Search

в данной статье исследователями рассматриваются фазы развития автоматизации в сфере производства, а также некоторые технические средства и процессы, сопутствующие этому., The article deals with the development phase of automation in manufacturing, as well as some of the technical tools and processes that accompany it.

Geologists in charge of a detailed lineament mapping in arid and desert area, face the extent of the land and the abundance of eolian deposits. This study presents a semi-automatic approach of extraction of lineament, different from other methods, such as the automatic extraction and manual extraction, by being both fast and objective. It consists of a series of digital processing (textural and spatial filtering, binarization by thresholding and mathematic morphology ... etc.) applied to a Landsat 7 ETM+scene. This semi-automatic approach has produced a detailed map of lineaments, while taking account of tectonic directions recognized in the region. It helps mitigate the effect of dune deposits meet the specifications of arid environment. The visual validation of these linear structures, by geoscientists and field data, allowed the identification of the majority of structural lineaments or at least those tried geological.[fr] Les géologues en charge d’une cartographie des linéaments détaillée en domaine aride et désertique, font face à l’étendue des terrains et la présence abondante de dépôts éoliens. La présente étude présente une approche semi-automatique différente des autres méthodes d’extraction des linéaments, à savoir l’extraction automatique et l’extraction manuelle par le fait d’être à la fois rapide et objective. Elle consiste en une succession de traitements numériques (filtrage textural et spatial, binarisation par seuillage et morphologie mathématique…etc.) appliqués sur une scène LANDSAT-7 ETM+. Cette approche semi-automatique a permis d’obtenir une carte détaillée des linéaments, tout en tenant compte des directions tectoniques reconnues dans la région. Elle permet d’atténuer l’effet des dépôts dunaires répondant aux spécifications du contexte aride. La validation visuelle de ces structures linéaires, effectuée sur terrain et sur la base de la carte géologique et des données géoscientifiques existantes, a permis l’identification de la majorité des linéaments jugés structuraux ou du moins géologiques.

In the recent years, a considerable level of interest has been developed on the use of earth in construction, led by its rediscovery as an environmentally building material. The Stabilized Earth Concrete (SEC) is a good alternative to the cement concrete, thanks to its thermal and moisture regulating features. Many parameters affect the behavior of stabilized earth concrete. This article presents research results related to the influence of the compacting nature on some SEC properties namely: The mechanical behavior, capillary absorption, shrinkage and sustainability to water erosion, and this, basing on two types of compacting: Manual and semi-automatic., {"references":["Kerali A-G, Durability of compressed and cement-stabilized building blocks. A thesis submitted in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Engineering. University of Warwick, School of Engineering, 2001.","CNERIB, Recommandations pour la production et la mise en œuvre des bétons de terre stabilisée. CNERIB – CRATerre, 1993.","Adam.E.A in collaboration with Professor A.R.A.Agib, Compressed Stabilised Earth Block Manufacture in Sudan. United Nations Educational, Scientific and Cultural Organization UNESCO, 2001.","By iyambo ipinge, durability of compressed stabilised earth blocks, A research report submitted to the Faculty of Engineering, University of the Witwatersrand, in partial fulfilment of the requirements of the Master of Science in Civil Engineering July, 2012.","H.B. Nagaraj, M.V. Sravan, T.G. Arun, K.S. Jagadish, Role of lime with cement in long-term strength of Compressed Stabilized Earth Blocks, International Journal of Sustainable Built Environment, 2014.","Bahar.R, Benazzoug.M, Kenai.S. (2004). Performance of compacted cement-stabilised soil, Cement & Concrete Composites 26, pp 811–820.","Guettala A, Houari H, Mezghiche B, Chebili R. Durability of lime stabilized earth bloks. In: Proceedings of Modern Earth Building, Berlin, Germany; 2002. p. 162–9.","Houben H, Guillaud H. CRATerre. Earth Construction 1984, Primer Brussels, CRATerre/PGC/CRA/UNCHS/AGCD.","Lan Wang (2002). Cementitious stabilization of soils in the presence of sulfate. A Dissertation Submitted to Graduate Faculty of the Louisiana State University and Agricultural and Mechanical College in partial fulfillment of the Requirements for the degree of Doctor of Philosophy. Wuhan University of Technology. \n[10]\tPeter Walker and Trevor Stace, Properties of some cement stabilised compressed earth blocks and mortars, Materials and Structures/Matériaux et Constructions, Vol. 30, November 1997, pp 545-551. \n[11]\tGoual Idriss, Goual Mohamed sayah, Ferhat Ahmida, stabilisation aux liants hydrauliques des tufs de la région de Laghouat : l'influence des conditions de durcissement à l'air libre et a l'eau sur le comportement mécanique, Colloque CMEDIMAT 2005, 06 et 07 Décembre 2005."]}

