Spelling suggestions: "subject:"microscope""
111 |
In Situ Transmission Elecron Microscope Triboprobe For Tribological Studies Of Materials At NanoscaleAnantheshwara, K 07 1900 (has links) (PDF)
In most of the tribological experiments studying friction and wear behaviour, the contact interface is hidden. The present work attempts to overcome this hidden-interface problem by carrying out real-time tribological experiments inside Transmission Electron Microscope (TEM). This is achieved by developing an in situ TEM triboprobe which can carry out nanoscale indentation, sliding and reciprocating tests on an electron transparent sample inside TEM. A novel in situ TEM triboprobe is developed by characterising the individual components involved in the development. Coarse positioning of a sharp probe is achieved using inertial sliders. Fine motion of the probe is controlled using a 4-quadrant tube piezoceramic. This triboprobe is capable of carrying out high stiffness tribological experiments inside TEM. The interface is viewed at high resolutions in real time during the experiments using a movie rate CCD camera.
In indentation experiments a sharp probe is brought into contact with the sample surface. During indentation of Aluminium alloy tribolayer, it has been observed that the cracks originate from subsurface and propagate to the surface causing delamination-like material removal. Indentation experiments on protruding silicon particle in Aluminium-Silicon (Al-Si) alloy shows that initial deformation is elastic. Once the load is increased, the particle starts indenting the soft aluminum matrix, and results in sinking of the particle into the aluminium matrix. Once the particle starts sinking, the increase in the displacement causes the generation of a crack and the propagation of this crack results in the fracture of the particle.
The sliding experiments inside TEM allowed the direct visualization of asperity level interaction during sliding. The preliminary experimental results of nanoscale sliding experiments carried out using an AFM tip as the sample. The adhesive instability is observed as snap-in and snap-out events. The snap-out distance seems to depend on the local geometry of the contact. To simulate reciprocating wear, a sharp diamond probe is brought into contact with Al-Si alloy and reciprocated sinusoidally at 0.5Hz. At lower loads no wear is observed. However, when the normal load is increased, material starts getting removed in thin slivers, and most of the wear debris generated get swept away from the track. Some wear debris get entrapped in between the sliding surfaces; subsequently they join to form larger wear particles. The trapped particles generated during the test act like rollers and a significant increase in the stroke-length is observed accompanying the rolling action of the particle. The phenomena like agglomeration and dissociation of the wear particles has also been observed. Repeated deformation of the trapped particles leads to the formation of tiny liquid drop on some of the wear debris. The liquid consists of gallium which comes from the sample preparation technique. The interaction between the liquid droplets has been studied by carrying out liquid-bridge pulling experiments. Liquid gallium gets cooled with time during tensile pulling of the droplets. A nano-filament is formed between the droplets during pulling. After some time, the droplet gets solidified and coalescence of droplets does not take place. Further frictional heating was necessary to form the bridge again.
The in situ TEM triboprobe, which allow the tribological processes to be observed dynamically under high resolutions, is a power full tool in detecting fundamental tribological interactions.
|
112 |
Crystal structure determination of β-lactoglobulin from electron micrographsRoeter, Richard 01 January 1971 (has links)
Often electron micrographs exhibit a repeating structure. Sometimes this repeating structure satisfies the definition of a crystal in that it has a three dimensional repeating structure. If the unit cell structure of this repeating structure can be determined it can be used to help categorize different sections of a particular sample. In some cases, the use of optical diffraction analysis of electron micrographs with repeating structure is a method of determining the unit cell structure.
Samples of β-Lactoglobulin were prepared for viewing in the electron microscope using both the crystalline material and carbon replicas of the crystal surface. Because the crystalline material was very unstable in the electron beam, images adequate for use as diffraction gratings could not be obtained. Electron images from the replicas were used to generate the optical diffraction patterns in this paper.
The structure of β-Lactoglobulin has been determined previously by X-ray diffraction analysis. This information was used to assist in the interpretation of the optical diffraction patterns.
