Integrating Machine Learning Models for Enhanced Soil Organic Carbon Estimation: A Multi-Model Fusion Approach

Bryan; Angel Ordóñez; Magdy Echeverría; Theofilos

doi:https://doi.org/10.54216/FPA.160202

Pure Mathematics for Theoretical Computer Science | 2024

On the Improving of the Efficiency of FL Controller Based on Genetic Algorithms to Control (DC-DC) Converters

DC-DC converter circuits effectively convert the DC input voltage into a regulated output voltage more efficiently than linear regulators or magnetic transformers. The electronic switches of these converters are controlled to obtain the desired regulated output voltage value. In recent years, the concept of using Artificial Intelligence systems to control electrical circuits and their practical applications has expanded, as Fuzzy Logic Controller (FLC) is one of the most famous types of these systems because it uses inferential logic to simulate the work of the human brain by formulating the fuzzy rule and following the membership of the system’s input and output and converting the output into a numerical value that controls it’s in turn the duty cycle of the converter. The research proposes the use of Genetic Algorithms (GA) that simulate the principle of natural inheritance (the survival of the fittest principle) to improve the accuracy of the fuzzy controller and thus the efficiency of the step-down converter (Buck) by finding the ideal values for its coefficients in order to obtain the closest value for the reference voltage by improving the parameters of the gain constants and changing the shape of membership. The results of the research using MATLAB show the improvement provided by the Genetic-Fuzzy controller (GA-FLC) compared to the fuzzy logic controller in terms of the response parameters and output curves of the Buck converter.

groups

Khaled Moaz mail

link https://doi.org/10.54216/PMTCS.040104

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

ML-based Intrusion Detection for Drone IoT Security

The integration of drones into various industries brings about cybersecurity challenges due to their reliance on internet connectivity. To address this, we propose a comprehensive cybersecurity architecture leveraging machine learning (ML) algorithms and Internet of Things (IoT) technologies within the Internet of Drones (IoD) framework. Our architecture employs IoT-enabled sensors strategically placed across the drone ecosystem to collect and analyze data on system behaviors, communication patterns, and environmental variables. This data is then processed by a centralized platform equipped with sophisticated ML algorithms for pattern identification and anomaly detection. A key feature is the dynamic learning mechanism, enabling real-time intrusion detection by adapting to evolving threats. By combining IoT and ML, the system proactively defends against cyberattacks by distinguishing between typical and abnormal activity. Emphasis is placed on data integrity and confidentiality through secure communication protocols and cryptographic algorithms. Extensive simulations and tests validate the framework's effectiveness in various IoD scenarios, demonstrating its ability to swiftly identify intrusions and informing future enhancements. This comprehensive study meticulously examines the pressing cybersecurity concerns within the burgeoning drone industry. It proposes a robust architectural framework designed to enhance security for drone-enabled applications in our increasingly interconnected world. By harnessing the synergies between Internet of Things (IoT) and Machine Learning (ML) technologies, this innovative approach aims to fortify the integrity and reliability of drone systems.

groups

Abdullah Al-Fuwaiers mail -

Shailendra Mishra mail

link https://doi.org/10.54216/JCIM.140105

Volume & Issue

Vol. Volume 14 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2024

Neutrosophic Structure of Sized Biased Exponential Distribution: Properties and Applications

This study presents a novel distribution derived from the exponential distribution, referred to as the neutrosophic size-biased exponential distribution (NSBED). Various characteristics of the proposed model, including moments, skewness, and kurtosis, are investigated. Plots depicting the cumulative distribution function, density function, and other relevant functions associated with the survival analysis hazard function under indeterminacy are provided. Parameter estimates for the proposed model within the neutrosophic framework are computed. To illustrate the statistical applications of the results in handling imprecise data, a motivation is provided. A simulation analysis is conducted to validate the theoretical aspects of the proposed NSBED. Results indicate that the new distribution exhibits right skewness and shares many properties with skewed distributions. Our novel distribution outperforms the size-biased exponential distribution. Finally, a real application of the proposed model is provided to illustrate the practical implications.

groups

Mansour F. Yassen mail

link https://doi.org/10.54216/IJNS.240323

Volume & Issue

Vol. Volume 24 / Iss. Issue 3

Details open_in_new

International Journal of Neutrosophic Science | 2024

The Impact of Anti-Predator Behavior and Toxicant on An Ecological Neutrosophic Model

