Novitasari Arlim, Siti Kania Kushadiani, S. Riyanto, Rodiah Rodiah, Rini Arianty, Maukar Maukar, Shidiq Al Hakim, A. Siagian
Since sarcasm has inverse meaning from what is said or written, it is very hard to detect sarcasm. Therefore, detecting sarcasm is an important task in Natural Language Processing (NLP) field. In this study, we use interjection, intensifier, capital letters, elongated words, and punctuation marks as hyperbole features to detect sarcasm in Indonesian tweets. Particularly, these hyperbole features are utilized by Support Vector Machine (SVM), Random Forest (RF), and RF+Bagging to classify Indonesian tweets in our testing data as sarcasm or not-sarcasm. English tweets obtained from Kaggle and SemEval are employed as our training data, while Indonesian tweets obtained from Drone Emprit are used as the testing data. Our experimental results show that our model with hyperbole features classifies more the tweets in the testing data as sarcasm than that without hyperbole ones. Our observation indicates that using hyperbole features could contribute well to detecting sarcasm.
{"title":"Sarcasm Detection in Indonesian Tweets Using Hyperbole Features","authors":"Novitasari Arlim, Siti Kania Kushadiani, S. Riyanto, Rodiah Rodiah, Rini Arianty, Maukar Maukar, Shidiq Al Hakim, A. Siagian","doi":"10.1145/3575882.3575908","DOIUrl":"https://doi.org/10.1145/3575882.3575908","url":null,"abstract":"Since sarcasm has inverse meaning from what is said or written, it is very hard to detect sarcasm. Therefore, detecting sarcasm is an important task in Natural Language Processing (NLP) field. In this study, we use interjection, intensifier, capital letters, elongated words, and punctuation marks as hyperbole features to detect sarcasm in Indonesian tweets. Particularly, these hyperbole features are utilized by Support Vector Machine (SVM), Random Forest (RF), and RF+Bagging to classify Indonesian tweets in our testing data as sarcasm or not-sarcasm. English tweets obtained from Kaggle and SemEval are employed as our training data, while Indonesian tweets obtained from Drone Emprit are used as the testing data. Our experimental results show that our model with hyperbole features classifies more the tweets in the testing data as sarcasm than that without hyperbole ones. Our observation indicates that using hyperbole features could contribute well to detecting sarcasm.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130383688","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}
Along with the development of drone technology, it is now possible to implement LoRa technology vertically, which can be used as a mobile LoRa repeater or tracker. We introduce the initial study and performance analysis of vertical LoRa communication using drones as forest repeater or trackers in monitoring systems. In addition, several test methods were also developed and carried out to determine whether using LoRa with drones vertically could increase the reception range of LoRa signals, particularly in forest areas considering vegetation density, signal propagation, multipath effect. From the results obtained in the experiments, the vertical LoRa system proved to have a better RSSI value than the horizontal LoRa system in forest areas. Using vertical LoRa at a distance of 100 meters shows a better RSSI value with a difference up to 16.24 dBm than the horizontal LoRa. In the forest with higher density, we got a variation of the RSSI measurement result of 4.67 to 4.73 dBm caused by the multipath effect. To conclude, the vertical LoRa using drones can improve the LoRa telecommunication coverage area and is possible to use as LoRa repeater or trackers.
