Despite their high sensitivity and rapid response characteristics, carbon nanotube (CNT) film-based gas sensors are plagued by bundle-induced poor gas selectivity and electrical noise. In this study, we developed thin-walled carbon nanotubes (TWCNTs) that were functionalized with a flavin mononucleotide (FMN) dispersant. This was done in order to reduce bundle size and enhance gas selectivity. Noncovalent functionalization with FMN has been demonstrated to improve CNT dispersion, minimize aggregation, and establish uniform electrical conduction pathways, thereby enhancing sensor stability. Gas sensing tests were conducted with NO2, CO2, and H2 (100 ppm each) to assess the selectivity of the sensor. The resistance change for NO2 was found to be four times higher than that for H2 and two times higher than that for CO2. This result indicates that the sensor exhibits improved selectivity. The riboflavin phosphate groups present on the modified CNTs provide additional adsorption sites and facilitate charge transfer processes. The combination of structural optimization, noise reduction, and superior selectivity exhibited by FMN-functionalized TWCNT sensors demonstrates their significant potential for high-performance gas detection, thereby establishing them as viable candidates for real-world applications.

To obtain light ensemble model through clearly explained effective ensemble member selection and finding data representation in various valuable forms are major challenges in medical image classification tasks. Despite numerous deep learning (DL) models were developed to solve the generalization problem in DL through ensemble learning, most of the models lacks the evaluation of the effects of each ensemble member for the final ensemble model. Additionally, existing ensemble models tend to include huge number of parameters and use images only in RGB channels or greyscale forms missing the crucial representations of the dataset to reach robust classification outcomes, particularly in medical applications. In this study, novel ensemble model IMed-CNN proposed solution to above-mentioned gaps in the field by introducing the data in ten various forms to the model and applying systematic model dropout (SMDE) with unique true prediction (UTP) analysis which insures to choose only useful ensemble members. To verify the performance of the IMed-CNN, extensive experiments was designed for testing. Results illustrate that IMed-CNN outperformed baseline models.