Mangosteen is one of the typical fruits of Southeast Asia and Indonesia's flagship fruit with promising export prospects. However, the poor quality of the mangosteen fruit, which is caused by diseases and pest attacks, is an obstacle in increasing export targets. Disease and pest attacks can be immediately overcome if farmers can identify the types of pests and diseases quickly based on the symptoms that appear on the mangosteen plant. The lack of knowledge of farmers in identifying the symptoms that appear and the limited number of experts lead to the late process of handling pests and diseases of the mangosteen plant. Therefore, this study aimed to build an expert system for diagnosing mangosteen diseases and pests using Bayes’ theorem. The knowledge base contained data of 5 diseases, 5 pests, and 42 symptoms. The inference engine utilized the Bayes’ theorem to produce a probability value of a disease or pest attacking the mangosteen plant based on the symptoms that arise. This study yielded an accuracy value of 94% based on 50 test data. This expert system can help farmers in identifying the diseases and pests that attack mangosteen plants quickly as well as finding solutions to the problem.
{"title":"Application of Bayes’ Theorem in an Expert System for Diagnosing Mangosteen Diseases and Pests","authors":"F. A. Setiawan, Freza Riana, Siti Aisyah","doi":"10.1145/3575882.3575927","DOIUrl":"https://doi.org/10.1145/3575882.3575927","url":null,"abstract":"Mangosteen is one of the typical fruits of Southeast Asia and Indonesia's flagship fruit with promising export prospects. However, the poor quality of the mangosteen fruit, which is caused by diseases and pest attacks, is an obstacle in increasing export targets. Disease and pest attacks can be immediately overcome if farmers can identify the types of pests and diseases quickly based on the symptoms that appear on the mangosteen plant. The lack of knowledge of farmers in identifying the symptoms that appear and the limited number of experts lead to the late process of handling pests and diseases of the mangosteen plant. Therefore, this study aimed to build an expert system for diagnosing mangosteen diseases and pests using Bayes’ theorem. The knowledge base contained data of 5 diseases, 5 pests, and 42 symptoms. The inference engine utilized the Bayes’ theorem to produce a probability value of a disease or pest attacking the mangosteen plant based on the symptoms that arise. This study yielded an accuracy value of 94% based on 50 test data. This expert system can help farmers in identifying the diseases and pests that attack mangosteen plants quickly as well as finding solutions to the problem.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"62 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":"124410903","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}
Andre Sihombing, Ariani Indrawati, Aris Yaman, Cahyo Trianggoro, L. Manik, Zaenal Akbar
It is difficult to understand a scientific domain’s structure and extract specific information from it. A lot of human work is needed to achieve this goal. Based on previous studies, most of the data sets used in identifying the scientific expertise of academia are obtained through the information in the metadata and the contents of the papers written by academia. Therefore, machine learning tools should be utilized to accurately represent how knowledge has been arranged and presented up to this point. In this research, we compare semantic analysis approaches (Latent Dirichlet Allocation/ LDA and knowledge graph / KG) and non-explainable variables (TF-IDF) in identifying categories of scientific expertise. Dataset used based on scientific expertise self-claims written organically by academia which has not been widely studied in previous studies. The TF-IDF approach can provide better classification model accuracy results because its character only looks at the level of word importance (word relevance). However, this approach does not give meaning to the independent variable. It is also supported by the dataset with single part of speech condition. Meanwhile, the semantic analysis approach can provide meaning and relation to form the topic or cluster graph, even with a lower accuracy value.
