International Journal of Information Technology, Research and Applications

Approaches for Analysing Ultrasound Images Using Image Processing and Machine Learning Techniques

2025-11-10T12:44:53+00:00

Abstract

Objective: This study's primary objective is to examine different machine learning and image processing techniques for ultrasound picture analysis. In order to facilitate early diagnosis in medical field, new innovative skills should be introduced to procure accurate result of ultrasound images. Methods: The study pre-processes ultrasonic pictures using sophisticated image processing methods like feature extraction, edge detection, and filtering. Machine learning techniques, such as Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and decision trees, are used to classify and segregate pertinent information in the ultrasound scans. In order to determine the most effective approaches for precise analysis, the study compares the effectiveness of machine learning models with conventional image processing methods. Findings: The findings demonstrate that machine learning-based strategies, especially deep learning approaches, perform faster and more accurately than conventional image processing techniques. Specifically, CNNs show excellent accuracy in identifying and classifying important anatomical characteristics in ultrasound pictures. In order to elevate model performance, the study also emphasizes the difficulties associated with data annotation and the requirement for sizable obtained datasets. Novelty: In order to give a thorough comparison for ultrasound image analysis, this work presents a novel methodology by fusing contemporary machine learning algorithms with conventional image processing techniques. Additionally, the study investigates how several machine learning models might be integrated to produce hybrid solutions that maximize diagnostic results. By simplifying medical imaging processes, the suggested framework may improve diagnostic precision and lower human error.

The Exponential Scaling in Quantum Science: Origins, Implications, and Opportunities across Chemistry and Quantum Technologies

2026-03-29T02:39:16+00:00

The Exponential scaling is a defining characteristic of quantum science that underpins both its transformative computational potential and its profound theoretical challenges. Unlike classical systems whose state spaces typically scale linearly or polynomially with system size, quantum systems exhibit exponential growth of Hilbert space dimensionality as the number of quantum degrees of freedom increases. This scaling governs quantum information storage, entanglement complexity, quantum simulation capabilities, and the difficulty of classical emulation of quantum phenomena. This article examines the physical origins of exponential scaling, its implications across quantum computing, quantum many-body physics, quantum sensing, and quantum communication, and the emerging strategies developed to harness or mitigate exponential complexity. The discussion highlights how exponential scaling simultaneously represents the power and the bottleneck of modern quantum technologies.

Support Vector Machine Based Classification of Students’ Mathematics Learning Preferences Using Educational Data Mining

2026-04-02T02:26:16+00:00

Educational institutions increasingly seek data-driven approaches to understand students’ learning preferences, particularly in mathematics education where differences in conceptual understanding across domains may influence learning outcomes. This study aims to develop a machine learning–based model to identify students’ mathematics learning preferences across Algebra, Geometry, and Statistics using questionnaire data. The research was conducted at Universitas PGRI Adi Buana Surabaya involving undergraduate students in mathematics education. A quantitative approach was employed using questionnaires as the primary instrument to capture students’ learning preference characteristics. The dataset was analyzed using the Support Vector Machine algorithm with a hold-out validation technique, where the data were divided into 75% training data and 25% testing data. Model performance was evaluated through multiple experimental trials using accuracy, precision, recall, and F1-score. The results show that the model achieved strong and stable performance across ten trials, obtaining an average accuracy of 97.05%, precision of 94.88%, recall of 98.32%, and F1-score of 96.39%. Domain-level analysis indicates that the model performs most consistently in identifying Algebra and Statistics preferences, while slightly greater variation occurs in the Geometry domain due to overlapping conceptual characteristics. Overall, the model successfully detects patterns in questionnaire responses and classifies students’ learning preferences across the three domains. The novelty of this study lies in integrating questionnaire-based educational preference analysis with a machine learning classification framework to automatically detect dominant mathematics learning domains. The implication of this research highlights the potential use of machine learning to support data-driven decision-making and personalized learning strategies in mathematics education. The contribution of this study is the development of a practical approach for applying computational classification techniques to educational datasets in order to better understand students’ learning characteristics and support adaptive learning environments.