Pub Date : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5047-5053
V. Cong, Thai Thanh Hiep
In this paper, a support vector machine (SVM) model is trained to classify objects in the automatic sorting system using a robot arm. The robot arm is used to grab objects and move them to the right position according to their shape predicted by the SVM model. The position of objects in the image is identified by using the contouring technique. The centroid of objects is calculated from the image moment of the object's contour. The calibration is conducted to get the parameters of the camera and combine with the pinhole camera model to compute the 3D position of the objects. The feature vector for SVM training is the zone feature and the SVM kernel is the Gaussian kernel. In the experiment, the SVM model is used to classify four objects with different shapes. The results show that the accuracy of the SVM classifier is 99.72%, 99.4%, 99.4% and 99.88% for four objects, respectively.
{"title":"Support vector machine-based object classification for robot arm system","authors":"V. Cong, Thai Thanh Hiep","doi":"10.11591/ijece.v13i5.pp5047-5053","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5047-5053","url":null,"abstract":"In this paper, a support vector machine (SVM) model is trained to classify objects in the automatic sorting system using a robot arm. The robot arm is used to grab objects and move them to the right position according to their shape predicted by the SVM model. The position of objects in the image is identified by using the contouring technique. The centroid of objects is calculated from the image moment of the object's contour. The calibration is conducted to get the parameters of the camera and combine with the pinhole camera model to compute the 3D position of the objects. The feature vector for SVM training is the zone feature and the SVM kernel is the Gaussian kernel. In the experiment, the SVM model is used to classify four objects with different shapes. The results show that the accuracy of the SVM classifier is 99.72%, 99.4%, 99.4% and 99.88% for four objects, respectively.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43172543","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5792-5803
Shimaa Fawzy, Hossam El-Din Moustafa, Ehab H. Abdelhay, M. M. Ata
One-third of all cancer diagnoses worldwide are skin malignancies. One of the most common tumors, skin cancer can develop from a variety of dermatological conditions and is subdivided into different categories based on its textile, color, body, and other morphological characteristics. The most effective strategy to lower the mortality rate of melanoma is early identification because skin cancer incidence has been on the rise recently. In order to categorize dermoscopy images into the four diagnosis classifications of melanoma, benign, malignant, and human against machine (HAM) not melanoma, this research suggests a computer-aided diagnosis (CAD) system. Experimental results show that the suggested approach enabled 97.25% classification accuracy. In order to automate the identification of skin cancer and expedite the diagnosis process in order to save a life, the proposed technique offers a less complex and cutting-edge framework.
{"title":"A deep convolutional structure-based approach for accurate recognition of skin lesions in dermoscopy images","authors":"Shimaa Fawzy, Hossam El-Din Moustafa, Ehab H. Abdelhay, M. M. Ata","doi":"10.11591/ijece.v13i5.pp5792-5803","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5792-5803","url":null,"abstract":"One-third of all cancer diagnoses worldwide are skin malignancies. One of the most common tumors, skin cancer can develop from a variety of dermatological conditions and is subdivided into different categories based on its textile, color, body, and other morphological characteristics. The most effective strategy to lower the mortality rate of melanoma is early identification because skin cancer incidence has been on the rise recently. In order to categorize dermoscopy images into the four diagnosis classifications of melanoma, benign, malignant, and human against machine (HAM) not melanoma, this research suggests a computer-aided diagnosis (CAD) system. Experimental results show that the suggested approach enabled 97.25% classification accuracy. In order to automate the identification of skin cancer and expedite the diagnosis process in order to save a life, the proposed technique offers a less complex and cutting-edge framework.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43480522","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5091-5100
Achmad Rizal, Risanuri Hidayat, Hanung Adi Nugroho, Willy Anugrah Cahyadi
Lung sound is one indicator of abnormalities in the lungs and respiratory tract. Research for automatic lung sound classification has become one of the interests for researchers because lung disease is one of the diseases with the most sufferers in the world. The use of lung sounds as a source of information because of the ease in data acquisition and auscultation is a standard method in examining pulmonary function. This study simulated the potential use of Higuchi fractal dimension (HFD) as a feature extraction method for lung sound classification. HFD calculations were run on a series of k values to generate some HFD values as features. According to the simulation results, the proposed method could produce an accuracy of up to 97.98% for five classes of lung sound data. The results also suggested that the shift in HFD values over the selection of a time interval k can be used for lung sound classification.