{"title":"A scientific expertise classification model based on experts’ self-claims using the semantic and the TF-IDF approach","authors":"Andre Sihombing, Ariani Indrawati, Aris Yaman, Cahyo Trianggoro, L. Manik, Zaenal Akbar","doi":"10.1145/3575882.3575940","DOIUrl":"https://doi.org/10.1145/3575882.3575940","url":null,"abstract":"It is difficult to understand a scientific domain’s structure and extract specific information from it. A lot of human work is needed to achieve this goal. Based on previous studies, most of the data sets used in identifying the scientific expertise of academia are obtained through the information in the metadata and the contents of the papers written by academia. Therefore, machine learning tools should be utilized to accurately represent how knowledge has been arranged and presented up to this point. In this research, we compare semantic analysis approaches (Latent Dirichlet Allocation/ LDA and knowledge graph / KG) and non-explainable variables (TF-IDF) in identifying categories of scientific expertise. Dataset used based on scientific expertise self-claims written organically by academia which has not been widely studied in previous studies. The TF-IDF approach can provide better classification model accuracy results because its character only looks at the level of word importance (word relevance). However, this approach does not give meaning to the independent variable. It is also supported by the dataset with single part of speech condition. Meanwhile, the semantic analysis approach can provide meaning and relation to form the topic or cluster graph, even with a lower accuracy value.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"29 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":"127582132","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}
Ariani Indrawati, Zaenal Akbar, D. Rini, Aris Yaman, Y. Kartika, D. R. Saleh
Various sectors now widely adopt knowledge graphs to describe and share their organizational knowledge bases. Unfortunately, the majority of knowledge-sharing systems are designed for domain experts. Making it extremely difficult for a non-expert to understand the content and explore the graph. A solution to this issue is using a machine-assisted knowledge graph exploration approach. This research introduces a knowledge exploration method to systematically and efficiently navigate a knowledge graph. First, we modeled the knowledge graphs based on the existing common schema. Second, we created a search tree technique to navigate the knowledge graph efficiently. The algorithm solves the problem by determining the path of knowledge graph exploration. We evaluated the method using a knowledge base of morphological characteristics of Capsicum. The goal of graph exploration was to identify a Capsicum species correctly. As a result, the proposed mechanism can achieve high precision, even when the search’s starting point is unknown beforehand.
{"title":"A Knowledge Graph Exploration Method with No Prior Knowledge","authors":"Ariani Indrawati, Zaenal Akbar, D. Rini, Aris Yaman, Y. Kartika, D. R. Saleh","doi":"10.1145/3575882.3575918","DOIUrl":"https://doi.org/10.1145/3575882.3575918","url":null,"abstract":"Various sectors now widely adopt knowledge graphs to describe and share their organizational knowledge bases. Unfortunately, the majority of knowledge-sharing systems are designed for domain experts. Making it extremely difficult for a non-expert to understand the content and explore the graph. A solution to this issue is using a machine-assisted knowledge graph exploration approach. This research introduces a knowledge exploration method to systematically and efficiently navigate a knowledge graph. First, we modeled the knowledge graphs based on the existing common schema. Second, we created a search tree technique to navigate the knowledge graph efficiently. The algorithm solves the problem by determining the path of knowledge graph exploration. We evaluated the method using a knowledge base of morphological characteristics of Capsicum. The goal of graph exploration was to identify a Capsicum species correctly. As a result, the proposed mechanism can achieve high precision, even when the search’s starting point is unknown beforehand.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"55 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":"125225561","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}
D. E. Kusumandari, A. Sutarto, M. F. Amri, A. I. Simbolon, M. Rizqyawan, Adriani Amalia
Good sleep is crucial for an individual to maintain her or his general well-being and quality of life. The goal of this study is to investigate the extent to which aromatherapy and music stimuli affect sleep quality parameters, measured by electroencephalogram (EEG) signals. Nine young healthy male subjects were recruited and exposed to music (classic or natural) and essential oil release (lavender or sandalwood) in counterbalanced ways (different days) before 90-minute napping. Using a within-subjects design, we measured sleep quality parameters, consisting of total sleep time (TST), time in bed (TiB), wake after sleep onset (WASO), sleep efficiency (SE), and three stages of nonrapid eye movement (NREM). We found that sandalwood significantly reduced the percentage of WASO to total time in bed while natural music increased sleep efficiency. However, neither aromatherapy nor music significantly improved NREM stage 1, 2, and 3 qualities. These findings indicate the positive effects of these stimuli on some objective sleep parameters among young healthy male subjects.
