“neural networks”Search All-EnPress Publisher LLC.

Dec 24, 2024

Estimating power generation of a combined cycle power plant using artificial intelligence technique

Among contemporary computational techniques, Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are favoured because of their capacity to tackle non-linear modelling and complex stochastic datasets. Nondeterministic models involve some computational intricacies when deciphering real-life problems but always yield better outcomes. For the first time, this study utilized the ANN and ANFIS models for modelling power generation/electric power output (EPO) from databases generated in a combined cycle power plant (CCPP). The study presents a comparative study between ANNs and ANFIS to estimate the power output generation of a combined cycle power plant in Turkey. The inputs of the ANN and ANFIS models are ambient temperature (AT), ambient pressure (AP), relative humidity (RH), and exhaust vacuum (V), correlated with electric power output. Several models were developed to achieve the best architecture as the number of hidden neurons varied for the ANNs, while the training process was conducted for the ANFIS model. A comparison of the developed hybrid models was completed using statistical criteria such as the coefficient of determination (R²), mean average error (MAE), and average absolute deviation (AAD). The R² of 0.945, MAE of 3.001%, and AAD of 3.722% for the ANN model were compared to those of R² of 0.9499, MAE of 2.843% and AAD of 2.842% for the ANFIS model. Even though both ANN and ANFIS are relevant in estimating and predicting power production, the ANFIS model exhibits higher superiority compared to the ANN model in accurately estimating the EPO of the CCPP located in Turkey and its environment.

Abstract

Download PDF(1.67M)

XML

0

133

Nov 22, 2024

Applying neural networks in student satisfaction analysis: Implications for university management

This study analyzes student satisfaction at a university using a structured survey and advanced artificial intelligence techniques, specifically neural networks. The main objective is to identify the key factors in students’ perception of educational quality. The methodology involved a survey with 38 items on a Likert scale of 1 to 7, applied to a diverse sample of undergraduate, postgraduate, and exchange students during the years 2022 and 2023. The final sample consisted of 9623 valid records. Artificial intelligence techniques were employed to analyze the data, with neural networks trained under the supervised learning paradigm to predict levels of student satisfaction. The results show a high correlation between satisfaction with the cashier service and overall student satisfaction, highlighting the importance of administrative services. Additionally, a close relationship was identified between the institutional mission and the educational process, suggesting that a clear and accessible mission improves student perception. The effectiveness of neural networks was demonstrated, achieving high precision and sensitivity in their predictions. In conclusion, this study provides valuable insights into the factors influencing student satisfaction and demonstrates the potential of artificial intelligence techniques to improve educational management. The findings offer a solid foundation for future research and practical improvements in higher education.

Abstract

Download PDF(722.75KB)

XML

0

88

Sept 6, 2024

Survey data preprocessing for optimal modelling through ANNs applied to management environments

Surveys are one of the most important tasks to be executed to get valued information. One of the main problems is how the data about many different persons can be processed to give good information about their environment. Modelling environments through Artificial Neural Networks (ANNs) is highly common because ANN’s are excellent to model predictable environments using a set of data. ANN’s are good in dealing with sets of data with some noise, but they are fundamentally surjective mathematical functions, and they aren’t able to give different results for the same input. So, if an ANN is trained using data where samples with the same input configuration has different outputs, which can be the case of survey data, it can be a major problem for the success of modelling the environment. The environment used to demonstrate the study is a strategic environment that is used to predict the impact of the applied strategies to an organization financial result, but the conclusions are not limited to this type of environment. Therefore, is necessary to adjust, eliminate invalid and inconsistent data. This permits one to maximize the probability of success and precision in modeling the desired environment. This study demonstrates, describes and evaluates each step of a process to prepare data for use, to improve the performance and precision of the ANNs used to obtain the model. This is, to improve the model quality. As a result of the studied process, it is possible to see a significant improvement both in the possibility of building a model as in its accuracy.

Abstract

Download PDF(1.15M)

XML

1

130

Aug 22, 2024

Determining factors for tourist arrivals in Hungary

This methodologically focused study examines the relationships between inflation and unemployment rates, political stability, and tourism, with particular emphasis on the impacts on tourist arrivals in Hungary. The research aims to uncover the direct and indirect influences of these macroeconomic indicators on the volume of tourism, specifically international tourist arrivals. The significance of the study lies in the clear correlation between economic stability and labor market conditions with tourism volume, where rising inflation and unemployment rates negatively correlate with the number of tourist arrivals. This relationship is further strengthened by the observation that improvements in political stability enhance tourist numbers over the long term, while political instability, such as conflicts and terrorist acts, negatively affects tourism demand. These correlations are crucial for aligning tourism policy with economic policy, as macroeconomic indicators and the political environment directly influence both domestic and foreign tourists’ willingness to travel. The research methodology focuses on forecasting using Random Forest and neural networks, which enables more accurate predictions of tourism volume and supports informed tourism policy-making. The findings indicate that the development of the tourism sector is closely linked to economic growth and underscore the necessity of boosting tourism to expand employment and maintain economic stability.

Abstract

Download PDF(595.10KB)

XML

1

102

Aug 26, 2024

Leveraging variational autoencoders and recurrent neural networks for demand forecasting in supply chain management: A case study

Accurate demand forecasting is key for companies to optimize inventory management and satisfy customer demand efficiently. This paper aims to Investigate on the application of generative AI models in demand forecasting. Two models were used: Long Short-Term Memory (LSTM) networks and Variational Autoencoder (VAE), and results were compared to select the optimal model in terms of performance and forecasting accuracy. The difference of actual and predicted demand values also ascertain LSTM’s ability to identify latent features and basic trends in the data. Further, some of the research works were focused on computational efficiency and scalability of the proposed methods for providing the guidelines to the companies for the implementation of the complicated techniques in demand forecasting. Based on these results, LSTM networks have a promising application in enhancing the demand forecasting and consequently helpful for the decision-making process regarding inventory control and other resource allocation.

Abstract

Download PDF(751.80KB)

XML

3

227