An illustrative non-technical review was published on Towards Data Science regarding our recent Journal paper “Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning”.While new technologies have changed almost every aspect of our lives, the construction field seems to be struggling to catch up. Currently, the structural condition of a building is still predominantly manually inspected. In simple terms, even nowadays when a structure needs to be inspected for any damage, an engineer will manually check all the surfaces and take a bunch of photos while keeping notes of the position of any cracks. Then a few more hours need to be spent at the office to sort all the photos and notes trying to make a meaningful report out of it. Apparently this a laborious, costly, and subjective process. On top of that, safety concerns arise since there are parts of structures with access restrictions and difficult to reach. To give you an example, the Golden Gate Bridge needs to be periodically inspected. In other words, up to very recently there would be specially trained people who would climb across this picturesque structure and check every inch of it.
LINK
Industrial robot manipulators are widely used for repetitive applications that require high precision, like pick-and-place. In many cases, the movements of industrial robot manipulators are hard-coded or manually defined, and need to be adjusted if the objects being manipulated change position. To increase flexibility, an industrial robot should be able to adjust its configuration in order to grasp objects in variable/unknown positions. This can be achieved by off-the-shelf vision-based solutions, but most require prior knowledge about each object tobe manipulated. To address this issue, this work presents a ROS-based deep reinforcement learning solution to robotic grasping for a Collaborative Robot (Cobot) using a depth camera. The solution uses deep Q-learning to process the color and depth images and generate a greedy policy used to define the robot action. The Q-values are estimated using Convolutional Neural Network (CNN) based on pre-trained models for feature extraction. Experiments were carried out in a simulated environment to compare the performance of four different pre-trained CNNmodels (RexNext, MobileNet, MNASNet and DenseNet). Results showthat the best performance in our application was reached by MobileNet,with an average of 84 % accuracy after training in simulated environment.
Background: Manual muscle mass assessment based on Computed Tomography (CT) scans is recognized as a good marker for malnutrition, sarcopenia, and adverse outcomes. However, manual muscle mass analysis is cumbersome and time consuming. An accurate fully automated method is needed. In this study, we evaluate if manual psoas annotation can be substituted by a fully automatic deep learning-based method.Methods: This study included a cohort of 583 patients with severe aortic valve stenosis planned to undergo Transcatheter Aortic Valve Replacement (TAVR). Psoas muscle area was annotated manually on the CT scan at the height of lumbar vertebra 3 (L3). The deep learning-based method mimics this approach by first determining the L3 level and subsequently segmenting the psoas at that level. The fully automatic approach was evaluated as well as segmentation and slice selection, using average bias 95% limits of agreement, Intraclass Correlation Coefficient (ICC) and within-subject Coefficient of Variation (CV). To evaluate performance of the slice selection visual inspection was performed. To evaluate segmentation Dice index was computed between the manual and automatic segmentations (0 = no overlap, 1 = perfect overlap).Results: Included patients had a mean age of 81 ± 6 and 45% was female. The fully automatic method showed a bias and limits of agreement of -0.69 [-6.60 to 5.23] cm2, an ICC of 0.78 [95% CI: 0.74-0.82] and a within-subject CV of 11.2% [95% CI: 10.2-12.2]. For slice selection, 84% of the selections were on the same vertebra between methods, bias and limits of agreement was 3.4 [-24.5 to 31.4] mm. The Dice index for segmentation was 0.93 ± 0.04, bias and limits of agreement was -0.55 [1.71-2.80] cm2.Conclusion: Fully automatic assessment of psoas muscle area demonstrates accurate performance at the L3 level in CT images. It is a reliable tool that offers great opportunities for analysis in large scale studies and in clinical applications.
