International Journal of Advances in Applied Sciences
Not a member yet
668 research outputs found
Sort by
Antimicrobial activity of hard candy with basil (Ocimum sanctum L.) essential oil addition
Get PDFThe basil plant belongs to the Lamiaceae family and contains various active compounds, including phenols, saponins, alkaloids, flavonoids, tannins, and essential oils. These compounds have antimicrobial activity against Streptococcus mutans and Candida albicans, two types of bacteria that can cause bad breath. The addition of basil essential oil to hard candy has the potential to reduce bad breath. This study aimed to determine the concentration effect of basil essential oil on hard candy in inhibiting the growth of Streptococcus mutans and Candida albicans and its acceptance by the panelists. This research was conducted with five treatments with variations in the concentration of basil essential oil, which were 0, 0.25, 0.5, 0.75, and 1%. The results showed that the higher basil essential oil concentration in hard candy inhibited the growth of Streptococcus mutans and Candida albicans. The best treatment was at 0.75% basil essential oil, with sensory panelist acceptance for color 69%, aroma 57%, taste 43%, and overall 58%. Several compounds in basil essential oil, including linalool, eugenol, caryophyllene, and trans-α-bergamotene, are thought to contribute to the ability of this candy to inhibit microbial growth
Bridging technology and healthcare: user acceptance of a surgical site infection system
Get PDFSurgical site infections (SSI) continue to be a problem for surgeons, and unfortunately, SSI information systems are underutilized. This study analyzed the user acceptance of the SSI information system based on the extended technology acceptance model (TAM2). A cross-sectional questionnaire-based study. The variables studied intention to use (IU), perceived ease of use (PEOU), demographic factors (FD), subjective norm (SN), Image (I), job relevance (JR), output quality (OQ), result demonstrability (RD), perceived usefulness (PU). Data were collected by filling out questionnaires and then analyzed using smart-partial least squares (PLS). In total, 61 nurses were included. Most respondents are aged 31-35 (26.23%), and most working periods are between 11-15 years (27.87%). There were significant positive effects on SN to PU (β=0.12; p 0.05). This study concluded that PEOU is the most influential variable in the IU the SSI information system
Advanced classification techniques for weed and crop species recognition using machine learning algorithms
Get PDFThis study proposes an intelligent machine learning framework integrating image analysis and environmental data for precision weed management. The framework leverages efficient feature extraction techniques combined with supervised machine learning algorithms to accurately classify multiple species. Features such as color, texture, and shape characteristics are utilized for model training, enabling high-precision classification while maintaining low computational complexity. The experimental results demonstrate the robustness of the approach, achieving an average classification accuracy of 94.3% across ten weed and crop species in diverse agricultural environments. The system also achieved a 90% reduction in herbicide application compared to traditional methods, showcasing its potential for sustainable farming. Real-time testing confirmed the framework’s efficiency, processing images in under 1.5 seconds per frame, making it suitable for deployment in drones and autonomous farming equipment. These results underscore the practical and scalable nature of the proposed system in automating weed management and advancing sustainable agricultural practices
Comparative study on fine-tuning deep learning models for fruit and vegetable classification
Get PDFFruit and vegetable recognition and classification can be a challenging task due to their diverse nature and have become a focal point in the agricultural sector. In addition to that, the classification of fruits and vegetables increases the cost of labor and time. In recent years, deep learning applications have surged to the forefront, offering promising solutions. Particularly, the classification of fruits using image features has garnered significant attention from researchers, reflecting the growing importance of this area in the agricultural domain. In this work, the focus was on fine-tuning hyperparameters and the evaluation of a state-of-the-art deep convolutional neural network (CNN) for the classification of fruits and vegetables. Among the hyperparameters studied are the number of batch size, number of epochs, type of optimizer, rectified unit, and dropout. The dataset used is the fruit_vegetable dataset which consists of 36 classes and each class contains 1,000 images. The results show that the proposed model based on the batch size=64 and the number of epochs=25, produces the most optimal model with an accuracy value (training) of 99.02%, while the validation is 95.73% and the loss is 6.06% (minimum)
A review of open-source energy system modeling tools
Get PDFNowadays, the transition to open markets, the rapid growth of renewable energy sources like wind and solar, and the shift towards electrification in transportation and industry for decarbonization have increased the demand for advanced energy system models with detailed spatial and temporal data. This paper utilizes a comprehensive literature review and selects a representative set of open-source tools for evaluation. A comparative analysis of 17 open-source energy system modeling tools and their commercial alternatives was conducted. The paper analyzes many open-source aspects such as code commits, updates, programming languages, license details, citations, and energy system modeling features such as power flows (PFs), continuation PF, dynamic analysis, short-circuit analysis, contingency analysis, transportation model, optimal PF (OPF), multi-period OPF, unit commitment (UC), investment optimization, and graphic user interface. Based on the results, the paper suggests appropriate tools used for according power/energy system analysis objective: MATPOWER for power system analysis and Python for power system analysis (PyPSA) for energy system analysis
Forecasting internet traffic patterns for the campus Metro-E network using a hybrid machine learning model
