| Volume 29, Issue 2 | |
| A Metagenome Diversity Profile of Springs Microbial for Oligotroph Springs Assessment in UB Forest | 105-116 |
| Viky Vidayanti, Catur Retnaningdyah, Endang Arisoesilaningsih, Feri Eko Hermanto | |
| doi: 10.7546/ijba.2025.29.2.000875 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Viky Vidayanti, Catur Retnaningdyah, Endang Arisoesilaningsih, Feri Eko Hermanto (2025) A Metagenome Diversity Profile of Springs Microbial for Oligotroph Springs Assessment in UB Forest, Int J Bioautomation, 29 (2), 105-116, doi: 10.7546/ijba.2025.29.2.000875 | |
| Abstract: Ecosystem quality is an emergent property of a complex system that interacts between biotic and abiotic factors. The study aims to determine the bacterial community profile of several springs with different surrounding ecosystems. Metagenomic analysis using next-generation sequencing (NGS) is performed to determine the microbial profile, taxa richness, and relative abundance of spring water from Buk Bejat (BB), Sumber Dampul (SD) 1, 2, and 3, respectively. The community profile of spring water bacteria at the phylum level shows the same pattern in all study areas. Proteobacteria, Firmicutes, Actinobacteria, and Bacteroidota are the dominant phyla in all sites. At the family level, Comamonadaceae is the most plentiful family in all study sites, along with Lactobacillales P5D1-392, which is found to have a low frequency in SD2 and SD3 compared to SD1 and BB. On the other hand, Muribaculaceae, Morganellaceae, Bacteroidaceae, Oscillospiraceae, Bifidobacteriaceae, Saccharimonadaceae, and Peptostreptococcaceae are found with higher frequency in SD2 and SD3 compared to BB and SD1. The hierarchical clustering at the family level shows two closely related clusters composed of the ecosystem, BB-SD1, and SD2-SD3, but this cluster is not followed by bacterial beta diversity. The alpha diversity in BB and SD1 is higher than in SD2 and SD3 based on ACE, Chao1, Margalef, and Simpson indexes.
Keywords: Diversity, Microbial profile, Spring water | |
| Optimizing SVM Performance through Combinatorial Hyperparameter Tuning and Model Selection | 117-144 |
| Hassan Tariq, Mehwish Majeed, Mueed Ahmad | |
| doi: 10.7546/ijba.2025.29.2.000981 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Hassan Tariq, Mehwish Majeed, Mueed Ahmad (2025) Optimizing SVM Performance through Combinatorial Hyperparameter Tuning and Model Selection, Int J Bioautomation, 29 (2), 117-144, doi: 10.7546/ijba.2025.29.2.000981 | |
| Abstract: Among the support vector machine (SVM) methods, the support vector classifier (SVC) is widely utilized for binary and multi classification tasks across various datasets. Hyperparameter tuning plays a critical role in optimizing the performance of SVM by helping to prevent overfitting or underfitting, enhancing model stability, adapting the model to different types of datasets, and increasing predictive power. This study aims to maximize SVM performance on datasets related to heart disease, liver disorder, breast cancer, and MINST (a digit dataset), which exhibit diverse sample and feature counts. Our proposed framework leverages Python libraries. It employs a combinatorial approach to tune the kernel, C, and degree hyperparameters for both the train-test-split and cross validation (CV) models with different input values. Model accuracy, the area under the curve (AUC), and the F1 score were used to evaluate the models. The most suitable model, hyperparameters, and validation size or number of folds, are selected to achieve maximum accuracy of SVM across all datasets. Results demonstrate that the train-test-split model generally improves SVM performance, except for the heart disease dataset, on which the CV model performs well. Our contribution lies in the development of a framework that combines combinatorial hyperparameter tuning and model selection, aiming to optimize SVM performance and predictive capabilities. Future research can focus on enhancing SVM performance for large-scale datasets and exploring ensemble techniques or deep learning models to enhance its applications in real-world scenarios.
