Pub Date : 2021-12-01DOI: 10.1109/ICICyTA53712.2021.9689171
Dafuallah Esameldien Dafaallah Mohamad, A. S. Hashim
Sentiment Analysis have been the most growing topic in the recent years. It is the use of text analysis to examine the opinion or attitude towards a topic. In the past years, there have been a significant growth in the volume of research on Sentiment Analysis, on different detection level such as document level, sentence level and feature level. One of the famous existing sentiment analysis models is Naïve Bayes, a supervised machine learning model. In this study, we identified that the existing Naïve Bayes model trained and tested with incident/accident-related dataset gave an accuracy level of 71%. Additionally, this study describes how the proposed B.R.A.GE. technique has slightly enhanced the sentiment analysis prediction accuracy using incident/accident-related dataset. In conclusion, the proposed B.R.A.G.E technique has not significantly improved the accuracy but hence could be further improvised.
{"title":"Enhanced Sentiment Analysis Technique using Machine Learning (B.R.A.G.E technique)","authors":"Dafuallah Esameldien Dafaallah Mohamad, A. S. Hashim","doi":"10.1109/ICICyTA53712.2021.9689171","DOIUrl":"https://doi.org/10.1109/ICICyTA53712.2021.9689171","url":null,"abstract":"Sentiment Analysis have been the most growing topic in the recent years. It is the use of text analysis to examine the opinion or attitude towards a topic. In the past years, there have been a significant growth in the volume of research on Sentiment Analysis, on different detection level such as document level, sentence level and feature level. One of the famous existing sentiment analysis models is Naïve Bayes, a supervised machine learning model. In this study, we identified that the existing Naïve Bayes model trained and tested with incident/accident-related dataset gave an accuracy level of 71%. Additionally, this study describes how the proposed B.R.A.GE. technique has slightly enhanced the sentiment analysis prediction accuracy using incident/accident-related dataset. In conclusion, the proposed B.R.A.G.E technique has not significantly improved the accuracy but hence could be further improvised.","PeriodicalId":448148,"journal":{"name":"2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114288673","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 : 2021-12-01DOI: 10.1109/ICICyTA53712.2021.9689153
M. Saudi, Azuan Ahmad, M. N. M. Liki, Mohd Afif Husainiamer
Risk management is significant in determining the resiliency of the action taken in any operations in organizations. Different tools can be used to measure risk management. Furthermore, it is essential to identify and evaluate external opportunities, risks, and threats related to daily operations, especially in the healthcare sector. Hence, this paper presents a case study on how political, economic, social, technological, legal, and environmental (especially weather) can affect the COVID-19 transmission by using a risk matrix based on PESTLE analysis and Spearman Rank Correlation Coefficient. The experiment was conducted by using the dataset from COVID-19 Malaysia GitHub and the Timeanddate website. The dataset was evaluated and analyzed using PESTLE and Spearman Rank Correlation, and the findings were kept in a central dashboard repository. Our results showed that weather, gloves, face mask, PPE, retrenchment, work from home, fake news, scamming, and malware are the external factors related to COVID-19. The details of the related issues, risks, and impacts of these external factors are presented in this paper. The weather negatively correlates to the COVID-19 transmission based on the weak positive correlation and a weak negative correlation for this case study. Different risk management techniques and risk assessment tools can be used for future reference in risk management analyses to ensure the organization's operation sustainability.
