This study utilizes knowledge management (KM) to highlight a documentation-centric approach that is enhanced through artificial intelligence. Knowledge management can improve the decision-making process for predicting models that involved datasets, such as air pollution. Currently, air pollution has become a serious global issue, impacting almost every major city worldwide. As the capital and a central hub for various activities, Jakarta experiences heightened levels of activity, resulting in increased vehicular traffic and elevated air pollution levels. The comparative study aims to measure the accuracy levels of the naïve bayes, decision trees, and random forest prediction models. Additionally, the study uses evaluation measurements to assess how well the machine learning performs, utilizing a confusion matrix. The dataset’s duration is three years, from 2019 until 2021, obtained through Jakarta Open Data. The study found that the random forest achieved the best results with an accuracy rate of 94%, followed by the decision tree at 93%, and the naïve bayes had the lowest at 81%. Hence, the random forest emerges as a reliable predictive model for prediction of air pollution.
{"title":"KNOWLEDGE MANAGEMENT APPROACH IN COMPARATIVE STUDY OF AIR POLLUTION PREDICTION MODEL","authors":"Siti Rohajawati, Hutanti Setyodewi, Ferryansyah Muji Agustian Tresnanto, Debora Marianthi, Maruli Tua Baja Sihotang","doi":"10.35784/acs-2024-11","DOIUrl":"https://doi.org/10.35784/acs-2024-11","url":null,"abstract":"This study utilizes knowledge management (KM) to highlight a documentation-centric approach that is enhanced through artificial intelligence. Knowledge management can improve the decision-making process for predicting models that involved datasets, such as air pollution. Currently, air pollution has become a serious global issue, impacting almost every major city worldwide. As the capital and a central hub for various activities, Jakarta experiences heightened levels of activity, resulting in increased vehicular traffic and elevated air pollution levels. The comparative study aims to measure the accuracy levels of the naïve bayes, decision trees, and random forest prediction models. Additionally, the study uses evaluation measurements to assess how well the machine learning performs, utilizing a confusion matrix. The dataset’s duration is three years, from 2019 until 2021, obtained through Jakarta Open Data. The study found that the random forest achieved the best results with an accuracy rate of 94%, followed by the decision tree at 93%, and the naïve bayes had the lowest at 81%. Hence, the random forest emerges as a reliable predictive model for prediction of air pollution.","PeriodicalId":36379,"journal":{"name":"Applied Computer Science","volume":"26 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140363670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The best emotion recognition system based on physiological signals with a simple operatory should have higher accuracy and fast response speed. This paper aims to develop an emotion recognition system using a novel hybrid system based on Hidden Markov Model and Poincare plot. For this purpose, an electrocardiogram from the MAHNOB-HCI database was used. A novel feature extraction from a hybrid system combining Hidden Markov Model and Poincare plot was presented. The authors extracted time and frequency domain features from heart rate variability, and used two central hybrid systems, the Support Vector Machine/ Hidden Markov Model and the Hidden Markov Model/ Poincare Plot. Finally, the support vector machine was used as a classifier to classify emotions into positive and negative. The proposed method showed a classification accuracy of 95.02 ± 1.97 % overall. Also, the computing time of the method is around 163 milliseconds. The key of this paper is in the use of hybrid machines to improve accuracy without high computation time. This method can be used as a real-time system due to the low computation time and can be developed in many fields, such as medical examination and security systems.
