Archives: Blog posts

Blog posts

Knowledge Database | Biometrics in computer vision systems 

Biometrics in computer vision is basically the combination of Image Processing and Pattern Recognition. Biometrics deals with the recognition of persons based on physiological characteristics, such as face, fingerprint, vascular pattern or iris, and behavioural traits, such as gait or speech.

Biometric technologies and computer vision are more and more needed to allow modern safe, fast and comfortable recognition, surveillance, protection and assistance services. Biometric systems are more and more relevant in applications which need visual, audio or other sensor data input to be able to collect these data and as well to recognize, analyse and steer the right expected actions.The applications are coming from many different industry domains for example healthcare, safety, surveillance, production, automotive, and many more. The sensors, cameras, and microphones are getting more and more safe, secure, accurate, robust and reliable and need to be integrated with adequate comparison, crosscheck and fusion functionality.

Computer Vision & Biometrics in Healthcare

In the last decades the healthcare industry has been supported by an ever increasing number of Computer Vision applications. One of the emerging fields in this scenario is biometric traits and related research that are typically aimed at security applications involving person authentication and identification. However, the increasing sensitiveness and image quality of the sensors available nowadays, along with the high accuracy and robustness achieved by the classification algorithms proposed nowadays, open new applicative horizons in the context of healthcare, to the aim of improving the supply of medical treatments in a more customised way, as well as computational tools for early diagnosis. The main implications of Computer Vision for medical usage are imaging analysis, predictive analysis and healthcare monitoring using biometrics in order to minimise false positives in the diagnostic process or control the treatment.

Following Devices & Sensors can been integrated in biometrics solutions:

🎦Biometrics cameras 

🎦3D Camera systems

🎦Iris scanners

🎦fingerprint sensors

🎦Microphones

🎦Health sensors (body temperature, blood-samples, heartbeat, blood pressure, …)

🎦Actuators

🎦Alarming systems

🎦Barring and lock systems

🎦Smart devices, watches

🎦Ultrasonic

🎦Radar and Lidar 

Biometrics | Some technical background

Biometric Authentication

Biometric systems rely on several discrete processes: enrolment, live capture, template extraction, and template comparison. 

The purpose of enrolment is to collect and archive biometric samples and to generate numerical templates for future comparisons.

 By archiving the raw samples, new replacement templates can be generated in the event that a new or updated comparison algorithm is introduced to the system.

 Practices that facilitate enrolment of high-quality samples are critical to sample consistency, and improve overall matching performance, which is particularly important for biometric identification by “one-to-many” search.

Template extraction requires signal processing of the raw biometric samples (e.g. images or audio samples) to yield a numerical template. Templates are typically generated and stored upon enrolment to save processing time upon future comparisons. Comparison of two biometric templates applies algorithmic computations to assess their similarity. Upon comparison, a match score is assigned. If it is above a specified threshold, the templates are deemed a match

Computer Vision and biometrics in different Industries

Computer vision technology is one of the most sought-after tech concepts these days. Raconteur reports that innovation is omnipresent in our lives, from driving cars to using search engines. We are going to dwell upon several popular fields for implementing computer vision solutions:

  • AR-enhanced images and videos
  • Robots in retail and supply chain
  • Advanced medical imaging tools
  • Tools to enhance OCR-ed images
  • Approaches to mitigate biases in sports
  • Techniques to boost agriculture industry
  • Facial recognition and access systems
  • Mood and thief detection
  • Iris matching and access control
  • Voice matching system
  • Fingerprint detection and identification
  • Payment and banking
  • Mobile recognition devices
  • Physical and safety solutions
  • Keyless locking systems
  • Area protection systems
  • Airport access systems
  • Surveillance and observation
  • Gesture and behaviour detection
  • Sleeping monitoring sensor observation 
  • Surgical head camera
  • Servant home robots
  • 24/7 patient monitoring
  • Operation room equipment
  • Robot and robotics solutions
  • Manufacturing and production quality control
  • and many more…..

Due to the many use cases for solutions with telemetry sensorics and data, a critical prerequisite to making the innovation a cross-industry trend is data growth worldwide. According to statistics, users share more than 3 billion images online daily. Built-in cameras and personal mobile devices generate data permanently. What is more, computing power for analysis of massive data has become available and affordable so far.

Computer Vision is using Machine Learning & Deep Learning the subareas in the field of Artificial Intelligence. 

This big amount of data makes it impossible to keep an overview about all tendencies, changes and aspects ongoing at any time and with best insight. Therefore AI technology is requested for analytics and evolutionary learning and fast and accurate visualisation or action triggers. 