{"title":"Risk Management Using PESTLE: External Factors Trigger COVID-19 Transmission","authors":"M. Saudi, Azuan Ahmad, M. N. M. Liki, Mohd Afif Husainiamer","doi":"10.1109/ICICyTA53712.2021.9689153","DOIUrl":"https://doi.org/10.1109/ICICyTA53712.2021.9689153","url":null,"abstract":"Risk management is significant in determining the resiliency of the action taken in any operations in organizations. Different tools can be used to measure risk management. Furthermore, it is essential to identify and evaluate external opportunities, risks, and threats related to daily operations, especially in the healthcare sector. Hence, this paper presents a case study on how political, economic, social, technological, legal, and environmental (especially weather) can affect the COVID-19 transmission by using a risk matrix based on PESTLE analysis and Spearman Rank Correlation Coefficient. The experiment was conducted by using the dataset from COVID-19 Malaysia GitHub and the Timeanddate website. The dataset was evaluated and analyzed using PESTLE and Spearman Rank Correlation, and the findings were kept in a central dashboard repository. Our results showed that weather, gloves, face mask, PPE, retrenchment, work from home, fake news, scamming, and malware are the external factors related to COVID-19. The details of the related issues, risks, and impacts of these external factors are presented in this paper. The weather negatively correlates to the COVID-19 transmission based on the weak positive correlation and a weak negative correlation for this case study. Different risk management techniques and risk assessment tools can be used for future reference in risk management analyses to ensure the organization's operation sustainability.","PeriodicalId":448148,"journal":{"name":"2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126482644","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 : 2021-12-01DOI: 10.1109/ICICyTA53712.2021.9689122
Pratama Azmi Atmajaya, Kurniadi Ahmad Wijaya, Alif Adwitiya Pratama, A. F. Ihsan
Group immunity or herd immunity is a crucial condition that determines whether or not the COVID-19 outbreak is controlled or not. Government policies, both in terms of social control and vaccination, are one of the important factors in achieving group immunity. In this paper, an analysis of the dynamics of COVID-19 cases in Indonesia is carried out in correlation with government policies and also the rate of vaccination. We found that vaccination is the most important key in achieving group immunity and this will lead to Indonesian mobility behavior towards COVID-19 from time to time. Government Policies also play a significant effort toward vaccinations starting from the beginning (PSBB) to Emergency PPKM. This study is not considered a new variant that is resistant against vaccines, it may take more time in achieving group immunity if the new variants exist. This analysis leads to a deduction of the time required for Indonesia to achieve herd immunity. This study also estimates the time series of cases and vaccinations using the N-Beats model to strengthen the deductions made from past dynamics. Based on this study, it is estimated that in February 2022 a mask removal policy will be issued and in October 2021 COVID-19 positive cases will be declined.
{"title":"Study on the Dynamics of COVID-19 Cases in Achieving Herd Immunity in Indonesia","authors":"Pratama Azmi Atmajaya, Kurniadi Ahmad Wijaya, Alif Adwitiya Pratama, A. F. Ihsan","doi":"10.1109/ICICyTA53712.2021.9689122","DOIUrl":"https://doi.org/10.1109/ICICyTA53712.2021.9689122","url":null,"abstract":"Group immunity or herd immunity is a crucial condition that determines whether or not the COVID-19 outbreak is controlled or not. Government policies, both in terms of social control and vaccination, are one of the important factors in achieving group immunity. In this paper, an analysis of the dynamics of COVID-19 cases in Indonesia is carried out in correlation with government policies and also the rate of vaccination. We found that vaccination is the most important key in achieving group immunity and this will lead to Indonesian mobility behavior towards COVID-19 from time to time. Government Policies also play a significant effort toward vaccinations starting from the beginning (PSBB) to Emergency PPKM. This study is not considered a new variant that is resistant against vaccines, it may take more time in achieving group immunity if the new variants exist. This analysis leads to a deduction of the time required for Indonesia to achieve herd immunity. This study also estimates the time series of cases and vaccinations using the N-Beats model to strengthen the deductions made from past dynamics. Based on this study, it is estimated that in February 2022 a mask removal policy will be issued and in October 2021 COVID-19 positive cases will be declined.","PeriodicalId":448148,"journal":{"name":"2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131416225","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 : 2021-12-01DOI: 10.1109/ICICyTA53712.2021.9689126
Fathan Abdul Shodiq, Rizka Reza Pahlevi, Parman Sukarno
The concept of the Internet of Things (IoT) is expected to be one of the network solutions of the future. One of the protocols that are often used in IoT communication is the MQTT protocol. The MQTT protocol uses less bandwidth, is light in computing, and is fast in transmission. Thus, the MQTT protocol can be applied to constraint devices. However, the MQTT protocol lacks a security mechanism by default. The use of TLS in the MQTT protocol does not suitable for constraint devices. One of the vulnerabilities encountered in the MQTT protocol is authentication. The lack of authentication causes unauthorized nodes to use MQTT network resources which can lead to over-connection. This study used the JSON Web Token (JWT) to build a token-based authentication mechanism on MQTT as a second authentication factor other than username and password. This was done to prevent the access of unauthenticated nodes to enter the MQTT network. From the validation results, the proposed authentication mechanism is validated for brute force and sniffing attacks. The proposed authentication mechanism validated that there are not exist unauthenticated nodes that can log in into the MQTT network. In addition, the proposed authentication mechanism is validated that the message sent has been encrypted using the XXTEA encryption algorithm to maintain the confidentiality of the communication. The proposed authentication mechanism can be run on constraint devices using 405912 bytes (38% of total program storage) on publisher nodes and 406856 (38% of total program storage) on subscriber nodes.
