At QuantumNet, the Research & Development division serves as the company’s core innovation hub, where science, technology, and industry converge to drive meaningful contributions to the global quantum ecosystem.
Our R&D unit merges industrial expertise with academic excellence to explore and apply quantum technologies with a pragmatic and impact-driven approach. What can quantum computing realistically achieve in solving today’s industrial challenges? This is the question we are trying to answer. To do so, we encourage an active dialogue with our partners, engaging in conversations about their needs, the limitations of current solutions, and exploring where quantum technologies could be a game changer in the near or long term.
On one hand, close collaboration with industry ensures we stay aligned with market needs, customer expectations, and strategic partnerships.
On the other hand, our R&D operates in close collaboration with leading academic laboratories such as QUASAR and key departments in physics and engineering across different universities. This enables active participation in cutting-edge research, including hosting thesis projects, PhD students, and internships in our labs, thus fostering a dynamic exchange of knowledge. Our own researchers design and develop hybrid quantum-classical algorithms to solve complex real-world challenges in sectors such as smart mobility, industrial production, cybersecurity, and artificial intelligence. Our work bridges theoretical research with deployable solutions, validated on real-world datasets and quantum hardware.
Our efforts extend to the convergence of quantum computing and artificial intelligence, where we develop models such as Quantum Convolutional Neural Networks (QCNNs) and Variational Quantum Classifiers (VQCs) for tasks ranging from plant species classification to predictive maintenance and anomaly detection. We actively contribute to digital transformation through the development of quantum solutions for traffic optimization, industrial analytics, quantum cryptography, and sustainable infrastructure.
Deep learning models for plant species recognition using leaf images
QuantumNet incorporates quantum computing into deep learning architectures tor image recognition. These hybrid models are particularly useful in industries undergoing digitai transtormation, such as agri-tood. Specifically, they develop
Al-powered tools tor identifying hazelnut plant varieties based on leaf images, aiding decision-making in the hazelnut industry.
Optimization Algorithms for Enhancing Cultural Site Accessibility
Quantum algorithms like QAOA (Quantum Approximate Optimization Algorithm) help solve complex route optimization problems. QuantumNet applies these algorithms to improve navigation within cultural sites, such as archaeological parks and tourist areas, integrating them into mobile applications to enhance visitor experiences.
Optimization Algorithms for Traffic Light Control in Urban Networks
Efficient traffic light management is crucial for urban mobility, especially in smart city contexts. QuantumNet designs hybrid metaheuristic algorithms combining classical and quantum computing to optimize traffic flow in real time, leveraging the growing capabilities of quantum processors.
Quantum classification models for anomaly detection in industrial processes
Quantum computing enhances artificial intelligence and machine learning by introducing quantum variational circuits. These models can be used tor classification tasks, such as identifying damaged components in production lines or detecting anomalies in telecommunication systems.