Pub Date : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865524
Tham Nguyen Thi, Trong-Hop Do
This paper applies two lexicon enhancement methods, that are lexica feature extraction and retrofitting to improve the accuracy of hate speech detection problem on Vietnamese social network data. The experiments were conducted on multiple datasets to achieve the statistical significance of the experimental results. The results show that the use of retrofitting lexicon enhancement improves the accuracy of hate speech detection. This paper also introduces a dictionary consisting of hateful words that can be used for lexicon enhancement for hate speech detection on Vietnamese social network data.
{"title":"Lexicon-enhanced hate speech detection on Vietnamese social network data","authors":"Tham Nguyen Thi, Trong-Hop Do","doi":"10.1109/CyberneticsCom55287.2022.9865524","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865524","url":null,"abstract":"This paper applies two lexicon enhancement methods, that are lexica feature extraction and retrofitting to improve the accuracy of hate speech detection problem on Vietnamese social network data. The experiments were conducted on multiple datasets to achieve the statistical significance of the experimental results. The results show that the use of retrofitting lexicon enhancement improves the accuracy of hate speech detection. This paper also introduces a dictionary consisting of hateful words that can be used for lexicon enhancement for hate speech detection on Vietnamese social network data.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125645015","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865500
Anna Patricia Z. Valeriano, Leanza Clarisse Z. Manalus, Jazha Alaiza Dennice C. Tejones, Rommel M. Anacan, Alice Jade Cabato, Emil Jann V. Mendoza, Arnino P. Rolusta, Ian Caezar M. Francisco, Cayetano D. Hiwatig
Filipinos, regarding meat consumption are more than global average. According to the Organization for Economic Cooperation and Development 2017 study, an ordinary Filipino eat 14.2 kilograms of pork which is two kilogram above world's pork consumption yearly while 3 kilos when in terms of beef. In the 2019 forecast, the trend increases at 15.8 kilos for pork and 3.2 kilos for beef. Freshness is the state of being made recently or not having declined on meat or food specifically. Cherry Red is the ideal color for fresh beef, and it should be reddish pink for fresh pork. Color can clearly affect their safety when the consumer eats the spoiled meat or even hot meat. Digital image processing is the use of computer algorithms for digital image processing. It is also used to manipulate images. Digital image processing has two main goals: human image enhancement; and autonomous machine perception, storage, transmission, and representation image data processing.
{"title":"Design of Image Processing Tool Using MATLAB for Freshness Assessment of Beef and Pork","authors":"Anna Patricia Z. Valeriano, Leanza Clarisse Z. Manalus, Jazha Alaiza Dennice C. Tejones, Rommel M. Anacan, Alice Jade Cabato, Emil Jann V. Mendoza, Arnino P. Rolusta, Ian Caezar M. Francisco, Cayetano D. Hiwatig","doi":"10.1109/CyberneticsCom55287.2022.9865500","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865500","url":null,"abstract":"Filipinos, regarding meat consumption are more than global average. According to the Organization for Economic Cooperation and Development 2017 study, an ordinary Filipino eat 14.2 kilograms of pork which is two kilogram above world's pork consumption yearly while 3 kilos when in terms of beef. In the 2019 forecast, the trend increases at 15.8 kilos for pork and 3.2 kilos for beef. Freshness is the state of being made recently or not having declined on meat or food specifically. Cherry Red is the ideal color for fresh beef, and it should be reddish pink for fresh pork. Color can clearly affect their safety when the consumer eats the spoiled meat or even hot meat. Digital image processing is the use of computer algorithms for digital image processing. It is also used to manipulate images. Digital image processing has two main goals: human image enhancement; and autonomous machine perception, storage, transmission, and representation image data processing.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127615605","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865465
Aviv Yuniar Rahman
Starlings are famous animals in Indonesia. Therefore, many in Indonesia maintain and cultivate starlings. Almost every region in Indonesia has different types of starlings. Therefore, the researchers used Artificial Neural Networks and Decision Trees to classify starlings. Both methods are useful for obtaining the accuracy values generated in the classification of the starlings. In this comparison, the Artificial Neural Network has a precision of 0.870, the highest recall value is 0.600, the f-measure is 0.865, and the accuracy is 93% at a split ratio of 90:10. The Decision Tree has resulted in the classification of starlings on features, shapes, and colours with the highest texture value at a precision of 1,000, recall reaching 1,000, f-measure reaching 1,000, and accuracy reaching 100% at a split ratio 90:10. The tests carried out show that the Decision Tree can classify starling images based on 3 feature levels. And in this case, it can be proven that the Decision Tree is more accurate in classifying starlings images. The method of this Decision Tree can make it easier to find the right accuracy value in classifying starling species.