Computer Vision & Machine Learning & Deep Learning evolution

Machine learning and computer vision are two fields that have become closely related to one another. Machine learning has improved computer vision about recognition and tracking. It offers effective methods for acquisition, image processing, and object focus which are used in computer vision. It is able to learn without being explicitly programmed.

In turn, Computer Vision has broadened the scope of machine learning. It involves a digital image or video, a sensing device, an interpreting device, and the interpretation stage. 

Machine learning is used in computer vision in the interpreting device and interpretation stage.

Deep Learning is a further step that the Network itself is capable of adapting to new data.  

Exploring and developing many PoC and product projects in these areas allows Thaumatec to support all industry domains with best experience and know how to develop, integrate and equip existing and new products with the not dispensable related SW elements.

If you should need more insight or any help, please contact us at
https://thaumatec.com/contact/

HealthTech industry Update | Access and Diversity in Clinical Trials

Physicians from underserved communities into research through a reimagined model, we can impact better health outcomes rooted in quality data that allows us to thrive from more diversity and better representation while providing patients with greater access to new care options.

🧑‍⚕️🧑‍⚕️🧑‍⚕️Clinical research partners must intentionally expand their reach to include investigators serving the people within these diverse and often underserved communities. This should be non-negotiable and integral to every research project plan.

To do so it is needed to:

🧑‍⚕️Building trust

🧑‍⚕️Empowering investigators

🧑‍⚕️Maintaining relationships with investigators

Conclusion is

🏥providing investigators with a strong infrastructure, top-notch support with day-to-day boots on the ground, and powerful, continuous training makes for solid and successful relationships. 

🏥A reimagined model will impact better health outcomes rooted in quality data that allows us to thrive from more diversity and better representation while providing patients with greater access to new care options.

https://medcitynews.com/2023/05/access-and-diversity-in-clinical-trials-requires-supporting-the-investigators/

Knowledge Database | The right IOT Operating System for your IOT product

The question is not which is the best in the world, it is the selection which one fits the best to your product. The first decision is which IOT functionality you are aiming:

  • IOT data collection, connectivity, remote controlled
  • IOT data collection, connectivity, immediate decisions, controlling
  • IOT data repository and IOT analytics

Here some overview of typical Operating System types for industrial use according function, with useability:

Embedded OS | IOT data collection, connectivity, remote controlled

This type of operating system is typically designed to be resource-efficient and reliable. Resource efficiency comes at the cost of losing some functionality or granularity that larger computer operating systems provide, including functions which may not be used by the specialized applications they run. Depending on the method used for multitasking, this type of OS is frequently considered to be a real-time operating system.

To be used in case of:

  • Embedded computer systems
  • Small machines with less autonomy
  • Device examples: Controllers, Smart Cards, Mobile devices, sensors, Car ECUs, M2M devices, …..
  • Compact and extremely efficient
  • Limited resources

Products commonly used:

  • INTEGRITY (RTOS)
  • VxWorks.
  • Linux, including RTLinux, Yocto (Linux distribution for IoT), MontaVista Linux
  • Embedded Android
  • iOS
  • Windows CE
  • MS-DOS or DOS Clones
  • Unison OS

Real time OS | IOT data collection, connectivity, immediate decisions, controlling

A RTOS is an operating system intended to serve real-time applications that process data as it comes in, typically without buffer delays. Processing time requirements & OS delay are measured in tenths of seconds or shorter increments of time. A real-time system is a time-bound system which has well-defined, fixed time constraints. Processing must be done within the defined constraints or the system will fail. They either are event-driven or time-sharing. Event-driven systems switch between tasks based on their priorities, while time-sharing systems switch the task based on clock interrupts. Most RTOSs use a pre-emptive scheduling algorithm.

To be used in case of:

  • deterministic nature of behaviour
  • Real time event handling and priority driven state / event coupling
  • specialized scheduling algorithms
  • Clock interrupt handling

Products commonly used:

  • INTEGRITY (RTOS)
  • VxWorks
  • Windows CE
  • DSP/BIOS
  • QNX
  • RTX
  • ROS
  • FreeRTOS (emb.)