{"title":"Lung sound classification using multiresolution Higuchi fractal dimension measurement","authors":"Achmad Rizal, Risanuri Hidayat, Hanung Adi Nugroho, Willy Anugrah Cahyadi","doi":"10.11591/ijece.v13i5.pp5091-5100","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5091-5100","url":null,"abstract":"<span lang=\"EN-GB\">Lung sound is one indicator of abnormalities in the lungs and respiratory tract. Research for automatic lung sound classification has become one of the interests for researchers because lung disease is one of the diseases with the most sufferers in the world. The use of lung sounds as a source of information because of the ease in data acquisition and auscultation is a standard method in examining pulmonary function. This study simulated the potential use of Higuchi fractal dimension (HFD) as a feature extraction method for lung sound classification. HFD calculations were run on a series of </span><em><span lang=\"EN-GB\">k</span></em><span lang=\"EN-GB\"> values to generate some HFD values as features. According to the simulation results, the proposed method could produce an accuracy of up to 97.98% for five classes of lung sound data. The results also suggested that the shift in HFD values over the selection of a time interval </span><em><span lang=\"EN-GB\">k</span></em><span lang=\"EN-GB\"> can be used for lung sound classification.</span>","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43477080","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5898-5907
Naveen Kumar Chowdaiah, Annapurna Dammur
One of the most challenging tasks in the internet of things-cloud-based environment is the resource allocation for the tasks. The cloud provides various resources such as virtual machines, computational cores, networks, and other resources for the execution of the various tasks of the internet of things (IoT). Moreover, some methods are used for executing IoT tasks using an optimal resource management system but these methods are not efficient. Hence, in this research, we present a resource-efficient workload task scheduling (RWTS) model for a cloud-assisted IoT environment to execute the IoT task which utilizes few numbers of resources to bring a good tradeoff, achieve high performance using fewer resources of the cloud, compute the number of resources required for the execution of the IoT task such as bandwidth and computational core. Furthermore, this model mainly focuses to reduce energy consumption and also provides a task scheduling model to schedule the IoT tasks in an IoT-cloud-based environment. The experimentation has been done using the Montage workflow and the results have been obtained in terms of execution time, power sum, average power, and energy consumption. When compared with the existing model, the RWTS model performs better when the size of the tasks is increased.
{"title":"Resource-efficient workload task scheduling for cloud-assisted internet of things environment","authors":"Naveen Kumar Chowdaiah, Annapurna Dammur","doi":"10.11591/ijece.v13i5.pp5898-5907","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5898-5907","url":null,"abstract":"One of the most challenging tasks in the internet of things-cloud-based environment is the resource allocation for the tasks. The cloud provides various resources such as virtual machines, computational cores, networks, and other resources for the execution of the various tasks of the internet of things (IoT). Moreover, some methods are used for executing IoT tasks using an optimal resource management system but these methods are not efficient. Hence, in this research, we present a resource-efficient workload task scheduling (RWTS) model for a cloud-assisted IoT environment to execute the IoT task which utilizes few numbers of resources to bring a good tradeoff, achieve high performance using fewer resources of the cloud, compute the number of resources required for the execution of the IoT task such as bandwidth and computational core. Furthermore, this model mainly focuses to reduce energy consumption and also provides a task scheduling model to schedule the IoT tasks in an IoT-cloud-based environment. The experimentation has been done using the Montage workflow and the results have been obtained in terms of execution time, power sum, average power, and energy consumption. When compared with the existing model, the RWTS model performs better when the size of the tasks is increased.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43606499","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5076-5090
Fredy H. Martínez, Holman Montiel, Fernando Martinez
In the present research, an innovative fuzzy control approach is developed specifically for synchronous buck converters utilized in renewable energy applications. The proposed control strategy effectively manages load changes, nonlinear loads, and input voltage variations while improving both stability and transient response. The method employs a fuzzy inference system (FIS) that integrates adaptive control, feedforward control, and multivariable control to guarantee optimal performance under a wide range of operating conditions. The design of the control scheme involves formulating a rule base connecting input variables to an output variable, which signifies the duty cycle of the switching signal. The rule base is configured to dynamically modify control rules and membership functions in accordance with load conditions, input voltage fluctuations, and other contributing factors. The performance of the control scheme is evaluated in comparison to conventional techniques, such as proportional integral derivative (PID) control. Results indicate that the advanced fuzzy control approach surpasses traditional methods in terms of voltage regulation, stability, and transient response, particularly when faced with variable load conditions and input voltage changes. As a result, this control scheme is highly compatible with renewable energy systems, encompassing solar and wind power installations where input voltage and load conditions may experience considerable fluctuations. This research highlights the potential of the proposed fuzzy control approach to significantly enhance the performance and reliability of renewable energy systems.