{"title":"Image Classification of Starlings Using Artificial Neural Network and Decision Tree","authors":"Aviv Yuniar Rahman","doi":"10.1109/CyberneticsCom55287.2022.9865465","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865465","url":null,"abstract":"Starlings are famous animals in Indonesia. Therefore, many in Indonesia maintain and cultivate starlings. Almost every region in Indonesia has different types of starlings. Therefore, the researchers used Artificial Neural Networks and Decision Trees to classify starlings. Both methods are useful for obtaining the accuracy values generated in the classification of the starlings. In this comparison, the Artificial Neural Network has a precision of 0.870, the highest recall value is 0.600, the f-measure is 0.865, and the accuracy is 93% at a split ratio of 90:10. The Decision Tree has resulted in the classification of starlings on features, shapes, and colours with the highest texture value at a precision of 1,000, recall reaching 1,000, f-measure reaching 1,000, and accuracy reaching 100% at a split ratio 90:10. The tests carried out show that the Decision Tree can classify starling images based on 3 feature levels. And in this case, it can be proven that the Decision Tree is more accurate in classifying starlings images. The method of this Decision Tree can make it easier to find the right accuracy value in classifying starling species.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125211551","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865253
Anis Sirwan, Kurniawan Adhie Thama, S. Suyanto
The Indonesian language is different from English in phonetics. It is challenging to develop AI technology, machine learning, and deep learning with various algorithms to select the appropriate methods and algorithms for Indonesian speech recognition needs. Much research on speech recognition has been performed for high-resource languages, such as English. Unfortunately, those models cannot be directly used for the Indonesian language. To create an excellent speech recognition model, we need a high-quality and quantity dataset of the Indonesian language. But, such a dataset is not available at the moment. Hence, in this research, we start collecting such a dataset. Next, the developed dataset is used to train an end-to-end deep learning-based speech recognition model. The evaluation shows that the developed model achieves a word error rate of 14.172%, better than two previous models: Mozilla DeepSpeech (23.10%) and Kaituoxu Speech-Transformer (22.00%).
{"title":"Indonesian Automatic Speech Recognition Based on End-to-end Deep Learning Model","authors":"Anis Sirwan, Kurniawan Adhie Thama, S. Suyanto","doi":"10.1109/CyberneticsCom55287.2022.9865253","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865253","url":null,"abstract":"The Indonesian language is different from English in phonetics. It is challenging to develop AI technology, machine learning, and deep learning with various algorithms to select the appropriate methods and algorithms for Indonesian speech recognition needs. Much research on speech recognition has been performed for high-resource languages, such as English. Unfortunately, those models cannot be directly used for the Indonesian language. To create an excellent speech recognition model, we need a high-quality and quantity dataset of the Indonesian language. But, such a dataset is not available at the moment. Hence, in this research, we start collecting such a dataset. Next, the developed dataset is used to train an end-to-end deep learning-based speech recognition model. The evaluation shows that the developed model achieves a word error rate of 14.172%, better than two previous models: Mozilla DeepSpeech (23.10%) and Kaituoxu Speech-Transformer (22.00%).","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122756961","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}
Monitoring vehicle activity both on the highway and in certain places such as parking lots needs to be done if there is a specific incident. Unexpected events such as accidents or vehicle theft may occur anytime. Therefore, tracking through number plate recognition has become something important and has become a hot topic with the various methods used. Previous research used machine learning techniques to recognize characters on number plates. The use of this technique has not produced optimal accuracy. Therefore, we propose using transfer learning techniques to achieve better accuracy results. This research evaluated three transfer learning models, namely DenseNet121, MobileNetV2, and NASNetMobile models. The experiment in this research was carried out using the data on number plates in the parking lot. The accuracy calculation counted the number of correctly recognized characters divided by the total characters on the number plate. The experimental results show that the DenseNet121 model produced the best accuracy, 96.42%. Differences in number plate writing style also affected the accuracy results. This research could provide insight into the use of transfer learning techniques in the case of number plate recognition.
