The first step is to understand the needs and requirements of the client. In the case of this application, it is important to know what functionalities are expected of it, such as displaying information about the state of the litter box, remote device control, usage monitoring, and so on.

Understanding customer requirements

Next, we conduct a market analysis to understand competitive applications and what features are already available. In this step, we also evaluate what features can help differentiate in the market and propose the best solutions to meet customer requirements.

Market analysis

During the execution of this project, we encountered a challenge related to processing large amounts of data transmitted by thousands of devices per second. To meet this challenge, we had to pay particular attention to aspects such as security, data analysis and aggregation, system architecture, scalability, and many others. Thanks to the hard work and perseverance of our team, we were able to achieve satisfactory results and we are proud of the success we have achieved.

Challenge

Prototyping and designing

Programming and testing

Project deployment

**We have completed a project to create an advanced mobile application for pet lovers. The application enables users to remotely manage devices used for pet care, as well as providing access to knowledge and tools necessary for effective pet care.** 

The project was completed based on a comprehensive solution that combines electronics, mechanics, a mobile application, and an administrative panel for device operators and sellers. Our main goal was to enable pet owners to remotely manage the care of their beloved pets.

Due to the diversity of product users, we decided to introduce the application on both iOS and Android platforms. We achieved this using tools that support both platforms simultaneously, thereby significantly lowering the project cost. Taking into account the wide range of audiences speaking different languages, we decided to use a tool that allows for easy introduction of additional languages without interfering with the application code.

Mobile application and service for managing IoT devices

###### **The goal of the project was to develop an electronic circuit with a Kintex 7 FPGA and QSFP connectors capable of 40 Gbps data transmission.**
As part of the project, an electronic system was developed based on a 12-layer printed circuit board equipped with two QSFP connectors, each operating at a speed of 40 Gbps. The main component in this system is an FPGA called Kintex7, which allows for programming of the system's functionalities.

The system was designed with applications that require high data throughput and programmability in mind. With the use of the Kintex7 FPGA and fast QSFP connectors, the project enables fast data transmission in high-performance networks such as data centers and servers. At the same time, the ability to program the FPGA opens up a wide range of possibilities for customizing the system for different applications and requirements, making the project universal and scalable.



Electronic system for high-frequency data transmission

The project cost 200,000 PLN and was financed by IDUB PW. The fund was allocated for designing a fluid mixer with cross activation using machine learning techniques.

For whom

Starting the design process, we used machine learning algorithms to create a model of the behavior of a fluid mixer. This model is trained on a dataset of known input and output parameters, such as flow rate, fluid viscosity, mixer geometry, and mixing efficiency. Once we obtained the model, we used it to explore the design space and optimize the mixer's performance. We can use techniques such as Bayesian optimization or genetic algorithms to search for the best combination of input parameters, such as cross-activation frequency, mixer blade angle, and flow rate.

By utilizing machine learning to assist in the design process, we can efficiently explore a vast design space and quickly identify optimal solutions. This approach can lead to the development of highly efficient fluid mixers that can be tailored to specific industrial applications.

The technology developed during the project has a wide spectrum of applications in areas where small and accurate representations of large data for future state predictions are needed. The most popular applications are:
Wind turbine industries
Computer vision-based technologies

Application

Prototyping and development

Application deployment

** In the project, we used deep neural network learning for the reduced order embedding for representing the dynamics of the flow system. **

We used reduced order embedding for training and predicting the flow in future flow time and obtained 2 orders of magnitude reduction in computational run times. We developed technology for reduced order modeling of complex processes, which generates a large amount of data.

The technology developed during the project can be used for the prediction or generation of video frames using small computational costs.


Machine Learning assisted design of a laminar fluid mixer with spanwise actuation

###### **We have developed a project of an intelligent module kit for toys of the future. The project was carried out from concept to a finished product. The implementation of the project included user needs analysis, feasibility study, electronic circuit design, enclosure design, and preparation of the project for laboratory testing.**

The module sets were used in educational robots, enabling the acquisition of knowledge in future professions such as programming/engineering, all in the form of a game/toy. The product was primarily aimed at children and youth without prior experience.


ELECTRONICS

ESP32

ESP8266

STM32

ARM

CORTEX

The set of smart modules