{"title":"Initial Study and Performance Analysis of Vertical LoRa Using Drone in Forest Areas","authors":"Dimas Biwas Putra, Bondan Suwandi, Riski Fitriani, Fito Herminawan, Yoga Wibawa, Moh Samudro","doi":"10.1145/3575882.3575889","DOIUrl":"https://doi.org/10.1145/3575882.3575889","url":null,"abstract":"Along with the development of drone technology, it is now possible to implement LoRa technology vertically, which can be used as a mobile LoRa repeater or tracker. We introduce the initial study and performance analysis of vertical LoRa communication using drones as forest repeater or trackers in monitoring systems. In addition, several test methods were also developed and carried out to determine whether using LoRa with drones vertically could increase the reception range of LoRa signals, particularly in forest areas considering vegetation density, signal propagation, multipath effect. From the results obtained in the experiments, the vertical LoRa system proved to have a better RSSI value than the horizontal LoRa system in forest areas. Using vertical LoRa at a distance of 100 meters shows a better RSSI value with a difference up to 16.24 dBm than the horizontal LoRa. In the forest with higher density, we got a variation of the RSSI measurement result of 4.67 to 4.73 dBm caused by the multipath effect. To conclude, the vertical LoRa using drones can improve the LoRa telecommunication coverage area and is possible to use as LoRa repeater or trackers.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128495558","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}
Y. Andrian, La Ode Muhammad Musafar Kilowasid, Siti Kurniawati Fatimah
Indonesia needs a satellite surveillance system for tracking its trajectory in real-time. Furthermore, this system is very useful in supporting the decision support system (DSS) through re-entry objects observation that has the potential to fall into Indonesian territories. System development leveraging a web-based application that can be easily accessed on various platforms. Commonly, applications rely on databases as the fundamental infrastructure for providing data input or storing the output produced by the model. Therefore, the proper database concept will enhance the application's reliability. This paper discusses the development of an orbital database system to support satellite surveillance applications. Our method combines relational and non-relational database approaches in collecting, querying, and writing data. We use a relational approach to store orbital parameter data from Space-Track API and a non-relational approach to record data yielded by the SGP4 model. As a result, this paper shows that our system can provide accessible data for the tracking application and display satellite trajectories map one hour ahead. In addition, we also present the orbital parameter information through a web-based catalog list providing detailed object properties.
{"title":"The Prototype of Orbital Database System for Satellite Tracking Information","authors":"Y. Andrian, La Ode Muhammad Musafar Kilowasid, Siti Kurniawati Fatimah","doi":"10.1145/3575882.3575923","DOIUrl":"https://doi.org/10.1145/3575882.3575923","url":null,"abstract":"Indonesia needs a satellite surveillance system for tracking its trajectory in real-time. Furthermore, this system is very useful in supporting the decision support system (DSS) through re-entry objects observation that has the potential to fall into Indonesian territories. System development leveraging a web-based application that can be easily accessed on various platforms. Commonly, applications rely on databases as the fundamental infrastructure for providing data input or storing the output produced by the model. Therefore, the proper database concept will enhance the application's reliability. This paper discusses the development of an orbital database system to support satellite surveillance applications. Our method combines relational and non-relational database approaches in collecting, querying, and writing data. We use a relational approach to store orbital parameter data from Space-Track API and a non-relational approach to record data yielded by the SGP4 model. As a result, this paper shows that our system can provide accessible data for the tracking application and display satellite trajectories map one hour ahead. In addition, we also present the orbital parameter information through a web-based catalog list providing detailed object properties.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121623891","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}
P. Khotimah, Andria Arisal, Dwi Alfianti, Nabila Putri, Ekasari Nugraheni, D. Riswantini
Small-Medium Enterprises (SMEs) do not have the resources to carry out large-scale promotions. SMEs can use social media to build brands and promote their products to the wider community using social media. Engagement between SMEs and their followers in social media is considered important for evaluating SMEs’ performance as indicated by the interaction such as the number of responses or reactions to published posts. This paper aims to conduct an analysis of one of the followers’ interactions (number of likes) on different types of SME posts; branding, promotion, and testimonial. We do the analysis of Instagram posts by SMEs in the culinary sector located in Bandung. Their posts and their followers’ interactions are collected and analyzed using time series visualization to understand the dynamic of follower interactions towards the posts. Additionally, we use predictive analysis to figure out the number of expected interactions on the specific type of posts using linear regression. Our prediction model gives fairly low error values (mean absolute error-MAE = 6.524 and root mean square error-RMSE: 9.780) and a good R-squared value of 0.783. An interesting insight from the prediction results suggested that testimonial posts will draw more interaction compared to promotion posts.