{"title":"EMOTION RECOGNITION FROM HEART RATE VARIABILITY WITH A HYBRID SYSTEM COMBINED HIDDEN MARKOV MODEL AND POINCARE PLOT","authors":"Sahar ZAMANI KHANGHAH, K. Maghooli","doi":"10.35784/acs-2024-07","DOIUrl":"https://doi.org/10.35784/acs-2024-07","url":null,"abstract":"The best emotion recognition system based on physiological signals with a simple operatory should have higher accuracy and fast response speed. This paper aims to develop an emotion recognition system using a novel hybrid system based on Hidden Markov Model and Poincare plot. For this purpose, an electrocardiogram from the MAHNOB-HCI database was used. A novel feature extraction from a hybrid system combining Hidden Markov Model and Poincare plot was presented. The authors extracted time and frequency domain features from heart rate variability, and used two central hybrid systems, the Support Vector Machine/ Hidden Markov Model and the Hidden Markov Model/ Poincare Plot. Finally, the support vector machine was used as a classifier to classify emotions into positive and negative. The proposed method showed a classification accuracy of 95.02 ± 1.97 % overall. Also, the computing time of the method is around 163 milliseconds. The key of this paper is in the use of hybrid machines to improve accuracy without high computation time. This method can be used as a real-time system due to the low computation time and can be developed in many fields, such as medical examination and security systems.","PeriodicalId":36379,"journal":{"name":"Applied Computer Science","volume":"27 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140364618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Kulisz, A. Duisenbekova, J. Kujawska, Danira Kaldybayeva, B. Issayeva, Piotr Lichograj, W. Cel
This study investigates the application of Artificial Neural Networks (ANN) in forecasting agricultural yields in Kazakhstan, highlighting its implications for economic management and policy-making. Utilizing data from the Bureau of National Statistics of the Republic of Kazakhstan (2000-2023), the research develops two ANN models using the Neural Net Fitting library in MATLAB. The first model predicts the total gross yield of main agricultural crops, while the second forecasts the share of individual crops, including cereals, oilseeds, potatoes, vegetables, melons, and sugar beets. The models demonstrate high accuracy, with the total gross yield model achieving an R-squared value of 0.98 and the individual crop model showing an R value of 0.99375. These results indicate a strong predictive capability, essential for practical agricultural and economic planning. The study extends previous research by incorporating a comprehensive range of climatic and agrochemical data, enhancing the precision of yield predictions. The findings have significant implications for Kazakhstan's economy. Accurate yield predictions can optimize agricultural planning, contribute to food security, and inform policy decisions. The successful application of ANN models showcases the potential of AI and machine learning in agriculture, suggesting a pathway towards more efficient, sustainable farming practices and improved quality management systems.
本研究探讨了人工神经网络（ANN）在哈萨克斯坦农业产量预测中的应用，强调了其对经济管理和决策的影响。研究利用哈萨克斯坦共和国国家统计局的数据（2000-2023 年），使用 MATLAB 中的神经网络拟合库开发了两个 ANN 模型。第一个模型预测主要农作物的总产量，第二个模型预测谷物、油籽、马铃薯、蔬菜、甜瓜和甜菜等单种作物的产量份额。这些模型显示出很高的准确性，总产量模型的 R 方值为 0.98，单种作物模型的 R 方值为 0.99375。这些结果表明，该模型具有很强的预测能力，对实际农业和经济规划至关重要。这项研究扩展了以往的研究，纳入了全面的气候和农用化学品数据，提高了产量预测的精确度。研究结果对哈萨克斯坦的经济具有重要意义。准确的产量预测可以优化农业规划，促进粮食安全，并为政策决策提供依据。ANN 模型的成功应用展示了人工智能和机器学习在农业领域的潜力，为实现更高效、可持续的农业实践和改进质量管理系统指明了道路。
{"title":"IMPLICATIONS OF NEURAL NETWORK AS A DECISION-MAKING TOOL IN MANAGING KAZAKHSTAN’S AGRICULTURAL ECONOMY","authors":"M. Kulisz, A. Duisenbekova, J. Kujawska, Danira Kaldybayeva, B. Issayeva, Piotr Lichograj, W. Cel","doi":"10.35784/acs-2023-39","DOIUrl":"https://doi.org/10.35784/acs-2023-39","url":null,"abstract":"This study investigates the application of Artificial Neural Networks (ANN) in forecasting agricultural yields in Kazakhstan, highlighting its implications for economic management and policy-making. Utilizing data from the Bureau of National Statistics of the Republic of Kazakhstan (2000-2023), the research develops two ANN models using the Neural Net Fitting library in MATLAB. The first model predicts the total gross yield of main agricultural crops, while the second forecasts the share of individual crops, including cereals, oilseeds, potatoes, vegetables, melons, and sugar beets. The models demonstrate high accuracy, with the total gross yield model achieving an R-squared value of 0.98 and the individual crop model showing an R value of 0.99375. These results indicate a strong predictive capability, essential for practical agricultural and economic planning. The study extends previous research by incorporating a comprehensive range of climatic and agrochemical data, enhancing the precision of yield predictions. The findings have significant implications for Kazakhstan's economy. Accurate yield predictions can optimize agricultural planning, contribute to food security, and inform policy decisions. The successful application of ANN models showcases the potential of AI and machine learning in agriculture, suggesting a pathway towards more efficient, sustainable farming practices and improved quality management systems.","PeriodicalId":36379,"journal":{"name":"Applied Computer Science","volume":"48 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139384267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A mathematical model is presented for investigating the temperature field caused by the rotary friction welding of dissimilar metals. For this purpose, an axisymmetric, nonlinear, boundary value problem of heat conduction is formulated with allowance for the frictional heating of two cylindrical specimens of finite length made of Al 6061 aluminium alloy and 304 stainless steel. The thermo-physical properties of materials change with increasing temperature. It was assumed that the coefficient of friction does not depend on the temperature. The mechanism of heat generation due to friction on the contact surface with the temperature field of samples is considered. The boundary problem of heat conduction was reduced to the set of nonlinear ordinary differential equations at time t relative to the values of temperature T at the finite elements nodes. The numerical solution of the problem was obtained with the inverse 2nd order differentiation method implemented in COMSOL FEM system (finite element method), with time step ∆t=0.1 (s). The influence of various values of friction coefficient is presented.
