Pub Date : 2023-12-20DOI: 10.13164/mendel.2023.2.169
Ricardo Andrés Cárdenas-Cuervo, Conrado Augusto Serna-Urán, C. G. Gómez-Marín
Municipalities play a key role in public waste management ensuring effective and efficient service performance. In Colombia, the public utilities sector has undergone significant changes since decentralization and the entry of private companies into the sector. In this study, our purpose is to analyze user perceptions and their willingness to pay for additional services regarding waste management. By using data analysis methods and a Mamdani fuzzy inference system, we were able to identify users’ service requirements and expected quality. According to the results of our analysis, a combination of minimum coverage and low frequency resulted in a tariff increase of 7.05%. Furthermore, we recommend expanding the model to include other waste management services, such as solid waste collection, as well as to consider environmental aspects and sustainable practices.
{"title":"Analysis of Users’ Requirements for Public Waste Management Services Using Fuzzy Inference","authors":"Ricardo Andrés Cárdenas-Cuervo, Conrado Augusto Serna-Urán, C. G. Gómez-Marín","doi":"10.13164/mendel.2023.2.169","DOIUrl":"https://doi.org/10.13164/mendel.2023.2.169","url":null,"abstract":"Municipalities play a key role in public waste management ensuring effective and efficient service performance. In Colombia, the public utilities sector has undergone significant changes since decentralization and the entry of private companies into the sector. In this study, our purpose is to analyze user perceptions and their willingness to pay for additional services regarding waste management. By using data analysis methods and a Mamdani fuzzy inference system, we were able to identify users’ service requirements and expected quality. According to the results of our analysis, a combination of minimum coverage and low frequency resulted in a tariff increase of 7.05%. Furthermore, we recommend expanding the model to include other waste management services, such as solid waste collection, as well as to consider environmental aspects and sustainable practices.","PeriodicalId":38293,"journal":{"name":"Mendel","volume":"32 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138955900","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}
Pub Date : 2023-12-20DOI: 10.13164/mendel.2023.2.295
Toai Kim Tran, R. Šenkeřík, Hanh Thi Xuan Vo, Huan Minh Vo, Adam Ulrich, Marek Musil, I. Zelinka
This paper explores using and hybridizing simple prediction models to maximize the accuracy of local weather prediction while maintaining low computational effort and the need to process and acquire large volumes of data. A hybrid RF-LSTM model is proposed and evaluated in this research paper for the task of short-term local weather forecasting. The local weather stations are built within an acceptable radius of the measured area and are designed to provide a short period of forecasting - usually within one hour. The lack of local weather data might be problematic for an accurate short-term valuable prediction in sustainable applications like agriculture, transportation, energy management, and daily life. Weather forecasting is not trivial because of the non-linear nature of time series. Thus, traditional forecasting methods cannot predict the weather accurately. The advantage of the ARIMA model lies in forecasting the linear part, while the SVR model indicates the non-linear characteristic of the weather data. Both non-linear and linear approaches can represent the combined model. The hybrid ARIMA-SVR model strengthens the matched points of the ARIMA model and the SVR model in weather forecasting. The LSTM and random forest are both popular algorithms used for regression problems. LSTM is more suitable for tasks involving sequential data with long-term dependencies. Random Forest leverages the wisdom of crowds by combining multiple decision trees, providing robust predictions, and reducing overfitting. Hybrid Random forest-LSTM potentially leverages the robustness and feature importance of Random Forest along with the ability of LSTM to capture sequential dependencies. The comparison results show that the hybrid RF-LSTM model reduces the forecasting errors in metrics of MAE, R-squared, and RMSE. The proposed hybrid model can also capture the actual temperature trend in its prediction performance, which makes it even more relevant for many other possible decision-making steps in sustainable applications. Furthermore, this paper also proposes the design of a weather station based on a real-time edge IoT system. The RF-LSTM leverages the parallelized characteristics of each decision tree in the forest to accelerate the training process and faster inferences. Thus, the hybrid RF-LSTM model offers advantages in terms of faster execution speed and computational efficiency in both PC and Raspberry Pi boards. However, the RF-LSTM consumes the highest peak memory usage due to being a combination of two different models.