{"title":"Secure MQTT Authentication and Message Exchange Methods for IoT Constrained Device","authors":"Fathan Abdul Shodiq, Rizka Reza Pahlevi, Parman Sukarno","doi":"10.1109/ICICyTA53712.2021.9689126","DOIUrl":"https://doi.org/10.1109/ICICyTA53712.2021.9689126","url":null,"abstract":"The concept of the Internet of Things (IoT) is expected to be one of the network solutions of the future. One of the protocols that are often used in IoT communication is the MQTT protocol. The MQTT protocol uses less bandwidth, is light in computing, and is fast in transmission. Thus, the MQTT protocol can be applied to constraint devices. However, the MQTT protocol lacks a security mechanism by default. The use of TLS in the MQTT protocol does not suitable for constraint devices. One of the vulnerabilities encountered in the MQTT protocol is authentication. The lack of authentication causes unauthorized nodes to use MQTT network resources which can lead to over-connection. This study used the JSON Web Token (JWT) to build a token-based authentication mechanism on MQTT as a second authentication factor other than username and password. This was done to prevent the access of unauthenticated nodes to enter the MQTT network. From the validation results, the proposed authentication mechanism is validated for brute force and sniffing attacks. The proposed authentication mechanism validated that there are not exist unauthenticated nodes that can log in into the MQTT network. In addition, the proposed authentication mechanism is validated that the message sent has been encrypted using the XXTEA encryption algorithm to maintain the confidentiality of the communication. The proposed authentication mechanism can be run on constraint devices using 405912 bytes (38% of total program storage) on publisher nodes and 406856 (38% of total program storage) on subscriber nodes.","PeriodicalId":448148,"journal":{"name":"2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116217322","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 : 2021-12-01DOI: 10.1109/ICICyTA53712.2021.9689203
Rocky Yefrenes Dillak, P. Sudarmadji
Pap smear test is a standard examination for cervical cancer diagnosis. However, this method is very time-consuming and is very subjective in interpreting an image. This paper developed a system to diagnose the cervical cancer phase based on pap smear images. Five classes were investigated, namely: normal, precancerous (CIN1, CIN2, and CIN3), and malignant. The flow of the model is as follows: (i) pre-processes image using amoeba median filter and Gaussian filter (ii) nuclei detection, and segmentation (iii) extracts characteristics image using texture and shape analysis (iv) classify the pap smear image using Ridge Polynomial Neural Network pre-trained by Chaos Optimization. Based on experiments conducted, the proposed method could detect and classify the pap smear images with a sensitivity of 96.8%, specificity of 97.8%, and accuracy of 97%.
{"title":"Cervical Cancer Classification Using Improved Ridge Polynomial Neural Network","authors":"Rocky Yefrenes Dillak, P. Sudarmadji","doi":"10.1109/ICICyTA53712.2021.9689203","DOIUrl":"https://doi.org/10.1109/ICICyTA53712.2021.9689203","url":null,"abstract":"Pap smear test is a standard examination for cervical cancer diagnosis. However, this method is very time-consuming and is very subjective in interpreting an image. This paper developed a system to diagnose the cervical cancer phase based on pap smear images. Five classes were investigated, namely: normal, precancerous (CIN1, CIN2, and CIN3), and malignant. The flow of the model is as follows: (i) pre-processes image using amoeba median filter and Gaussian filter (ii) nuclei detection, and segmentation (iii) extracts characteristics image using texture and shape analysis (iv) classify the pap smear image using Ridge Polynomial Neural Network pre-trained by Chaos Optimization. Based on experiments conducted, the proposed method could detect and classify the pap smear images with a sensitivity of 96.8%, specificity of 97.8%, and accuracy of 97%.","PeriodicalId":448148,"journal":{"name":"2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)","volume":"89 40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129806662","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 : 2021-12-01DOI: 10.1109/ICICyTA53712.2021.9689105
Noor Farahdila Abdullah, T. Tang, E. Ho
An outstanding open problem in neuroscience is to understand how the brain reacts towards certain stimuli, capable of producing and sustaining in complex spatiotemporal dynamics. Therefore, human brain signals from the electroencephalography (EEG) apparatus are time-varying signals and provide the temporal resolution which describe the dynamic changes in brain. The different positions of electrodes give different time-varying signals. A dynamic correlation between these signals may exist. We conduct the study to identify the group of attractors which occurred during resting state due to the dynamic changes in human brain. To describe the pattern of dynamic, we refer to chaos theory. First, the simulation signals were executed using the Rössler model where this system could produce complex behavior over a range of parameters, thus being capable of capturing multiple observables at the same time. The level of correlation within the generated attractors was defined. By using an EEG signal, the triplet EEG trajectory was generated from the combination of the Binomial matrix of each electrode and each frequency band by cutting the time-series signal throughout the 2s of data. Then the types of attractors that occurred in the 2s of data for each Rs-EC (Resting state -Eyes Close) were observed. Thus, the correlation coefficient of each combination triplet trajectory of EEG signal was measured. Our observations support the view of the brain as a non-equilibrium system in which multistability may arise due to the attractor. The need to identify and classify the human EEG signal into types of attractors was highlighted.