Geologists in charge of a detailed lineament mapping in arid and desert area, face the extent of the land and the abundance of eolian deposits. This study presents a semi-automatic approach of extraction of lineament, different from other methods, such as the automatic extraction and manual extraction, by being both fast and objective. It consists of a series of digital processing (textural and spatial filtering, binarization by thresholding and mathematic morphology ... etc.) applied to a Landsat 7 ETM+scene. This semi-automatic approach has produced a detailed map of lineaments, while taking account of tectonic directions recognized in the region. It helps mitigate the effect of dune deposits meet the specifications of arid environment. The visual validation of these linear structures, by geoscientists and field data, allowed the identification of the majority of structural lineaments or at least those tried geological. [fr] Les géologues en charge d’une cartographie des linéaments détaillée en domaine aride et désertique, font face à l’étendue des terrains et la présence abondante de dépôts éoliens. La présente étude présente une approche semi-automatique différente des autres méthodes d’extraction des linéaments, à savoir l’extraction automatique et l’extraction manuelle par le fait d’être à la fois rapide et objective. Elle consiste en une succession de traitements numériques (filtrage textural et spatial, binarisation par seuillage et morphologie mathématique…etc.) appliqués sur une scène LANDSAT-7 ETM+. Cette approche semi-automatique a permis d’obtenir une carte détaillée des linéaments, tout en tenant compte des directions tectoniques reconnues dans la région. Elle permet d’atténuer l’effet des dépôts dunaires répondant aux spécifications du contexte aride. La validation visuelle de ces structures linéaires, effectuée sur terrain et sur la base de la carte géologique et des données géoscientifiques existantes, a permis l’identification de la majorité des linéaments jugés structuraux ou du moins géologiques.

In this thesis, we have studied the problem of detecting automated Twitter accounts related to the Ukraine conflict using supervised learning. A striking problem with the collected data set is that it was initially lacking a ground truth. Traditionally, supervised learning approaches rely on manual annotation of training sets, but it incurs tedious work and becomes expensive for large and constantly changing collections. We present a novel approach to synthetically generate large amounts of labeled Twitter accounts for detection of automation using a rule-based classifier. It significantly reduces the effort and resources needed and speeds up the process of adapting classifiers to changes in the Twitter-domain. The classifiers were evaluated on a manually annotated test set of 1,000 Twitter accounts. The results show that rule-based classifier by itself achieves a precision of 94.6% and a recall of 52.9%. Furthermore, the results showed that classifiers based on supervised learning could learn from the synthetically generated labels. At best, the these machine learning based classifiers achieved a slightly lower precision of 94.1% compared to the rule-based classifier, but at a significantly better recall of 93.9% Detta exjobb har undersökt problemet att detektera automatiserade Twitter-konton relaterade till Ukraina-konflikten genom att använda övervakade maskininlärningsmetoder. Ett slående problem med den insamlade datamängden var avsaknaden av träningsexempel. I övervakad maskininlärning brukar man traditionellt manuellt märka upp en träningsmängd. Detta medför dock långtråkigt arbete samt att det blir dyrt förstora och ständigt föränderliga datamängder. Vi presenterar en ny metod för att syntetiskt generera uppmärkt Twitter-data (klassifieringsetiketter) för detektering av automatiserade konton med en regel-baseradeklassificerare. Metoden medför en signifikant minskning av resurser och anstränging samt snabbar upp processen att anpassa klassificerare till förändringar i Twitter-domänen. En utvärdering av klassificerare utfördes på en manuellt uppmärkt testmängd bestående av 1,000 Twitter-konton. Resultaten visar att den regelbaserade klassificeraren på egen hand uppnår en precision på 94.6% och en recall på 52.9%. Vidare påvisar resultaten att klassificerare baserat på övervakad maskininlärning kunde lära sig från syntetiskt uppmärkt data. I bästa fall uppnår dessa maskininlärningsbaserade klassificerare en något lägre precision på 94.1%, jämfört med den regelbaserade klassificeraren, men med en betydligt bättre recall på 93.9%.

