Transylvanian Review

Educational and socio-economic strategies for the sustainability of Iberian Mediterranean grasslands

Eusebio Cano Carmona — 2024-04-09

In the study of Mediterranean grasslands, field students identified two large groups of grasses belonging to two phytosociological classes: Stellarietea mediae, of interest as a CO² sink and as a pasture for cattle and horses, and Poetea bulbosae, of great importance for sheep farming. Coverage of the study plots is between 60-100%. Hordeum leporinum communities absorb high amounts of CO²and can support 1.8 cows/ha/year, while Poa bulbosa communities can support 25 sheep/ha/year. Both classes are identified and studied in the field and in the laboratory by the students of the double master's degree Olive and Olive Oil and Teaching, ESO, Baccalaureate, Vocational Training or Language Teaching. The student in the field learns to take data, and then in an analytical phase in the laboratory to differentiate the inventories on the basis of floristic composition, so he has been able to differentiate the alliances of the two classes studied in depth, as is the case of Hordeion leporini and Trifolio subterranei-Periballion. An active didactic methodology is applied, in which the students assimilate 100% of the contents, and obtain a training that enables them to defend the conservation of Mediterranean grasslands. In short, this work combines botany with education to achieve a sustainable current development, but also to ensure the future of the planet. Therefore, we have focused this work on grasslands and educational strategies to train future environmental managers, achieving 100% success.

Improved prediction of stock market trends in Saudi Arabia by combining artificial neural networks and fuzzy logic techniques

Khalil A. Alruwaitee — 2024-04-09

An integrated prediction model designed for the KSA Stock Exchange utilizes Artificial Neural Networks (ANNs) and Fuzzy Logic approaches. The analysis examines thedaily closin g prices of the Al Rajhi share index in the Saudi stock market index from January 15, 2020, to July 15, 2020, to identify important market moves and patterns throughout this timeframe. The suggested model is rigorously assessed utilizing essential statistical metrics such as R-squared, Mean Absolute Percentage Error(MAPE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Squared Error (MSE). The indicators together offer a strong evaluation of the model's accuracy and predictive capability, providing significant insights for investors and stakeholders in navigating the changing Saudi Arabian stock market.

Prediction of safety factors on slopes by using machine learning multilayer perceptron and decision tree techniques

Mohammed Mnzool — 2024-04-09

A more accurate strategy for measuring and predicting slope safety and risk was the study's goal. This study used machine learning methods to create accurate forecast models for the earth slope factor of safety (F.S). Multilayer perceptron (MLP) and decision tree (DT) have been chosen for the analysis. These methods have been widely used in geotechnical analysis and domain stability because of their unique benefits. We chose MLP, DT, and learning algorithms
as our core analytical approaches. The MLP and DT methods predicted the security component value as the main result of the earth slope mathematical models. In this study, 69.5 percent of the 105-group database was used to train the model, and 30.5% tested its accuracy. The controlled machine learning method-based decision tree (DT) and multilayer perceptron (MLP) computer models are used to analyze dump slope stability. SoftMax activates the output layer. The model summary showed 19.21 training cross-entropy errors and 11% erroneous predictions. The testing model had a 10.59 cross-entropy error and 21.9 wrong predictions. In the training classification phase, 36 viruses failed and two remained stable. This yields 94.7% accuracy. Testing classification yielded 18 failing viruses and 4 stable viruses. Maximum tree depth is 3, minimum parent node cases are 100, and minimum child nodes are 50. MLP models
have superior accuracy, precision, and recall than DT models, which have 0.676, 0.604, and 0.711. The results summary reveals 3 nodes, 2 terminal nodes, and 1 depth. Therefore, MLP models outperform DT models.

Discharge of NCA battery using copper strip in salt water

Erdenebold Urtnasan — 2024-04-09

The application of Li-ion batteries has been growing with the e-mobility revolution of computers, cellular phones and electric vehicles. As this revolution accompanies, manufacturers consider recycling wasted Li-ion batteries an important resource of raw material for manufacturing the lithium-ion battery. During the disposal, transport and crushing for recycling of the battery, it is necessary to crush for separation into black mass, plastic and metal parts, but there is a risk of explosion because of the residual voltage of the battery. Therefore, the discharge process is an important step in the recycling. This work aimed to investigate a new method to discharge the cylinder-type battery using salt water solution with the copper conductor that contacted and no-contacted with the battery. A gap value between the battery and copper conductor was a variable factor in the discharge process. The salt water called as electrolyte solution in the gap caused an electrical short circuit and accelerated discharging. During the discharge process, the battery cap and valve corroded when the battery did not come into contact with the copper conductor, causing the elements of the battery’s anode and cathode to dissolve into the solution. But, the voltage drop reached nearly 99%. However, the battery did not corrode when it contacted the copper during discharge, and the voltage drop reached approximately 90% after 8 hours with a 2 mm gap. Here, we report the battery discharge based on an electrochemical reaction, schematic diagram, and chemical analysis of the precipitate generated during the discharge test.

PREDICTION OF NEW OSTEOPOROSIS CASES USING TIME SERIES AND ARTIFICIAL NEURAL NETWORKS: A COMPARATIVE STUDY

Afrah Al-Bossly — 2024-04-09

Osteoporosis stands as a significant public health concern characterized by diminished bone density and heightened susceptibility to fractures, affecting over 200 million individuals globally. Recent statistics from the International Osteoporosis Foundation indicate that approximately 33% of women aged 50 and above and 20% of males are at risk of experiencing osteoporotic fractures during their lifetime. This study aims to juxtapose the predictive efficacy of time series models and artificial neural networks to enhance the early detection of osteoporosis cases. Methodologically, the research involves preprocessing and standardization of datasets to optimize their suitability for machine learning applications. An Artificial Neural Network (ANN) tailored for osteoporosis prediction demonstrates superior predictive performance when compared to conventional approaches such as the autoregressive integrated moving average (ARIMA) model. The enhanced predictive capabilities are substantiated through rigorous statistical analyses evaluating the model's accuracy. Osteoporosis data spanning from 1965 to 2023 are sourced from the official website of the Australian Government Institute of Health and Welfare.