{"title":"Discrete Attractor Pattern Recognition During Resting State in EEG Signal","authors":"Noor Farahdila Abdullah, T. Tang, E. Ho","doi":"10.1109/ICICyTA53712.2021.9689105","DOIUrl":"https://doi.org/10.1109/ICICyTA53712.2021.9689105","url":null,"abstract":"An outstanding open problem in neuroscience is to understand how the brain reacts towards certain stimuli, capable of producing and sustaining in complex spatiotemporal dynamics. Therefore, human brain signals from the electroencephalography (EEG) apparatus are time-varying signals and provide the temporal resolution which describe the dynamic changes in brain. The different positions of electrodes give different time-varying signals. A dynamic correlation between these signals may exist. We conduct the study to identify the group of attractors which occurred during resting state due to the dynamic changes in human brain. To describe the pattern of dynamic, we refer to chaos theory. First, the simulation signals were executed using the Rössler model where this system could produce complex behavior over a range of parameters, thus being capable of capturing multiple observables at the same time. The level of correlation within the generated attractors was defined. By using an EEG signal, the triplet EEG trajectory was generated from the combination of the Binomial matrix of each electrode and each frequency band by cutting the time-series signal throughout the 2s of data. Then the types of attractors that occurred in the 2s of data for each Rs-EC (Resting state -Eyes Close) were observed. Thus, the correlation coefficient of each combination triplet trajectory of EEG signal was measured. Our observations support the view of the brain as a non-equilibrium system in which multistability may arise due to the attractor. The need to identify and classify the human EEG signal into types of attractors was highlighted.","PeriodicalId":448148,"journal":{"name":"2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124270093","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 : 2021-12-01DOI: 10.1109/ICICyTA53712.2021.9689182
Adit F. Andi, H. Nuha, M. Abdurohman
The process of grouping or sorting fruits that is carried out at this time is still using the manual method by humans, basically humans have properties that make the process of grouping or sorting can take a long time. Based on these conditions, a sorting machine is needed that has the ability to detect and group fruits based on color automatically and faster. So it is expected that the manufacture of this machine can assist in productivity in the process of grouping or sorting fruits. The system is made in the form of a sorting machine that will classify the colors of each fruit using a TCS3200 sensor as a color detector and all these processes will be controlled using Arduino with an ATmega328 microcontroller.
