Accueil
Catégories
> Apprentissage automatique
L'apprentissage automatique (en anglais : machine learning, litt. "apprentissage machine"), apprentissage artificiel ou apprentissage statistique est un champ d'étude de l'intelligence artificielle qui se fonde sur des approches mathématiques et statistiques pour donner aux ordinateurs la capacité d'"apprendre" à partir de données, c'est-à -dire d'améliorer leurs performances à résoudre des tâches sans être explicitement programmés pour chacune. Plus largement, il concerne la conception, l'analyse, l'optimisation, le développement et l'implémentation de telles méthodes. (Wikipedia)
Apprentissage automatique
Commentaire :
L'apprentissage automatique (en anglais : machine learning, litt. "apprentissage machine"), apprentissage artificiel ou apprentissage statistique est un champ d'étude de l'intelligence artificielle qui se fonde sur des approches mathématiques et statistiques pour donner aux ordinateurs la capacité d'"apprendre" à partir de données, c'est-à -dire d'améliorer leurs performances à résoudre des tâches sans être explicitement programmés pour chacune. Plus largement, il concerne la conception, l'analyse, l'optimisation, le développement et l'implémentation de telles méthodes. (Wikipedia)
Voir aussi |
Ajouter le résultat dans votre panier Affiner la recherche
Etendre la recherche sur niveau(x) vers le bas
Artificial Intelligence in hair research : A proof-of-concept study on evaluating hair assembly features / Gabriela Daniels in INTERNATIONAL JOURNAL OF COSMETIC SCIENCE, Vol. 43, N° 4 (08/2021)
[article]
Titre : Artificial Intelligence in hair research : A proof-of-concept study on evaluating hair assembly features Type de document : document électronique Auteurs : Gabriela Daniels, Auteur ; Slobodanka Tamburic, Auteur ; Sergio Benini, Auteur ; Jane Randall, Auteur ; Tracey Sanderson, Auteur ; Mattia Savardi, Auteur Année de publication : 2021 Article en page(s) : p. 405-418 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Analyse sensorielle
Apprentissage automatiqueL'apprentissage automatique (en anglais : machine learning, litt. "apprentissage machine"), apprentissage artificiel ou apprentissage statistique est un champ d'étude de l'intelligence artificielle qui se fonde sur des approches mathématiques et statistiques pour donner aux ordinateurs la capacité d'"apprendre" à partir de données, c'est-à -dire d'améliorer leurs performances à résoudre des tâches sans être explicitement programmés pour chacune. Plus largement, il concerne la conception, l'analyse, l'optimisation, le développement et l'implémentation de telles méthodes. (Wikipedia)
Cheveux -- analyse
Cheveux décolorés
Détection de défauts (Ingénierie)
Intelligence artificielleIndex. décimale : 668.5 Parfums et cosmétiques Résumé : - Objective : The first objective of this study was to apply computer vision and machine learning techniques to quantify the effects of haircare treatments on hair assembly and to identify correctly whether unknown tresses were treated or not. The second objective was to explore and compare the performance of human assessment with that obtained from artificial intelligence (AI) algorithms.
- Methods : Machine learning was applied to a data set of hair tress images (virgin and bleached), both untreated and treated with a shampoo and conditioner set, aimed at increasing hair volume whilst improving alignment and reducing the flyway of the hair. The automatic quantification of the following hair image features was conducted : local and global hair volumes and hair alignment. These features were assessed at three time points: t0 (no treatment), t1 (two treatments) and t2 (three treatments). Classifier tests were applied to test the accuracy of the machine learning. A sensory test (paired comparison of t0 vs t2) and an online front image-based survey (paired comparison of t0 vs t1, t1 vs t2, t0 vs t2) were conducted to compare human assessment with that of the algorithms.
- Results : The automatic image analysis identified changes to hair volume and alignment which enabled the successful application of the classification tests, especially when the hair images were grouped into untreated and treated groups. The human assessment of hair presented in pairs confirmed the automatic image analysis. The image assessment for both virgin hair and bleached only partially agreed with the analysis of the subset of images used in the online survey. One hypothesis is that treatments changed somewhat the shape of the hair tress, with the effect being more pronounced in bleached hair. This made human assessment of flat images more challenging than when viewed directly in 3D. Overall, the bleached hair exhibited effects of higher magnitude than the virgin hair.