Electron micrographs and optical diffraction patterns were recorded which were found to be consistent with the structure of β-Lactoglobulin which were found to be consistent with the structure of β-Lactoglobulin as determined by X-ray diffraction analysis. The unit cell dimensions were determined to be a = 58±4Å, b = 59±3Å and c = 102±12Å.
|
113 |
Design and assembly of a multimodal nonlinear laser scanning microscopeBélisle, Jonathan. January 2006 (has links)
No description available.
|
114 |
Automated sperm identification using MetaSystems Metafer imaging systemAlao, Itunu 13 February 2024 (has links)
Thousands of sexual assault cases in the United States are backlogged. This has been a growing issue for years that has increased the difficulty of solving these cases and providing closure to the victims. The analysis process for each case includes the identification of body fluids, presumptive testing, confirmatory testing, and DNA extraction. The only confirmatory method for semen identification is a microscopic visualization of sperm cells. The time spent on microscopic analysis varies depending on the complexity of the samples and the skills of the analyst. While the identification of sperm cells is informative, it can be very time-consuming and labor intensive. Some forensic laboratories choose to skip this step and submit samples directly for DNA analysis. Conducting DNA analysis on unscreened samples can increase the cost of testing when negative samples are analyzed as well as the time it takes to process each case.
Automated microscopy has been available for decades and more recently has been paired with artificial intelligence to detect sperm cells on microscope slides. In this research, the MetaSystems automated microscope was used to analyze slides that mimic forensic sexual assault samples. Slides were also examined using traditional microscopy. The automated system quickly provided an accurate quantification of the number of sperm cells present in a sample, which can inform downstream DNA testing. The software was successful in identifying sperm cells treated with Christmas tree and hematoxylin and eosin stains, even among epithelial cells and various contaminants. Results demonstrated that an artificial intelligence-driven forensic sperm cell detection microscope can significantly reduce the time it takes to locate and identify sperm cells and estimate sperm cell quantity compared to a lengthier and more tedious manual search. Drawbacks to the system include the relatively high cost and reduced ability to accurately detect sperm cells amid contaminants that are of similar morphology.
|
115 |
La microscopie à illumination à tavelure laser de type HiLo pour l'imagerie volumétrique rapide de l'activité calcique du cerveau du poisson-zèbrePineau Noël, Valérie 13 December 2023 (has links)
Ce présent projet de maîtrise porte sur le développement et l'optimisation d'une technique d'imagerie volumétrique rapide à grand champ, appelée la microscopie HiLo, pour imager l'activité calcique du cerveau de poisson-zèbres transgéniques GCaMP au stade juvénile. La microscopie HiLo peut effectivement amener divers avantages au domaine, tels que les faibles coûts et la facilité de conception et d'alignement, tout en procurant des performances d'imagerie similaires aux techniques déjà utilisées dans le domaine. Elle produit des images sectionnées optiquement en combinant deux images à grand champ pour extraire les informations provenant uniquement du plan focal : une à illumination uniforme et l'autre à illumination à tavelures laser. Le contraste des tavelures laser est un paramètre intéressant pour moduler l'épaisseur du sectionnement optique selon les besoins. Dans ce projet, un module Python est développé pour aider à la conception optique, ce qui est employé pour concevoir et construire le microscope HiLo avec les composantes optiques optimales. Le microscope est testé de multiple façon expérimentalement, définissant ses paramètres d'imagerie et démontrant ses performances. Un des aspects les plus intéressants du système est l'incorporation d'une lentille à focale variable pour produire des images volumétriques ainsi qu'un réducteur de tavelures laser pour alterner entre les deux types d'illumination. Beaucoup de travail est fait en ce qui concerne leur optimisation et synchronisation dans le système HiLo. L'algorithme permettant de produire des images sectionnées optiquement avec les deux images brutes à grand champ est développé en langage de programmation Python pour faciliter son utilisation future. Finalement, l'utilisation du microscope HiLo pour acquérir des images d'activité calcique du cerveau de poisson-zèbres permet de conclure que cette technique est prometteuse pour obtenir de l'information sur les connectivités du cerveau selon différents stimuli et stades de développement compte tenu de sa rapidité d'acquisition, son sectionnement optique et son faible coût. / The goal of this master's project is to optimize and develop a widefield imaging technique called HiLo microscopy for fast volumetric calcium imaging in a juvenile transgenic zebrafish brain expressing GCaMP. HiLo microscopy brings multiple advantages to the field, such as the low cost and the ease to design and align it and its performance is comparable to techniques already used in the field. The HiLo technique produces optically sectioned images by combining two raw widefield images to extract the information coming exclusively from the focal plane only. The first of the two images is acquired with a uniform illumination and the second is acquired with a speckle illumination. The speckle contrast is an interesting parameter to tune the optical sectioning thickness because they are indicators of objects' depth position. In this project, a Python module is developed to simulate optical design and calculations, which is then used to design the HiLo microscope with the most optimal optical components. The microscope's function is also tested with many different experiments that define its imaging parameters and demonstrates its performances. Some of the most interesting aspects of this system are the use of an electrically tunable lens to scan the sample in depth and a laser speckle reducer that is used to switch between the uniform and speckle illumination patterns. A significant amount of work is done to optimize and synchronize the components in the system. Next, the algorithm used to produce the optically sectioned images is also developed in this project with the Python programming language to facilitate its future usage. Finally, the HiLo microscope is used to produce calcium imaging acquisitions of zebrafish brains, which show that HiLo microscopy is promising to obtain connectivity information of the brain with different stimuli and at different developmental stages due to its fast acquisition speed, optical sectioning and low cost.