This paper discusses a neutrosophic mathematical model consisting of three nonlinear ordinary differential equations describing the interaction between two prey and a predator with the use of function response Holling's type IV and Lotka Volttra. It appears that the first prey has a way to defend itself by using the toxic substance directly to the predator, as well as the effect of the predator on the toxic substance. The conditions for the existence of the solution and the uniqueness of the boundaries were discussed, and then the different equilibrium points and the stability of the system around the equilibrium points were analyzed. The Lyapunov function was used to study the global dynamics of this proposed model. Finally, numerical simulations were performed to show the analytical results.

groups

Huda Salah Kareem mail -

Aseel Amer Abd mail

link https://doi.org/10.54216/IJNS.240324

Volume & Issue

Vol. Volume 24 / Iss. Issue 3

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Security Validation in OpenStack: A Comprehensive Evaluation

The study delves into the security architecture of OpenStack, an open-source cloud platform that is increasingly prevalent in modern computing environments. Its primary goal is to rigorously assess and confirm hypotheses about OpenStack's security infrastructure while identifying vulnerabilities and potential threats using a comprehensive security evaluation framework. The study utilizes a multifaceted security assessment methodology to analyze both private and public cloud deployments of OpenStack. This methodology involves various techniques, including vulnerability scanning, penetration testing, and analysis of security policies and configurations. Benchmarking against industry standards and previous studies further strengthens the analytical framework, ensuring a thorough exploration of various dimensions of OpenStack security. The assessment revealed that OpenStack has a robust security posture, with vulnerabilities detected in only 2% of cases across both private and public cloud deployments. The study also found a resilience rate of 95% against common security challenges. The comprehensive analysis covered various dimensions of OpenStack security, providing valuable insights into the platform's security resilience and vulnerabilities, thereby significantly contributing to the body of knowledge in cloud security research. The research underscores the importance of implementing robust security protocols in OpenStack environments to ensure the reliability of cloud infrastructure. Regular security updates and adherence to best practices can strengthen the security posture of OpenStack deployments. The insights from this study can inform the development of guidelines and policies aimed at enhancing security practices in cloud computing environments. Overall, the study evaluates the security framework of OpenStack and emphasizes the significance of implementing robust security measures to ensure the dependability of cloud infrastructure, guiding the creation of recommendations and superior practices for strengthening security in cloud computing environments.

groups

Mohammed Saffran mail -

Shailendra Mishra mail

link https://doi.org/10.54216/JCIM.140106

Volume & Issue

Vol. Volume 14 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2024

Technological Tools before and after COVID-19 in Ecuador

The COVID-19-induced state of emergency in Ecuador necessitated compulsory isolation for most of the people. During this period, there was a rise in the utilization of technical equipment as individuals had to perform their tasks remotely from their homes. This study sought to assess the utilization of technology resources during the period of quarantine, necessitating the creation of a survey. Specific indicators were considered and standardized for processing. The data processing techniques employed were the Hierarchical Analytical Process and Logic Scoring of Preference. The key findings indicate that the indicators "Modes of Use," "Use Preferences," "Daily Usage Frequency," and "Monthly Expenditure" are crucial for measuring the composite indicator "use of technological tools." A survey was created to contribute to the research.

groups

Manuel A. Abarca-Zaquinaula mail -

Matius R.Mendoza-Poma mail -

Freddy A. Álvarez-Lema mail -

Milton A. Sampedro-Arrieta mail

link https://doi.org/10.54216/FPA.160117

Volume & Issue

Vol. Volume 16 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2024

Climate Optimization in Greenhouses Using the NARMA-L2 Model: An Advanced Integration of Environmental Variables

Agricultural systems, such as greenhouses, can be used to control environmental factors, such as temperature and humidity, to increase output by employing traditional automation techniques. The advancement of science has resulted in the utilization of mathematical models to understand the behavior of data by analyzing its variability. The objective of this project is to validate a method for controlling temperature and humidity in controlled experimental environments using artificial intelligence and Neutrosophy. The transfer functions obtained from temperature and humidity readings gathered via a SCADA system are utilized. Neutrosophic numbers are used to adjust the temperature and humidity values based on the experimental conditions of the greenhouse, indicating the optimal, important, and sensitive ranges. The control system being investigated employs NARMA-L2 neural networks that belong to the multilayer perception category. This facilitates efficient system administration and showcases outstanding performance in simulations conducted across several temperature and humidity scenarios. The observed errors consistently remain below 5% and any instances of exceeding this threshold are insignificant.

