression tasks, and implemented in various CNN architectures to demonstrate its versatility and effectiveness. Promising results demonstrate the usefulness of our proposed approach in improving models accuracy due to the proposed activation function and Bayesian estimation of the parameters.
    Language English
    Publishing date 2024-04-10
    Publishing country United States
    Document type Journal Article
    ISSN 1939-3539
    ISSN (online) 1939-3539
    DOI 10.1109/TPAMI.2024.3387073
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Article ; Online: mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments.

    Baban A Erep, Thierry Roland / Chaari, Lotfi

    Sensors (Basel, Switzerland)

    2023  Volume 24, Issue 1

    Abstract: Recent decades have witnessed the development of vision-based dietary assessment (VBDA) systems. These systems generally consist of three main stages: food image analysis, portion estimation, and nutrient derivation. The effectiveness of the initial step ...

    Abstract Recent decades have witnessed the development of vision-based dietary assessment (VBDA) systems. These systems generally consist of three main stages: food image analysis, portion estimation, and nutrient derivation. The effectiveness of the initial step is highly dependent on the use of accurate segmentation and image recognition models and the availability of high-quality training datasets. Food image segmentation still faces various challenges, and most existing research focuses mainly on Asian and Western food images. For this reason, this study is based on food images from sub-Saharan Africa, which pose their own problems, such as inter-class similarity and dishes with mixed-class food. This work focuses on the first stage of VBDAs, where we introduce two notable contributions. Firstly, we propose mid-DeepLabv3+, an enhanced food image segmentation model based on DeepLabv3+ with a ResNet50 backbone. Our approach involves adding a middle layer in the decoder path and SimAM after each extracted backbone feature layer. Secondly, we present CamerFood10, the first food image dataset specifically designed for sub-Saharan African food segmentation. It includes 10 classes of the most consumed food items in Cameroon. On our dataset, mid-DeepLabv3+ outperforms benchmark convolutional neural network models for semantic image segmentation, with an mIoU (mean Intersection over Union) of 65.20%, representing a +10.74% improvement over DeepLabv3+ with the same backbone.
    MeSH term(s) Nutrition Assessment ; Semantics ; Food ; Diet ; Nutrients
    Language English
    Publishing date 2023-12-29
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2052857-7
    ISSN 1424-8220 ; 1424-8220
    ISSN (online) 1424-8220
    ISSN 1424-8220
    DOI 10.3390/s24010209
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  4. Book ; Online: Bayesian optimization for sparse neural networks with trainable activation functions

    Fakhfakh, Mohamed / Chaari, Lotfi

    2023  

    Abstract: In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that ... ...

    Abstract In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that can be trained throughout the learning process, as they appear to improve network performance, especially by reducing overfitting. In this paper, we propose a trainable activation function whose parameters need to be estimated. A fully Bayesian model is developed to automatically estimate from the learning data both the model weights and activation function parameters. An MCMC-based optimization scheme is developed to build the inference. The proposed method aims to solve the aforementioned problems and improve convergence time by using an efficient sampling scheme that guarantees convergence to the global maximum. The proposed scheme is tested on three datasets with three different CNNs. Promising results demonstrate the usefulness of our proposed approach in improving model accuracy due to the proposed activation function and Bayesian estimation of the parameters.
    Keywords Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Statistics - Methodology
    Subject code 006
    Publishing date 2023-04-10
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  5. Article: Non-smooth Bayesian learning for artificial neural networks.

    Fakhfakh, Mohamed / Chaari, Lotfi / Bouaziz, Bassem / Gargouri, Faiez

    Journal of ambient intelligence and humanized computing

    2022  , Page(s) 1–19

    Abstract: Artificial neural networks (ANNs) are being widely used in supervised machine learning to analyze signals or images for many applications. Using an annotated learning database, one of the main challenges is to optimize the network weights. A lot of work ... ...

    Abstract Artificial neural networks (ANNs) are being widely used in supervised machine learning to analyze signals or images for many applications. Using an annotated learning database, one of the main challenges is to optimize the network weights. A lot of work on solving optimization problems or improving optimization methods in machine learning has been proposed successively such as gradient-based method, Newton-type method, meta-heuristic method. For the sake of efficiency, regularization is generally used. When non-smooth regularizers are used especially to promote sparse networks, such as the
    Language English
    Publishing date 2022-06-25
    Publishing country Germany
    Document type Journal Article
    ZDB-ID 2543187-0
    ISSN 1868-5145 ; 1868-5137
    ISSN (online) 1868-5145
    ISSN 1868-5137
    DOI 10.1007/s12652-022-04073-8
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  6. Article: Disclosing the Functional Potency of Three Oxygenated Monoterpenes in Combating Microbial Pathogenesis: From Targeting Virulence Factors to Chicken Meat Preservation.