Server OS | IOT data repository and IOT analytics 

A server operating system (OS) is a type of operating system that is designed to be installed and used on a server computer. It is an advanced version of an operating system, having features and capabilities required within a client-server architecture or similar enterprise computing environment. Some of the key features of a server operating system include:

  • Ability to access the server both in GUI and command-level interface
  • Execute all or most processes from OS commands
  • Advanced-level hardware, software and network configuration services
  • Install/deploy business applications and/or web applications
  • Provides central interface to manage users, implement security and other administrative processes
  • Manages and monitors client computers and/or operating systems

To be used in case of:

  • Virtual machine
  • Virtualization
  • large server warehouses
  • Micro Service based

Products commonly used:

  • Windows Server 
  • Mac OS X Server
  • Red Hat Enterprise Linux (RHEL)
  • SUSE Linux Enterprise Server
  • Debian, Ubuntu
  • CentOS
  • Gentoo
  • Fendora
  • ROS

Thaumatec has got a lot of experience with Operating Systems during the execution of many projects which required OS tuning. We helped the clients with PoC investigation, OS porting projects and product development to have the right OS in place.

HealthTech industry Update | Better Data Quality Means a better future for Public Health

Public health is heavily dependent on collecting and sharing accurate patient data. 

Standards for data collection and interoperability can move the needle toward better health data, but it is up to healthcare organisations.

Unfortunately, persistent data-quality issues beginning at the provider level continue to undermine population health. 

These include:

➡️ Inaccurate and incomplete patient records.

➡️ Duplicate patient records. 

➡️ When patient records are inaccurate or incomplete

➡️ Inconsistent data stored in disparate systems across different institutions. 

➡️ Outdated reporting for purposes of health equity and SDOH measures. 

Modern data platforms allow healthcare organisations to:

 💪Improve return on investment in their data

 💪Aggregate data access

 💪Free up staff time and resources with better tools and processes

 💪Enhance health equity and SDoH initiatives

 💪Be better prepared for the next public health crisis.  

Here some more information and an overview:

https://medcitynews.com/2023/06/better-data-quality-means-a-better-future-for-public-health/

If you would like to see or search more interesting posts, check our KNOWLEDGE DATA BASE | BLOGPOST DIRECTORY: https://thaumatec.com/knowledge/

Healthtech Industry Update | Digital Technology in Heart Health Care and Monitoring for Cardiac Patients

The Cardiac world has changed

in the last decade in many ways, digital technologies enable patients to obtain care closer to the home and doctors will diagnose cardiovascular disease earlier to assist carers, families, friends and patients undergoing and recuperating for major heart surgeries and rehabilitation processes.

Main focus

is on a holistic recovery journey with cardiovascular technologies and all equipment and methods for speed up detection and treatment for predictive checks, enabling more safe surgery, improving healing cycle, providing online resources, support and counselling of the patients.

There are trials ongoing with Artificial Intelligence and chatbots, big data, analytics and much more using a system framework and developing solutions using:

➡️ Big data that Cardiovascular Disorders can be detected

➡️ Artificial Intelligence and Therapy of cardiovascular disease

➡️ Alexa capabilities and voice technology for support

➡️ Apps for Telemedicine to consult periodically or fast the medics

Here some more information and an overview:

HealthTech Industry Update | New Framework to Evaluate Digital Health Products

The framework, which evaluates the evidence for digital health products, seeks to provide hospitals, payers and trade organizations with a clear set of steps they can use to determine whether or not a digital health product is evidence-based and therefore suitable for their company to adopt.

The framework includes four steps

🧑‍⚕️Screen the product for failure to meet your organization’s absolute requirements

👨‍⚕️Apply an existing evidence assessment framework

🧑‍⚕️Use the Evidence Defined supplementary checklist

👩‍⚕️Produce actionable, justifiable recommendations

Advantages

🩺Careful evidence assessment can mean the difference between identifying critical evidence flaws and failing to do so.

🩺This can, in turn, impact countless patients, by dictating whether patients get access to digital health interventions that are effective and safe.

🩺Difference between medication adherence and nonadherence

🩺Resolution of affective symptoms and chronic emotional struggles

📖Here the MedCity News article:

https://medcitynews.com/2023/06/digital-health-evidence/

If you would like to see or search more interesting posts, check our KNOWLEDGE DATA BASE | BLOGPOST DIRECTORY: https://thaumatec.com/knowledge/

Knowledge Database | Medical reimbursement in EU

Important topics are identification and application for procedure codes and device codes in each European country and applications for inclusion in each country’s reimbursement catalogues and reimbursement lists.

Reimbursement Landscape in Europe – Important is to understand the current reimbursement environment in Europe, relevant for your medical device:

  • Clarify the relevant type of coding systems and guidelines
  • Locate any specific reimbursement mechanisms that could be utilized by the device, 
  • Identify the main decision makers
  • Developing a Winning

Reimbursement Planning for European Decision Makers – Develop the required evidence for European decision makers:

  • Value Story
  • Economic Model
  • Clinical Data
  • Decision Makers’ Feedback 

Implementation – conduct the following activities

  • Billing Guide
  • Reimbursement Applications
  • Pilot Projects
  • Other Funding Options

here more insight by MEDIClever: 

https://mediclever.com/medical-device-reimbursement-europe-eu.php

If you would like to see more interesting posts, visit our whole knowledge database: https://thaumatec.com/knowledge/

Knowledge Data Base | Europe Healthcare Systems and Reimbursement

If Europe wants its citizens to be healthy it must innovate more to deliver better healthcare, to more people in a more efficient manner.