{"title":"Exploring Hybrid Models For Short-Term Local Weather Forecasting in IoT Environment","authors":"Toai Kim Tran, R. Šenkeřík, Hanh Thi Xuan Vo, Huan Minh Vo, Adam Ulrich, Marek Musil, I. Zelinka","doi":"10.13164/mendel.2023.2.295","DOIUrl":"https://doi.org/10.13164/mendel.2023.2.295","url":null,"abstract":"This paper explores using and hybridizing simple prediction models to maximize the accuracy of local weather prediction while maintaining low computational effort and the need to process and acquire large volumes of data. A hybrid RF-LSTM model is proposed and evaluated in this research paper for the task of short-term local weather forecasting. The local weather stations are built within an acceptable radius of the measured area and are designed to provide a short period of forecasting - usually within one hour. The lack of local weather data might be problematic for an accurate short-term valuable prediction in sustainable applications like agriculture, transportation, energy management, and daily life. Weather forecasting is not trivial because of the non-linear nature of time series. Thus, traditional forecasting methods cannot predict the weather accurately. The advantage of the ARIMA model lies in forecasting the linear part, while the SVR model indicates the non-linear characteristic of the weather data. Both non-linear and linear approaches can represent the combined model. The hybrid ARIMA-SVR model strengthens the matched points of the ARIMA model and the SVR model in weather forecasting. The LSTM and random forest are both popular algorithms used for regression problems. LSTM is more suitable for tasks involving sequential data with long-term dependencies. Random Forest leverages the wisdom of crowds by combining multiple decision trees, providing robust predictions, and reducing overfitting. Hybrid Random forest-LSTM potentially leverages the robustness and feature importance of Random Forest along with the ability of LSTM to capture sequential dependencies. The comparison results show that the hybrid RF-LSTM model reduces the forecasting errors in metrics of MAE, R-squared, and RMSE. The proposed hybrid model can also capture the actual temperature trend in its prediction performance, which makes it even more relevant for many other possible decision-making steps in sustainable applications. Furthermore, this paper also proposes the design of a weather station based on a real-time edge IoT system. The RF-LSTM leverages the parallelized characteristics of each decision tree in the forest to accelerate the training process and faster inferences. Thus, the hybrid RF-LSTM model offers advantages in terms of faster execution speed and computational efficiency in both PC and Raspberry Pi boards. However, the RF-LSTM consumes the highest peak memory usage due to being a combination of two different models.","PeriodicalId":38293,"journal":{"name":"Mendel","volume":"57 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138957042","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}
Pub Date : 2023-12-20DOI: 10.13164/mendel.2023.2.111
Wee Chea Chang, A. Sangodiah
Semantic Web is the vision to make Internet data machine-readable to achieve information retrieval with higher granularity and personalisation. Semantic annotation is the process that binds machine-understandable descriptions into Web resources such as text and images. Hence, the success of Semantic Web dependson the wide availability of semantically annotated Web resources. However, there remains a huge amount of unannotated Web resources due to the limited annotation capability available. In order to address this, machine learning approaches have been used to improve the automation process. This Systematic Review aims to summarise the existing state-of-the-art literature to answer five Research Questions focusing on machine learning driven semantic annotation automation. The analysis of 40 selected primary studies reveals that the use of unitary and combination of machine learning algorithms are both the current directions. SupportVector Machine (SVM) is the most-used algorithm, and supervised learning is the predominant machine learning type. Both semi-automated and fully automated annotation are almost nearly achieved. Meanwhile, text is the most annotated Web resource; and the availability of third-party annotation tools is in-line with this. While Precision, Recall, F-Measure and Accuracy are the most deployed quality metrics, not all the studies measured the quality of the annotated results. In the future, standardising quality measures is the direction for research.
