Yevhen Kukoba
Offer Yevhen work on your next project.
Rating
Skills and abilities
Programming
Mobile development
Portfolio
-
REST API for automated order analysis
AI & Machine LearningREST API for automated order analysis
Technologies: Python, FastAPI, SQLite, OpenCV, NumPy, TensorFlow, OpenAI ChatGPT API, SQLAlchemy, Redis, Celery, FastAPI TestClient, Unit tests, Mypy
I am developing a REST API for automated order analysis, designed to improve the order verification process in an online auto parts store. The API accepts images, where the customer can check if the parts shown in the photo match those that were ordered. The system uses OpenCV and NumPy to determine object contours and classifies them using a pre-trained TensorFlow model and the ChatGPT API, which enhances the recognition process and increases classification accuracy.
…
After processing the image and classifying the objects, the results are sent to the user for confirmation. The user can adjust the recognition, resend requests, and confirm contours and classification. The information is saved in the database using SQLAlchemy and sent to the warehouse management system (WMS).
To improve performance, an asynchronous model caching mechanism has been implemented, which helps avoid delays during initialization. Redis is used to manage the cache and track asynchronous tasks executed via Celery.
Additionally, a model training system has been developed, including functionality for adding new classes and images for training. Unit and integration tests cover all components using FastAPI TestClient, and strict typing is ensured with mypy. Database migrations are managed through SQLAlchemy.
I am fully responsible for the project architecture, technology selection, and implementation of all components, carrying out the work without external guidance.
-
Inventory Management System
PHPInventory System Developer (PHP, Kotlin, MySQL, Nette, Zebra, Honeywell, SQLite, Jetpack Compose, Retrofit, CameraX, MVVM, REST API, Redis)
As a key participant in the development of a comprehensive inventory system, I played an important role in creating both the backend and the web version and mobile application, working with a wide range of technologies, including RFID and barcode scanning.
… The system allows for efficient asset management, giving users the ability to add items to the inventory and assign employees to perform tasks. Employees use mobile devices with RFID scanners to locate assets in buildings, rooms, and floors. RFID tags, QR codes, and barcodes are used during the inventory process, ensuring seamless synchronization between the mobile application and the server. The system supports offline mode, allowing work to continue without an internet connection. Data is synchronized when the connection is restored, and built-in mechanisms prevent data overwriting when multiple employees scan objects simultaneously.
In the mobile application, I integrated various RFID scanners (Zebra, Honeywell) and implemented QR code scanning using the camera. The application is built on the MVVM architecture using Jetpack Compose, Room, Retrofit, CameraX, Dagger Hilt, and operates within a single Activity. I also ensured Bluetooth support for integration with Zebra printers, allowing RFID labels to be printed directly from the application.
On the backend side, I developed a REST API using the Nette framework and integrated Zebra printers for printing RFID labels via Zebra Browser Print. Additionally, I created modules for visual configuration of templates and synchronized data between the mobile and web applications.
Currently, I continue to maintain the system, ensuring its reliable operation and implementing new features and integrations.
-
Factory planning system
PythonI developed a planning system for a factory aimed at optimizing the order of processing parts on machines, minimizing the overall time for all processes, and increasing the efficiency of equipment usage. For this, optimization algorithms were used, implemented with Google OR-Tools.
The system took an array of data about the parts as input, including the sequence of operations (turning, welding, re-turning, and others), required equipment, time constraints, and execution priorities. The algorithm analyzed this data and generated an optimized schedule for each part, indicating which machine and at what time the processing should take place. It was important to consider the availability of machines, time constraints, and deadlines for high-priority tasks.
… The project was fully completed by me, starting from the development of the system architecture and ending with the implementation of key components. The implementation took about a week and required deep knowledge in the field of algorithms and optimization methods.
Activity
| Latest proposals 2 | Budget | Added | Deadlines | Proposal | |
|---|---|---|---|---|---|
|
Need a simple script in Python or another (script to filter words in txt)
22 USD
|
|||||
|
Computer vision
100 USD
|