{"title":"Comparative Transfer Learning Techniques for Plate Number Recognition","authors":"Rizki Rafiif Amaanullah, Rifqi Akmal Saputra, Faisal Dharma Adhinata, Nur Ghaniaviyanto Ramadhan","doi":"10.1109/CyberneticsCom55287.2022.9865370","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865370","url":null,"abstract":"Monitoring vehicle activity both on the highway and in certain places such as parking lots needs to be done if there is a specific incident. Unexpected events such as accidents or vehicle theft may occur anytime. Therefore, tracking through number plate recognition has become something important and has become a hot topic with the various methods used. Previous research used machine learning techniques to recognize characters on number plates. The use of this technique has not produced optimal accuracy. Therefore, we propose using transfer learning techniques to achieve better accuracy results. This research evaluated three transfer learning models, namely DenseNet121, MobileNetV2, and NASNetMobile models. The experiment in this research was carried out using the data on number plates in the parking lot. The accuracy calculation counted the number of correctly recognized characters divided by the total characters on the number plate. The experimental results show that the DenseNet121 model produced the best accuracy, 96.42%. Differences in number plate writing style also affected the accuracy results. This research could provide insight into the use of transfer learning techniques in the case of number plate recognition.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131952742","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865355
Rifqi Fachruddin, J. L. Buliali
The growth of system detection has significant development. The circle detection system is widely used to help people based on their needs, and it also could be used as learning media in educational fields. Especially for students with special needs, applying a circle detection system in Augmented Reality (AR) media would help them a lot. In order to make the study activity more effective and suit the learning material purpose, a circle detection system that only detects perfect full circles is needed to minimalize misconceptions in circle learning material. From the previous method such as Circle Hough Transform (CHT), circle detection faces the complex transition from cartesian coordinate into Hough coordinate. The use of image moments would give a coordinate of centroid that could use to find the radius by using the circle equation. Two groups of datasets would test the newly proposed method of detecting circles. Based on the experiment, the accuracy of the new method was 96.7%. The average time consumption is 0. 405 s which is faster than the CHT method with 1.024 s. Circle detection using image moments is also more robust towards noise than the previous CHT method.
{"title":"Circle Detection System Using Image Moments","authors":"Rifqi Fachruddin, J. L. Buliali","doi":"10.1109/CyberneticsCom55287.2022.9865355","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865355","url":null,"abstract":"The growth of system detection has significant development. The circle detection system is widely used to help people based on their needs, and it also could be used as learning media in educational fields. Especially for students with special needs, applying a circle detection system in Augmented Reality (AR) media would help them a lot. In order to make the study activity more effective and suit the learning material purpose, a circle detection system that only detects perfect full circles is needed to minimalize misconceptions in circle learning material. From the previous method such as Circle Hough Transform (CHT), circle detection faces the complex transition from cartesian coordinate into Hough coordinate. The use of image moments would give a coordinate of centroid that could use to find the radius by using the circle equation. Two groups of datasets would test the newly proposed method of detecting circles. Based on the experiment, the accuracy of the new method was 96.7%. The average time consumption is 0. 405 s which is faster than the CHT method with 1.024 s. Circle detection using image moments is also more robust towards noise than the previous CHT method.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114601127","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865637
Bayu Setho K.S, Arfianto Fahmi, N. Adriansyah, V. S. W. Prabowo
The usage of Device-to-Device (D2D) underlaying to reuse spectrum has a substantial influence on spectrum efficiency. On the other side, interference issues arise as a result of frequency reused by D2D users. Furthermore, wearable devices or communication devices have limited power sources, such as batteries. As a result, the fundamental problem formulation that must be solved is power allocation, with the goal function being to maximize the energy efficiency of the system. In order to provide optimum power allocation, conventional methods such as Convex Approximation (CA)-based algorithm need to run multiple iterations to solve the non-convex problem formulation. Therefore, Convolution Neural Network (CNN) as part of Deep Learning (DL) is utilized to approach (CA)-based algorithm for generating power allocation policies to maximize the systems energy efficiency. However, the conventional method of CNN has limitations in accepting arbitrary input size. Accordingly, to the limitation of CNN, this research proposed the combination of CNN with Spatial Pyramid Pooling (SPP) to overcome the limitation on the input size of conventional CNN. Specifically, the inputs of the model are the user's channel state information, and its outputs are power control policies. The simulation results show that both CNN-SPP and CNN can achieve similar performance to the traditional method up to 95 % accuracy. Furthermore, the combination of CNN and SPP can overcome the limitation on the input size of the conventional CNN method, reducing the number of models that must be trained to just one and applying it to all scenarios regardless of the number of CUEs D2D pairs.
