Mission
Our mission is to help our clients understand the value of the data they possess, use this data in the best possible way and thereby increase their efficiency and productivity.
We work in the field of data engineering and analysis, build complex data processing systems in real time using computing resources in the cloud or in the data center as efficiently as possible.
We also love doing research. We are participating in the international OpenNFT project for neural feedback signals processing.
We use the full range of modern tools to analyze data, including deep learning technologies and use open source solutions in our practice.
seamless
data science implementation for your advancement
services
01 — 05
Ad hoc legacy improvement
Augment your team
Pump up your business with our outstaffing resources
Consulting
Enrich your team with our expertise
Education
Boost your team skills with our workshops
Research
Keep your business at the top via implementing new features
Understand your goals better with our in-depth research
Expertise
We form our work based on the business cases of our customers, build processes from collecting raw data from sources to visualizing reliable and useful datasets for decision-making and operational actions. At the same time, data leverage is maintained throughout the entire working cycle.
Data engineering
Data analysis
We help our clients see the real business picture behind the data sets by applying modern methods of analyzing data from large distributed storages to help increase productivity and reduce costs.
Where insights are unclear we help build smart models based on deep learning and historical data.
Machine learning
Primary VERTICALS
DNS infrastructure, telecom and subscriber safety
Telecom
We offer digital strategy consulting for service providers who are looking into implement solutions for higher operations efficiency and better customer service outcome.
Manufacturing
We empower manufacturers via accelerating their business growth with predictive analysis and computer vision solutions.
Computer Vision (Healthcare)
We boost modern healthcare and offer tailored computer vision solutions for better support.
Marketing & Media
We help businesses reach their clients needs while implementing modern solutions.
Traffic patterns for fixed line and mobile subscribers
Analytics
Medical imaging analysis
Surgical navigation augmentation (AR/VR)
Case STUDIES
Telecommunications
Manufacturing
Healthcare
Marketing
Our client laid out a problem - telecom company was dissatisfied with the quality of its Parental Control service.
PARENTAL CONTROL
Using Raspberry Pi with remote access, that was placed in a registered household with the telecom’s parental control turned on, we built an environment that automatically register the user experience when visiting a website. We created a list of the top 500 UK websites based on DNS traffic, and ran them through our client’s Parental Control services and compared the results and presented them as a Venn diagram.
As a result, our Parental Control proved to have higher precision and broader coverage to eliminate under-blocking and over-blocking.
The telecom was impressed with our resourcefulness to obtain data on the competing solution and it turned out that our results were easily reproducible by the telecom's engineers.
We had no access to the lists of categorized internet sites used for protection and had to prove that our solution had higher precision and broader coverage.
Our client was facing a Problem: High waste of expensive aluminum fluoride was used to control and stabilize the electrolyzer temperature. With the given source of information consisiting of aluminum production control system sensors, raw material supply information, technical inspection and repair logs, output product analysis and weather information (200 unique parameters
On-prem data processing for remarkable savings
streamed to on-prem data center) we built a real-time predictive model forecasts electrolyzer temperature and recommends precise increments of aluminum fluoride, at the right time, to stabilize electrolyzer temperature and minimize aluminum fluoride consumption. Our AI model training reduced the number of required dataset parameters from 200 to 50.
The final model is a result of a rapidly prototyping of 20+ models and taking advantage of on-prem computational resources.
The result speaks for itself - total savings of aluminum fluoride went up to 20% !
Surgical navigation & visualization system
We included in the development of the component :
Our technology proved to be precise and reliable, assisting more than 200 surgical procedures in 20 medical centers, including clinics in Saint Étienne, France and Düsseldorf, Germany.
Medical image processing library, including ML-based features such as 2D object segmentation (bone, soft tissue, vessel), 3D segmentation (soft tissue), 4D brain perfusion, tumor detection, realtime image registration, and statistical shape modelling;
Video-capturing and AR rendering systems based on simultaneous work of stereo cameras, viewpoints and lidars.
3D pre-surgical visualization of patient’s body and inner tissues based on DICOM in MRI or CT modalities;
guides surgical procedures
aligns stored images with camera input
creates 3D-models of internal organs
Our team built the AR component of a Surgical Assistance System that:
We created a photorealistic human avatar for one of the leading Eastern European banks - Sberbank. Powered by our text-to-face technology, the human avatar can be created from any person and function in real time.
Elena
We designed a neural network architecture and trained it with videos to generate realistic head and facial muscle movements in a human avatar in response to any spoken language. We accelerated rendering by 83 times to enable real-time video generation.
How does it work?
The bank received a full stack of production-grade ML container-based solution with RESTful API and backed by Redis for minimal latency, concurrent deep learning-based image processing.
Av. do Mal. Gomes da Costa 1131, 4150-360, Porto, Portugal
Made on
Tilda