Get PDFComplex traffic patterns lead to crucial campus Metro-E network management and resource allocation. This paper presents an internet traffic forecasting by pre-processing data to offer better bandwidth quality of service (QoS). Eight (8) campuses' traffic data were analysed for modelling predictions using statistical analysis. A Metro-E campus network presents four (4) locations: A, E, F, and H have is a strong correlation between inbound and outbound traffic, with correlation values between 0.4547 and 0.5204. As the inbound traffic increases, outbound traffic tends to rise as well. Conversely, locations B, C, and G have weak correlations, indicating more independent traffic patterns. Data outliers were found for locations C and F, where unusual traffic spikes require further network exploration and show key trends in traffic data. Descriptive statistics reveal notable differences, with H has the highest average traffic at about 75 Mbps, while C has the lowest at around 30 Mbps. Location F shows the greatest traffic fluctuation with a standard deviation of 0.4076, whereas Location G has very little fluctuation with a standard deviation of 0.0240. Overall, this pre process data is use to combine machine learning (ML) to improve prediction abilities for better bandwidth management and real-time handling in digital campus environments
Optimized transfer learning for detection susceptibility vessel sign in stroke using gorilla troops optimizer
Get PDFThe blockage of blood vessels causes ischemic stroke due to clots. The susceptibility vessel sign (SVS), observed through susceptibility-weighted imaging (SWI) via magnetic resonance imaging (MRI), is a key indicator that reveals clots within brain vessels. Early detection of these clots is crucial for timely and effective treatment. Image-based detection methods, particularly non-invasive techniques like MRI, offer a superior approach compared to other modalities. This study proposes an optimized method using transfer learning to classify SVS. The deep convolutional neural network (DCNN) residual network 50 version 2 (ResNet50V2) was applied for classification, with hyperparameters fine-tuned using the gorilla troops optimizer (GTO). The optimized proposed model achieved an accuracy of 94%, sensitivity of 100%, specificity of 88%, and an F1-score of 93%. This significantly outperforms the standard ResNet50V2 model using the default parameter, which achieved an accuracy of 91%, sensitivity of 82%, specificity of 100%, and an F1-score of 77%. These results demonstrate that the proposed method significantly enhances the detection of SVS, offering a promising tool for early ischemic stroke diagnosis
Financing model for demand response information services with bundled incentives
Get PDFThis study attempts to build a new model for information service financing schemes by considering utility functions to measure heterogeneous consumer satisfaction. This model was developed by involving a combination of reverse charging, demand response, and heterogeneous incentive models, and considering the quality of user service measured by a quasi-linear utility function against the information service financing scheme. The incentive financing scheme is applied to a local data server, including traffic during peak hours and off-peak hours. This internet incentive financing model is solved using the LINGO 13.0 application. Furthermore, the development model for incentive financing for information services based on demand response and bundling in the information service financing scheme is subjected to sensitivity analysis with the aim of identifying parameters that affect model performance. Based on the analysis that has been done, the results of this study indicate that the new model in the incentive financing scheme for information services with a quasi-linear utility function involving a combination of reverse charging, demand response, and heterogeneous incentive models produces an optimal solution in a fixed cost financing scheme for data traffic usage during peak hours and off-peak hours
Investigating relationships between reading comprehension and oral reading fluency through AI-driven tool reading progress
Get PDFThis study investigates the relationship between reading comprehension and oral reading fluency components—accuracy and rate—among 113 Vietnamese EFL university students using the AI-powered tool Microsoft Reading Progress. Over 14 weeks, students engaged in weekly oral reading and comprehension tasks using integrated Microsoft Teams features. Fluency metrics (accuracy and rate) and comprehension scores were automatically collected and analyzed using Pearson correlation. The results revealed weak but statistically significant positive correlations between reading comprehension and accuracy (r = .257, p < .01), and between comprehension and rate (r = .289, p < .01), suggesting that improvements in fluency modestly support comprehension. A strong correlation between accuracy and rate (r = .765, p < .01) was also observed. The study highlights the effectiveness of Reading Progress in capturing fluency data and promoting self-paced improvement. However, limitations such as the short duration, localized sample, and constraints of accent recognition in AI-based speech analysis affect the generalizability and validity of results. The findings support the pedagogical integration of AI tools in EFL instruction while calling for future research with larger samples, extended timelines, and diversified digital tools to further validate and expand on these results
Harvesting insights: exploring machine learning for crop selection and predictive farming
Get PDFModern agriculture has undergone a significant evolution, adopting advanced techniques to streamline crop management processes. One such advancement is the integration of machine learning (ML) technology, which shows great promise in optimizing crop selection and enhancing economic returns. Key determinants of crop productivity, including water availability, soil quality, weather conditions, and timely resource allocation, play pivotal roles in the farming ecosystem. Harnessing these factors, ML algorithms facilitate the identification of optimal crop choices and provide continuous monitoring of cultivation processes to anticipate evolving crop needs. This paper investigates various ML techniques employed for crop selection and evaluates their effectiveness in agricultural settings. Through a comparative analysis, we highlight the advantages of these techniques and provide insights into their potential impact on current farming management practices. By leveraging ML for predictive farming, stakeholders can make informed decisions to maximize yields, minimize resource wastage, and promote sustainable agricultural practices. This study contributes to the ongoing discourse on the integration of technology in agriculture and underscores the transformative potential of ML in shaping the future of crop management. We investigate recent papers from the years 2020 to 2024