- Conclusions : This study illustrated the capacity of artificial intelligence for hair image detection and classification, and for image analysis of hair assembly features following treatments. The human assessment partially confirmed the image analysis and highlighted the challenges imposed by the presentation mode.Note de contenu : - Hair assembly volume, alignment and flyaway
- Hair assembly properties and Artificial Intelligence
- MATERIALS AND METHODS : Hair tresses and treatment - Image dataset - Automatic hair segmentation - Automatic quantification of hair assembly features - Timepoint recognition on single hair images with AI - Online paired image-comparison test with naïve assessors (n = 100) - Paired difference test with naïve assessors )n = 50) - Statistical analysis
- RESULTS : Hair volume analysis - Fibre alignment analysis - Machine learning: treatment order test - Machine learning : timepoint recognition - Online paired image-comparison test : image analysis - Online paired image-comparison test : human assessment - Visual paired difference test
- DISCUSSION : Image data analysis and machine learning - Classifiers tests - The online survey and AI - Visual paired difference test
- Table 1 : Global and local hair volumes for the three time points of the training data set
- Table 2 : Fibre alignment indices for three time points of the training data set
- Table 3 : Confusion matrices. Correct results in bold
- Table 4 : Results of the online paired image-comparison test
- Table 5 : Fibre alignment indices for the selected image subset used in the online survey, based on three images for each tress
- Table 6 : Results of the online paired image-comparison test
- Table 7 : Volume and hair straightness comparisons between the different time points reported in the survey (Table 6) and their agreement with AI-generated GHV
- Table 8 : Results of the visual paired difference test (n = 50 responses)DOI : https://doi.org/10.1111/ics.12706 En ligne : https://drive.google.com/file/d/1RnhXaRtILFJxcQM1zyk09SH7pQcXM1Mh/view?usp=shari [...] Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=36675
in INTERNATIONAL JOURNAL OF COSMETIC SCIENCE > Vol. 43, N° 4 (08/2021) . - p. 405-418[article]Deep learning and machine learning neural network approaches for multi class leather texture defect classification and segmentation / Praveen Kumar Moganam in JOURNAL OF LEATHER SCIENCE AND ENGINEERING, Vol. 4 (Année 2022)
[article]
Titre : Deep learning and machine learning neural network approaches for multi class leather texture defect classification and segmentation Type de document : texte imprimé Auteurs : Praveen Kumar Moganam, Auteur ; Denis Ashok Sathia Seelan, Auteur Année de publication : 2022 Article en page(s) : 21 p. Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Apprentissage automatique L'apprentissage automatique (en anglais : machine learning, litt. "apprentissage machine"), apprentissage artificiel ou apprentissage statistique est un champ d'étude de l'intelligence artificielle qui se fonde sur des approches mathématiques et statistiques pour donner aux ordinateurs la capacité d'"apprendre" à partir de données, c'est-à -dire d'améliorer leurs performances à résoudre des tâches sans être explicitement programmés pour chacune. Plus largement, il concerne la conception, l'analyse, l'optimisation, le développement et l'implémentation de telles méthodes. (Wikipedia)
Cuirs et peaux -- Défauts
Détection de défauts (Ingénierie)
Réseaux neuronaux (informatique)Tags : 'Réseaux de neurones à convolution' 'Classificateur d'apprentissage automatique' 'Défauts du cuir' 'Classement multi-classes' 'Carte d'activation classe' Segmentation Index. décimale : 675 Technologie du cuir et de la fourrure Résumé : Modern leather industries are focused on producing high quality leather products for sustaining the market competitiveness. However, various leather defects are introduced during various stages of manufacturing process such as material handling, tanning and dyeing. Manual inspection of leather surfaces is subjective and inconsistent in nature; hence machine vision systems have been widely adopted for the automated inspection of leather defects. It is necessary develop suitable image processing algorithms for localize leather defects such as folding marks, growth marks, grain off, loose grain, and pinhole due to the ambiguous texture pattern and tiny nature in the localized regions of the leather. This paper presents deep learning neural network-based approach for automatic localization and classification of leather defects using a machine vision system. In this work, popular convolutional neural networks are trained using leather images of different leather defects and a class activation mapping technique is followed to locate the region of interest for the class of leather defect. Convolution neural networks such as Google net, Squeeze-net, RestNet are found to provide better accuracy of classification as compared with the state-of-the-art neural network architectures and the results are presented. Note de contenu : - MACHINE VISION-BASED LEATHER INSPECTION SYSTEM : Leather Image acquisition - Leather texture defects
- DEEP LEARNING NEURAL NETWORK APPROACH FOR CLASSIFICATION AND LOCALIZATION OF LEATHER DEFECTS : Leather image Data Set preparation and preprocessing - Deep learning convolutional neural network architectures - Visualization of region of interest for defect localization