groups

María F. Molina mail -

Secundino Marrero mail

link https://doi.org/10.54216/FPA.160118

Volume & Issue

Vol. Volume 16 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2024

Integrative Analysis of Diesel-Kerosene Blends on Engine Performance and Emissions

Combines diesel fuel with cheese to enhance engine efficiency and mitigate detrimental pollutants. Analyzed using a meticulous approach derived from the ISO 8178 standard, combinations containing different ratios of cheese are investigated. The aim of the research is to conduct a multivariate analysis that provides insights into the rheology of diesel and kerosene mixes, thereby enhancing our understanding of the fuel's properties and performance. The researchers conducted experimental trials utilizing diesel blends with varying proportions of cheese, including 5%, 10%, 15%, 20%, 25%, and 30%. A descriptive and multivariate analysis was conducted to measure parameters such as opacity, NOx, CO, HC emissions, and fuel efficiency under different load circumstances. The study identified key elements that determine gasoline characteristics and emissions, including density, viscosity, calorific value, and sulfur content. It emphasized that the addition of cheese had a significant impact on these crucial factors. Two separate categories were created based on the composition of fuel. Blends containing a lower amount of cheesesine (up to 20%) formed a cluster that exhibited an ideal equilibrium in terms of both performance and emissions. The groupings of factors are interconnected, with substantial correlations shown between the physical qualities of the fuel and emissions. This highlights the direct impact of the fuel composition on the engine's environmental performance.

groups

Cristian I. Eugenio-Pilliza mail -

Francisco J. Montalvo-Marquez mail -

Ángel Portilla mail

link https://doi.org/10.54216/FPA.160119

Volume & Issue

Vol. Volume 16 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2024

Fusion Data Management and Modeling Techniques in Power Quality Compensation Using SAPF

The development of transportation today encompasses a broad range of technological applications that occasionally present new challenges arising from difficulties that require solutions. The article analyzes the difficulties in electric trains concerning the compensation of electric power quality in a traction system using a parallel active power filter (SAPF). From the literature review of several studies, the test distribution system in a distribution network for an electric train system is analyzed, with a variable load and harmonic content. The estimation and control technique used in the SAPF to compensate for the harmonic content and reduce the reactive power at the output of a traction substation is described. A data fusion management strategy is employed in the analyses, demonstrating the system's effectiveness.

groups

Jessica N. Castillo mail -

Guido G. Carrillo mail -

Luigi O. Freire mail -

Javier Culqui mail

link https://doi.org/10.54216/FPA.160201

Volume & Issue

Vol. Volume 16 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2024

Integrating Machine Learning Models for Enhanced Soil Organic Carbon Estimation: A Multi-Model Fusion Approach

Machine learning approaches are utilized to identify patterns in behavior and generate predictions across various applications. The objective of this work is to create a highly efficient model for accurately measuring and analyzing the levels of soil organic carbon (SOC) in the Chambo river sub-basin, which is situated in the province of Chimborazo. The model evaluation entails the application of diverse machine learning algorithms and approaches to determine the most efficient regression model. Regression models are improved using techniques such as Artificial Neural Networks, Support Vector Machines, and Decision Trees. The Resilient Backpropagation method yields the most precise model, as it accounts for a greater proportion of the variability in SOC content for the test data. This aligns with the findings from the training data, demonstrating a relatively low mean absolute error and a processing time that is approximately 400 times faster than that of the Multilayer Perceptron algorithm. The evaluation of estimating models is an objective procedure that considers not only the findings and precise metrics derived from the model's design, but also other relevant elements. The effectiveness of the Random Forest approach, specifically the quantile regression forests technique, has been established for estimating SOC contents in the Chambo river sub-basin data.

groups

Bryan Barragán-Pazmiño mail -

Angel Ordóñez Echeverría mail -

Magdy Echeverría Guadalupe mail -

Theofilos Toulkeridis mail

link https://doi.org/10.54216/FPA.160202

Volume & Issue

Vol. Volume 16 / Iss. Issue 2

Details open_in_new