Innovation in Computer Related | Innoget

Innovation in Computer Related | Innoget

Yissum - Research Development Company of the Hebrew University posted this:

SPADE: Sub-Image Anomaly Detection with Deep Pyramid Correspondences Nearest neighbor (kNN) methods utilizing deep pre-trained features exhibit very strong anomaly detection performance when applied to entire images. A limitation of kNN methods is the lack of segmentation map describing where the anomaly lies inside the image. In this work we present a novel anomaly segmentation approach based on alignment between the anomalous image and a constant number of the nearest normal images. Our method, Semantic Pyramid Anomaly Detection (SPADE) uses correspondences based on a multi-resolution feature pyramid. SPADE is shown to achieve state-of-the-art performance on unsupervised anomaly detection and localization while requiring virtually no training time. Project ID : 47-2020-10918

SPADE: Sub-Image Anomaly Detection with Deep Pyramid Correspondences

Yissum - Research Development Company of the Hebrew University posted this:

Eliminate Blurry Images Caused by Camera Shake and Movement a new architecture which breaks the deblurring network into an analysis network which estimates the blur, and a synthesis network that uses this kernel to deblur the image. Project ID : 47-2020-10908

Eliminate Blurry Images Caused by Camera Shake and Movement

Yissum - Research Development Company of the Hebrew University posted this:

Ultra-Low Dose Radiation for Repeat CT Scanning Ultra-Low Dose Radiation for Repeat CT Scanning Project ID : 46-2019-10755

Yissum - Research Development Company of the Hebrew University posted this:

Learning from Rough Group Comparisons in applying machine learning algorithms to the domains with the limited amount of labeled data - cyber, insurance. Developing a machine learning model requires data samples containing both normal and abnormal events, where each sample is labeled accordingly; however,it is often the case that unlabeled data is abundant, but labeled instances are difficult, expensive, or time-consuming to obtain. We proposed a simple and intuitive bi-convex formulation and an efficient algorithm for the problem. Despite the simplicity of our methods, we achieve high accuracy with a very modest amount of input, and considerably loose (or even misspecified) constraints Project ID : 46-2020-13911

Learning from Rough Group Comparisons

Unitat de Valorització de la URV posted this:
Licensing Manager at Fundació URV

RETIPROGRAM 2.0: A clinical decision support system for Diabetic Retinopathy early detection This program, jointly developed by the Rovira i Virgili University and the Pere Virgili Institute, is a Clinical Decision Support System that helps to discriminate between diabetic people that may develop Diabetic Retinopathy and others who do not have any risk.

RETIPROGRAM 2.0: A clinical decision support system for Diabetic Retinopathy early detection

Unitat de Valorització de la URV posted this:
Licensing Manager at Fundació URV

MIRA: Classifier of eye fundus images to detect the degree of Diabetic Retinopathy Preventive screening of the eye fundus is a usual technique to detect Diabetic Retinopathy disease (DR). This disease is one of the most important causes of blindness in adults worldwide. Automatic tools for image processing and classification may facilitate the hard work of manual labelling of this kind of images, which requires of high expertise and a lot of time of expert doctors. An eye with DR may present some of the following lesions: microaneurisms, exudates, hemorrages. The number, location and level permits to classify the disease in different stages. The computer System we offer, called MIRA, receives an eye fundus image (from a non-mydriatic camera) and classifies the image into 4 categories: No DR, Mild DR, Moderate DR and Severe DR.

MIRA: Classifier of eye fundus images to detect the degree of Diabetic Retinopathy

Andrew James posted this:
Managing Partner at Siskin Capital

SouqBox - Giving clients the platform to create the defacto B2B market place for its sector B2B Product companies still trade mostly offline - $6.7Tn annually. There is no easy way to go online for most of the smaller businesses in this category. SouqBox is the world's first dedicated B2B SAAS platform for the online journey. We say “Journey” because its customers can start by having a risk free, fully branded ecommerce platform with complete control over the trading models in less than 30 minutes. It’s self-serve and fully branded to the customers’ needs. And at a time that is appropriate for them, can have the same platform evolve into being a fully fledged market market place i.e. a platform where customers are able to access other suppliers. By becoming the defacto marketplace, and not just a shop window, a SouqBox client is able to generate incremental revenue streams from its competitor’s trading activity too - if it chooses to.

Covid-19 Innovation Challenges by Innoget posted this:

Early warning system for detecting deterioration in post intensive care patients In the UK 28% of deaths in patients treated on an Intensive Care Unit (ICU) occur after the patients return to the general ward. These patients often suffer late developing complications after initial successful treatment in the ICU. There is usually a period of deterioration when a patient shows some signs of developing a complication. PICRAM (Post Intensive Care Risk Adjusted Monitoring) is a system that watches over the electronic records of the vital signs of patients after discharge from an ICU. It analyses the information to estimate the likelihood that a patient will suffer a complication in the next 24-48 hours. Patients most at risk of complications can then be identified and specialist nurses sent to start treatment early to the patients who need them most. The early detection of deterioration provided by PICRAM can save lives and reduce treatment costs.