    Akermi, Sarra / Chaari, Moufida / Elhadef, Khaoula / Fourati, Mariam / Chakchouk Mtibaa, Ahlem / Agriopoulou, Sofia / Smaoui, Slim / Mellouli, Lotfi

    Foods (Basel, Switzerland)

    2024  Volume 13, Issue 6

    Abstract: During the last few decades, there has existed an increased interest in and considerable consumer preference towards using natural and safe compounds derived from medicinal plants as alternatives to synthetic preservatives to combat microbial ... ...

    Abstract During the last few decades, there has existed an increased interest in and considerable consumer preference towards using natural and safe compounds derived from medicinal plants as alternatives to synthetic preservatives to combat microbial pathogenicity. In this regard, the present study investigated the possible synergistic interactions of the anti-foodborne bacterial capacity of linalool (L), eucalyptol (E), and camphor (C). The antibacterial synergistic effect was determined against
    Language English
    Publishing date 2024-03-21
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2704223-6
    ISSN 2304-8158
    ISSN 2304-8158
    DOI 10.3390/foods13060965
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  7. Article: Covid-19 pandemic by the "real-time" monitoring: the Tunisian case and lessons for global epidemics in the context of 3PM strategies.

    Chaari, Lotfi / Golubnitschaja, Olga

    The EPMA journal

    2020  Volume 11, Issue 2, Page(s) 133–138

    Abstract: Covid-19 is neither the first nor the last viral epidemic which societies around the world are, were and will be affected by. Which lessons should be taken from the current pandemic situation? The Covid-19 disease is still not well characterised, and ... ...

    Abstract Covid-19 is neither the first nor the last viral epidemic which societies around the world are, were and will be affected by. Which lessons should be taken from the current pandemic situation? The Covid-19 disease is still not well characterised, and many research teams all over the world are working on prediction of the epidemic scenario, protective measures to populations and sub-populations, therapeutic and vaccination issues, amongst others. Contextually, countries with currently low numbers of Covid-19-infected individuals such as Tunisia are intended to take lessons from those countries which already reached the exponential phase of the infection distribution as well as from those which have the exponential phase behind them and record a minor number of new cases such as China. To this end, in Tunisia, the pandemic wave has started with a significant delay compared with Europe, the main economic partner of the country. In this paper, we do analyse the current pandemic situation in this country by studying the infection evolution and considering potential protective strategies to prevent a pandemic scenario. The model is predictive based on a large number of undetected Covid-19 cases that is particularly true for some country regions such as Sfax. Infection distribution and mortality rate analysis demonstrate a highly heterogeneous picture over the country. Qualitative and quantitative comparative analysis leads to a conclusion that the reliable "real-time" monitoring based on the randomised laboratory tests is the optimal predictive strategy to create the most effective evidence-based preventive measures. In contrast, lack of tests may lead to incorrect political decisions causing either unnecessary over-protection of the population that is risky for a long-term economic recession, or under-protection of the population leading to a post-containment pandemic rebound. Recommendations are provided in the context of advanced predictive, preventive and personalised (3P) medical approach.
    Keywords covid19
    Language English
    Publishing date 2020-04-25
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2545928-4
    ISSN 1878-5085 ; 1878-5077
    ISSN (online) 1878-5085
    ISSN 1878-5077
    DOI 10.1007/s13167-020-00207-0
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  8. Article ; Online: Combined in vitro/in silico approaches, molecular dynamics simulations and safety assessment of the multifunctional properties of thymol and carvacrol: A comparative insight.

    Akermi, Sarra / Smaoui, Slim / Chaari, Moufida / Elhadef, Khaoula / Gentile, Rocco / Hait, Milan / Roymahapatra, Gourisankar / Mellouli, Lotfi

    Chemistry & biodiversity

    2024  Volume 21, Issue 2, Page(s) e202301575

    Abstract: Bioactive compounds derived from medicinal plants have acquired immense attentiveness in drug discovery and development. The present study investigated in vitro and predicted in silico the antibacterial, antifungal, and antiviral properties of thymol and ...