{"title":"IMPACT OF FRICTION COEFFICIENT VARIATION ON TEMPERATURE FIELD IN ROTARY FRICTION WELDING OF METALS – FEM STUDY","authors":"Andrzej ŁUKASZEWICZ, Jerzy JÓZWIK, Kamil CYBUL","doi":"10.35784/acs-2023-22","DOIUrl":"https://doi.org/10.35784/acs-2023-22","url":null,"abstract":"A mathematical model is presented for investigating the temperature field caused by the rotary friction welding of dissimilar metals. For this purpose, an axisymmetric, nonlinear, boundary value problem of heat conduction is formulated with allowance for the frictional heating of two cylindrical specimens of finite length made of Al 6061 aluminium alloy and 304 stainless steel. The thermo-physical properties of materials change with increasing temperature. It was assumed that the coefficient of friction does not depend on the temperature. The mechanism of heat generation due to friction on the contact surface with the temperature field of samples is considered. The boundary problem of heat conduction was reduced to the set of nonlinear ordinary differential equations at time t relative to the values of temperature T at the finite elements nodes. The numerical solution of the problem was obtained with the inverse 2nd order differentiation method implemented in COMSOL FEM system (finite element method), with time step ∆t=0.1 (s). The influence of various values of friction coefficient is presented.","PeriodicalId":36379,"journal":{"name":"Applied Computer Science","volume":"229 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135902059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Today's market competition requires constant improvement of manufacturing companies. The primary key to sustainable improvement is evaluating the efficiency of manufacturing processes, which inevitably demands access to thorough and comprehensive information. However, due to the multiple numbers of effective factors that are varied in nature and value, it is impossible to identify certain factors that ensure the efficiency of a manufacturing procedure. As a solution, this paper proposes a novel approach that applies fuzzy TOPSIS. This approach provides the flexibility of evaluating multiple and varied factors of different weights in scrutinizing the efficiency of a manufacturer. The proposed approach has been applied to three different manufacturers (i.e., alternatives) in three steps. In the first step, with reference to the related literature and comments of manufacturing experts, the valuable factors (i.e., the criteria) have been selected to which experts specified linguistic terms. Linguistic terms were then converted to fuzzy numbers. Fuzzy TOPSIS was applied to analyze the efficiency performance of manufacturers. In the last step, to determine the impact of criteria weights on the decision-making process, sensitivity analysis was carried out. The findings confirm the implacability of the proposed approach to manufacturing performances in a consolidated manner. The approach can be employed by marketing managers, senior administrators, and other authorities in the manufacturing and business sectors.