Aaltjes: automatisch classificeren en tellen. Agrariërs laten bodemmonsters analyseren op onder meer aanwezigheid van aaltjes. Deze bodemanalyse is voor agrariërs cruciaal om de bodemgezondheid- en vruchtbaarheid vast te stellen maar behelst een grote kostenpost. Het identificeren, analyseren en tellen van aaltjes (nematoden) in een bodemmonster geschiedt in een gespecialiseerd laboratorium. Dit is tijdrovend, specialistisch en seizoensgebonden werk. Het tellen- en analyseren van aaltjes is mensenwerk en vergt training en ervaring van de laborant. Daarnaast hebben de laboratoria te maken met personeelstekort en de laboranten met sterk fluctuerende werkdruk. Derhalve is het speciaal voor dit project opgerichte samenwerkingsverband tussen Fontys GreenTechLab, ROBA Laboratorium en CytoSMART voornemens om een oplossing te ontwikkelen voor het automatisch classificeren en tellen van aaltjes. Dit project richt zich op de ontwikkeling van een proof of concept van een analysescanner. Het werk van de laboranten wordt grotendeels geautomatiseerd waarbij door de scanner de bodemmonsters middels toepassing van deep learning en virtual modeling kan worden geanalyseerd. Daarmee wordt beoogd een oplossing te bieden waarmee het personeelstekort wordt tegengegaan, de werkdruk kan worden verlaagd, mensenwerk wordt geautomatiseerd (waardoor de kans op fouten wordt verkleind) en de kosten voor agrariërs worden verlaagd.
Artificial Intelligence (AI) wordt realiteit. Slimme ICT-producten die diensten op maat leveren accelereren de digitalisering van de maatschappij. De grote innovaties van de komende jaren –zelfrijdende auto’s, spraakgestuurde virtuele assistenten, autodiagnose systemen, robots die autonoom complexe taken uitvoeren – zijn datagedreven en hebben een AI-component. Dit gaat de rol van professionals in alle domeinen, gezondheidzorg, bouwsector, financiële dienstverlening, maakindustrie, journalistiek, rechtspraak, etc., raken. ICT is niet meer volgend en ondersteunend (een ‘enabling’ technologie), maar de motor die de transformatie van de samenleving in gang zet. Grote bedrijven, overheidsinstanties, het MKB, en de vele startups in de Brainport regio zijn innovatieve datagedreven scenario’s volop aan het verkennen. Dit wordt nog eens versterkt door de democratisering van AI; machine learning en deep learning algoritmes zijn beschikbaar zowel in open source software als in Cloud oplossingen en zijn daarmee toegankelijk voor iedereen. Data science wordt ‘applied’ en verschuift van een PhD specialisme naar een HBO-vaardigheid. Het stadium waarin veel bedrijven nu verkeren is te omschrijven als: “Help, mijn AI-pilot is succesvol. Wat nu?” Deze aanvraag richt zich op het succesvol implementeren van AI binnen de context van softwareontwikkeling. De onderzoeksvraag van dit voorstel is: “Hoe kunnen we state-of-the-art data science methoden en technieken waardevol en verantwoord toepassen ten behoeve van deze slimme lerende ICT-producten?” De postdoc gaat fungeren als een linking pin tussen alle onderzoeksprojecten en opdrachten waarbij studenten ICT-producten met AI (machine learning, deep learning) ontwikkelen voor opdrachtgevers uit de praktijk. Door mee te kijken en mee te denken met de studenten kan de postdoc overzicht en inzicht creëren over alle cases heen. Als er overzicht is kan er daarna ook gestuurd worden op de uit te voeren cases om verschillende deelaspecten samen met de studenten te onderzoeken. Deliverables zijn rapporten, guidelines en frameworks voor praktijk en onderwijs, peer-reviewed artikelen en kennisdelingsevents.
The European creative visual industry is undergoing rapid technological development, demanding solid initiatives to maintain a competitive position in the marketplace. AVENUE, a pan-European network of Centres of Vocational Excellence, addresses this need through a collaboration of five independent significant ecosystems, each with a smart specialisation. AVENUE will conduct qualified industry-relevant research to assess, analyse, and conclude on the immediate need for professional training and educational development. The primary objective of AVENUE is to present opportunities for immediate professional and vocational training, while innovating teaching and learning methods in formal education, to empower students and professionals in content creation, entrepreneurship, and innovation, while supporting sustainability and healthy working environments. AVENUE will result in a systematised upgrade of workforce to address the demand for new skills arising from rapid technological development. Additionally, it will transform the formal education within the five participating VETs, making them able to transition from traditional artistic education to delivering skills, mindsets and technological competencies demanded by a commercial market. AVENUE facilitates mobility, networking and introduces a wide range of training formats that enable effective training within and across the five ecosystems. A significant portion of the online training is Open Access, allowing professionals from across Europe to upgrade their skills in various processes and disciplines. The result of AVENUE will be a deep-rooted partnership between five strong ecosystems, collaborating to elevate the European industry. More than 2000 professionals, employees, students, and young talents will benefit from relevant and immediate upgrading of competencies and skills, ensuring that the five European ecosystems remain at the forefront of innovation and competitiveness in the creative visual industry.
