The Nucleus

Deep Q Networks for Classification: Performance Analysis on Iris and Diabetes Datasets

M. Rehman, M. Baig — Mon, 14 Jul 2025 00:00:00 +0500

This study explores how Deep Q Networks (DQNS) can be applied to classifying data with standard datasets. Though DQNs are designed for sequential decisions, this study uses the Iris and Diabetes datasets, which are both used for classification, to test the performance. It investigates DQNs with different data imbalances and compares their results based on the quantity of data. Models are assessed using accuracy, precision, recall, F1 score, ROC-AUC, the amount of memory required, and their training speed. As demonstrated by the results, DQNs can match other algorithms in accuracy while attaining accuracy rates between 84% and 95% for various datasets and modified configurations. Based on the study, performance can be affected by adjusting hyperparameters and the distribution of data classes. DQNs are more complex than common classifiers such as SVMs and decision trees, and their main contribution in simple classification is yet to be proven. It adds to the enthusiasm for using reinforcement learning models in the context of supervised learning. The paper highlights the value of correct evaluation, points out risks linked to model over-fitting and includes new areas to pursue in the future such as benchmarking, clarifying models and using hybrid systems.

An Antibacterial Potential of Cerium Oxide Nanoparticles against Mycobacterium tuberculosis: A Novel Approach for Tuberculosis Treatment

S. A. Noonari, M. Gul, J. Ali, H. A. Khan, F. Mustafa — Mon, 04 Aug 2025 00:00:00 +0500

This study investigated the antibacterial effects of cerium oxide nanoparticles (CON) on Mycobacterium tuberculosis. Cerium oxide nanoparticles were synthesised using a microwave-induced technique and characterized by Scanning Electron Microscopy. Results indicated that an increase in synthesis time led to a reduction in nanoparticle size, demonstrating that the duration of the synthesis process influenced particle size. Additionally, the antibacterial activity of CON particles was found to be size-dependent. In a disc diffusion assay, cerium oxide nanoparticles enhanced the efficacy of antibacterial agents, significantly improving the effectiveness against Terivid, Amikin, Grasil, Velosef, Spraxin, and Ceftriaxone against Mycobacterium tuberculosis.

Laser-Induced Breakdown Spectroscopy in Vegetable Analysis: Contaminants and Nutrients

A. Anwar, A. Rashid, M. Rashid — Mon, 15 Sep 2025 00:00:00 +0500

Vegetables are rich in minerals, but pollutants and wastewater, which introduce heavy metals into the soil, heavily impact their cultivation. As an efficient and effective methodology, scientists prefer using Laser-Induced Breakdown Spectroscopy (LIBS) as a light-based technique to determine the elemental constituents of vegetables. It aids in safety and quality assurance by allowing them to image nutrients and hazardous metals, such as cadmium. This study explored the application of LIBS for detecting contaminants, such as Cd, and profiling essential nutrients in vegetables. Unlike conventional methods such as ICP-MS and AAS, LIBS offers fast, on-site, and multi-element analyses with minimal sample preparation. This review consolidates recent studies on carrots, potatoes, spinach, broccoli, and other leafy greens, emphasizing enhancements using nanoparticles and chemometric tools to improve sensitivity and accuracy. According to the results, LIBS has also been effectively employed to analyze the components of vegetables, enhancing the control and safety of food quality surveillance. The results also prove that LIBS can be a better method for monitoring food quality and safety. LIBS is more consumer-and environmentally friendly because it is portable, fast, and capable of simultaneously analyzing various components.