In light of the increasing availability of commercial high-resolution imaging sensors, automatic interpretation tools are needed to extract road features. Currently, many approaches for road extraction are available, but it is acknowledged that there is no single method that would be successful in extracting all types of roads from any remotely sensed imagery. In this paper, a novel classification of roads is proposed, based on both the roads' geometrical, radiometric properties and the characteristics of the sensors. Subsequently, a general road tracking framework is proposed, and one or more suitable road trackers are designed or combined for each type of roads. Extensive experiments are performed to extract roads from aerial/satellite imagery, and the results show that a combination strategy can automatically extract more than 60% of the total roads from very high resolution imagery such as QuickBird and DMC images, with a time-saving of approximately 20%, and acceptable spatial accuracy. It is proven that a combination of multiple algorithms is more reliable, more efficient and more robust for extracting road networks from multiple-source remotely sensed imagery than the individual algorithms.

In medical imaging, segmentation of different areas of human body like bones, organs, tissues, etc. is an important issue. Image segmentation allows isolating the object of interest for further processing that can lead for example to 3D model reconstruction of whole organs. Difficulty of this procedure varies from trivial for bones to quite difficult for organs like liver. The liver is being considered as one of the most difficult human body organ to segment. It is mainly for its complexity, shape versatility and proximity of other organs and tissues. Due to this facts usually substantial user effort has to be applied to obtain satisfactory results of the image segmentation. Process of image segmentation then deteriorates from automatic or semi-automatic to fairly manual one. In this paper, overview of selected available software applications that can handle semi-automatic image segmentation with further 3D volume reconstruction of human liver is presented. The applications are being evaluated based on the segmentation results of several consecutive DICOM images covering the abdominal area of the human body., {"references":["Suhuai, L., Xuechen, L., Jiaming, L., 2014. Review on the methods of\nautomatic liver segmentation from abdominal images. In Journal of\nComputer and Communications, Vol. 2, No. 2, pp 1-7. Scientific\nResearch. DOI: 10.4236/jcc.2014.22001.","Mharib, A., Ramli, A., Mashohor, S., Mahmood, R., 2012. Survey on\nliver CT image segmentation methods. In Artificial Intelligence Review,\nVol. 37, No. 2 , pp 83-95. Springer Netherlands. DOI: 10.1007/s10462-\n011-9220-3.","ITK - Segmentation & Registration Toolkit, 2014. Available from:\n. (9 November 2014).","VTK - The Visualization Toolkit, 2014. Available from:\n. (9 November 2014).","ITK-SNAP Home Page, 2014. Available from:\n. (9 November 2014).","General Public License, 2007. Available from:\n. (9 November 2014).","Yushkevich, P., Piven, J., Cody, H., Smith, R., Ho, S., Gee, J., Gerig, G.,\n2006. User-guided 3D active contour segmentation of anatomical\nstructures: Significantly improved efficiency and reliability. In\nNeuroimage,Vol. 31, No. 3, pp. 1116-28. Elsevier. DOI:\n10.1016/j.neuroimage.2006.01.015.","DICOM Homepage, 2014. Available from: . (9\nNovember 2014).","GeoS - Microsoft Research, 2014. Available from:\n. (9 November 2014).\n[10] Microsoft Research License Agreement, 2013. Available from:\n. (9 November 2014).\n[11] Criminisi, A., Sharp, T., Blake, A., 2008. GeoS: Geodesic Image\nSegmentation. In ECCV 2008, eds D. Forsyth, P. Torr, and A.\nZisserman, Part I, LNCS 5302, pp. 99–112, Springer-Verlag Berlin\nHeidelberg.\n[12] Jirik, M., Ryba, T., Svobodova, M., Mira, H., Liska, V., 2014. Lisa –\nLiver surgery analyser software development. In Proceedings of WCCM\nXI-ECCM V-ECFD VI. Barcelona.\n[13] Lisa GitHub, 2012. Available from: . (9 November 2014).\n[14] Boykov, Y., Funka-Lea, G., 2006. Graph cuts and efficient N-D image\nsegmentation. In International Journal of Computer Vision, Vol. 70, No.\n2, pp 109–131. Kluwer Academic Publishers. DOI: 10.1007/s11263-\n006-7934-5.\n[15] Introduction – SlicerWeb, 2014. Available from:\n. (9 November 2014).\n[16] LicenseText – SlicerWeb, 2005. Available from:\n. (9 November 2014).\n[17] Ghosh, P., Antani, S. K., Long, L. R., Thoma, G. R., 2011.\nUnsupervised grow-cut: Cellular automata-based medical image\nsegmentation. In Healthcare Informatics, Imaging and Systems Biology,\npp 40-47. IEEE. DOI: 10.1109/HISB.2011.44.\n[18] About OsiriX, 2014. Available from: . (9 November 2014).\n[19] License - license.pdf, 2007. Available from: . (9 November 2014).\n[20] DICOM files, 2014. Available from: . (9 November 2014)."]}