{"title":"Automated Semantic Annotation Deploying Machine Learning Approaches: A Systematic Review","authors":"Wee Chea Chang, A. Sangodiah","doi":"10.13164/mendel.2023.2.111","DOIUrl":"https://doi.org/10.13164/mendel.2023.2.111","url":null,"abstract":"Semantic Web is the vision to make Internet data machine-readable to achieve information retrieval with higher granularity and personalisation. Semantic annotation is the process that binds machine-understandable descriptions into Web resources such as text and images. Hence, the success of Semantic Web dependson the wide availability of semantically annotated Web resources. However, there remains a huge amount of unannotated Web resources due to the limited annotation capability available. In order to address this, machine learning approaches have been used to improve the automation process. This Systematic Review aims to summarise the existing state-of-the-art literature to answer five Research Questions focusing on machine learning driven semantic annotation automation. The analysis of 40 selected primary studies reveals that the use of unitary and combination of machine learning algorithms are both the current directions. SupportVector Machine (SVM) is the most-used algorithm, and supervised learning is the predominant machine learning type. Both semi-automated and fully automated annotation are almost nearly achieved. Meanwhile, text is the most annotated Web resource; and the availability of third-party annotation tools is in-line with this. While Precision, Recall, F-Measure and Accuracy are the most deployed quality metrics, not all the studies measured the quality of the annotated results. In the future, standardising quality measures is the direction for research.","PeriodicalId":38293,"journal":{"name":"Mendel","volume":"49 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138955515","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}
Pub Date : 2023-12-20DOI: 10.13164/mendel.2023.2.261
Didi Supriyadi, Purwanto Purwanto, Budi Warsito
The features present in large datasets significantly affect the performance of machine learning models. Redundant and irrelevant features will be rejected and cause a decrease in machine learning model performance. This paper proposes HyFeS-ROS-ANN: Hybrid Feature Selection and Resampling combination method for binary classification using artificial neural network multilayer perceptron (MLP). The first stage of this approach is to use a combination of two feature selection methods to select essential features that are highly correlated with model performance. The second stage of this approach is to use a combination of resampling methods to handle unbalanced data classes. Both approaches are applied to the academic performance classification model using the MLP neural network. This research dataset is obtained using three-dimensional (3D) frameworks such as the Big Five Personality to determine the Personality that affects academic performance from the student dimension, the Family Influence Scale (FIS), which measures factors that affect academic performance from the family dimension, and Higher Education Institutions Service Quality (HEISQUAL) to measure service quality and its influence on academic performance from the Education institution dimension. Previous research shows that the CoR-ANN algorithm has a model accuracy rate of 94%. The research results based on the dataset show that our proposed method can improve accuracy by selecting more relevant and essential features in improving model performance. The results show that the features are reduced from 135 to 108, while the HyFS-ROS-ANN model for binary classification accuracy increases to 100%.