{"title":"FUZZY MULTIPLE CRITERIA GROUP DECISION-MAKING IN PERFORMANCE EVALUATION OF MANUFACTURING COMPANIES","authors":"Sara SALEHI","doi":"10.35784/acs-2023-23","DOIUrl":"https://doi.org/10.35784/acs-2023-23","url":null,"abstract":"Today's market competition requires constant improvement of manufacturing companies. The primary key to sustainable improvement is evaluating the efficiency of manufacturing processes, which inevitably demands access to thorough and comprehensive information. However, due to the multiple numbers of effective factors that are varied in nature and value, it is impossible to identify certain factors that ensure the efficiency of a manufacturing procedure. As a solution, this paper proposes a novel approach that applies fuzzy TOPSIS. This approach provides the flexibility of evaluating multiple and varied factors of different weights in scrutinizing the efficiency of a manufacturer. The proposed approach has been applied to three different manufacturers (i.e., alternatives) in three steps. In the first step, with reference to the related literature and comments of manufacturing experts, the valuable factors (i.e., the criteria) have been selected to which experts specified linguistic terms. Linguistic terms were then converted to fuzzy numbers. Fuzzy TOPSIS was applied to analyze the efficiency performance of manufacturers. In the last step, to determine the impact of criteria weights on the decision-making process, sensitivity analysis was carried out. The findings confirm the implacability of the proposed approach to manufacturing performances in a consolidated manner. The approach can be employed by marketing managers, senior administrators, and other authorities in the manufacturing and business sectors.","PeriodicalId":36379,"journal":{"name":"Applied Computer Science","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135084107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jolanta BRZOZOWSKA, Jakub PIZOŃ, Gulzhan BAYTIKENOVA, Arkadiusz GOLA, Alfiya ZAKIMOVA, Katarzyna PIOTROWSKA
The paper describes one of the methods of data acquisition in data mining models used to support decision-making. The study presents the possibilities of data collection using the phases of the CRISP-DM model for an organization and presents the possibility of adapting the model for analysis and management in the decisionmaking process. The first three phases of implementing the CRISP-DM model are described using data from an enterprise with small batch production as an example. The paper presents the CRISP-DM based model for data mining in the process of predicting assembly cycle time. The developed solution has been evaluated using real industrial data and will be a part of methodology that allows to estimate the assembly time of a finished product at the quotation stage, i.e., without the detailed technology of the product being known.
{"title":"DATA ENGINEERING IN CRISP-DM PROCESS PRODUCTION DATA – CASE STUDY","authors":"Jolanta BRZOZOWSKA, Jakub PIZOŃ, Gulzhan BAYTIKENOVA, Arkadiusz GOLA, Alfiya ZAKIMOVA, Katarzyna PIOTROWSKA","doi":"10.35784/acs-2023-26","DOIUrl":"https://doi.org/10.35784/acs-2023-26","url":null,"abstract":"The paper describes one of the methods of data acquisition in data mining models used to support decision-making. The study presents the possibilities of data collection using the phases of the CRISP-DM model for an organization and presents the possibility of adapting the model for analysis and management in the decisionmaking process. The first three phases of implementing the CRISP-DM model are described using data from an enterprise with small batch production as an example. The paper presents the CRISP-DM based model for data mining in the process of predicting assembly cycle time. The developed solution has been evaluated using real industrial data and will be a part of methodology that allows to estimate the assembly time of a finished product at the quotation stage, i.e., without the detailed technology of the product being known.","PeriodicalId":36379,"journal":{"name":"Applied Computer Science","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135127140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Md. Torikur RAHMAN, Mohammad ALAUDDIN, Uttam Kumar DEY, Dr. A.H.M. Saifullah SADI
Nowadays Mobile Ad Hoc Network (MANET) is an emerging area of research to provide various communication services to end users. Mobile Ad Hoc Networks (MANETs) are self-organizing wireless networks where nodes communicate with each other without a fixed infrastructure. Due to their unique characteristics, such as mobility, autonomy, and ad hoc connectivity, MANETs have become increasingly popular in various applications, including military, emergency response, and disaster management. However, the lack of infrastructure and dynamic topology of MANETs pose significant challenges to designing a secure and efficient routing protocol. This paper proposes an adaptive, secure, and efficient routing protocol that can enhance the performance of MANET. The proposed protocol incorporates various security mechanisms, including authentication, encryption, key management, and intrusion detection, to ensure secure routing. Additionally, the protocol considers energy consumption, network load, packet delivery fraction, route acquisition latency, packets dropped and Quality of Service (QoS) requirements of the applications to optimize network performance. Overall, the secure routing protocol for MANET should provide a reliable and secure communication environment that can adapt to the dynamic nature of the network. The protocol should ensure that messages are delivered securely and efficiently to the intended destination, while minimizing the risk of attacks and preserving the network resources Simulation results demonstrate that the proposed protocol outperforms existing routing protocols in terms of network performance and security. The proposed protocol can facilitate the deployment of various applications in MANET while maintaining security and efficiency.