Computer-assisted image processing for extracting of IMP on the basis of object oriented analysis (using images segmentation) was carried out (by means of factor and cluster analysis) within the interactive interpretation of images. The final evaluation will be conducted by experienced interpreter and it will be also carried out on the basis of NIIRS and IQM parameters. The one aim of this research is to establish a methodology and guidelines for interactive semi-automatic interpretation of digital images in humanitarian demining for the purpose of detection and extraction of (strong) indicators of mine presence and absence which can be seen on the images. The experience gathered in working with AI DSS in undertaken projects led to the conclusion that a man (the human eye and contextual view on the scene) as interpreter (of mine scene) can hardly be replaced by automatic methods of digital image processing. However, some methods of digital image processing (implemented in certain ways) may help the interpreter in the identification of certain anomalies in the scene and easier detection of indicators. The basic idea of interactive methods of semi-automatic interpretation of digital images of SHA is to provide assistance to the interpreter in the interpretation of digital images rather than to replace him. The objective of this method is to be sensor independent and independent of object of research. The concept of this method was defined and initial research carried out in 2013.

Background Objective techniques to assess the amelioration of vision in patients with impaired visual function are needed to standardize efficacy assessment in gene therapy trials for ocular diseases. Pupillometry has been investigated in several diseases in order to provide objective information about the visual reflex pathway and has been adopted to quantify visual impairment in patients with Leber Congenital Amaurosis (LCA). In this paper, we describe detailed methods of pupillometric analysis and a case study on three Italian patients affected by Leber Congenital Amaurosis (LCA) involved in a gene therapy clinical trial at two follow-up time-points: 1 year and 3 years after therapy administration. Methods Pupillary light reflexes (PLR) were measured in patients who had received a unilateral subretinal injection in a clinical gene therapy trial. Pupil images were recorded simultaneously in both eyes with a commercial pupillometer and related software. A program was generated with MATLAB software in order to enable enhanced pupil detection with revision of the acquired images (correcting aberrations due to the inability of these severely visually impaired patients to fixate), and computation of the pupillometric parameters for each stimulus. Pupil detection was performed through Hough Transform and a non-parametric paired statistical test was adopted for comparison. Results The developed program provided correct pupil detection also for frames in which the pupil is not totally visible. Moreover, it provided an automatic computation of the pupillometric parameters for each stimulus and enabled semi-automatic revision of computerized detection, eliminating the need for the user to manually check frame by frame. With reference to the case study, the amplitude of pupillary constriction and the constriction velocity were increased in the right (treated eye) compared to the left (untreated) eye at both follow-up time-points, showing stability of the improved PLR in the treated eye. Conclusions Our method streamlined the pupillometric analyses and allowed rapid statistical analysis of a range of parameters associated with PLR. The results confirm that pupillometry is a useful objective measure for the assessment of therapeutic effect of gene therapy in patients with LCA. Trial registration ClinicalTrials.gov NCT00516477