|
116 |
The body through the lens : anatomy and medical microscopy during the enlightenmentFoland, Jed Rivera January 2014 (has links)
This thesis examines the role of microscope technology in informing medical and anatomical knowledge during the Enlightenment. Past historians have claimed that microscopy generally stagnated until the popularisation of achromatic microscopes and cell theory in the middle of the nineteenth century. As evidence for this decline, historians have pointed to the poor quality and slow development of microscope designs until the popularisation of achromatic microscopes in the 1820s. In contrast, this thesis highlights the role of specific Enlightenment-era microscopes in answering medical and anatomical questions. It suggests that medical microscopy was far more advanced than previous scholarship has ascertained. Thus far, instrument historians have focused more attention on competing instrument makers as opposed to rival instrument users. This thesis presents several case studies which explore both makers and users. These concern the histories of Enlightenment-era epidemiology, reproduction theory, anatomy, and physiology as well as the different types of microscopes which influenced these fields. In terms of methodology, this thesis neither follows nor casts doubt on any particular theory of historical development; rather, it attempts to shed further light on available primary sources and their contexts. Presenting key case studies illustrates the difficulties that early microscope users faced in acquiring and publishing new observations. To explore the practice of early microscopy further, this thesis presents re-enactments of these case studies using Enlightenment-era microscopes and modern tissue samples. Thus, this thesis is a call to broaden the scope of primary sources available to historians of science and medicine to include instruments and re-enactments. This thesis finds that technological advances did not correlate to microscopical discovery in medicine or anatomy. Both simple and complex microscope designs aided anatomical and medical research. Broader advances in anatomy, physiology, and medical etiology dictated the utility of medical microscopy. Although various groups, such as the French clinicians, saw little need for microscopy towards the end of the eighteenth century, microscope-based evidence continued to play a diagnostic role among lesser-known practitioners despite its lack of visibility in medical literature.
|
117 |
Estudo dos estados imune e de portador em marrecos de pequim (Anas platyrhynchos) frente ao vírus da doença de NewcastleNishizawa, Márcia [UNESP] 22 February 2007 (has links) (PDF)
Made available in DSpace on 2014-06-11T19:33:26Z (GMT). No. of bitstreams: 0
Previous issue date: 2007-02-22Bitstream added on 2014-06-13T18:07:34Z : No. of bitstreams: 1
nishizawa_m_dr_jabo.pdf: 817217 bytes, checksum: c7d2f29bf8d4ac1ee5c3fbc71c4756c1 (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Parâmetros imunológicos, clínicos, epidemiológicos e patológicos da vacinação em marrecos de Pequim foram avaliados por 3 experimentos. Para tanto, foram utilizadas amostras vacinais Ulster 2C, B1 e LaSota do vírus da doença de Newcastle (VDN). No experimento 1, foram utilizados 120 marrecos de Pequim de 1 dia de idade, distribuídos em 4 tratamentos de 30 animais cada, submetidos a diferentes programas imunoprofiláticos. A resposta imune foi avaliada pelo teste de HI, com posterior desafio frente a estirpe patogênica do VDN, aos 60 dias de vida das aves. Após o desafio, em todos os grupos, procedeu-se o reisolamento de vírus patogênico em embriões SPF. Independente do grupo experimental, sinais clínicos da reação vacinal não foram observados. Os resultados dos títulos de anticorpos (HI) mostraram que os programas imunoprofiláticos ensaiados foram igualmente eficientes no estímulo da resposta imune humoral. Os marrecos de Pequim desafiados mostraram-se refratários à enfermidade clínica com o VDN. Entretanto, ficou caracterizado o estado de portador de VDN nesta espécie decorridos até 30 dias da infecção experimental com este patógeno. Nos grupos vacinados, o reisolamento de vírus patogênico foi nulo, evidenciando -se assim a importância da imunoprofilaxia na supressão do estado de portador de VDN dos marrecos de Pequim. No experimento 2, aves SPF foram colocadas em contato íntimo com marrecos de Pequim inoculados com uma estirpe patogênica do