Here an overview about the different Healthcare systems in Europe with some data and comparison on spendings and following topics:

  • Healthcare System Characteristics and Coverage/Insurance
  • Different models e.g. in UK and Germany
  • Country to Country variations in provision and care
  • Different willingness and ability to pay for innovations

If you would like to see more interesting posts, visit our whole knowledge database: https://thaumatec.com/knowledge/

HealthTech Industry Update | Dignose Diseases Via Retinal Scans

AI analyses photos of the eye that were taken with a retinal camera. These analyses are meant not only to screen for eye disease, but also those located throughout the body. 

In fact, the AI can help clinicians screen for more than 140 eye and systemic conditions — some of them cardiovascular and neurological

The company Optain has gained an initial seed investment of $12 million and is an AI company meant to enable earlier disease detection and prevention through retinal imaging.

Some background:

👁️ there are a lot of camera companies out there that can shoot an image through the eye and look at the back of the eye, blood vessels, lesions, the optical nerve and various other features. 

👁️ But not a lot of companies are very good at looking at that from an artificial intelligence and deep learning scenario to figure out which disease states we can predict or screen for by assessing those features.

👁️ The eye can often be a window to a person’s health

👁️ most clinicians lack non-invasive diagnostics and screenings that focus on the eye

👁️ adding a camera to Optain’s product could address this problem

Technology aspects:

📷Technology is based on technology developed by Mingguang He, an Australian clinician researcher

📷Eyetelligence’s technology

📷Eyetelligence’s AI was trained on third party cameras

📷Robust and flexible $15,000 cameras in optometry space

It’s difficult to say when Optain will clear regulatory hurdles and be able to enter the U.S. market, but Dunkel predicts this could happen in 2025. 📷💪

Here the Article by MedCityNews : https://medcitynews.com/2023/05/northwell-retinal-scan-eye-diagnosis-ai/

HealthTech Industry Update | Machine Learning Prediction Model for Inflammatory Bowel Disease

Machine Learning Prediction Model for Inflammatory Bowel Disease Based on Laboratory Markers. Working Model in a Discovery Cohort Study. The Authors aimed to create an IBD machine learning prediction model based on routinely performed blood, urine, and fecal tests.

by Sebastian Kraszewski 1, Witold Szczurek 2, Julia Szymczak 3, Monika Reguła 3 and Katarzyna Neubauer 4*

*Author to whom correspondence should be addressed.

Inflammatory bowel disease (IBD) is a chronic, incurable disease involving the gastrointestinal tract. It is characterized by complex, unclear pathogenesis, increased prevalence worldwide, and a wide spectrum of extraintestinal manifestations and comorbidities. Recognition of IBD remains challenging and delays in disease diagnosis still poses a significant clinical problem as it negatively impacts disease outcome. The main diagnostic tool in IBD continues to be invasive endoscopy.

Based on historical patients’ data (702 medical records: 319 records from 180 patients with ulcerative colitis (UC) and 383 records from 192 patients with Crohn’s disease (CD)), and using a few simple machine learning classificators, we optimized necessary hyperparameters in order to get reliable few-features prediction models separately for CD and UC.

Following methods have been used and topics checked

  • The k-Nearest Neighbour
  • Gradient Boosting Classifier
  • Random Forests
  • Support Vector Classifiers
  • Majority Voting
  • Best Classifiers and Most Important Predictors
  • Model Robustness
  • Web Application Integrated Model

Here the full article and results published by Journal of Clinical Medicine:

https://www.mdpi.com/2077-0383/10/20/4745

Thaumatec Sp. z o.o.
ul. Joachima Lelewela 8
53-505 Wrocław, Poland

VAT-ID/NIP: PL897-179-80-51
REGON: 022396417
KRS: 0000506158



Phone: +48 698 632 801
Mail:office@thaumatec.com

Thaumatec IoT Cloud Services Sp. z o.o
ul. Joachima Lelewela 8
53-505 Wrocław, Poland
VAT-ID/NIP: PL897-187-43-03
REGON: 385101524
KRS: 0000819766

Polityka prywatności

Privacy policy

WE ARE ISO CERTIFIED:

iso_9001
iso_27001
iso_13485
Copyrights © Thaumatec 2025