{"title":"ADAPTIVE SECURE AND EFFICIENT ROUTING PROTOCOL FOR ENHANCE THE PERFORMANCE OF MOBILE AD HOC NETWORK","authors":"Md. Torikur RAHMAN, Mohammad ALAUDDIN, Uttam Kumar DEY, Dr. A.H.M. Saifullah SADI","doi":"10.35784/acs-2023-29","DOIUrl":"https://doi.org/10.35784/acs-2023-29","url":null,"abstract":"Nowadays Mobile Ad Hoc Network (MANET) is an emerging area of research to provide various communication services to end users. Mobile Ad Hoc Networks (MANETs) are self-organizing wireless networks where nodes communicate with each other without a fixed infrastructure. Due to their unique characteristics, such as mobility, autonomy, and ad hoc connectivity, MANETs have become increasingly popular in various applications, including military, emergency response, and disaster management. However, the lack of infrastructure and dynamic topology of MANETs pose significant challenges to designing a secure and efficient routing protocol. This paper proposes an adaptive, secure, and efficient routing protocol that can enhance the performance of MANET. The proposed protocol incorporates various security mechanisms, including authentication, encryption, key management, and intrusion detection, to ensure secure routing. Additionally, the protocol considers energy consumption, network load, packet delivery fraction, route acquisition latency, packets dropped and Quality of Service (QoS) requirements of the applications to optimize network performance. Overall, the secure routing protocol for MANET should provide a reliable and secure communication environment that can adapt to the dynamic nature of the network. The protocol should ensure that messages are delivered securely and efficiently to the intended destination, while minimizing the risk of attacks and preserving the network resources Simulation results demonstrate that the proposed protocol outperforms existing routing protocols in terms of network performance and security. The proposed protocol can facilitate the deployment of various applications in MANET while maintaining security and efficiency.","PeriodicalId":36379,"journal":{"name":"Applied Computer Science","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135126780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Stock prediction is an exciting issue and is very much needed by investors and business people to develop their assets. The main difficulties in predicting stock prices are dynamic movements, high volatility, and noises caused by company performance and external influences. The traditional method used by investors is the technical analysis based on statistics, valuation of previous stock portfolios, and news from the mass media and social media. Deep learning can predict stock price movements more accurately than traditional methods. As a solution to the issue of stock prediction, we offer the Exponential Moving Average Gated Recurrent Unit (EMAGRU) model and demonstrate its utility. The EMAGRU architecture contains two stacked GRUs arranged in parallel. The inputs and outputs are the EMA10 and EMA20, formed from the closing prices over ten years. We also combine the AntiReLU and ReLU activation functions into the model so that EMAGRU has 6 model variants. Our proposed model produced low losses and high accuracy. RMSE, MEPA, MAE, R2 and were 0.0060, 0.0064, 0.0050, and 0.9976 for EMA10, and 0.0050, 0.0058, 0.0045, and 0.9982 for EMA20, respectively.
{"title":"PERFORMANCE EVALUATION OF STOCK PREDICTION MODELS USING EMAGRU","authors":"Erizal ERIZAL, Mohammad DIQI","doi":"10.35784/acs-2023-30","DOIUrl":"https://doi.org/10.35784/acs-2023-30","url":null,"abstract":"Stock prediction is an exciting issue and is very much needed by investors and business people to develop their assets. The main difficulties in predicting stock prices are dynamic movements, high volatility, and noises caused by company performance and external influences. The traditional method used by investors is the technical analysis based on statistics, valuation of previous stock portfolios, and news from the mass media and social media. Deep learning can predict stock price movements more accurately than traditional methods. As a solution to the issue of stock prediction, we offer the Exponential Moving Average Gated Recurrent Unit (EMAGRU) model and demonstrate its utility. The EMAGRU architecture contains two stacked GRUs arranged in parallel. The inputs and outputs are the EMA10 and EMA20, formed from the closing prices over ten years. We also combine the AntiReLU and ReLU activation functions into the model so that EMAGRU has 6 model variants. Our proposed model produced low losses and high accuracy. RMSE, MEPA, MAE, R2 and were 0.0060, 0.0064, 0.0050, and 0.9976 for EMA10, and 0.0050, 0.0058, 0.0045, and 0.9982 for EMA20, respectively.","PeriodicalId":36379,"journal":{"name":"Applied Computer Science","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135083795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zbigniew CZYŻ, Paweł KARPIŃSKI, Krzysztof SKIBA, Szymon BARTKOWSKI
The study involved a numerical analysis of the water dropping process by fixed-wing aircraft. This method, also known as air attack, is used for aerial firefighting, primarily in green areas such as forests and meadows. The conducted calculations allowed for the analysis of the process over time. The calculations were performed based on a SolidWorks model of the M18B Dromader aircraft. After defining the computational domain and setting the boundary conditions, the simulations were carried out using the ANSYS Fluent software. The resulting water dropping area was used to analyze the intensity of water distribution. The volumetric distribution and airflow velocity distribution were analyzed for specified time steps. The boundary layer where air no longer mixes with water during the final phase of water dropping was also determined. The obtained results provide an important contribution to further analyses aimed at optimizing the water dropping process by fixed-wing aircraft.
