ZUZEX

Our developers have analyzed numerous images and videos, demonstrating the proper performance of exercises, in order to define how the coordinates of the points correlate with each other and the surrounding surfaces.

As a result, the app can detect improper positions of the human body parts during the performance of the 5 exercise types:

- Plank;

- Push-ups;

- Squats;

- Pull-ups;

- Lunges.

To estimate the body positions while working out, the user only needs to launch the camera within the app and set the phone so that the whole body is visible. The next step will be to select an exercise from the list, and you can start working out!

In case the exercise is being performed in an improper way, the mislocated body part will be highlighted, and a recommendation message will describe how to achieve the proper pose.

Client location: USA

We have developed bespoke web software for the practical DevOps Training courses that allows teaching staff to create lab sessions. 

This private hands-on lab environment is used by:

- clients of the DevOps training school to build custom Linux/Docker/Kubernetes/Python labs;

- students as a DevOps project to learn the deployment of a real-world application to dev/staging/production environments with all the components including CI/CD.

The labs are built as bash scripts and task lists.

The student can see the available labs on their Dashboard. From there, the Lab Completion Statistics page can be accessed. 

Client location: USA

Today about 25% of virus attacks start with an infected ad! Adware detection and removal is therefore a guarantee of your digital safety. It is your shield from conceivably mischievous online advertisements. Not only does Adware Cleaner stop redirecting to dangerous websites, but it also protects your privacy.

Adware Cleaner scans for real adware using adware signatures. The software makes it easy to identify the malicious files, remove all adware, and restore the user's web browser back to normal in one click.

Key functionality:

- Animated interface

- Browser extensions removal

- Adware scanning and cleaning

Client location: UK

The application is created for equestrian organizers. It's a Windows desktop application with complex machine learning algorithms on the backend. Mostly, OpenCV library is used, in addition, we improved the algorithms for our particular situation for better results.

It's only required to have videos from different cameras and a list of Ride participants to get the result.

The interface of the application allows setting folders where the videos are located on the computer, uploading a .xls file with Ride participants list (or a Google Sheets link). Nothing else is required. All the magic happens behind the user's view: models are trained, videos are processed. It is possible to turn-off certain riders to reduce processing time.

As a result, the application returns Rider's name, Horse color, Rider's number, and the most important - Time interval for this particular Rider. All this data can be recorded to Google Sheets document or can be downloaded as a .xls file.

Also, it's possible to generate a video with custom music on it containing all the videos from different cameras for this particular Rider detected by the algorithm. We've reached about 90% of accuracy by training Models on different video arrays.

Client location: Ireland

The first user selects two subjects where he has highest expertise, and his competitor can select other two subjects he likes. Four rounds with four questions in each round can be played in real-time if the players are online. Or it can spread up to 24 hours if someone is busy and wants to switch to the next round in a while.

The highlight of the game is an avatar builder where each user can construct a game character by selecting haircut, skin color, eyes and other parts of the face.

The project includes a web-based administrator panel where game subjects, questions, answers and users can be flexibly managed.

As for the technologies used, the iOS application is developed in native Swift language, the backend is written in Golang, and the admin panel is a React+Golang bundle.

Client location: Australia 

Implementing the design mockups, we were impressed by clean designs in order not to disturb users with too bright colors or a huge amount of useless information. It is obvious that traders are spending all day on the platform so our goal was to show the most important information only and leave all extra behind.  

Several iterations of the design and prototyping process allowed us to get the most optimal layout which only required API integration before being delivered to the end-users. 

Client location: Singapore 

Users can request personalised guides via a built-in request form. Every minute of a session a new inspiring photo is displayed. Each session ends up with a countdown. 

With the ability to create your own unique guides, the application becomes a powerful tool that allows you to raise the quality of your mind and body.

The IOS version of the application was developed with Swift, while Kotlin was used for the Android app. 

Client location: Canada

The amount of data that is presented on the platform is enormous. Moreover, it's possible to get data in real-time to make the best betting decisions.

Each user can easily customize the interface on any device.

If they are using a weak smartphone or having a bad Internet connection they can simply turn off the animations, change update frequency or hide the sports that they are not interested in to save resources of the device.

Client location: USA

Web platform for a linguistic company making high-quality translations of documents, technical instructions, and manuals.

Using the web portal interpreters upload translations they performed, and the employees responsible for the quality check carry out control - make edits, comments, and eventually verify the overall quality of the translation.

Client location: Germany.

The Baseline energy application service (BEAS) is a Machine Learning System (MLS) with an API where business intelligence like baseline (the normal amount of kWh) and predictions for MeasuringPointIDs (MPID) and Grid Location IDs (GLID) are provided.

Using Historical Power Consumption data and Historical weather data we developed functions that have added the following parameters: A number of the most relevant pairs of temperature-energy values, an average value of the temperature-energy ratio for each hour for the current month, and the presence of a national holiday/weekend on a specific day. 

We taught our model on a large dataset that included air temperature on a current day and the amount of electrical power that was consumed that day. In addition to the raw data, we have added some contextual functions. As a result, we have achieved a very good statistical representativeness of the predictions.

Client location: Norway

The website provides interfaces to arrange moving in and moving out of the apartments for 3 types of users - residents, building managers and real estate agents.

Building managers can manage all their buildings 24/7: Connect with all residents – residing owners, non-residing owners and tenants. Forget printing A4 flyers, send important building announcements to one, some or all residents by SMS or email.

Residents access all their building information online saving managers a substantial amount of time. Know who is living in their buildings – residents book their move-in or out and managers receive an immediate email notification with all the information. Manage their common areas efficiently with an intuitive booking system for areas such as BBQs and SPAs.

Real Estate Agents can have access to all their tenant’s building information in one central location. Save time by directing all their tenant’s inquiries to the administrator. Know who to call on behalf of their tenants if there are any issues. Receive optional email notifications to keep track of any important building announcements your tenants should know about.

Key functionality:

• Book a Move In/Out
• Notifications by email and SMS
• Users management
• Buildings management
• Maps integration

Client location: Australia