{"title":"Effects of Aromatherapy and Music on Napping-Time Quality in Young Adults: EEG Sleep Study","authors":"D. E. Kusumandari, A. Sutarto, M. F. Amri, A. I. Simbolon, M. Rizqyawan, Adriani Amalia","doi":"10.1145/3575882.3575932","DOIUrl":"https://doi.org/10.1145/3575882.3575932","url":null,"abstract":"Good sleep is crucial for an individual to maintain her or his general well-being and quality of life. The goal of this study is to investigate the extent to which aromatherapy and music stimuli affect sleep quality parameters, measured by electroencephalogram (EEG) signals. Nine young healthy male subjects were recruited and exposed to music (classic or natural) and essential oil release (lavender or sandalwood) in counterbalanced ways (different days) before 90-minute napping. Using a within-subjects design, we measured sleep quality parameters, consisting of total sleep time (TST), time in bed (TiB), wake after sleep onset (WASO), sleep efficiency (SE), and three stages of nonrapid eye movement (NREM). We found that sandalwood significantly reduced the percentage of WASO to total time in bed while natural music increased sleep efficiency. However, neither aromatherapy nor music significantly improved NREM stage 1, 2, and 3 qualities. These findings indicate the positive effects of these stimuli on some objective sleep parameters among young healthy male subjects.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"70 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":"116789619","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. Rahmadiansyah, S. P. Anggraeni, Muhammad Firdaus, Mustika Fitriana Dewi, S. Rahardjo, M. P. Rasuanta, M. Hamidah, L. Setianingrum, A. Hatta
In long-haul communication, fiber optic cable plays an important role as transmission medium. The C-Band is the typical spectrum used in common optical link implementation, especially for long-range. Generally, dense wavelength division multiplexing (DWDM) uses specific wavelength spectrum based on grid stated in ITU-T G.694.1 recommendation, in which it is proposed to acquire several wavelengths to be used as the channels in the system of DWDM communication-based sensor network. In this paper, C-band DWDM channel determination method is presented. The selected DWDM channels are determined by considering lower attenuation and chromatic dispersion in the G.652.D-based fiber optic from Corning SMF-28 fiber optic technical datasheet towards entire wavelength in C-Band area, thus the optimum channels could be discovered. As conclusion, our research found the attenuation parameter has much more significant effect to Q-factor and BER values compared to the chromatic dispersion effect and the top-five most optimized channels are listed.
{"title":"The Consideration of Attenuation and Chromatic Dispersion Parameters to Long-Haul Optical Communication","authors":"M. Rahmadiansyah, S. P. Anggraeni, Muhammad Firdaus, Mustika Fitriana Dewi, S. Rahardjo, M. P. Rasuanta, M. Hamidah, L. Setianingrum, A. Hatta","doi":"10.1145/3575882.3575892","DOIUrl":"https://doi.org/10.1145/3575882.3575892","url":null,"abstract":"In long-haul communication, fiber optic cable plays an important role as transmission medium. The C-Band is the typical spectrum used in common optical link implementation, especially for long-range. Generally, dense wavelength division multiplexing (DWDM) uses specific wavelength spectrum based on grid stated in ITU-T G.694.1 recommendation, in which it is proposed to acquire several wavelengths to be used as the channels in the system of DWDM communication-based sensor network. In this paper, C-band DWDM channel determination method is presented. The selected DWDM channels are determined by considering lower attenuation and chromatic dispersion in the G.652.D-based fiber optic from Corning SMF-28 fiber optic technical datasheet towards entire wavelength in C-Band area, thus the optimum channels could be discovered. As conclusion, our research found the attenuation parameter has much more significant effect to Q-factor and BER values compared to the chromatic dispersion effect and the top-five most optimized channels are listed.","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":"128211635","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}
J. Prakosa, Azwirman Gusrialdi, Mohamad Syahadi, E. Kurniawan, H. Septanto, Chifayah Astuti
Agricultural land, especially in Indonesia, is generally square, so it has become an exciting topic of study to employ agricultural robots. In the era of the industrial revolution 4.0, agricultural robots were widely used in monitoring tasks, planting seeds, watering fertilizers, and applying smart agriculture. Cooperative control techniques in coordinating many robots in a square formation are very challenging to study in-depth. The purpose of this study was to evaluate the cooperative formation control for agricultural robots’ simulation on the distinction in the area of the square on agricultural land. From the calculation and simulation results, this method has succeeded in reaching a consensus on comparing the variation of the square area and the type of robotic communication. The consensus value tended to take a longer period to reach according to the broader square, particularly in the nonlinear relation of the suitable logarithm. In addition, one-way robotic communication had more rough position, speed, relation graph, and control signals than bidirectional communication in this square formation control.