{"title":"Optimizing Neural Networks for Academic Performance Classification Using Feature Selection and Resampling Approach","authors":"Didi Supriyadi, Purwanto Purwanto, Budi Warsito","doi":"10.13164/mendel.2023.2.261","DOIUrl":"https://doi.org/10.13164/mendel.2023.2.261","url":null,"abstract":"The features present in large datasets significantly affect the performance of machine learning models. Redundant and irrelevant features will be rejected and cause a decrease in machine learning model performance. This paper proposes HyFeS-ROS-ANN: Hybrid Feature Selection and Resampling combination method for binary classification using artificial neural network multilayer perceptron (MLP). The first stage of this approach is to use a combination of two feature selection methods to select essential features that are highly correlated with model performance. The second stage of this approach is to use a combination of resampling methods to handle unbalanced data classes. Both approaches are applied to the academic performance classification model using the MLP neural network. This research dataset is obtained using three-dimensional (3D) frameworks such as the Big Five Personality to determine the Personality that affects academic performance from the student dimension, the Family Influence Scale (FIS), which measures factors that affect academic performance from the family dimension, and Higher Education Institutions Service Quality (HEISQUAL) to measure service quality and its influence on academic performance from the Education institution dimension. Previous research shows that the CoR-ANN algorithm has a model accuracy rate of 94%. The research results based on the dataset show that our proposed method can improve accuracy by selecting more relevant and essential features in improving model performance. The results show that the features are reduced from 135 to 108, while the HyFS-ROS-ANN model for binary classification accuracy increases to 100%.","PeriodicalId":38293,"journal":{"name":"Mendel","volume":"85 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138956683","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}
Pub Date : 2023-12-20DOI: 10.13164/mendel.2023.2.181
Trong-Minh Hoang, Van-Hau Bui, Nam-Hoang Nguyen
Fast and reliable authentication is a crucial requirement of communications networks and has various research challenges in an Internet of Things (IoT) environment. In IoT-based applications, as fast and user-friendly access and high security are required simultaneously, biometric identification of the user, such as the face, iris, or fingerprint, is broadly employed as an authentication approach. Moreover, a so-called multi-factor authentication that combines user identification with other identification information, including token information and device identity, is usedto enhance the authentication security level. This paper proposes a novel twofactor authentication scheme for intelligent communication and control systems by utilizing the watermarking technique to incorporate the mobile device authentication component into the user’s facial recognition image. Our proposed scheme offers user-friendliness while improving user security and privacy and reducing authentication information exchange procedures to provide a secure and lightweight schema in real applications. The proposed scheme’s security advantages are validated using the widely accepted Burrows–Abadi–Needham (BAN) logic and experimentally assessed using the Automated Validation of Internet Security Protocols and Applications (AVISPA) simulator tool. Finally, our experimental results show that the proposed authentication scheme is an innovative solution for a smarthome control system, such as a smart lock door operation.
{"title":"An Integrated Two-Factor Authentication Scheme for Smart Communications and Control Systems","authors":"Trong-Minh Hoang, Van-Hau Bui, Nam-Hoang Nguyen","doi":"10.13164/mendel.2023.2.181","DOIUrl":"https://doi.org/10.13164/mendel.2023.2.181","url":null,"abstract":"Fast and reliable authentication is a crucial requirement of communications networks and has various research challenges in an Internet of Things (IoT) environment. In IoT-based applications, as fast and user-friendly access and high security are required simultaneously, biometric identification of the user, such as the face, iris, or fingerprint, is broadly employed as an authentication approach. Moreover, a so-called multi-factor authentication that combines user identification with other identification information, including token information and device identity, is usedto enhance the authentication security level. This paper proposes a novel twofactor authentication scheme for intelligent communication and control systems by utilizing the watermarking technique to incorporate the mobile device authentication component into the user’s facial recognition image. Our proposed scheme offers user-friendliness while improving user security and privacy and reducing authentication information exchange procedures to provide a secure and lightweight schema in real applications. The proposed scheme’s security advantages are validated using the widely accepted Burrows–Abadi–Needham (BAN) logic and experimentally assessed using the Automated Validation of Internet Security Protocols and Applications (AVISPA) simulator tool. Finally, our experimental results show that the proposed authentication scheme is an innovative solution for a smarthome control system, such as a smart lock door operation.","PeriodicalId":38293,"journal":{"name":"Mendel","volume":"19 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139169434","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}
