Research Article
Comparing Classical and Quantum Machine Learning Models for Breast Cancer Classification on the WDBC Dataset
Jovana Gluhovic*
Issue:
Volume 9, Issue 3, September 2026
Pages:
95-114
Received:
29 June 2026
Accepted:
11 July 2026
Published:
6 August 2026
Abstract: Breast cancer is a major health concern, and early detection can make a great difference in treatment and survival rates for breast cancer patients. Machine learning methods have noticeably improved prediction accuracy on high-dimensional medical datasets and have become widely used tools in medical diagnostics. The transition to a quantum computational framework has opened new directions in machine learning research. By using qubits instead of classical bits, quantum models may provide new ways to represent and process complex medical data. In medical diagnostics, this has led to a growing interest in whether quantum approaches can improve classification performance more effectively than classical methods. The purpose of this paper is to compare classical and quantum machine learning models on the task of breast cancer classification and to determine whether quantum models can achieve higher accuracy and faster prediction on a selected dataset. Alongside the main simulator-based experiment, a smaller experiment was performed on a real IBM quantum computer to demonstrate the practical execution of the same task under current hardware constraints. In the practical part of the study, the Wisconsin Diagnostic Breast Cancer (WDBC) dataset was used. This dataset consists of 569 samples with 30 numerical features extracted from digitized fine needle aspirate images and provides a reliable basis for evaluating model performance. A comparative analysis was conducted between classical and quantum machine learning models, including a support vector machine (SVM), an artificial neural network (ANN), a quantum support vector machine (QSVM), and a hybrid quantum-classical neural network (QNN). In the simulator-based experiment, both SVM and ANN achieved an accuracy of 0.956 with an F1-score of 0.965 on the test set, while QSVM reached an accuracy of 0.807 with an F1-score of 0.866 and the Hybrid QNN achieved 0.623 accuracy with an F1-score of 0.677. These quantum and hybrid models also required substantially longer training times than the classical baselines. A small hardware experiment on an IBM quantum device further illustrates both the practical feasibility and the current limitations of executing this classification task on noisy intermediate-scale quantum hardware.
Abstract: Breast cancer is a major health concern, and early detection can make a great difference in treatment and survival rates for breast cancer patients. Machine learning methods have noticeably improved prediction accuracy on high-dimensional medical datasets and have become widely used tools in medical diagnostics. The transition to a quantum computat...
Show More
Research Article
Methods for Counting and Enumerating Set Partitions
Arnav Khinvasara,
Alexander Pikovski*
Issue:
Volume 9, Issue 3, September 2026
Pages:
115-119
Received:
30 July 2026
Accepted:
30 July 2026
Published:
23 September 2026
DOI:
10.11648/j.ajcst.20260903.12
Downloads:
Views:
Abstract: Set partitions are arrangements of distinct objects into groups. After a brief review of the subject, we consider the task of counting and enumerating set partitions. The number of set partitions, known as Bell number, is a rapidly increasing number and does not have an explicit formula. We study approximate expressions for the Bell number given in the literature. We find that an asymptotic formula of Moser and Wyman gives a surprisingly accurate approximation to the Bell number even for small set sizes. Furthermore, a simple expression due to Berend and Tasssa can be conveniently used to approximate the Bell number for small set sizes. % Next, we consider enumeration of set partitions. The problem of listing all set partitions arises in a variety of settings, in particular in combinatorial optimization tasks. Algorithms for enumerating all set partitions are reviewed. The focus is on non-recursive algorithms without Gray code constructions. We compare the classic algorithm of Hutchinson with three more modern ones. Empirically, it is found that all of them scale exponentially with the set size. While the exact compiler and optimization settings do matter, it can be concluded that the algorithm of Djokic et al. is the fastest one, thus it is recommended for practical use.
Abstract: Set partitions are arrangements of distinct objects into groups. After a brief review of the subject, we consider the task of counting and enumerating set partitions. The number of set partitions, known as Bell number, is a rapidly increasing number and does not have an explicit formula. We study approximate expressions for the Bell number given in...
Show More
Research Article
A Comparative Performance Analysis of Source and Channel Coding Techniques for Digital Communication Systems
Anis Zebiane*
Issue:
Volume 9, Issue 3, September 2026
Pages:
120-137
Received:
12 October 2025
Accepted:
12 October 2025
Published:
23 September 2026
DOI:
10.11648/j.ajcst.20260903.13
Downloads:
Views:
Abstract: This research investigates and compares the performance of five major coding techniques - Huffman, Run-Length Encoding, Arithmetic, Convolutional, and Bose-Chaudhuri-Hocquenghem (BCH) coding - within a complete digital communication system comprising source coding, channel coding, Binary Phase Shift Keying (BPSK) modulation, and transmission over an Additive White Gaussian Noise (AWGN) channel. The study evaluates these methods in terms of compression efficiency, error correction capability, and overall system reliability under different signal-to-noise ratio (SNR) conditions. MATLAB simulations were conducted for both text and image data to quantify compression ratios and bit error rate (BER) performance across SNR values ranging from 0 dB to 24 dB. Results demonstrate that Run-Length Encoding achieves superior compression performance for highly repetitive text, whereas Arithmetic coding provides near-optimal compression efficiency for general, non-repetitive data distributions such as natural images. Among channel coding schemes, Convolutional codes exhibit better resilience to noise at low-to-moderate SNR levels compared to BCH codes, particularly when decoded using the Viterbi algorithm, while BCH codes retain an advantage where guaranteed multiple-error correction within fixed-length blocks is required. Moreover, integrating Arithmetic coding with Convolutional coding into a single hybrid pipeline enhances end-to-end robustness by balancing data reduction and error resilience, achieving a bit error rate of zero at SNR levels of 4 dB and above while sustaining channel capacities exceeding 1.8 Mbps. These findings provide valuable insights into the optimal combination of source and channel coding strategies for modern digital communication systems, emphasizing the trade-offs between computational complexity, compression efficiency, and transmission reliability, and offering practical guidance for system designers working on bandwidth-constrained or noise-limited communication links.
Abstract: This research investigates and compares the performance of five major coding techniques - Huffman, Run-Length Encoding, Arithmetic, Convolutional, and Bose-Chaudhuri-Hocquenghem (BCH) coding - within a complete digital communication system comprising source coding, channel coding, Binary Phase Shift Keying (BPSK) modulation, and transmission over a...
Show More