Arbeitsberichte Verkehrs- und Raumplanung, 727

These works take place in the framework of building extraction and 3D building reconstruction in urban and semi-urban areas, from high-resolution optical and SAR satellite images. The main objective is to develop a complete semi-automatic processing chain, able to provide a simple and reliable reconstruction of parallelepipedic buildings on the scene, from a specific configuration of the input data, composed of an optical image and a SAR image, and from a digital terrain model. This restricted configuration, particularly delicate to deal with but likely to happen in operational conditions, has been until now studied only in a few works. Proposing a specific approach to manage such a scenario seems thus very interesting for a lot of applications in remote sensing. We aim to fully benefit from the data fusion context, by exploiting, in an appropriate way, the optical-SAR complementarities for the reconstruction of the scene, through the combination of planimetric and altimetric information. The proposed chain is decomposed into four steps: potential building detection in optical monoscopy; projection and registration of the potential optical footprints into SAR data; height estimation and building validation on the SAR image; qualification of the reconstructed buildings. The whole chain is applied on studied scenes issued from a couple of Quickbird and TerraSAR-X real data. The obtained results are qualitatively and quantitatively analyzed. A globally satisfying reconstruction of the buildings is achieved., Ces travaux s'inscrivent dans le cadre de l'extraction et de la reconstruction 3D des bâtiments en milieu urbain et semi-urbain, à partir d'images satellitaires optiques et RADAR à haute résolution. L'objectif majeur réside dans le développement d'une chaîne complète de traitements semi-automatiques, capable de fournir une reconstruction simple et fiable des bâtiments parallélépipédiques de la scène, à partir d'une configuration spécifique des données d'entrée, composée d'une image optique et d'une image RADAR, ainsi que d'un modèle numérique de terrain. Cette configuration restreinte, particulièrement délicate à traiter mais susceptible d'intervenir en milieu opérationnel, a fait l'objet de peu de travaux. La proposition d'une démarche dédiée à la gestion d'un tel scénario représente donc un intérêt certain pour plusieurs applications de télédétection. L'enjeu consiste à bénéficier pleinement du contexte de la fusion de données, en exploitant, de façon appropriée, les complémentarités optiques et RADAR, en vue d'une reconstruction de la scène par combinaison d'informations planimétriques et altimétriques. La chaîne proposée se décompose en quatre étapes : détection des bâtiments potentiels en monoscopie optique ; projection et recalage des emprises optiques potentielles dans la donnée RADAR ; estimation des hauteurs et validation des bâtiments sur l'image RADAR ; qualification des bâtis reconstruits. La chaîne complète est mise en œuvre sur des scènes d'étude issues d'un couple de données réelles Quickbird et TerraSAR-X. Les résultats fournis sont analysés qualitativement et quantitativement. Une reconstruction globalement satisfaisante des bâtiments est obtenue.