Pub Date : 2023-12-20DOI: 10.13164/mendel.2023.2.097
Tran Van Duc, Pham Quang Tien, Hoang Duc Minh Trieu, Nguyen Thi Ngoc Anh, Dat Tien Nguyen
Online shopping using virtual try-on technology is becoming popular and widely used for digital transformation because of sustainably sourced materials and enhancing customers’ experience. For practical applicability, the process is required for two main factors: (1) accuracy and reliability, and (2) the processing time. To meet the above requirements, we propose a state-of-the-art technique for generating a user’s visualization of model costumes using only a single user portrait and basic anthropometrics. To start, this research would summarize different methods of most virtual try-on clothes approaches, including (1) Interactive simulation between the 3D models, and (2) 2D Photorealistic Generation. In spite of successfully creating the visualization and feasibility, these approaches have to face issues of their efficiency and performance. Furthermore, the complexity of input requirements and the users’ experiments are leading to difficulties in practical application and future scalability. In this regard, our study combines (1) a head-swapping technique using a face alignment model for determining, segmenting, and swapping heads with only a pair of a source and a target image as inputs (2) a photorealistic body reshape pipeline for direct resizing user visualization, and (3) an adaptive skin color models for changing user’s skin, which ensures remaining the face structure and natural. The proposed technique was evaluated quantitatively and qualitatively using three types of datasets which include: (1) VoxCeleb2, (2) Datasets from Viettel collection, and (3) Users Testing to demonstrate its feasibility and efficiency when used in real-world applications
{"title":"A Hybrid Photorealistic Architecture Based on Generating Facial Features and Body Reshaping for Virtual Try-on Applications","authors":"Tran Van Duc, Pham Quang Tien, Hoang Duc Minh Trieu, Nguyen Thi Ngoc Anh, Dat Tien Nguyen","doi":"10.13164/mendel.2023.2.097","DOIUrl":"https://doi.org/10.13164/mendel.2023.2.097","url":null,"abstract":"Online shopping using virtual try-on technology is becoming popular and widely used for digital transformation because of sustainably sourced materials and enhancing customers’ experience. For practical applicability, the process is required for two main factors: (1) accuracy and reliability, and (2) the processing time. To meet the above requirements, we propose a state-of-the-art technique for generating a user’s visualization of model costumes using only a single user portrait and basic anthropometrics. To start, this research would summarize different methods of most virtual try-on clothes approaches, including (1) Interactive simulation between the 3D models, and (2) 2D Photorealistic Generation. In spite of successfully creating the visualization and feasibility, these approaches have to face issues of their efficiency and performance. Furthermore, the complexity of input requirements and the users’ experiments are leading to difficulties in practical application and future scalability. In this regard, our study combines (1) a head-swapping technique using a face alignment model for determining, segmenting, and swapping heads with only a pair of a source and a target image as inputs (2) a photorealistic body reshape pipeline for direct resizing user visualization, and (3) an adaptive skin color models for changing user’s skin, which ensures remaining the face structure and natural. The proposed technique was evaluated quantitatively and qualitatively using three types of datasets which include: (1) VoxCeleb2, (2) Datasets from Viettel collection, and (3) Users Testing to demonstrate its feasibility and efficiency when used in real-world applications","PeriodicalId":38293,"journal":{"name":"Mendel","volume":"57 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139169891","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}
Pub Date : 2023-12-20DOI: 10.13164/mendel.2023.2.211
M. A. Saouli
We deal with fractional mean field backwardWe deal with fractional mean field backward stochastic differential equations with hurst parameter $Hin (frac{1}{2},1)$ when the coefficient $f$ satisfy a stochastic Lipschitz conditions, we prove the existence and uniqueness of solution and provide a comparison theorem. Via an approximation and comparison theorem, we show the existence of a minimal solution when the drift satisfies a stochastic growth condition.