中小企业没有进行大规模推广的资源。中小企业可以利用社交媒体建立品牌，并通过社交媒体向更广泛的社区推广自己的产品。中小企业与其关注者在社交媒体上的互动被认为是评估中小企业绩效的重要因素，如对发布的帖子的回复或反应的数量。本文旨在分析关注者在不同类型的中小企业帖子上的互动(点赞数);品牌推广、推广和推荐。我们对万隆烹饪行业中小企业的Instagram帖子进行了分析。他们的帖子和他们的粉丝互动被收集和分析，使用时间序列可视化来了解粉丝对帖子的互动动态。此外，我们使用预测分析来计算特定类型的帖子使用线性回归的预期相互作用的数量。我们的预测模型给出了相当低的误差值(平均绝对误差- mae = 6.524，均方根误差- rmse: 9.780)和良好的r平方值0.783。从预测结果中得出的一个有趣的见解表明，与推广帖子相比，推荐帖子将吸引更多的互动。
{"title":"Engagement Analysis on Local Small-Medium Enterprises: Case Study in Bandung","authors":"P. Khotimah, Andria Arisal, Dwi Alfianti, Nabila Putri, Ekasari Nugraheni, D. Riswantini","doi":"10.1145/3575882.3575944","DOIUrl":"https://doi.org/10.1145/3575882.3575944","url":null,"abstract":"Small-Medium Enterprises (SMEs) do not have the resources to carry out large-scale promotions. SMEs can use social media to build brands and promote their products to the wider community using social media. Engagement between SMEs and their followers in social media is considered important for evaluating SMEs’ performance as indicated by the interaction such as the number of responses or reactions to published posts. This paper aims to conduct an analysis of one of the followers’ interactions (number of likes) on different types of SME posts; branding, promotion, and testimonial. We do the analysis of Instagram posts by SMEs in the culinary sector located in Bandung. Their posts and their followers’ interactions are collected and analyzed using time series visualization to understand the dynamic of follower interactions towards the posts. Additionally, we use predictive analysis to figure out the number of expected interactions on the specific type of posts using linear regression. Our prediction model gives fairly low error values (mean absolute error-MAE = 6.524 and root mean square error-RMSE: 9.780) and a good R-squared value of 0.783. An interesting insight from the prediction results suggested that testimonial posts will draw more interaction compared to promotion posts.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122285962","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}
Melva Hilda Stephanie Situmorang, B. I. Nasution, M. E. Aminanto, Y. Nugraha, J. Kanggrawan
This study aims to compare the Air Pollution Index (API) clustering between fuzzy c-means (FCM) with gaussian mixture model. This study used air quality data on each parameter in 2019-2020 from five monitoring stations, that is Bundaran HI (DKI1), Kelapa Gading (DKI2), Jagakarsa (DKI3), Lubang Buaya (DKI4), and Kebon Jeruk (DKI5). Determination of the optimum cluster number on Fuzzy C-Means based on Partition Coefficient (PC), Classification Entropy (CE), Separation Index (SI), Silhouette Index, and Effectiveness. The optimum cluster number in the Gaussian Mixture Model is based on BIC and Silhouette Index values. Almost all Silhouette values on Fuzzy C-Means are more significant than the Silhouette Gaussian Mixture Model. Fuzzy C-Means is more suitable for clustering Jakarta Air Pollution Index (API) than The Gaussian Mixture Model method.
{"title":"Air Pollution Index (API) Analysis at Jakarta in 2019-2020 using Fuzzy C-Means and Gaussian Mixture Model","authors":"Melva Hilda Stephanie Situmorang, B. I. Nasution, M. E. Aminanto, Y. Nugraha, J. Kanggrawan","doi":"10.1145/3575882.3575916","DOIUrl":"https://doi.org/10.1145/3575882.3575916","url":null,"abstract":"This study aims to compare the Air Pollution Index (API) clustering between fuzzy c-means (FCM) with gaussian mixture model. This study used air quality data on each parameter in 2019-2020 from five monitoring stations, that is Bundaran HI (DKI1), Kelapa Gading (DKI2), Jagakarsa (DKI3), Lubang Buaya (DKI4), and Kebon Jeruk (DKI5). Determination of the optimum cluster number on Fuzzy C-Means based on Partition Coefficient (PC), Classification Entropy (CE), Separation Index (SI), Silhouette Index, and Effectiveness. The optimum cluster number in the Gaussian Mixture Model is based on BIC and Silhouette Index values. Almost all Silhouette values on Fuzzy C-Means are more significant than the Silhouette Gaussian Mixture Model. Fuzzy C-Means is more suitable for clustering Jakarta Air Pollution Index (API) than The Gaussian Mixture Model method.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130964733","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}
Zaid Cahya, D. Cahya, T. Nugroho, Ardani Zuhri, W. Agusta
Fruit grading is a significant problem in the fruit industry because each maturity stage of the fruit represents a distinct economic worth. Banana is one of the most mass-produced fruits that must be visually classified. However, because human eye perception varies, precise classification using a machine is necessary to standardise the grading system. This research develops a four-layered CNN deep-learning model to classify bananas into seven ripening stages. To train the model, we employed Mazen and Nashat dataset and expanded it using data augmentation techniques. As a baseline, we trained a basic four-layer CNN model and achieved 88.2% of accuracy in fine-grained categorisation due to the similarity of the adjacent ripening class. To enhance the accuracy of our basic model, we applied a parameter optimisation approach to get the best hyper-parameters for the profound banana ripeness indicator. As a result, the time-constrained parameter optimisation method that we utilised successfully increased the model accuracy up to 91.2% and the F1 score at 90.5%, which is satisfactory for fine-grained banana classification compared to the previous research.