VDN, decorridos cinco e 14 dias... / The clinical, epidemiological, immunological and pathological parameters of vaccination in white Pekin ducks were investigated using 3 experiments. Ulster 2C, B1 and LaSota vaccines strains of the Newcastle disease virus (NDV) were used. In experiment 1, 120 one-day-old white Pekin ducks were used, and divided into 4 different groups with 30 birds per group. They were submitted to different vaccination programs. The immunological responses in these birds were measured by HI test. These birds were also challenged with a pathogenic VDN strain at 60 days of age. After challenge, in all the groups, tracheal and cloacal swabs were collected for re-isolation of the virus in SPF embrionated eggs. Independent of the group, clinical signs of reaction to the vaccine were not observed. The antibody titers (HI) results showed that the immune vaccine programs adopted were equally efficient in stimulating protective levels of humoral immune responses. Challenged white Pekin ducks were refractory to the NDV clinical disease. However, a NDV carrier state was shown in this species until 30 days after experimental infection. The vaccinated groups of white Pekin ducks did not present any virus in the re-isolation of the pathogenic virus. Therefore, these results show the relevance of vaccination in suppressing a NDV carrier state in the white Pekin ducks. In experiment 2, SPF chickens housed with white Pekin ducks which were previously inoculated with a pathogenic NDV strain, developed severe and characteristic NDV lesions and died, after five and 14 days...(Complete abstract, acess undermentioned eletronic address)
|
118 |
Efeitos do campo eletromagnetico em celulas e bacterias / Effects of electromagnetic field in cell and bacteriaAmaduci, Marcia Regina Lombardo 27 April 2007 (has links)
Orientador: Vitor Baranauskas / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-11T09:59:32Z (GMT). No. of bitstreams: 1
Amaduci_MarciaReginaLombardo_M.pdf: 2445338 bytes, checksum: 4bb1cb55957a33fb2a440282e189204d (MD5)
Previous issue date: 2007 / Resumo: Este trabalho refere-se a alguns efeitos de um campo eletromagnético aplicados em colônias bacterianas. A bactéria escolhida é bastante conhecida no mundo científico e tratase da Escherichia coli (E. coli). A parte experimental divide-se entre a análise quantitativa, qualitativa e morfológica sobre o ciclo de vida da E. coli. O circuito eletromagnético foi gerado a partir de uma freqüência de 60Hz. Durante um período de 18h, as bactérias acopladas ao circuito eletromagnético se proliferaram em meio aquoso e a cada fase do ciclo de vida da E. coli, foram realizadas diluições em tubos de ensaio para a análise da absorbância e contagem de bactérias viáveis. Ao mesmo tempo foram colocados em uma estufa, na mesma temperatura do circuito, tubos contendo a mesma amostra em quantidade e qualidade, para uma análise paralela do seu ciclo de vida. O trabalho inclui análise morfológica, com a utilização da microscopia eletrônica de transmissão (MET) e da microscopia eletrônica de varredura (MEV) / Abstract: This research work studies some effects of an electromagnetic field applied on bacteria. The chosen bacterium is quite known in the scientific world, the Escherichia coli (E. coli). The experimental part was divided into the quantitative, qualitative and morphologic analysis on the life of bacterium Escherichia coli. The electromagnetic circuit was generated from a frequency of 60Hz. During a period of 18h, the bacteria connected to the electromagnetic circuit proliferated in watery way, and for each phase of the life cycle of E. coli LT1, dilutions in test tube were performed for the analysis of the absorbancy and counting of viable bacteria. At the same time, other test tubes holding the same sample in amount and quality were placed in a incubator, at the same temperature of the circuit, for a parallel analysis of its cycle of life. The work includes morphologic analysis, with the use of transmission electronic microscopy (TEM), and scanning electronic microscopy (SEM) / Mestrado / Eletrônica, Microeletrônica e Optoeletrônica / Mestre em Engenharia Elétrica
|
119 |
Méthodes d'augmentation de résolution en microscopie optique exploitant le modelage de faisceau laser et la déconvolutionThibon, Louis 03 May 2019 (has links)