{"title":"Modified CNN to Maximize Energy Efficiency in D2D Underlying with Multi-Cell Cellular Network","authors":"Bayu Setho K.S, Arfianto Fahmi, N. Adriansyah, V. S. W. Prabowo","doi":"10.1109/CyberneticsCom55287.2022.9865637","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865637","url":null,"abstract":"The usage of Device-to-Device (D2D) underlaying to reuse spectrum has a substantial influence on spectrum efficiency. On the other side, interference issues arise as a result of frequency reused by D2D users. Furthermore, wearable devices or communication devices have limited power sources, such as batteries. As a result, the fundamental problem formulation that must be solved is power allocation, with the goal function being to maximize the energy efficiency of the system. In order to provide optimum power allocation, conventional methods such as Convex Approximation (CA)-based algorithm need to run multiple iterations to solve the non-convex problem formulation. Therefore, Convolution Neural Network (CNN) as part of Deep Learning (DL) is utilized to approach (CA)-based algorithm for generating power allocation policies to maximize the systems energy efficiency. However, the conventional method of CNN has limitations in accepting arbitrary input size. Accordingly, to the limitation of CNN, this research proposed the combination of CNN with Spatial Pyramid Pooling (SPP) to overcome the limitation on the input size of conventional CNN. Specifically, the inputs of the model are the user's channel state information, and its outputs are power control policies. The simulation results show that both CNN-SPP and CNN can achieve similar performance to the traditional method up to 95 % accuracy. Furthermore, the combination of CNN and SPP can overcome the limitation on the input size of the conventional CNN method, reducing the number of models that must be trained to just one and applying it to all scenarios regardless of the number of CUEs D2D pairs.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133058190","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865292
A. M. Syarif, K. Hastuti, P. Andono
This research aims to formalize kendhangs play, an instrument that is part of traditional music orchestra from Java called Gamelan. Knowledge acquisition of the kendhang (traditional Javanese drum) play patterns was carried out by involving experts, and the knowledge was then used to set rules and implemented into traditional Javanese drums play automation system. Considering kendhang is a membranophone and an unpitched instrument, note sequences data from the composition, including the sound of each note from several pitched metallophone instruments, are collected as well to support the evaluation of the play in virtual orchestra mode. The Gamelan virtual orchestra automation system consisted of a set of traditional virtual music instruments is designed based on the symbolic representation. The input is a collection of compositions in the form of note sequence data. The system reads beat-by-beat data and calls out sounds. The evaluation was carried out by asking experts to choose the correct automation of kendhang play patterns from several compositions played by the system. The results of the evaluation showed that the proposed system could play kendhangs correctly. All the correct compositions selected by experts are compositions played by the system using the correct kendhangs pattern.
{"title":"Traditional Javanese Membranophone Percussion Play Formalization for Virtual Orchestra Automation","authors":"A. M. Syarif, K. Hastuti, P. Andono","doi":"10.1109/CyberneticsCom55287.2022.9865292","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865292","url":null,"abstract":"This research aims to formalize kendhangs play, an instrument that is part of traditional music orchestra from Java called Gamelan. Knowledge acquisition of the kendhang (traditional Javanese drum) play patterns was carried out by involving experts, and the knowledge was then used to set rules and implemented into traditional Javanese drums play automation system. Considering kendhang is a membranophone and an unpitched instrument, note sequences data from the composition, including the sound of each note from several pitched metallophone instruments, are collected as well to support the evaluation of the play in virtual orchestra mode. The Gamelan virtual orchestra automation system consisted of a set of traditional virtual music instruments is designed based on the symbolic representation. The input is a collection of compositions in the form of note sequence data. The system reads beat-by-beat data and calls out sounds. The evaluation was carried out by asking experts to choose the correct automation of kendhang play patterns from several compositions played by the system. The results of the evaluation showed that the proposed system could play kendhangs correctly. All the correct compositions selected by experts are compositions played by the system using the correct kendhangs pattern.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"532 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130294248","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865484
Erina Fika Noviani, Bayu Kembara, Bakti Anugrah Yudha Pratama, Dyah Ayu Permata Sari, A. M. Shiddiqi, B. J. Santoso
Cloud servers are currently in high demand because of their low cost and wide range of service providers. Businesses use cloud servers because of their quick response times and ability to meet the needs of their customers. Users frequently require recommendations on which service provider best meets their needs. Using the Golang Framework (Gorilla Mux) and an SQLite database, we examine how powerful AWS and GCP are in CPU processing, latency, and throughput. This study aims to help users select a cloud provider based on their needs. JMeter is used to load tests to the APIs. Requests are sent to the API via the GET method and are saved as parameter query data in the SQLite database. We discovered that the success rate on AWS was higher than the success rate on GCP.