{"title":"Fuzzy control of synchronous buck converters utilizing fuzzy inference system for renewable energy applications","authors":"Fredy H. Martínez, Holman Montiel, Fernando Martinez","doi":"10.11591/ijece.v13i5.pp5076-5090","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5076-5090","url":null,"abstract":"In the present research, an innovative fuzzy control approach is developed specifically for synchronous buck converters utilized in renewable energy applications. The proposed control strategy effectively manages load changes, nonlinear loads, and input voltage variations while improving both stability and transient response. The method employs a fuzzy inference system (FIS) that integrates adaptive control, feedforward control, and multivariable control to guarantee optimal performance under a wide range of operating conditions. The design of the control scheme involves formulating a rule base connecting input variables to an output variable, which signifies the duty cycle of the switching signal. The rule base is configured to dynamically modify control rules and membership functions in accordance with load conditions, input voltage fluctuations, and other contributing factors. The performance of the control scheme is evaluated in comparison to conventional techniques, such as proportional integral derivative (PID) control. Results indicate that the advanced fuzzy control approach surpasses traditional methods in terms of voltage regulation, stability, and transient response, particularly when faced with variable load conditions and input voltage changes. As a result, this control scheme is highly compatible with renewable energy systems, encompassing solar and wind power installations where input voltage and load conditions may experience considerable fluctuations. This research highlights the potential of the proposed fuzzy control approach to significantly enhance the performance and reliability of renewable energy systems.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47897843","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5035-5046
M. Essabre, Ilham Hmaiddouch, A. El Assoudi, E. H. El Yaagoubi
Recent years have seen a great deal of interest in implicit nonlinear systems, which are used in many different engineering applications. This study is dedicated to presenting a new method of fuzzy unknown inputs observer design to estimate simultaneously both non-measurable states and unknown inputs of continuous-time nonlinear implicit systems defined by Takagi-Sugeno (T-S) models with unmeasurable premise variables. The suggested observer is based on the singular value decomposition approach and rewritten the continuous-time T-S implicit models into an augmented fuzzy system, which gathers the unknown inputs and the state vector. The exponential convergence condition of the observer is established by using the Lyapunov theory and linear matrix inequalities are solved to determine the gains of the observer. Finally, the effectiveness of the suggested method is then assessed using a numerical application. It demonstrates that the estimated variables and the unknown input converge to the real variables accurately and quickly (less than 0.5 s).
{"title":"Unknown input observer for Takagi-Sugeno implicit models with unmeasurable premise variables","authors":"M. Essabre, Ilham Hmaiddouch, A. El Assoudi, E. H. El Yaagoubi","doi":"10.11591/ijece.v13i5.pp5035-5046","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5035-5046","url":null,"abstract":"Recent years have seen a great deal of interest in implicit nonlinear systems, which are used in many different engineering applications. This study is dedicated to presenting a new method of fuzzy unknown inputs observer design to estimate simultaneously both non-measurable states and unknown inputs of continuous-time nonlinear implicit systems defined by Takagi-Sugeno (T-S) models with unmeasurable premise variables. The suggested observer is based on the singular value decomposition approach and rewritten the continuous-time T-S implicit models into an augmented fuzzy system, which gathers the unknown inputs and the state vector. The exponential convergence condition of the observer is established by using the Lyapunov theory and linear matrix inequalities are solved to determine the gains of the observer. Finally, the effectiveness of the suggested method is then assessed using a numerical application. It demonstrates that the estimated variables and the unknown input converge to the real variables accurately and quickly (less than 0.5 s).","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48600616","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5444-5453
Bahaa Eddine Elbaghazaoui, M. Amnai, Y. Fakhri
Mental health disorders affect many aspects of patient’s lives, including emotions, cognition, and especially behaviors. E-health technology helps to collect information wealth in a non-invasive manner, which represents a promising opportunity to construct health behavior markers. Combining such user behavior data can provide a more comprehensive and contextual view than questionnaire data. Due to behavioral data, we can train machine learning models to understand the data pattern and also use prediction algorithms to know the next state of a person’s behavior. The remaining challenges for this issue are how to apply mathematical formulations to textual datasets and find metadata that aids to identify the person’s life pattern and also predict the next state of his comportment. The main idea of this work is to use a hidden Markov model (HMM) to predict user behavior from social media applications by analyzing and detecting states and symbols from the user behavior dataset. To achieve this goal, we need to analyze and detect the states and symbols from the user behavior dataset, then convert the textual data to mathematical and numerical matrices. Finally, apply the HMM model to predict the hidden user behavior states. We tested our program and identified that the log-likelihood was higher and better when the model fits the data. In any case, the results of the study indicated that the program was suitable for the purpose and yielded valuable data.