{"title":"Cooperative Formation Control Study for Agricultural Robot Simulation in Square Farmland Areas","authors":"J. Prakosa, Azwirman Gusrialdi, Mohamad Syahadi, E. Kurniawan, H. Septanto, Chifayah Astuti","doi":"10.1145/3575882.3575895","DOIUrl":"https://doi.org/10.1145/3575882.3575895","url":null,"abstract":"Agricultural land, especially in Indonesia, is generally square, so it has become an exciting topic of study to employ agricultural robots. In the era of the industrial revolution 4.0, agricultural robots were widely used in monitoring tasks, planting seeds, watering fertilizers, and applying smart agriculture. Cooperative control techniques in coordinating many robots in a square formation are very challenging to study in-depth. The purpose of this study was to evaluate the cooperative formation control for agricultural robots’ simulation on the distinction in the area of the square on agricultural land. From the calculation and simulation results, this method has succeeded in reaching a consensus on comparing the variation of the square area and the type of robotic communication. The consensus value tended to take a longer period to reach according to the broader square, particularly in the nonlinear relation of the suitable logarithm. In addition, one-way robotic communication had more rough position, speed, relation graph, and control signals than bidirectional communication in this square formation control.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"23 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":"125302773","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}
I. Wahyuni, A. Latifah, Rido Dwi Ismanto, Ariani Indrawati, Usnida Umma Zahra, A. Gunawan
Forest and land fires cause various negative impacts on human life and the environment. Understanding the fire spread over an area is important for developing a mitigation strategy. This paper aims to model the fire spread in Kalimantan using Cellular Automata. Simulations of the effects of land cover, terrain, and wind on fire spread during September 2015 are presented. Our results reveal that the proposed model can describe fire spread reliably well, showing that the most impacted area occurs in the southern part of Kalimantan. For the wind effect, its direction to the north is seemingly the dominant direction for the fire spread at most locations and affects fire spreads much faster in lowlands than in other locations. The present study also summarizes that the type of land cover gives more influence to the fire spread rate on lowlands, while the elevation contributes more to accelerating the fire spread over complex terrain.
{"title":"Effects Of Land Cover, Topography, And Wind On Fire Spread In Kalimantan Using Cellular Automata","authors":"I. Wahyuni, A. Latifah, Rido Dwi Ismanto, Ariani Indrawati, Usnida Umma Zahra, A. Gunawan","doi":"10.1145/3575882.3575914","DOIUrl":"https://doi.org/10.1145/3575882.3575914","url":null,"abstract":"Forest and land fires cause various negative impacts on human life and the environment. Understanding the fire spread over an area is important for developing a mitigation strategy. This paper aims to model the fire spread in Kalimantan using Cellular Automata. Simulations of the effects of land cover, terrain, and wind on fire spread during September 2015 are presented. Our results reveal that the proposed model can describe fire spread reliably well, showing that the most impacted area occurs in the southern part of Kalimantan. For the wind effect, its direction to the north is seemingly the dominant direction for the fire spread at most locations and affects fire spreads much faster in lowlands than in other locations. The present study also summarizes that the type of land cover gives more influence to the fire spread rate on lowlands, while the elevation contributes more to accelerating the fire spread over complex terrain.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"28 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":"123157407","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}
A. A. Waskita, Zaenal Akbar, D. R. Saleh, Y. Kartika, Ariani Indrawati
The open science movement has been widely adopted in multiple scientific fields across nations. Its benefit has been proven in many cases, most notably when the practice accelerated the search for solutions to the Covid-19 pandemic both in medical and socio-economic contexts. Still, the movement has faced multiple challenges, including an imbalance in the adoption of its numerous aspects. For example, the open access aspect which indicates the starting point of the movement has been widely practiced. Unfortunately, while open access is essential, an open access practice alone is not enough to pursue open science. In this work, we would like to assess the imbalance of the adoption, especially to measure how open access practice contributes to other practices, namely open data and open source as a sub-aspect of the open reproducibility research. Our assessment is based on descriptive statistic analysis of 300 open access articles from three domains, that is engineering, social and life science. Our findings indicated that the free and open source computer codes were dominantly adopted by the three scientific fields. However, social science has the lowest involvement in public data.