{"title":"NUMERICAL CALCULATIONS OF WATER DROP USING A FIREFIGHTING AIRCRAFT","authors":"Zbigniew CZYŻ, Paweł KARPIŃSKI, Krzysztof SKIBA, Szymon BARTKOWSKI","doi":"10.35784/acs-2023-24","DOIUrl":"https://doi.org/10.35784/acs-2023-24","url":null,"abstract":"The study involved a numerical analysis of the water dropping process by fixed-wing aircraft. This method, also known as air attack, is used for aerial firefighting, primarily in green areas such as forests and meadows. The conducted calculations allowed for the analysis of the process over time. The calculations were performed based on a SolidWorks model of the M18B Dromader aircraft. After defining the computational domain and setting the boundary conditions, the simulations were carried out using the ANSYS Fluent software. The resulting water dropping area was used to analyze the intensity of water distribution. The volumetric distribution and airflow velocity distribution were analyzed for specified time steps. The boundary layer where air no longer mixes with water during the final phase of water dropping was also determined. The obtained results provide an important contribution to further analyses aimed at optimizing the water dropping process by fixed-wing aircraft.","PeriodicalId":36379,"journal":{"name":"Applied Computer Science","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135084112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The objective of this research was to compare the effectiveness of the GARCH method with machine learning techniques in predicting asset volatility in the main Latin American markets. The daily squared return was utilized as a volatility indicator, and the accuracy of the predictions was assessed using root mean square error (RMSE) and mean absolute error (MAE) metrics. The findings consistently demonstrated that the linear SVR-GARCH models outperformed other approaches, exhibiting the lowest MAE and MSE values across various assets in the test sample. Specifically, the SVRGARCH RBF model achieved the most accurate results for the IPC asset. It was observed that GARCH models tended to produce higher volatility forecasts during periods of heightened volatility due to their responsiveness to significant past changes. Consequently, this led to larger squared prediction errors for GARCH models compared to SVR models. This suggests that incorporating machine learning techniques can provide improved volatility forecasting capabilities compared to the traditional GARCH models.
{"title":"A LATIN AMERICAN MARKET ASSET VOLATILITY ANALYSIS: A COMPARISON OF GARCH MODEL, ARTIFICIAL NEURAL NETWORKS AND SUPPORT VECTOR REGRESSION","authors":"Victor CHUNG, Jenny ESPINOZA","doi":"10.35784/acs-2023-21","DOIUrl":"https://doi.org/10.35784/acs-2023-21","url":null,"abstract":"The objective of this research was to compare the effectiveness of the GARCH method with machine learning techniques in predicting asset volatility in the main Latin American markets. The daily squared return was utilized as a volatility indicator, and the accuracy of the predictions was assessed using root mean square error (RMSE) and mean absolute error (MAE) metrics. The findings consistently demonstrated that the linear SVR-GARCH models outperformed other approaches, exhibiting the lowest MAE and MSE values across various assets in the test sample. Specifically, the SVRGARCH RBF model achieved the most accurate results for the IPC asset. It was observed that GARCH models tended to produce higher volatility forecasts during periods of heightened volatility due to their responsiveness to significant past changes. Consequently, this led to larger squared prediction errors for GARCH models compared to SVR models. This suggests that incorporating machine learning techniques can provide improved volatility forecasting capabilities compared to the traditional GARCH models.","PeriodicalId":36379,"journal":{"name":"Applied Computer Science","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135126953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：