{"title":"Existence Solution for Fractional Mean-Field Backward Stochastic Differential Equation with Stochastic Linear Growth Coefficients","authors":"M. A. Saouli","doi":"10.13164/mendel.2023.2.211","DOIUrl":"https://doi.org/10.13164/mendel.2023.2.211","url":null,"abstract":"We deal with fractional mean field backwardWe deal with fractional mean field backward stochastic differential equations with hurst parameter $Hin (frac{1}{2},1)$ when the coefficient $f$ satisfy a stochastic Lipschitz conditions, we prove the existence and uniqueness of solution and provide a comparison theorem. Via an approximation and comparison theorem, we show the existence of a minimal solution when the drift satisfies a stochastic growth condition.","PeriodicalId":38293,"journal":{"name":"Mendel","volume":"44 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138955491","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}
Pub Date : 2023-12-20DOI: 10.13164/mendel.2023.2.307
Reham Amin, Ghada El-Taweel, Ahmed Fouad Ali, Mohamed Tahoun
The vast amounts of data, lack of scalability, and low detection rates of traditional intrusion detection technologies make it impossible to keep up with evolving and increasingly sophisticated cyber threats. Therefore, there is an urgent need to detect and stop cyber threats early. Deep Learning has greatly improved intrusion detection due to its ability to self-learn and extract highly accurate features. In this paper, a Hybrid XG Boosted and Long Short-Term Memory algorithm (HXGBLSTM) is proposed. A comparative analysis is conducted between the computational performance of six established evolutionary computation algorithms and the recently developed bio-inspired metaheuristic algorithm called Zebra Optimisation Algorithm. These algorithms include the Particle Swarm Optimisation Algorithm, the Bio-inspired Algorithms, Bat Optimisation Algorithm, Firefly Optimisation Algorithm, and Monarch Butterfly Optimisation Algorithm, as well as the Genetic Algorithm as an Evolutionary Algorithm. The dimensionality curse has been mitigated by using these metaheuristic methods for feature selection, and the results are compared with the wrapper-based feature selection XGBoost algorithm. The proposed algorithm uses the CSE-CIC -IDS2018 dataset, which contains the latest network attacks. XGBoost outperformed the other FS algorithms and was used as the feature selection algorithm. In evaluating the effectiveness of the newly proposed HXGBLSTM, binary and multi-class classifications are considered. When comparing the performance of the proposed HXGBLSTM for cyber threat detection, it outperforms seven innovative deep learning algorithms for binary classification and four of them for multi-class classification. Other evaluation criteria such as recall, F1 score, and precision have been also used for comparison. The results showed that the best accuracy for binary classification is 99.8%, with F1-score of 99.83%, precision of 99.85%, and recall of 99.82%, in extensive and detailed experiments conducted on a real dataset. The best accuracy, F1-score, precision, and recall for multi-class classification were all around 100%, which does give the proposed algorithm an advantage over the compared ones.
{"title":"A Hybrid Extreme Gradient Boosting and Long Short-Term Memory Algorithm for Cyber Threats Detection","authors":"Reham Amin, Ghada El-Taweel, Ahmed Fouad Ali, Mohamed Tahoun","doi":"10.13164/mendel.2023.2.307","DOIUrl":"https://doi.org/10.13164/mendel.2023.2.307","url":null,"abstract":"The vast amounts of data, lack of scalability, and low detection rates of traditional intrusion detection technologies make it impossible to keep up with evolving and increasingly sophisticated cyber threats. Therefore, there is an urgent need to detect and stop cyber threats early. Deep Learning has greatly improved intrusion detection due to its ability to self-learn and extract highly accurate features. In this paper, a Hybrid XG Boosted and Long Short-Term Memory algorithm (HXGBLSTM) is proposed. A comparative analysis is conducted between the computational performance of six established evolutionary computation algorithms and the recently developed bio-inspired metaheuristic algorithm called Zebra Optimisation Algorithm. These algorithms include the Particle Swarm Optimisation Algorithm, the Bio-inspired Algorithms, Bat Optimisation Algorithm, Firefly Optimisation Algorithm, and Monarch Butterfly Optimisation Algorithm, as well as the Genetic Algorithm as an Evolutionary Algorithm. The dimensionality curse has been mitigated by using these metaheuristic methods for feature selection, and the results are compared with the wrapper-based feature selection XGBoost algorithm. The proposed algorithm uses the CSE-CIC -IDS2018 dataset, which contains the latest network attacks. XGBoost outperformed the other FS algorithms and was used as the feature selection algorithm. In evaluating the effectiveness of the newly proposed HXGBLSTM, binary and multi-class classifications are considered. When comparing the performance of the proposed HXGBLSTM for cyber threat detection, it outperforms seven innovative deep learning algorithms for binary classification and four of them for multi-class classification. Other evaluation criteria such as recall, F1 score, and precision have been also used for comparison. The results showed that the best accuracy for binary classification is 99.8%, with F1-score of 99.83%, precision of 99.85%, and recall of 99.82%, in extensive and detailed experiments conducted on a real dataset. The best accuracy, F1-score, precision, and recall for multi-class classification were all around 100%, which does give the proposed algorithm an advantage over the compared ones.","PeriodicalId":38293,"journal":{"name":"Mendel","volume":"26 25","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138955839","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}