Tez (Doktora) -- İstanbul Teknik Üniversitesi, Fen Bilimleri Enstitüsü, 2006, Thesis (PhD) -- İstanbul Technical University, Institute of Science and Technology, 2006, Bu çalışmada; dijital hava fotoğrafları üzerinden yollar, binalar, dereler ve göller gibi çizgisel ve alansal detayların sınırlarının ve merkez hatlarının yarı otomatik olarak belirlenmesini sağlayan bir yöntem ve bu yöntemin uygulamaya konmasına yönelik bir yazılım geliştirilmiştir. Otomatik ve yarı otomatik detay belirleme yöntemleri üzerine yapılan çalışmalarda yol izleme ve aktif kontur modeller gibi yöntemler kullanılmakta ve bu yöntemler kullanılan fotoğrafın, düşük veya yüksek çözünürlüğe sahip olmasına bağlı olarak sınıflandırılmaktadır. Geliştirilen yöntem, görüntü bölümleme ve düzey kümesi algoritmalarının birlikte kullanılmasına dayanmaktadır Yöntemin uygulanabilirliğinin araştırılması amacıyla farklı ölçekte ve özelliklerde hava fotoğrafları ve uydu görüntüleri üzerinde yarı otomatik detay çizme işlemleri gerçekleştirilmiştir. Bununla birlikte; İTÜ Ayazağa Kampüsünü içeren ortotofo görüntüler kullanılarak bir doğruluk araştırması yapılıp, yöntemin hata kriterinin ± 0.5m., başka bir deyişle ± 1 piksel olduğu belirlenmiştir. Elde edilen sonuçlar, bu yöntemin harita üretiminde ve coğrafi bilgi sistemleri için veri toplamada kullanılabileceğini göstermiştir., In this study, a semi-automatic extraction method for extracting the center lines and the boundaries of line and area features from digital aerial photographs and a software of this method is developed. Automatic and semi-automatic feature extraction methods are generally using road tracing and snake algorithms and they are classified as the feature extraction methods in low, high and multi resolutions by the resolution of the used digital images. The developed method is based on the image segmentation by the level set algorithms. Some semi-automatic extraction applications are made by the help of the developed software using the different aerial and satellite images for determining the capabilities of this method. Another application for the Ayazağa Campus of İTU, is also carried out. In this application two ortho images, which have 0.5m resolution, are used. An accuracy test is carried out in this application area for determining the accuracy of this method and the square mean root is found for buildings as ± 0.463 m. and for roads as ± 0.663 m. In other words it means ±1 pixel of the image. It can be said as the results of the applications, that this method can be used for producing the maps and for collecting vector data for geographic information systems., Doktora, PhD

BACKGROUND: Delayed enhancement magnetic resonance imaging depicts scar in the left ventricle which can be quantitatively measured. Manual segmentation and scar determination is time consuming. The purpose of this study was to evaluate a software for infarct quantification, to compare with manual scar determination, and to measure the time saved. METHODS: Delayed enhancement magnetic resonance imaging was performed in 40 patients where myocardial perfusion single photon emission computed tomography imaging showed irreversible uptake reduction suggesting a myocardial scar. After segmentation, the semi-automatic software was applied. A scar area was displayed, which could be corrected and compared with manual delineation. The different time steps were recorded with both methods. RESULTS: The software shortened the average evaluation time by 12.4 min per cardiac exam, compared with manual delineation. There was good correlation of myocardial volume, infarct volume and infarct percentage (%) between the two methods, r = 0.95, r = 0.92 and r = 0.91 respectively. CONCLUSION: A computer software for myocardial volume and infarct size determination cut the evaluation time by more than 50% compared with manual assessment, with maintained clinical accuracy.