Early warning system for detecting deterioration in post intensive care patients

Lidia Aguilera posted this:
Technology Transfer Officer at University of Luxembourg

BIOMARKER FOR PREDICTION OF RECURRENCE IN COLORECTAL CANCER PATIENTS Approximately 20% of colorectal cancer patients with stage II colorectal cancer experience relapse of the disease. Current clinical-pathologic stratification factors do not allow clear identification of these high-risk patients. The invention is a powerful prognostic biomarker in colorectal cancer, especially in early stages (stages I and II), which might help stratifying patients with stage II for adjuvant chemotherapy. The invention provides a gene expression classifier that distinguishes patients with low or high risk of disease relapse in colorectal cancer and that might be used in the clinics to help clinicians identify high-risk patients and choose the most appropriate treatment for a given patient.

BIOMARKER FOR PREDICTION OF RECURRENCE IN COLORECTAL CANCER PATIENTS

Lidia Aguilera posted this:
Technology Transfer Officer at University of Luxembourg

Modular educational wave kit: Plug and play 3D printable sine waves The plug and play 3D printable sine waves are a simple but effective teaching aid which helps the students to understand wave properties better. They get to try for themselves how wave properties like constructive and destructive interference work. Further they get to explore the interdependence of the wavelengths and diffraction angles, the distances between the slits and the distances from the slits to the observation screen. This way, the famous single and double slit experiments, as well as the diffraction grating and its equation can be understood in an handson manner that does not require any animations, as it is interactive by its playful nature. Further use of the same kit or a slightly modified version could include but would not be limited to: the modelling of water, pressure and all kinds of electromagnetic waves, all kinds of waves in general.

Modular educational wave kit: Plug and play 3D printable sine waves

Lidia Aguilera posted this:
Technology Transfer Officer at University of Luxembourg

GoFlex Reconfigurable flexible stripes to create Möbius Bands Interconnected reconfigurable flexible stripes attached by integrated joints that can be composed as to build Möbius bands and other geometrical objects. Potential applications are exhibits for mathematical museums, 3D-puzzles, Lego-style building bricks, jewelry (decomposable bracelets).

GoFlex Reconfigurable flexible stripes to create Möbius Bands

Lidia Aguilera posted this:
Technology Transfer Officer at University of Luxembourg

Sim!Cong! Mathematical Didactics Card Game about Triangles Card game with 32 cards. The aim of the game is proving that two given triangles are congruent (or similar) by applying one Congruence (or Similarity) Theorem. The players have to collect assumption cards until they have sufficient information to apply the theorem.

Sim!Cong! Mathematical Didactics Card Game about Triangles

Lidia Aguilera posted this:
Technology Transfer Officer at University of Luxembourg

ModuLys – modular toolkit for customize optical setups ModuLys is an affordable, yet advanced and modular toolkit for the construction of custom optical setups made of multi-purpose standardized units, with strong focus on ease of use. The unit concept, together with a unique lattice-based mounting solution reduces the complexity of individual setups, while maximizing flexibility and re-usability of components in a plethora of possible scenarios. Core of the proposed device is the alignment-free placement of optical components, e.g., light sources, lenses, filters, mirrors, and combined assemblies of the former on a two dimensional mounting platform (breadboard). Optical components are mounted into cubic units that can be positioned at pre-defined locations on the breadboard in a square-lattice arrangement. Complementary shapes on cubic units and breadboard allow for a tight fit of both, alleviating the need for component alignment.

ModuLys – modular toolkit for customize optical setups

Lidia Aguilera posted this:
Technology Transfer Officer at University of Luxembourg

Luxembourg 1665 History Serious Game for Schools Applying Game Technology to the Experience of Learning History Model game structure that applies game technology to education, both teaching and learning, about the past. In this model, the teacher is no longer the stand-alone expert but rather the guide to enhance the students’ learning journey. This way, historical and archaeological research will be transmitted in an innovative way to pupils. The game is intended for grammar and professional school students, ages 13-16, in a formal educational environment.

Luxembourg 1665 History Serious Game for Schools

Lidia Aguilera posted this:
Technology Transfer Officer at University of Luxembourg

MaGrid – Early Mathematical Training tool MaGrid is an innovative early math tablet-based training tool designed to foster pre-schoolers math precursor skills. To provide each child with a sound foundation in basic mathematical abilities, effective instruction over the pre-school years is necessary. MaGrid is language-neutral and thus makes early mathematical instruction accessible to all children, regardless of their language background or proficiency. By this means it is not only suitable for a highly multilingual school setting with a heterogeneous student population, but it can be used on a global level.

MaGrid – Early Mathematical Training tool

1
2
3
4
5