{"title":"CNN Model with Parameter Optimisation for Fine-Grained Banana Ripening Stage Classification","authors":"Zaid Cahya, D. Cahya, T. Nugroho, Ardani Zuhri, W. Agusta","doi":"10.1145/3575882.3575900","DOIUrl":"https://doi.org/10.1145/3575882.3575900","url":null,"abstract":"Fruit grading is a significant problem in the fruit industry because each maturity stage of the fruit represents a distinct economic worth. Banana is one of the most mass-produced fruits that must be visually classified. However, because human eye perception varies, precise classification using a machine is necessary to standardise the grading system. This research develops a four-layered CNN deep-learning model to classify bananas into seven ripening stages. To train the model, we employed Mazen and Nashat dataset and expanded it using data augmentation techniques. As a baseline, we trained a basic four-layer CNN model and achieved 88.2% of accuracy in fine-grained categorisation due to the similarity of the adjacent ripening class. To enhance the accuracy of our basic model, we applied a parameter optimisation approach to get the best hyper-parameters for the profound banana ripeness indicator. As a result, the time-constrained parameter optimisation method that we utilised successfully increased the model accuracy up to 91.2% and the F1 score at 90.5%, which is satisfactory for fine-grained banana classification compared to the previous research.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132251928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Rezaldi, Hendrik Napitupulu, E. Husni, E. Prakasa
This paper discusses the understanding of augmented reality (AR), types of AR, its current AR use, and reviews the used AR specifically for ship safety navigation. The paper will make recommendations on what type of AR products are possible to develop. The AR can be used to support maritime navigation applications in Indonesia. The method used is primary literature review analysis through Systematic Literature Review (SLR) from thirty articles. Results of the literature review show that four types of AR based on the projection techniques. The types are a marker-based AR (image recognition), markerless AR, projection-based AR (hologram), and super impositing-based AR (object recognition). Currently, in various countries, AR products have begun to be developed for maritime navigation applications such as AR social to determine point of interest (POI), AR navigation, AR safety, and an immersive underwater world. From the literature review analysis results, this paper recommends that the right AR products based on the projection technique are markerless AR and projection-based AR types. However, in the future, it is necessary to make an in-depth study of the need for AR products for maritime navigation in Indonesia. The products include traditional navigation tools, navigational aid, and simulations for marine navigation training and then be implemented so that the AR products for maritime navigation that are produced are truly in accordance with the needs of ship crew and policymakers in Indonesia.