- MACHINE LEARNING BASED APPROACHES FOR MULTI CLASS DEFECT CLASSIFICATION OF LEATHER DEFECTS : Hand crafted Feature extraction from leather images - Shallow feed-forward neural network-based machine learning classifier
- PERFORMANCE METRICS OF DEEP LEARNING AND MACHINE LEARNING CLASSIFIERS
- RESULTS AND DISCUSSION : Feature maps of convolution neural networks - Feature extraction using GLCM, autocorrelation - Training and testing performance of deep learning neural networks
Training performance of shallow feed forward neural network classifier - Classification performance of deep learning neural networks - Classification performance of machine learning approaches - Class activation maps for selection of region of interest in leather imagesDOI : https://doi.org/10.1186/s42825-022-00080-9 En ligne : https://link.springer.com/content/pdf/10.1186/s42825-022-00080-9.pdf Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=37575
in JOURNAL OF LEATHER SCIENCE AND ENGINEERING > Vol. 4 (Année 2022) . - 21 p.[article]
[article]
Titre : Leather machine learning Type de document : texte imprimé Auteurs : Karl Flowers, Auteur Année de publication : 2022 Article en page(s) : p. 32-34 Langues : Anglais (eng) Catégories : Apprentissage automatique L'apprentissage automatique (en anglais : machine learning, litt. "apprentissage machine"), apprentissage artificiel ou apprentissage statistique est un champ d'étude de l'intelligence artificielle qui se fonde sur des approches mathématiques et statistiques pour donner aux ordinateurs la capacité d'"apprendre" à partir de données, c'est-à -dire d'améliorer leurs performances à résoudre des tâches sans être explicitement programmés pour chacune. Plus largement, il concerne la conception, l'analyse, l'optimisation, le développement et l'implémentation de telles méthodes. (Wikipedia)
Cuirs et peaux -- Industrie
Industrie 4.0Le concept d’Industrie 4.0 correspond à une nouvelle façon d’organiser les moyens de production : l’objectif est la mise en place d’usines dites "intelligentes" ("smart factories") capables d’une plus grande adaptabilité dans la production et d’une allocation plus efficace des ressources, ouvrant ainsi la voie à une nouvelle révolution industrielle. Ses bases technologiques sont l'Internet des objets et les systèmes cyber-physiques.
Intelligence artificielleIndex. décimale : 675 Technologie du cuir et de la fourrure Résumé : Industry 4.0 is the concept where leather factories of the future are interconnected, have many measurement data streams flowing into a central processing point that learns, improves and continuously implements improvements or corrective actions, e.g., a tannery machine that from the data of its own performance requests a maintenance activity, or a technical service, or part-replacement (within the consents set by the user).
The topic of how the modem tannery implement and profit from Industry 4.0 is mentioned in previous articles in the ILM March/April and September/October 2018 issues. Artificial intelligence (M) can further be broken down into the tools required: machine learning and its subset, deep learning. This article details how modern machines use AI, and specifically machine learning to improve themselves. The ethics of AI will not be considered in this article, but is covered comprehensively elsewhere (Müller, 2021).Note de contenu : - Artificial intelligence
- Machine learning
- Machine vision
- Fig. 1 : A hide/skin moves on a conveyor under a machine with "vision" (a scanner)
- Fig. 2 : A crucial development for toggling is detecting the edge of a leather
- Fig. 3 : The difference between great contrast, average/low contrast and blurred edge
- Fig. 4 : Colour printingEn ligne : https://drive.google.com/file/d/17oI3edzcI3bxIYhILEU0jTSOjjK_Tm-d/view?usp=drive [...] Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=36941
in INTERNATIONAL LEATHER MAKER (ILM) > N° 51 (01-02/2022) . - p. 32-34[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 23197 - Périodique Bibliothèque principale Documentaires Disponible Machine learning workflow for microparticle composite thin-film process–structure linkages / Peter R. Griffiths in JOURNAL OF COATINGS TECHNOLOGY AND RESEARCH, Vol. 19, N° 1 (01/2022)
[article]
Titre : Machine learning workflow for microparticle composite thin-film process–structure linkages Type de document : texte imprimé Auteurs : Peter R. Griffiths, Auteur Année de publication : 2022 Article en page(s) : p. pages 83-96 Note générale : Bibliogr. Langues : Américain (ame) Catégories : Apprentissage automatique L'apprentissage automatique (en anglais : machine learning, litt. "apprentissage machine"), apprentissage artificiel ou apprentissage statistique est un champ d'étude de l'intelligence artificielle qui se fonde sur des approches mathématiques et statistiques pour donner aux ordinateurs la capacité d'"apprendre" à partir de données, c'est-à -dire d'améliorer leurs performances à résoudre des tâches sans être explicitement programmés pour chacune. Plus largement, il concerne la conception, l'analyse, l'optimisation, le développement et l'implémentation de telles méthodes. (Wikipedia)
Composites
Couches minces
Microstructures
Particules (matières)