{"title":"Open science progress: A literature assessment of open access articles","authors":"A. A. Waskita, Zaenal Akbar, D. R. Saleh, Y. Kartika, Ariani Indrawati","doi":"10.1145/3575882.3575934","DOIUrl":"https://doi.org/10.1145/3575882.3575934","url":null,"abstract":"The open science movement has been widely adopted in multiple scientific fields across nations. Its benefit has been proven in many cases, most notably when the practice accelerated the search for solutions to the Covid-19 pandemic both in medical and socio-economic contexts. Still, the movement has faced multiple challenges, including an imbalance in the adoption of its numerous aspects. For example, the open access aspect which indicates the starting point of the movement has been widely practiced. Unfortunately, while open access is essential, an open access practice alone is not enough to pursue open science. In this work, we would like to assess the imbalance of the adoption, especially to measure how open access practice contributes to other practices, namely open data and open source as a sub-aspect of the open reproducibility research. Our assessment is based on descriptive statistic analysis of 300 open access articles from three domains, that is engineering, social and life science. Our findings indicated that the free and open source computer codes were dominantly adopted by the three scientific fields. However, social science has the lowest involvement in public data.","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":"123118543","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}
Aspect-based sentiment analysis (ABSA) is an NLP task for predicting sentiment polarities of specific aspects in a given opinion sentence. Recent research shows that deep learning and language modeling like BERT has become state-of-the-art in NLP tasks, including ABSA. However, most methods still ignore conflict opinion or methods that reached high performance in 2-class (positive and negative), and 3-class (positive, negative, and neutral) classification will be degraded when applied in a 4-class classification where conflict opinion is included. In this paper, we propose a BERT-based method that can identify and handle aspects containing conflict opinions in three steps: (i) designing input representation for BERT-based sentence-pair classification task, (ii) processing two-label sentiment classification for each aspect, and lastly (iii) translating the second step result to 4-class sentiment classification. Experimental results on the SemEval-2014 restaurant domain dataset demonstrate that our proposed method has effectively identified conflict opinion and achieved better results on 3-class and 4-class classification tasks.
{"title":"Identification of Conflict Opinion in Aspect-Based Sentiment Analysis using BERT-based Method","authors":"N. Nuryani, A. Purwarianti, D. H. Widyantoro","doi":"10.1145/3575882.3575935","DOIUrl":"https://doi.org/10.1145/3575882.3575935","url":null,"abstract":"Aspect-based sentiment analysis (ABSA) is an NLP task for predicting sentiment polarities of specific aspects in a given opinion sentence. Recent research shows that deep learning and language modeling like BERT has become state-of-the-art in NLP tasks, including ABSA. However, most methods still ignore conflict opinion or methods that reached high performance in 2-class (positive and negative), and 3-class (positive, negative, and neutral) classification will be degraded when applied in a 4-class classification where conflict opinion is included. In this paper, we propose a BERT-based method that can identify and handle aspects containing conflict opinions in three steps: (i) designing input representation for BERT-based sentence-pair classification task, (ii) processing two-label sentiment classification for each aspect, and lastly (iii) translating the second step result to 4-class sentiment classification. Experimental results on the SemEval-2014 restaurant domain dataset demonstrate that our proposed method has effectively identified conflict opinion and achieved better results on 3-class and 4-class classification tasks.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"39 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":"121102387","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}
Shadows are the obstacle parts of a vision-based during the driving an autonomous vehicle (AV). The shadow also can be detected as an object. It is feared the AV’s system doesn’t well-work or hits another object. Many methods of the images and video shadow detection and removal in the AVs. However, to handle the various backgrounds on the video shadow and objects, we need to exploit many scenarios of single video shadow detection, removal, and semantic segmentation. We propose a new novelty method in the shadow video detection and removal which is combined with the re-coloring method in the segmentation process. It’s namely the D-ViShaDeRec. We also propose a new modified Sobel algorithm which has a kernel size of 5 × 5. The D-ViShaDeRec’s outcomes show , , , , , and of the recall, selectivity, precision, NPV, accuracy, and F1-Score, respectively.
{"title":"D-ViShaDeRec: Double Intensity of Video Shadow Detection, Removal, and Re-coloring in Autonomous Vehicle","authors":"Risnandar, Deeva Nabila","doi":"10.1145/3575882.3575936","DOIUrl":"https://doi.org/10.1145/3575882.3575936","url":null,"abstract":"Shadows are the obstacle parts of a vision-based during the driving an autonomous vehicle (AV). The shadow also can be detected as an object. It is feared the AV’s system doesn’t well-work or hits another object. Many methods of the images and video shadow detection and removal in the AVs. However, to handle the various backgrounds on the video shadow and objects, we need to exploit many scenarios of single video shadow detection, removal, and semantic segmentation. We propose a new novelty method in the shadow video detection and removal which is combined with the re-coloring method in the segmentation process. It’s namely the D-ViShaDeRec. We also propose a new modified Sobel algorithm which has a kernel size of 5 × 5. The D-ViShaDeRec’s outcomes show , , , , , and of the recall, selectivity, precision, NPV, accuracy, and F1-Score, respectively.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"15 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":"131804748","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：