{"title":"Fruit Ripeness Sorting Machine using Color Sensors","authors":"Adit F. Andi, H. Nuha, M. Abdurohman","doi":"10.1109/ICICyTA53712.2021.9689182","DOIUrl":"https://doi.org/10.1109/ICICyTA53712.2021.9689182","url":null,"abstract":"The process of grouping or sorting fruits that is carried out at this time is still using the manual method by humans, basically humans have properties that make the process of grouping or sorting can take a long time. Based on these conditions, a sorting machine is needed that has the ability to detect and group fruits based on color automatically and faster. So it is expected that the manufacture of this machine can assist in productivity in the process of grouping or sorting fruits. The system is made in the form of a sorting machine that will classify the colors of each fruit using a TCS3200 sensor as a color detector and all these processes will be controlled using Arduino with an ATmega328 microcontroller.","PeriodicalId":448148,"journal":{"name":"2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115315686","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 : 2021-12-01DOI: 10.1109/ICICyTA53712.2021.9689176
Nurrahma Nurrahma, Rahadian Yusuf, A. Prihatmanto
Sign language is a method of communication using hand gestures that are usually used by Deaf people. In Indonesia, there are 2 types of sign language, namely SIBI and BISINDO. However, in everyday life, BISINDO is more often used. Communication gaps often occur between Deaf people and hearing people. So that we need media that can bridge their communication. one of the technologies that can be used is SLR (Sign Language Recognition). SLR itself has various kinds of approaches, one of which is a vision-based SLR. Vision-based SLR has an advantage, such as not requiring a special device attached to the hand, but simply making gestures with bare hands in front of the camera. In this study, we created a machine learning model with a vision-based SLR approach. The model we created was using the CNN (Convolutional Neural Network) architecture. The CNN model was trained and tested on the BISINDO alphabet (A-Z) dataset that we created on our own. This model achieves an accuracy of 99.28% on validation accuracy, 98.57% on testing accuracy, and 98.07% on real-time testing accuracy.
{"title":"Indonesian Sign Language Fingerspelling Recognition using Vision-based Machine Learning","authors":"Nurrahma Nurrahma, Rahadian Yusuf, A. Prihatmanto","doi":"10.1109/ICICyTA53712.2021.9689176","DOIUrl":"https://doi.org/10.1109/ICICyTA53712.2021.9689176","url":null,"abstract":"Sign language is a method of communication using hand gestures that are usually used by Deaf people. In Indonesia, there are 2 types of sign language, namely SIBI and BISINDO. However, in everyday life, BISINDO is more often used. Communication gaps often occur between Deaf people and hearing people. So that we need media that can bridge their communication. one of the technologies that can be used is SLR (Sign Language Recognition). SLR itself has various kinds of approaches, one of which is a vision-based SLR. Vision-based SLR has an advantage, such as not requiring a special device attached to the hand, but simply making gestures with bare hands in front of the camera. In this study, we created a machine learning model with a vision-based SLR approach. The model we created was using the CNN (Convolutional Neural Network) architecture. The CNN model was trained and tested on the BISINDO alphabet (A-Z) dataset that we created on our own. This model achieves an accuracy of 99.28% on validation accuracy, 98.57% on testing accuracy, and 98.07% on real-time testing accuracy.","PeriodicalId":448148,"journal":{"name":"2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123048176","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}
Forest and land fires impact the destruction of ecosystems and destroy flora and fauna. Forest fires haze can also disrupt the transportation sector, especially aviation transportation. Forest fire is a recurring disaster problem in Indonesia, especially on Sumatra island. That requires solutions to overcome it, one of which is the monitoring hotspot. A hotspot is an object on the earth's surface represented in a point with certain coordinates that have relatively higher temperatures than its surrounding areas. This study classified hotspots using the C5.0 algorithm to generate forest fire prediction model. The dataset is divided into two categories, namely the explanatory factors representing four region characteristics (cities, river, road, and land cover) and three climate data (rainfall, temperature, and wind speed), and the target class representing the hotspot class (true/false) in the study area, namely Indragiri Hulu Regency, Riau Province, Indonesia. The result is forest fire prediction model that obtained an accuracy of 98.47% on training data, while on test data of 98.68%. The resulting rules are 80 rules excluding three attributes, river, road, and wind speed. The rules can be used as information on preventing forest fires based on the characteristics of the land and the weather of an area.