Keywords: Support vector machine, Hyper parameter tuning, Combinatorial optimization, Model selection, Machine learning, Cross validation | |
| Comparative Evaluation of Traditional Methods and Deep Learning for Brain Glioma Imaging. Review Paper | 145-166 |
| Kiranmayee Janardhan, Vinay Martin D’Sa Prabhu, T. Christy Bobby | |
| doi: 10.7546/ijba.2025.29.2.001022 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Kiranmayee Janardhan, Vinay Martin D’Sa Prabhu, T. Christy Bobby (2025) Comparative Evaluation of Traditional Methods and Deep Learning for Brain Glioma Imaging. Review Paper, Int J Bioautomation, 29 (2), 145-166, doi: 10.7546/ijba.2025.29.2.001022 | |
| Abstract: Segmentation is crucial for brain gliomas as it delineates the glioma’s extent and location, aiding in precise treatment planning and monitoring, thus improving patient outcomes. Accurate segmentation ensures proper identification of the glioma’s size and position, transforming images into applicable data for analysis. Classification of brain gliomas is also essential because different types require different treatment approaches. Accurately classifying brain gliomas by size, location, and aggressiveness is essential for personalized prognosis prediction, follow-up care, and monitoring disease progression, ensuring effective diagnosis, treatment, and management. In glioma research, irregular tissues are often observable, but error-free and reproducible segmentation is challenging. Many researchers have surveyed brain glioma segmentation, proposing both fully automatic and semi-automatic techniques. The adoption of these methods by radiologists depends on ease of use and supervision, with semi-automatic techniques preferred due to the need for accurate evaluations. This review evaluates effective segmentation and classification techniques post-magnetic resonance imaging acquisition, highlighting that convolutional neural network architectures outperform traditional techniques in these tasks.
Keywords: Brain glioma analysis, Classification, Deep learning, Segmentation techniques, Magnetic resonance imaging | |
| Cybersecurity for Sustainable Internet of Things Implementation in Healthcare | 167-178 |
| Teodora Bakardjieva, Antonina Ivanova, Yanko Yankov, Zhivko Zhekov | |
| doi: 10.7546/ijba.2025.29.2.001045 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Teodora Bakardjieva, Antonina Ivanova, Yanko Yankov, Zhivko Zhekov (2025) Cybersecurity for Sustainable Internet of Things Implementation in Healthcare, Int J Bioautomation, 29 (2), 167-178, doi: 10.7546/ijba.2025.29.2.001045 | |
| Abstract: The current systematic review aims to summarise and discuss the impact and implications of the Internet of Things (IoT) in the healthcare sector. An electronic search for articles using Google Scholar, PubMed, and Scopus was conducted from January 1, 2019, up to July 1, 2024, under Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The review presents cybersecurity threats in IoT-based healthcare infrastructure and applications that enable smart healthcare services to operate. When collecting and storing medical data from IoT sensors, there is an opportunity to analyse this data, which can improve the identification of risk factors, diagnosis of diseases, treatment, and remote monitoring, which creates prerequisites for reliable self-monitoring by patients. Advantages and risks have been evaluated, and recommendations for further research have been suggested. IoT provides an opportunity to improve the quality and efficiency of the entire service delivery ecosystem, including hospital management, medical asset management, staff workflow monitoring, and optimisation of medical resources based on patient flow.
Keywords: Cybersecurity, Internet of Things, IoT, Healthcare, Vulnerabilities, Threats | |
| Book Review. Why Constant False Alarm Rate? | 179-185 |
| Ivan Popchev | |
| doi: 10.7546/ijba.2025.29.2.001066 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Ivan Popchev (2025) Book Review. Why Constant False Alarm Rate?, Int J Bioautomation, 29 (2), 179-185, doi: 10.7546/ijba.2025.29.2.001066 | |
| Abstract: Thе book presents the algorithms that ensure the maintenance of a constant false alarm rate (CFAR detectors) in the detection of radar targets in conditions of an intensively noisy environment. This type of detectors uses an adaptive threshold dependent on the disturbance level, thus ensuring that a constant false alarm probability is kept. The rapid development of algorithms in this area in recent years can be explained both by the very pronounced need in various fields of science and technology to automatically perform the procedure of detecting a useful signal against the background of disturbances, and by the theoretical interest to interpret the classical approaches to the detection tasks in a modern way.
Keywords: Book Review |
Sponsored by National Science Fund of Bulgaria, Grant No КП-06-НП6-14, 2025
© 2025, BAS, Institute of Biophysics and Biomedical Engineering