La microscopie à balayage laser est limitée en résolution par la limite de diffraction de la lumière. Plusieurs méthodes de superrésolution ont été développées depuis les années 90 pour franchir cette limite. Cependant, la superrésolution est souvent obtenue au prix d'une grande complexité (laser de haute puissance pulsé, temps d'acquisition long, fluorophores spécifiques) ainsi que des limitations dans le type d'échantillon observé (observation en surface uniquement). Dans certains cas, comme pour l'illumination structurée et la microscopie SLAM, une amélioration en résolution plus modeste est obtenue, mais avec une complexité et des limites d'utilisation fortement réduites par rapport aux autres méthodes de superrésolution. Les mé- thodes que nous proposons ici sont des méthodes d'augmentation de résolution qui visent à minimiser les contraintes expérimentales et à garder un maximum des avantages des techniques d'imagerie conventionnelles. Dans les cas que nous avons étudiés, les méthodes proposées sont basées sur la microscopie confocale. Nous allons montrer dans un premier temps qu'il est possible d'augmenter de 20% la résolution d'un microscope confocal en changeant le faisceau laser utilisé pour l'excitation par un faisceau Bessel-Gauss tout en ayant un sténopé de la bonne taille (soit 1 Airy Unit). Les avantages de la méthode proposée résident dans sa simplicité d'installation et d'utilisation et sa compatibilité avec d'autres méthodes d'augmentation de résolution. Nous avons démontré les capacités d'augmentation de résolution des faisceaux Bessel-Gauss théoriquement puis exp érimentalement sur des échantillons de nano-sphères et de tissus biologiques obtenant ainsi une résolution de 0.39. Nous avons également montré que l'amélioration en résolution des faisceaux Bessel-Gauss donne une analyse statistique de la colocalisation avec un taux plus faible de faux positifs. Nous avons utilisé des faisceaux Bessel-Gauss de différents ordres pour améliorer la méthode de la microscopie SLAM et ainsi obtenir une résolution descendant à 0.17 (90 nm avec une longueur d'onde de 532 nm). La méthode proposée est entièrement basée sur la microscopie confocale et seul un module permettant de changer le faisceau laser doit être ajouté au montage. Dans un second temps, nous proposons une méthode permettant de bénéficier au maximum des propriétés de la déconvolution pour augmenter la résolution de la microscopie confocale. Pour cela, nous avons utilisé différents modes laser pour l'acquisition d'images et ces images sont utilisées comme données d'entrée pour la déconvolution (avec des mesures des PSF respectives). Les faisceaux laser utilisés apportent ainsi des informations complémentaires à l'algorithme de déconvolution permettant ainsi d'obtenir des images avec une résolution encore meilleure que si une simple déconvolution (utilisant le même algorithme) était utilisée sur l'image confocale. Par la suite, nous avons changé les faisceaux laser par des faisceaux Bessel-Gauss pour augmenter davantage l'ecacité de la déconvolution. Encore une fois, la méthode proposée est entièrement basée sur la microscopie confocale et seul un module permettant de changer le faisceau laser doit être ajouté au montage. Enfin, nous proposons d'aborder une méthode de reconstruction en trois dimensions par tomographie basée sur des projections obtenues en microscopie à deux photons utilisant les faisceaux Bessel-Gauss. En focalisant des faisceaux Bessel-Gauss à angle en microscopie deux photons, on obtient une série de projections utilisables pour une reconstruction tomographique. Le but est de tester la faisabilité de la méthode qui permettrait de reconstruire un volume, en nécessitant moins d'images que dans le cas d'une acquisition plan par plan, en microscopie deux photons classique. / Laser scanning microscopy is limited in lateral resolution by the diffraction of light. Superresolution methods have been developed since the 90s to overcome this limitation. However, superresolution is generally achieved at the cost of a greater complexity (high power lasers, very long acquisition times, specic uorophores) and limitations on the observable samples. In some cases, such as Structured Illumination Microscopy (SIM) and Switching Laser Modes (SLAM), a more modest improvement in resolution is obtained with a reduced complexity and fewer limitations. We propose here methods which improve the resolution while minimizing the experimental constraints and keeping most of the advantages of classical microscopy. First, we show that we can improve by twenty