    Abstract Bioactive compounds derived from medicinal plants have acquired immense attentiveness in drug discovery and development. The present study investigated in vitro and predicted in silico the antibacterial, antifungal, and antiviral properties of thymol and carvacrol, and assessed their safety. The performed microbiological assays against Pseudomonas aeruginosa, Escherichia coli, Salmonella enterica Typhimurium revealed that the minimal inhibitory concentration values ranged from (0.078 to 0.312 mg/mL) and the minimal fungicidal concentration against Candida albicans was 0.625 mg/mL. Molecular docking simulations, stipulated that these compounds could inhibit bacterial replication and transcription functions by targeting DNA and RNA polymerases receptors with docking scores varying between (-5.1 to -6.9 kcal/mol). Studied hydroxylated monoterpenes could hinder C. albicans growth by impeding lanosterol 14α-demethylase enzyme and showed a (ΔG=-6.2 and -6.3 kcal/mol). Computational studies revealed that thymol and carvacrol could target the SARS-Cov-2 spike protein of the Omicron variant RBD domain. Molecular dynamics simulations disclosed that these compounds have a stable dynamic behavior over 100 ns as compared to remdesivir. Chemo-computational toxicity prediction using Protox II webserver indicated that thymol and carvacrol could be safely and effectively used as drug candidates to tackle bacterial, fungal, and viral infections as compared to chemical medication.
    MeSH term(s) Humans ; Thymol/pharmacology ; Thymol/metabolism ; Molecular Dynamics Simulation ; Molecular Docking Simulation ; Monoterpenes/pharmacology ; Monoterpenes/metabolism ; Salmonella typhimurium ; Candida albicans ; Escherichia coli ; Cymenes ; Spike Glycoprotein, Coronavirus
    Chemical Substances Thymol (3J50XA376E) ; carvacrol (9B1J4V995Q) ; spike protein, SARS-CoV-2 ; Monoterpenes ; Cymenes ; Spike Glycoprotein, Coronavirus
    Language English
    Publishing date 2024-01-15
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2139001-0
    ISSN 1612-1880 ; 1612-1872
    ISSN (online) 1612-1880
    ISSN 1612-1872
    DOI 10.1002/cbdv.202301575
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  9. Article ; Online: Covid-19 pandemic by the “real-time” monitoring

    Chaari, Lotfi / Golubnitschaja, Olga

    EPMA Journal

    the Tunisian case and lessons for global epidemics in the context of 3PM strategies

    2020  Volume 11, Issue 2, Page(s) 133–138

    Keywords Health Policy ; Drug Discovery ; Biochemistry, medical ; covid19
    Language English
    Publisher Springer Science and Business Media LLC
    Publishing country us
    Document type Article ; Online
    ZDB-ID 2545928-4
    ISSN 1878-5085 ; 1878-5077
    ISSN (online) 1878-5085
    ISSN 1878-5077
    DOI 10.1007/s13167-020-00207-0
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  10. Article: Covid-19 pandemic by the "real-time" monitoring: the Tunisian case and lessons for global epidemics in the context of 3PM strategies

    Chaari, Lotfi / Golubnitschaja, Olga

    EPMA J

    Abstract: Covid-19 is neither the first nor the last viral epidemic which societies around the world are, were and will be affected by. Which lessons should be taken from the current pandemic situation? The Covid-19 disease is still not well characterised, and ... ...

    Abstract Covid-19 is neither the first nor the last viral epidemic which societies around the world are, were and will be affected by. Which lessons should be taken from the current pandemic situation? The Covid-19 disease is still not well characterised, and many research teams all over the world are working on prediction of the epidemic scenario, protective measures to populations and sub-populations, therapeutic and vaccination issues, amongst others. Contextually, countries with currently low numbers of Covid-19-infected individuals such as Tunisia are intended to take lessons from those countries which already reached the exponential phase of the infection distribution as well as from those which have the exponential phase behind them and record a minor number of new cases such as China. To this end, in Tunisia, the pandemic wave has started with a significant delay compared with Europe, the main economic partner of the country. In this paper, we do analyse the current pandemic situation in this country by studying the infection evolution and considering potential protective strategies to prevent a pandemic scenario. The model is predictive based on a large number of undetected Covid-19 cases that is particularly true for some country regions such as Sfax. Infection distribution and mortality rate analysis demonstrate a highly heterogeneous picture over the country. Qualitative and quantitative comparative analysis leads to a conclusion that the reliable "real-time" monitoring based on the randomised laboratory tests is the optimal predictive strategy to create the most effective evidence-based preventive measures. In contrast, lack of tests may lead to incorrect political decisions causing either unnecessary over-protection of the population that is risky for a long-term economic recession, or under-protection of the population leading to a post-containment pandemic rebound. Recommendations are provided in the context of advanced predictive, preventive and personalised (3P) medical approach.
    Keywords covid19
    Publisher WHO
    Document type Article
    Note WHO #Covidence: #116804
    Database COVID19

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top