PolymèresIndex. décimale : 667.9 Revêtements et enduits Résumé : Microparticle composite thin films (MCTFs) have applications in a variety of fields, ranging from water filtration, to advanced energy storage, to medical devices. Variations in processing parameters during casting and solidification have been demonstrated to lead to morphological and therefore property changes in the final film. However, the wide range and number of possible combinations of parameters can make robust process–structure (PS) linkages a complex problem. Material informatics has shown to be well suited for developing PS linkages in other materials, but there are challenges that must first be addressed for MCTFs given the lack of separation between the characteristic length scales of the microstructure (i.e., particles, pores, etc.) and the film thickness. The objective of this work is to identify reduced-order spatial models and machine learning algorithms to address these problems. To achieve this, simulated microstructures of microparticle distributions based upon slot die coating simulations have been generated. Reduced-order representations of the microstructures were then created to capture variation in the microstructure across small slices through thickness of the film using two-point particle autocorrelation statistics and principal component analysis. Results showed that predictive PS linkages can be created using Gaussian process regression between the final film morphology and processing parameters; however, image size must be considered to ensure convergence in spatial statistics to increase accuracy. Note de contenu : - Methods : Simulated microstructures - Spatial statistical models : two-point spatial statistics and principal component analysis - Process–structure linkages
- Results and discussion : Microstructure generation - Spatial statistical model - Process–structure linkages
- Table 1 : Microstructure dataset parameter rangesDOI : https://doi.org/10.1007/s11998-021-021-00512-x En ligne : https://link.springer.com/content/pdf/10.1007/s11998-021-00512-x.pdf Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=37147
in JOURNAL OF COATINGS TECHNOLOGY AND RESEARCH > Vol. 19, N° 1 (01/2022) . - p. pages 83-96[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 23313 - Périodique Bibliothèque principale Documentaires Disponible Molded part quality prediction using machine learning / Alexander Schulze Struchtrup in KUNSTSTOFFE INTERNATIONAL, Vol. 110, N° 5 (2020)
[article]
Titre : Molded part quality prediction using machine learning : How much added value does cavity pressure sensor technology offer for the quality prediction in injection molding ? Type de document : texte imprimé Auteurs : Alexander Schulze Struchtrup, Auteur ; Dimitri Kvaktun, Auteur ; Reinhard Schiffers, Auteur Année de publication : 2020 Article en page(s) : p. 22-25 Langues : Anglais (eng) Catégories : Apprentissage automatique L'apprentissage automatique (en anglais : machine learning, litt. "apprentissage machine"), apprentissage artificiel ou apprentissage statistique est un champ d'étude de l'intelligence artificielle qui se fonde sur des approches mathématiques et statistiques pour donner aux ordinateurs la capacité d'"apprendre" à partir de données, c'est-à -dire d'améliorer leurs performances à résoudre des tâches sans être explicitement programmés pour chacune. Plus largement, il concerne la conception, l'analyse, l'optimisation, le développement et l'implémentation de telles méthodes. (Wikipedia)
Matières plastiques -- Moulage par injection
Prévision technologique
Qualité -- ContrôleIndex. décimale : 668.4 Plastiques, vinyles Résumé : The general aim of quality prediction is to derive statements about the resulting molded part quality based on process data. For injection molded parts, a high level of informative value is generally attributed to the cavity pressure curve. The question arises whether the quality prediction yields more precise results if, in addition to the process data from the machine’s internal sensors, the data from the mold sensor(s) are also included. Note de contenu : - Fundamentals of molded part quality production
- Consistent data processing chain
- Themolded part is weighed and photographed after removal
- Central composite design
- Higher model grades for molded part weight
- Fig. 1 : Before the application of a model-based quality prediction, a learning phase is necessary, in which both process and quality data are provided
- Fig. 2 : The consistent data processing allows the automatic generation of quality models
- Fig. 3 : The mold to produce the plate specimen contains two cavity pressure sensors
- Fig. 4 : Very high model grades are possible when predicting the part weight. Only the quality prediction exclusively based on cavity pressure features yield slightly lower model qualities
- Fig. 5 : The model grades for the prediction of the part length are a bit lower than those for the weight prediction. Nevertheless, they show the same qualitative behaviorEn ligne : https://drive.google.com/file/d/1wCRWPWglDqToebAa0IhWlEunJGE2eeX2/view?usp=drive [...] Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=34462
in KUNSTSTOFFE INTERNATIONAL > Vol. 110, N° 5 (2020) . - p. 22-25[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 21834 - Périodique Bibliothèque principale Documentaires Disponible PermalinkProcess set-up through machine learning / Christian Hopmann in KUNSTSTOFFE INTERNATIONAL, Vol. 108, N° 6 (06-07/2018)
PermalinkTime series data for process monitoring in injection molding : a quantitative study of the benefits of a high sampling rate / Lucas Bogedale in INTERNATIONAL POLYMER PROCESSING, Vol. 38, N° 2 (2023)
PermalinkPermalink