Pub Date : 2023-12-20DOI: 10.13164/mendel.2023.2.084
I. Sembiring, Paminto Agung Christianto, Eko Sediyono
The majority of In-Vitro Fertilization (IVF) patients immediately call a fertility doctor when they experience different symptoms than usual. However, the high workload makes fertility doctors unable to immediately provide recommendations to handle complaints of IVF patients, while the longer wait for recommendations from fertility doctors will increase the anxiety of IVF patients and high levels of anxiety affect the success rate of IVF programs. The Case-Based Reasoning (CBR) model has lower performance than the modified CBR model, and the CBR model adds to the workload of fertility doctors, namely having to handle the revision stage. To overcome these problems, the CBR model was modified by applying the Chris Case-Based Reasoning (CCBR) similarity formula and combining it with the Rule-Based Reasoning model. The results of performance measurements showed that the accuracy score increased to 47% and the precision score remained 100%, so the results of this modification of the CBR model are worthy of being recommended for application to a smart system for handling complaints of IVF patients.
{"title":"Hybrid of Smart System Model to Support the Service of Fertility Doctors in Handling In-Vitro Fertilization Patient Complaints","authors":"I. Sembiring, Paminto Agung Christianto, Eko Sediyono","doi":"10.13164/mendel.2023.2.084","DOIUrl":"https://doi.org/10.13164/mendel.2023.2.084","url":null,"abstract":"The majority of In-Vitro Fertilization (IVF) patients immediately call a fertility doctor when they experience different symptoms than usual. However, the high workload makes fertility doctors unable to immediately provide recommendations to handle complaints of IVF patients, while the longer wait for recommendations from fertility doctors will increase the anxiety of IVF patients and high levels of anxiety affect the success rate of IVF programs. The Case-Based Reasoning (CBR) model has lower performance than the modified CBR model, and the CBR model adds to the workload of fertility doctors, namely having to handle the revision stage. To overcome these problems, the CBR model was modified by applying the Chris Case-Based Reasoning (CCBR) similarity formula and combining it with the Rule-Based Reasoning model. The results of performance measurements showed that the accuracy score increased to 47% and the precision score remained 100%, so the results of this modification of the CBR model are worthy of being recommended for application to a smart system for handling complaints of IVF patients.","PeriodicalId":38293,"journal":{"name":"Mendel","volume":"17 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138955924","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}
Pub Date : 2023-12-20DOI: 10.13164/mendel.2023.2.147
A. Sangodiah, Wei Chooi Yi, Ayu Norafida binti Ayob, N. Jalil, Charles Ramendran S PR Subramaniam, Lirong Gong
The advanced digital revolution has shifted conventional teaching and learning into digital education. In consistency with digital education, Augmented Reality (AR) applications started to shine in the education industry for their ability to create conducive teaching and learning environments, especially in remote learning during the COVID-19 pandemic. Movement Control Order (MCO) implemented in the year 2020 has led to emergency remote teaching and learning without much preparation for all educators and learners. Throughout these few years, most educators got familiar with digital teaching tools and online teaching platforms. Hence, this study aims to explore educators’ readiness to adopt AR as a teaching tool in their teaching during the endemic period. A quantitative approach via questionnaire has been distributed to the Private Higher Education Institutions (PHEIs) in the states of Selangor and Kuala Lumpur. Machine learning using a clustering technique was used to find patterns between the demographics of educators towards the AR perception of educators. The results revealed that educators' perceptions of AR technology are influenced by their familiarity with it, their personal beliefs, and their attitudes toward technology. This study provides an insightful overview of the benefits of AR applications in education and the implications of the adoption of AR in Malaysian schools and educational institutions. It also highlights the importance of motivating educators and students to embrace AR as an enhancement learning tool, providing a valuable discussion for the government, learning institutions, and educators on the implementation of AR in Malaysia.