La cartografía de Modelos de Combustibles es una herramienta clave en los procesos de toma de decisiones para la prevención y defensa frente a los incendios forestales. Siendo por tanto necesario mantenerla actualizada para describir de la forma más fiable posible la realidad; aunque esta tarea es complicada debido a los constante cambios en las coberturas del suelo. Los objetivos planteados en este trabajo son tres: (1) Cartografía de cuatro grandes tipos de combustibles en base a diferencias espectrales, empleando imágenes de satélite y software libre, (2) Cartografía de áreas quemadas a partir de un análisis multitemporal de imágenes satélite, empleando una plataforma web para el procesamiento geoespacial, y (3) Evaluación de la metodología propuesta para actualizar el mapa de combustibles actual de forma semi-automática. Los procesos seguidos se han divido en dos bloques: cartografía de cuatro tipos de combustibles y de zonas quemadas, en los que aunque planteando un tipo de análisis distinto se comparten varios pasos. Para generar la cartografía de los cuatro tipos de vegetación se llevó a cabo un análisis basado en objetos (OAA) u Object Based Analysis (OBIA) sobre una colección multitemporal de imágenes Satélite Sentinel 2 MSI. El primer paso consistió en la adquisición y el procesado de las imágenes, que posteriormente fueron segmentadas para generar la base de datos necesaria para llevar a cabo la clasificación automática supervisada final. Para general la cartografía de áreas quemadas, se empleó una serie temporal de imágenes Sentinel 2 MSI. En este caso se llevó a cabo la adquisición y el procesado de las imágenes y posteriormente se efectuó directamente el proceso de clasificación, ya que al plantear un análisis a nivel de píxel la base de datos de referencia se creó sin llevar a cabo la segmentación de las imágenes. Los resultados obtenidos demuestran la posibilidad de identificar diferentes coberturas de forma fiable en base a la información que ofrecen las imágenes multiespectrales Sentinel 2 MSI. La clasificación de los grupos de combustibles alcanzó una exactitud global del 87,01 %, mientras el valor de la exactitud global de clasificación de áreas quemadas es 98, 28 %. La metodología empleada en este trabajo, que se basa en el uso sensores remotos pasivos en la combinación de diferentes softwares libres y comerciales, permite actualizar la cartografía existente y por tanto disponer de herramientas con información actualizada, muy apreciadas en tareas de planificación de la gestión y defensa de los incendios forestales.

[CATALÀ] Actualment, existeixen moltes màquines de cafè per a ús particular, permetent a l’usuari fer-se una tassa a qualsevol hora del dia. El problema d’aquestes cafeteres és que no s’acaben d’adaptar a totes les necessitats dels usuaris. Per exemple, un sol usuari pot arribar a tenir diferents preferències alhora de beure cafè, és a dir, que un dia li pot preferir prendre un cafè de càpsula i un altre dia un cafè expresso tradicional elaborat a partir del gra. L’objectiu d’aquest projecte és dissenyar una cafetera que admeti els tres formats de cafè: gra, mòlt o mono-dosis. A més, el projecte pretén tornar a apassionar als usuaris a beure cafè expresso tradicional a partir del gra, intentat conservar el màxim el seu aroma i sabor particular. Al final del projecte s’ha aconseguit dissenyar una màquina de cafè semiautomàtica que admet els tres formats de cafè: gra, mòlt o mono-dosis, oferint a l’usuari una diversitat de tipologies de cafè. A més, la cafetera del projecte elabora un autèntic cafè expresso italià a partir del gra, conservant el màxim el seu sabor i aroma particular. La cafetera presenta un avanç tecnològic a l’incorporar una pantalla tàctil per a la comunicació entre l’usuari i la màquina, a més manté informat a l’usuari sobre l’estat de la cafetera. I finalment, l’estètica exterior de la cafetera trenca amb els esquemes de les màquines de cafè actuals, ja que consta d’una forma esfèrica, aportant una elegància i suavitat al disseny. La forma exterior fa que la cafetera deixi de ser un simple aparell més de la casa sinó que passa a ser part de la decoració. [ANGLÈS] Currently, there are many coffee machines for private use, allowing the user to make a cup at any time of day. The problem with these coffee makers is that they do not end up adapting to all the needs of the users. For example, a single user can have different preferences at the same time to drink coffee, that is, one day it may be more desiderate to have a coffee of capsule and another day, a traditional espresso made from grains. The objective of this project is to design a coffee machine that supports the three formats of coffee: grain, ground or mono-doses. In addition, the project aims to re-inspire the users to drink traditional espresso coffee from grains, trying to keep their particular aroma and taste. At the end of the project, a semi-automated coffee machine has been designed that supports the three formats of coffee: grain, ground or monodoses, offering the user a variety of types of coffee. In addition, the coffeemaker of the project produces a genuine Italian espresso coffee from the grain, keeping most its taste and aroma. The coffee machine presents a technological breakthrough when incorporating a touch screen for communication between the user and the machine, and also keeps the user informed about the state of the coffee machine. And finally, the exterior aesthetics of the coffee maker breaks with the schemes of the current coffee machines, since it consists of a spherical shape, providing elegance and softness to the design. The outside shape makes the coffee maker stop being a simple device more than the house but instead becomes part of the decoration.