{"title":"Predicting user behavior using data profiling and hidden Markov model","authors":"Bahaa Eddine Elbaghazaoui, M. Amnai, Y. Fakhri","doi":"10.11591/ijece.v13i5.pp5444-5453","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5444-5453","url":null,"abstract":"Mental health disorders affect many aspects of patient’s lives, including emotions, cognition, and especially behaviors. E-health technology helps to collect information wealth in a non-invasive manner, which represents a promising opportunity to construct health behavior markers. Combining such user behavior data can provide a more comprehensive and contextual view than questionnaire data. Due to behavioral data, we can train machine learning models to understand the data pattern and also use prediction algorithms to know the next state of a person’s behavior. The remaining challenges for this issue are how to apply mathematical formulations to textual datasets and find metadata that aids to identify the person’s life pattern and also predict the next state of his comportment. The main idea of this work is to use a hidden Markov model (HMM) to predict user behavior from social media applications by analyzing and detecting states and symbols from the user behavior dataset. To achieve this goal, we need to analyze and detect the states and symbols from the user behavior dataset, then convert the textual data to mathematical and numerical matrices. Finally, apply the HMM model to predict the hidden user behavior states. We tested our program and identified that the log-likelihood was higher and better when the model fits the data. In any case, the results of the study indicated that the program was suitable for the purpose and yielded valuable data.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43123331","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 article is devoted to the study of four-wave mixing (FWM) in a semiconductor optical amplifier with quantum dots (QD-SOA). Experimental measurements of FWM signals are characterized in nonlinear media of GaAs-based QD-SOA with gain in the 1,550 nm region. Theoretical part of nonlinear effect of FWM is studied and important all-optical communication applications are listed. Experimental studies of a four-wave system are described and an analysis of FWM signals is given for various input powers of pump signals and injection currents. The devices are compared in terms of such parameters as conversion efficiency and signal-to-noise ratio. The results of the study made it possible to reveal the possibility of the effect of FWM signals on useful signals in channels with spectral division multiplexing wavelength division multiplexing (WDM) in the downstream and upstream in a semiconductor optical amplifier. Based on the experimental results, it was concluded that FWM does not affect adjacent channels of WDM signals and does not generate additional optical noise when scaling the WDM gigabit passive optical network (GPON) up to 60 km using semiconductor optical amplifiers (SOAs).
{"title":"Experimental study of four-wave mixing based on a quantum dot semiconductor optical amplifier","authors":"Tokhmetov Akylbek, Tussupov Akhmet, Tanchenko Liliya","doi":"10.11591/ijece.v13i5.pp5179-5189","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5179-5189","url":null,"abstract":"The article is devoted to the study of four-wave mixing (FWM) in a semiconductor optical amplifier with quantum dots (QD-SOA). Experimental measurements of FWM signals are characterized in nonlinear media of GaAs-based QD-SOA with gain in the 1,550 nm region. Theoretical part of nonlinear effect of FWM is studied and important all-optical communication applications are listed. Experimental studies of a four-wave system are described and an analysis of FWM signals is given for various input powers of pump signals and injection currents. The devices are compared in terms of such parameters as conversion efficiency and signal-to-noise ratio. The results of the study made it possible to reveal the possibility of the effect of FWM signals on useful signals in channels with spectral division multiplexing wavelength division multiplexing (WDM) in the downstream and upstream in a semiconductor optical amplifier. Based on the experimental results, it was concluded that FWM does not affect adjacent channels of WDM signals and does not generate additional optical noise when scaling the WDM gigabit passive optical network (GPON) up to 60 km using semiconductor optical amplifiers (SOAs).","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49578029","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp4777-4788
R. A. Subekti, S. Wijaya, A. Sudarmaji, T. D. Atmaja, B. Prawara, Anjar Susatyo, A. Fudholi
This study discusses the numerical optimisation and performance testing of the turbine runner profile for the designed gravitational water vortex turbine. The initial design of the turbine runner is optimised using a surface vorticity algorithm coded in MATLAB to obtain the optimal stagger angle. Design validation is carried out using computational fluid dynamics (CFD) Ansys CFX to determine the performance of the turbine runner with the turbulent shear stress transport model. The CFD analysis shows that by optimising the design, the water turbine efficiency increases by about 2.6%. The prototype of the vortex turbine runner is made using a 3D printing machine with resin material. It is later tested in a laboratory-scale experiment that measures the shaft power, shaft torque and turbine efficiency in correspondence with rotational speeds varying from 150 to 650 rpm. Experiment results validate that the optimised runner has an efficiency of 45.3% or about 14% greater than the initial design runner, which has an efficiency of 39.7%.
