Quantum Machine Learning (QML) combines quantum computing principles and traditional machine learning principles to provide new ways to solve difficult classification problems through the use of quantum technology. The goal of this paper is to implement a Quantum Kernel Support Vector Machine (QKSVM) using PennyLane and evaluate it against a standard image classification dataset, Fashion-MNIST. The Fashion-MNIST images are represented as 28x28 grayscale pixel arrays; they are normalized using a min-max normalizer with output values between zero and one. The 28x28 arrays are then dimensionally reduced to a size of four principal components (approximately 85% cumulative explained variance), and the QKSVM will utilize a quantum circuit limited to four qubits which is consistent with today's Noisy, Intermediate-Scale Quantum (NISQ) capabilities for performing simulations. Each input feature is represented as a qubit via an RY rotation and the qubits are then entangled using a CNOT circuit to generate the quantum kernel matrix, which is computed as the pairwise fidelity of each input image's state, which is subsequently used by a classical SVM classifier implementing a one-versus-all classification method. The QKSVM achieved approximately 40% accuracy and a macro-F1 score of 0.37 on a 100 sample stratified subset of the Fashion-MNIST test dataset, compared with 60% and 91.2%, respectively, using a classical Radial Basis Function Support Vector Machine (RBF-SVM) classifier with the same four principal components of input features and a Convolutional Neural Network (CNN) with full input images. With a primary bottleneck of qubit count, circuit depth, and shot noise, this work serves as a fully documented and reproducible baseline for future research on quantifying the performance of hybrid classical and quantum image classifiers across standardized image dataset benchmarks.
M. Devi, S.Sravanthi, V. Chaithanya et al.· 2026 7th International Confe...· 0 citations
Software-Defined Networking (SDN) is a new technology that makes the network programmable by decoupling the control plane from the data plane. In large-scale SDN deployments, however, a single controller can be a performance bottleneck due to high number of flow requests, slow control-plane response time, and its inability to withstand failures. In contrast to single-controller SDN architectures, multi-controller SDN architectures reduce the number of controllers required and distribute control across multiple domains, making coordination among multiple controllers and the isolation of static domains inefficient when traffic is dynamic. Based on the above, this paper presents an Adaptive Traffic-Aware Domain Isolation Framework (AT-DI) for multi-controller SDN environments. The proposed framework combines traffic-aware domain monitoring, controller-load estimation, adaptive inter-domain coordination, and dynamic flow-handling decisions. Rather than using a single synchronization method for all inter-domain flows, AT-DI chooses the appropriate coordination mode based on traffic locality, controller stress, and the volume of inter-domain traffic. The proposed architecture has been tested with the Ryu controller in a Mininet Fat-Tree topology and compared with Single-Controller SDN, HyperFlow, ONOS, Kandoo, Rama, and the static Domain Isolation Multi-controller (DiM) architecture. Experimental results demonstrate that AT-DI increases throughput, decreases latency and round-trip time, reduces inter-controller control overhead, and provides balanced controller utilization under various traffic loads. The results validate the claim that adaptive domain isolation is a scalable and lightweight control-plane solution for dynamic multi-controller SDN deployments.
O. Sirisha, M. Haritha, M. Devi et al.· 2026 6th International Confe...· 0 citations