森林和土地火灾对生态系统和动植物造成破坏。森林火灾雾霾也会扰乱交通运输部门，尤其是航空运输。森林火灾在印度尼西亚是一个反复发生的灾害问题，尤其是在苏门答腊岛。这需要解决方案来克服它，其中之一是监测热点。热点是地球表面上的一个物体，用特定的坐标表示一个点，这个点的温度相对高于它周围的区域。本研究采用C5.0算法对热点进行分类，生成森林火灾预测模型。数据集分为两类，即代表四个区域特征(城市、河流、道路和土地覆盖)的解释因子和三个气候数据(降雨、温度和风速)，目标类代表研究区域的热点类(真/假)，即印度尼西亚廖内省Indragiri Hulu Regency。结果表明，该模型对训练数据的预测准确率为98.47%，对测试数据的预测准确率为98.68%。由此产生的规则是80条规则，排除了河流、道路、风速三个属性。这些规则可以作为根据一个地区的土地和天气特征预防森林火灾的信息。
{"title":"Hotspot Classification for Forest Fire Prediction using C5.0 Algorithm","authors":"Andi Nurkholis, Styawati, Debby Alita, Adi Sucipto, Muchammad Chanafy, Zahrina Amalia","doi":"10.1109/ICICyTA53712.2021.9689085","DOIUrl":"https://doi.org/10.1109/ICICyTA53712.2021.9689085","url":null,"abstract":"Forest and land fires impact the destruction of ecosystems and destroy flora and fauna. Forest fires haze can also disrupt the transportation sector, especially aviation transportation. Forest fire is a recurring disaster problem in Indonesia, especially on Sumatra island. That requires solutions to overcome it, one of which is the monitoring hotspot. A hotspot is an object on the earth's surface represented in a point with certain coordinates that have relatively higher temperatures than its surrounding areas. This study classified hotspots using the C5.0 algorithm to generate forest fire prediction model. The dataset is divided into two categories, namely the explanatory factors representing four region characteristics (cities, river, road, and land cover) and three climate data (rainfall, temperature, and wind speed), and the target class representing the hotspot class (true/false) in the study area, namely Indragiri Hulu Regency, Riau Province, Indonesia. The result is forest fire prediction model that obtained an accuracy of 98.47% on training data, while on test data of 98.68%. The resulting rules are 80 rules excluding three attributes, river, road, and wind speed. The rules can be used as information on preventing forest fires based on the characteristics of the land and the weather of an area.","PeriodicalId":448148,"journal":{"name":"2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124724866","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 : 2021-12-01DOI: 10.1109/ICICyTA53712.2021.9689093
Muhammad Umair, M. Hashmani
Wind waves are generated by winds blowing over long stretches of the sea surface. They are considered as one of the important elements of marine weather. A sea state describes prevailing wind wave conditions. Due to its constant presence, it is important to classify the sea state for safety and optimal operations of coastal and offshore structures, maritime traffic, and recreational activities etc. The Beaufort wind force scale provides an empirical solution for sea state classification. Additionally, wave parameters acquired from sea buoys can be used to identify the sea state. However, the deployment and maintenance costs of buoys are high. Recent advancements in deep learning-based image classification can lead toward the development of low-cost sea state classification solutions. However, to train and test such models, required visual-range sea state image dataset is not yet publicly available. Hence, the authors have proposed the development of said dataset, which is currently in its later stages of construction. In this paper, we present general observations, design considerations, and guidelines formulated during the development of the visual-range sea state image dataset. The paper discusses the important factors related to sensor and field observation site selection, data acquisition considerations, data processing, and the manual sea state identification mechanism. The paper also provides guidelines for application specific augmentation policy development and recommends a baseline number of representative instances per class for the dataset. The research community can refer to the presented work for further research in the development of sea state image datasets.
{"title":"Towards Development of Visual-Range Sea State Image Dataset for Deep Learning Models","authors":"Muhammad Umair, M. Hashmani","doi":"10.1109/ICICyTA53712.2021.9689093","DOIUrl":"https://doi.org/10.1109/ICICyTA53712.2021.9689093","url":null,"abstract":"Wind waves are generated by winds blowing over long stretches of the sea surface. They are considered as one of the important elements of marine weather. A sea state describes prevailing wind wave conditions. Due to its constant presence, it is important to classify the sea state for safety and optimal operations of coastal and offshore structures, maritime traffic, and recreational activities etc. The Beaufort wind force scale provides an empirical solution for sea state classification. Additionally, wave parameters acquired from sea buoys can be used to identify the sea state. However, the deployment and maintenance costs of buoys are high. Recent advancements in deep learning-based image classification can lead toward the development of low-cost sea state classification solutions. However, to train and test such models, required visual-range sea state image dataset is not yet publicly available. Hence, the authors have proposed the development of said dataset, which is currently in its later stages of construction. In this paper, we present general observations, design considerations, and guidelines formulated during the development of the visual-range sea state image dataset. The paper discusses the important factors related to sensor and field observation site selection, data acquisition considerations, data processing, and the manual sea state identification mechanism. The paper also provides guidelines for application specific augmentation policy development and recommends a baseline number of representative instances per class for the dataset. The research community can refer to the presented work for further research in the development of sea state image datasets.","PeriodicalId":448148,"journal":{"name":"2021 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130321690","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：