{"title":"Performance Analysis of AWS and GCP Cloud Providers","authors":"Erina Fika Noviani, Bayu Kembara, Bakti Anugrah Yudha Pratama, Dyah Ayu Permata Sari, A. M. Shiddiqi, B. J. Santoso","doi":"10.1109/CyberneticsCom55287.2022.9865484","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865484","url":null,"abstract":"Cloud servers are currently in high demand because of their low cost and wide range of service providers. Businesses use cloud servers because of their quick response times and ability to meet the needs of their customers. Users frequently require recommendations on which service provider best meets their needs. Using the Golang Framework (Gorilla Mux) and an SQLite database, we examine how powerful AWS and GCP are in CPU processing, latency, and throughput. This study aims to help users select a cloud provider based on their needs. JMeter is used to load tests to the APIs. Requests are sent to the API via the GET method and are saved as parameter query data in the SQLite database. We discovered that the success rate on AWS was higher than the success rate on GCP.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122662105","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}
Palm oil is a commodity that plays an important role in economic activity. The oil palm tree is capable of producing palm oil and is the most widely consumed vegetable oil in the world. Indonesia is the world's largest producer and exporter of palm oil. The huge potential of the palm oil industry in Indonesia demands the availability of accurate and up-to-date data sources. The latest remote sensing methods have now been widely used in detecting oil palm. We focus on modeling for oil palm detection as well as identifying features that affect oil palm to differentiate it from other land covers. This study compares the performance of the machine learning model with the Random Forest (RF), Xtreme Gradient Boosting (XGBoost), and Classification and Regression Tree (CART) methods. Grid Search is used to perform hyperparameter tuning. The results showed that the XGBoost model gave the best results with an F1 score of 0.90 and an accuracy of 90.97%. The most influential features on the model are B3 (blue). In addition, B3 is also mostly used by the palm oil class. The estimated area of oil palm based on the best model is 14,390.65 Ha, which is 13.18 percent higher than the official data.
{"title":"Machine Learning Approaches using Satellite Data for Oil Palm Area Detection in Pekanbaru City, Riau","authors":"Arie Wahyu Wijayanto, Natasya Afira, Wahidya Nurkarim","doi":"10.1109/CyberneticsCom55287.2022.9865301","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865301","url":null,"abstract":"Palm oil is a commodity that plays an important role in economic activity. The oil palm tree is capable of producing palm oil and is the most widely consumed vegetable oil in the world. Indonesia is the world's largest producer and exporter of palm oil. The huge potential of the palm oil industry in Indonesia demands the availability of accurate and up-to-date data sources. The latest remote sensing methods have now been widely used in detecting oil palm. We focus on modeling for oil palm detection as well as identifying features that affect oil palm to differentiate it from other land covers. This study compares the performance of the machine learning model with the Random Forest (RF), Xtreme Gradient Boosting (XGBoost), and Classification and Regression Tree (CART) methods. Grid Search is used to perform hyperparameter tuning. The results showed that the XGBoost model gave the best results with an F1 score of 0.90 and an accuracy of 90.97%. The most influential features on the model are B3 (blue). In addition, B3 is also mostly used by the palm oil class. The estimated area of oil palm based on the best model is 14,390.65 Ha, which is 13.18 percent higher than the official data.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"260 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115497872","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：