{"title":"Runner profile optimisation of gravitational vortex water turbine","authors":"R. A. Subekti, S. Wijaya, A. Sudarmaji, T. D. Atmaja, B. Prawara, Anjar Susatyo, A. Fudholi","doi":"10.11591/ijece.v13i5.pp4777-4788","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp4777-4788","url":null,"abstract":"This study discusses the numerical optimisation and performance testing of the turbine runner profile for the designed gravitational water vortex turbine. The initial design of the turbine runner is optimised using a surface vorticity algorithm coded in MATLAB to obtain the optimal stagger angle. Design validation is carried out using computational fluid dynamics (CFD) Ansys CFX to determine the performance of the turbine runner with the turbulent shear stress transport model. The CFD analysis shows that by optimising the design, the water turbine efficiency increases by about 2.6%. The prototype of the vortex turbine runner is made using a 3D printing machine with resin material. It is later tested in a laboratory-scale experiment that measures the shaft power, shaft torque and turbine efficiency in correspondence with rotational speeds varying from 150 to 650 rpm. Experiment results validate that the optimised runner has an efficiency of 45.3% or about 14% greater than the initial design runner, which has an efficiency of 39.7%.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46142211","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 : 2023-10-01DOI: 10.11591/ijece.v13i5.pp5737-5746
Amr Abdel-aal, Ibrahim El-Henawy
Feature selection entails choosing the significant features among a wide collection of original features that are essential for predicting test data using a classifier. Feature selection is commonly used in various applications, such as bioinformatics, data mining, and the analysis of written texts, where the dataset contains tens or hundreds of thousands of features, making it difficult to analyze such a large feature set. Removing irrelevant features improves the predictor performance, making it more accurate and cost-effective. In this research, a novel hybrid technique is presented for feature selection that aims to enhance classification accuracy. A hybrid binary version of side-blotched lizard algorithm (SBLA) with genetic algorithm (GA), namely SBLAGA, which combines the strengths of both algorithms is proposed. We use a sigmoid function to adapt the continuous variables values into a binary one, and evaluate our proposed algorithm on twenty-three standard benchmark datasets. Average classification accuracy, average number of selected features and average fitness value were the evaluation criteria. According to the experimental results, SBLAGA demonstrated superior performance compared to SBLA and GA with regards to these criteria. We further compare SBLAGA with four wrapper feature selection methods that are widely used in the literature, and find it to be more efficient.
{"title":"Improved feature selection using a hybrid side-blotched lizard algorithm and genetic algorithm approach","authors":"Amr Abdel-aal, Ibrahim El-Henawy","doi":"10.11591/ijece.v13i5.pp5737-5746","DOIUrl":"https://doi.org/10.11591/ijece.v13i5.pp5737-5746","url":null,"abstract":"Feature selection entails choosing the significant features among a wide collection of original features that are essential for predicting test data using a classifier. Feature selection is commonly used in various applications, such as bioinformatics, data mining, and the analysis of written texts, where the dataset contains tens or hundreds of thousands of features, making it difficult to analyze such a large feature set. Removing irrelevant features improves the predictor performance, making it more accurate and cost-effective. In this research, a novel hybrid technique is presented for feature selection that aims to enhance classification accuracy. A hybrid binary version of side-blotched lizard algorithm (SBLA) with genetic algorithm (GA), namely SBLAGA, which combines the strengths of both algorithms is proposed. We use a sigmoid function to adapt the continuous variables values into a binary one, and evaluate our proposed algorithm on twenty-three standard benchmark datasets. Average classification accuracy, average number of selected features and average fitness value were the evaluation criteria. According to the experimental results, SBLAGA demonstrated superior performance compared to SBLA and GA with regards to these criteria. We further compare SBLAGA with four wrapper feature selection methods that are widely used in the literature, and find it to be more efficient.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"65382767","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：