percent the resolution of confocal microscopy by using Bessel-Gauss beams, and by having the right pinhole size (1 Airy Unit), compared to conventional Gaussian beam based confocal microscopy. The advantages of this strategy include simplicity of installation and use, linear polarization compatibility, possibility to combine it with other resolution enhancement and superresolution strategies. We demonstrate the resolution enhancement capabilities of Bessel-Gauss beams both theoretically and experimentally on nano-spheres and biological tissue samples with a resolution of 0.39. We achieved these resolutions without any residual artifacts coming from the Bessel-Gauss beam side lobes. We also show that the resolution enhancement of Bessel-Gauss beams leads to a better statistical colocalization analysis with fewer false positive results than when using Gaussian beams. We have also used Bessel-Gauss beams of different orders to further improve the resolution by combining them in SLAM microscopy achieving a resolution of 0.17 (90 nm with a wavelength of 532 nm). In a second step, we propose a method to improve the resolution of confocal microscopy by combining different laser modes and deconvolution. Two images of the same eld are acquired with the confocal microscope using different laser modes and are used as inputs to a deconvolution algorithm. The two laser modes have different Point Spread Functions and thus provide complementary information leading to an image with enhanced resolution compared to using a single confocal image as input to the same deconvolution algorithm. By changing the laser modes to Bessel-Gauss beams, we were able to improve the effciency of the deconvolution algorithm and to obtain images with a residual Point Spread Function having a width smaller than 100 nm. The proposed method requires only a few add-ons to the classic confocal or two photon microscopes. Finally, we propose a three dimensional tomography reconstruction method using Bessel-Gauss beams as projection tools in two-photon microscopy. While focussing Bessel-Gauss beams at an angle in two photon microscopy, we can obtain a series of projections that can be used for tomography reconstruction. The aim is to test the practicality of the methods allowing to reconstruct a volume while using fewer images than plane by plane acquisitions as in classic two-photon microscopy.
|
120 |
Automatic recognition of low-level and high-level surgical tasks in the Operating Room from video imagesLalys, Florent 03 May 2012 (has links) (PDF)
La besoin d'une meilleure intégration des nouveaux systèmes de chirurgie assistée par ordinateur dans les salles d'opération à récemment été souligné. Une nécessité pour atteindre cet objectif est de récupérer des données dans les salles d'opérations avec différents capteurs, puis à partir de ces données de créer des modèles de processus chirurgicaux. Récemment, l'utilisation de vidéos dans la salle d'opération a démontré son efficacité pour aider à la création de systèmes de CAO sensibles au contexte. Le but de cette thèse était de présenter une nouvelle méthode pour la détection automatique de tâches haut niveaux (i.e. phases chirurgicales) et bas-niveaux (i.e. activités chirurgicales) à partir des vidéos des microscopes uniquement. La première étape a consisté à reconnaitre automatiquement les phases chirurgicales. L'idée fut de combiner des techniques récentes de vision par ordinateur avec une analyse temporelle. Des classifieurs furent tout d'abord mis en œuvre pour extraire des attributs visuels et ainsi caractériser chaque image, puis des algorithmes de classification de séries temporelles furent utilisés pour reconnaitre les phases. La deuxième étape a consisté à reconnaitre les activités chirurgicales. Des informations concernant des outils chirurgicaux et des structures anatomiques furent détectées et combinées avec l'information de la phase précédemment obtenu au sein d'un système de reconnaissance intelligent. Après des validations croisées sur des vidéos de neurochirurgie et de chirurgie de l'œil, nous avons obtenu des taux de reconnaissance de l'ordre de 94% pour la reconnaissance des phases et 64% pour la reconnaissance des activités. Ces systèmes de reconnaissance pourraient être utiles pour générer automatiquement des rapports post-opératoires, pour l'enseignement, l'apprentissage, mais aussi pour les futurs systèmes sensibles au contexte.
|
Page generated in 0.064 seconds