先进的数字革命已将传统教学转变为数字教育。与数字教育相一致，增强现实（AR）应用开始在教育行业大放异彩，因为它能够创造有利的教学环境，特别是在 COVID-19 大流行期间的远程学习中。2020 年实施的《调度令》（MCO）导致所有教育工作者和学习者在没有太多准备的情况下进行紧急远程教学。在这几年中，大多数教育工作者都熟悉了数字教学工具和在线教学平台。因此，本研究旨在探讨教育工作者是否准备好在疫情流行期间采用 AR 作为教学工具。研究采用定量方法，向雪兰莪州和吉隆坡州的私立高等教育机构（PHEIs）发放了调查问卷。使用聚类技术进行机器学习，以发现教育工作者的人口统计学特征与教育工作者的 AR 感知之间的模式。研究结果表明，教育工作者对 AR 技术的看法受到他们对该技术的熟悉程度、个人信念以及对技术的态度的影响。本研究深入概述了 AR 应用于教育的益处，以及在马来西亚学校和教育机构采用 AR 的意义。它还强调了激励教育工作者和学生接受 AR 作为增强学习工具的重要性，为政府、学习机构和教育工作者在马来西亚实施 AR 提供了有价值的讨论。
{"title":"Machine Learning Clustering Analysis Towards Educator’s Readiness to Adopt Augmented Reality as a Teaching Tool","authors":"A. Sangodiah, Wei Chooi Yi, Ayu Norafida binti Ayob, N. Jalil, Charles Ramendran S PR Subramaniam, Lirong Gong","doi":"10.13164/mendel.2023.2.147","DOIUrl":"https://doi.org/10.13164/mendel.2023.2.147","url":null,"abstract":"The advanced digital revolution has shifted conventional teaching and learning into digital education. In consistency with digital education, Augmented Reality (AR) applications started to shine in the education industry for their ability to create conducive teaching and learning environments, especially in remote learning during the COVID-19 pandemic. Movement Control Order (MCO) implemented in the year 2020 has led to emergency remote teaching and learning without much preparation for all educators and learners. Throughout these few years, most educators got familiar with digital teaching tools and online teaching platforms. Hence, this study aims to explore educators’ readiness to adopt AR as a teaching tool in their teaching during the endemic period. A quantitative approach via questionnaire has been distributed to the Private Higher Education Institutions (PHEIs) in the states of Selangor and Kuala Lumpur. Machine learning using a clustering technique was used to find patterns between the demographics of educators towards the AR perception of educators. The results revealed that educators' perceptions of AR technology are influenced by their familiarity with it, their personal beliefs, and their attitudes toward technology. This study provides an insightful overview of the benefits of AR applications in education and the implications of the adoption of AR in Malaysian schools and educational institutions. It also highlights the importance of motivating educators and students to embrace AR as an enhancement learning tool, providing a valuable discussion for the government, learning institutions, and educators on the implementation of AR in Malaysia.","PeriodicalId":38293,"journal":{"name":"Mendel","volume":"41 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138957219","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：