{"title":"The Recommendation Augmented Reality: For Maritime Navigation Applications in Indonesia","authors":"M. Rezaldi, Hendrik Napitupulu, E. Husni, E. Prakasa","doi":"10.1145/3575882.3575930","DOIUrl":"https://doi.org/10.1145/3575882.3575930","url":null,"abstract":"This paper discusses the understanding of augmented reality (AR), types of AR, its current AR use, and reviews the used AR specifically for ship safety navigation. The paper will make recommendations on what type of AR products are possible to develop. The AR can be used to support maritime navigation applications in Indonesia. The method used is primary literature review analysis through Systematic Literature Review (SLR) from thirty articles. Results of the literature review show that four types of AR based on the projection techniques. The types are a marker-based AR (image recognition), markerless AR, projection-based AR (hologram), and super impositing-based AR (object recognition). Currently, in various countries, AR products have begun to be developed for maritime navigation applications such as AR social to determine point of interest (POI), AR navigation, AR safety, and an immersive underwater world. From the literature review analysis results, this paper recommends that the right AR products based on the projection technique are markerless AR and projection-based AR types. However, in the future, it is necessary to make an in-depth study of the need for AR products for maritime navigation in Indonesia. The products include traditional navigation tools, navigational aid, and simulations for marine navigation training and then be implemented so that the AR products for maritime navigation that are produced are truly in accordance with the needs of ship crew and policymakers in Indonesia.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133119255","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 COVID-19 pandemic has influenced many aspects of human life, including working environments. Some research finds that there is a tendency to the increase of energy and CO2 emissions of large office buildings in developed countries, such as US and Europe’s top five economics, post-pandemic. Therefore, advanced heating, ventilation and air-conditioning (HVAC) technology that can reduce energy consumption in the building sector will yield a significant impact on the total national energy consumption. Many buildings equipped with conventional control in their HVAC control systems, such as PI or PID controls. Such controllers have drawbacks like unable to handle cross-coupling nature and constraints in a HVAC system. Conversely, model predictive control (MPC)—which belongs to advanced control—has the advantages when dealing with the system with constraints and uncertainties as it can take into account them in its optimization control problem formulation. This paper derived mathematically an industrial HVAC system based on Hammerstein-bilinear model—a model consists of a static nonlinearity followed by a dynamic bilinear subsystem. The obtained linear output-error (OE) models are subsequently used as plant models in the MPC design. The MPC controller performance is quite superior and proven to be able to meet the desired control objective (keeping the zone temperature in range of . In addition, the MPC controller gives more economic energy consumption (about save) than the PI one both for temperature and humidity control loop.
{"title":"Advanced Control for Hammerstein-bilinear HVAC System","authors":"I. Kasiyanto","doi":"10.1145/3575882.3575893","DOIUrl":"https://doi.org/10.1145/3575882.3575893","url":null,"abstract":"The COVID-19 pandemic has influenced many aspects of human life, including working environments. Some research finds that there is a tendency to the increase of energy and CO2 emissions of large office buildings in developed countries, such as US and Europe’s top five economics, post-pandemic. Therefore, advanced heating, ventilation and air-conditioning (HVAC) technology that can reduce energy consumption in the building sector will yield a significant impact on the total national energy consumption. Many buildings equipped with conventional control in their HVAC control systems, such as PI or PID controls. Such controllers have drawbacks like unable to handle cross-coupling nature and constraints in a HVAC system. Conversely, model predictive control (MPC)—which belongs to advanced control—has the advantages when dealing with the system with constraints and uncertainties as it can take into account them in its optimization control problem formulation. This paper derived mathematically an industrial HVAC system based on Hammerstein-bilinear model—a model consists of a static nonlinearity followed by a dynamic bilinear subsystem. The obtained linear output-error (OE) models are subsequently used as plant models in the MPC design. The MPC controller performance is quite superior and proven to be able to meet the desired control objective (keeping the zone temperature in range of . In addition, the MPC controller gives more economic energy consumption (about save) than the PI one both for temperature and humidity control loop.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"93 Pt A 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122657042","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}
Abdurrakhman Prasetyadi, M. Rezaldi, Ambar Yoganingrum, N. Hanifa, W. Kongko
Making 3D animation using an Unmanned Aerial Vehicle (UAV) – photogrammetric technique requires appropriate specifications in taking serial aerial photographs. This paper aims to compare two specifications for orthomosaic image capture. The study focuses on the comparison of Close Range Photogrammetry (CRP) and Ground Control Points (GCP) specifications. After analyzing the orthomosaic image using the visual analytics method, it was found that the combined of both specifications produced better image quality for 3D Animation Modeling.
{"title":"UAV-Photogrammetry Specification for Generating 3D-Orthomosaic in Case of 3D Animation Modeling","authors":"Abdurrakhman Prasetyadi, M. Rezaldi, Ambar Yoganingrum, N. Hanifa, W. Kongko","doi":"10.1145/3575882.3575933","DOIUrl":"https://doi.org/10.1145/3575882.3575933","url":null,"abstract":"Making 3D animation using an Unmanned Aerial Vehicle (UAV) – photogrammetric technique requires appropriate specifications in taking serial aerial photographs. This paper aims to compare two specifications for orthomosaic image capture. The study focuses on the comparison of Close Range Photogrammetry (CRP) and Ground Control Points (GCP) specifications. After analyzing the orthomosaic image using the visual analytics method, it was found that the combined of both specifications produced better image quality for 3D Animation Modeling.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123860059","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}
Josua Geovani Pinem, Aulia Haritsuddin Karisma Muhammad Subekti, G. Wibowanto, Siti Shaleha, Muhammad Reza Alfin, Agung Septiadi, Elvira Nurfadhilah, Dian Isnaeni Nurul Afra, J. Muliadi, Agung Santosa, M. T. Uliniansyah, Asril Jarin, Andi Djalal Latief, Gunarso, Hammam Riza
The increasing use of Twitter for conveying the general public's sentiment toward a specific public policy generates pros and cons and has led to much research in sentiment analysis. Instead of exploring the most suitable classifier for a sentiment analysis model individually, there is a trend of employing an ensemble of classifiers to improve the accuracy and performance of the model. We proposed a model, initially by training word embedding using word2vec from 12.5K Indonesian Twitter on the relocation issue of the new capitol city of Indonesia (IKN) and by utilizing CNN, Bidirectional LSTM, and MLP as the base classifiers. Finally, we performed a stack generalization ensemble technique using MLP and LR as the meta-classifiers and compared the performance of the ensemble techniques with individual base classifiers. The base classifiers take advantage of the weights the word embedding provides to do the learning process. The results show that the stacking ensemble using MLP performs slightly better than LR as the meta-classifier, with the F-1 score of 74.65% vs. 73.78%, respectively. MLP meta-classifiers also perform somewhat better than the hard and soft majority voting ensemble with difference F-1 scores of 3.75% and 2.56%, respectively. The results show that the proposed stacked generalization technique model has improved the performance of the sentiment analysis model.
{"title":"Sentiment Analysis of Indonesian New Capitol (IKN) Tweets by Stacked Generalization of Deep Learning","authors":"Josua Geovani Pinem, Aulia Haritsuddin Karisma Muhammad Subekti, G. Wibowanto, Siti Shaleha, Muhammad Reza Alfin, Agung Septiadi, Elvira Nurfadhilah, Dian Isnaeni Nurul Afra, J. Muliadi, Agung Santosa, M. T. Uliniansyah, Asril Jarin, Andi Djalal Latief, Gunarso, Hammam Riza","doi":"10.1145/3575882.3575922","DOIUrl":"https://doi.org/10.1145/3575882.3575922","url":null,"abstract":"The increasing use of Twitter for conveying the general public's sentiment toward a specific public policy generates pros and cons and has led to much research in sentiment analysis. Instead of exploring the most suitable classifier for a sentiment analysis model individually, there is a trend of employing an ensemble of classifiers to improve the accuracy and performance of the model. We proposed a model, initially by training word embedding using word2vec from 12.5K Indonesian Twitter on the relocation issue of the new capitol city of Indonesia (IKN) and by utilizing CNN, Bidirectional LSTM, and MLP as the base classifiers. Finally, we performed a stack generalization ensemble technique using MLP and LR as the meta-classifiers and compared the performance of the ensemble techniques with individual base classifiers. The base classifiers take advantage of the weights the word embedding provides to do the learning process. The results show that the stacking ensemble using MLP performs slightly better than LR as the meta-classifier, with the F-1 score of 74.65% vs. 73.78%, respectively. MLP meta-classifiers also perform somewhat better than the hard and soft majority voting ensemble with difference F-1 scores of 3.75% and 2.56%, respectively. The results show that the proposed stacked generalization technique model has improved the performance of the sentiment analysis model.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127789668","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：