Smart logistics is a crucial aspect of constructing smart cities, which entails efficiently finding a solution to a problem using a fleet of vehicles to serve geographically dispersed clients. It comprises the capacitated vehicle routing problem (CVRP), a well-known NP-hard complex optimization problem that a genetic algorithm (GA) can solve even with some weaknesses. The weaknesses include time-consuming, difficult-to-achieve convergence, and easy-to-get premature convergence, resulting in infeasible and low-quality solutions in a limited population. Based on these weaknesses, the authors propose three improvements to GA to optimize the solution. The improvement strategies are enhancing the initial population with the nearest neighbor algorithm, improving the new mutated offspring with a 2-opt heuristic, and optimizing the route with a give-and-exchange operator. The test is undergone on 53 CVRP problem sets to evaluate the performance of our proposed algorithm. The result shows that the proposed algorithm successfully improves GA performance quality, reduces the execution time, reaches some optimum values, and obtains a better solution than the best-known value.
{"title":"Genetic Algorithm Improvement: A Case Study of Capacitated Vehicle Routing Problem","authors":"H. Firdaus, Tri Widianti","doi":"10.1145/3575882.3575885","DOIUrl":"https://doi.org/10.1145/3575882.3575885","url":null,"abstract":"Smart logistics is a crucial aspect of constructing smart cities, which entails efficiently finding a solution to a problem using a fleet of vehicles to serve geographically dispersed clients. It comprises the capacitated vehicle routing problem (CVRP), a well-known NP-hard complex optimization problem that a genetic algorithm (GA) can solve even with some weaknesses. The weaknesses include time-consuming, difficult-to-achieve convergence, and easy-to-get premature convergence, resulting in infeasible and low-quality solutions in a limited population. Based on these weaknesses, the authors propose three improvements to GA to optimize the solution. The improvement strategies are enhancing the initial population with the nearest neighbor algorithm, improving the new mutated offspring with a 2-opt heuristic, and optimizing the route with a give-and-exchange operator. The test is undergone on 53 CVRP problem sets to evaluate the performance of our proposed algorithm. The result shows that the proposed algorithm successfully improves GA performance quality, reduces the execution time, reaches some optimum values, and obtains a better solution than the best-known value.","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":"116936027","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}
Jovanka Jeremy Wijaya, M. Setyo, K. William, Y. U. Chandra
Product review video is one of the genres created by many people on short video platforms such as TikTok, Instagram Reels, and YouTube Shorts. Especially for the business owner to promote their products to influencers so they can sell products better. Product reviews not only give an advantage to influencers and help business owners but also advise consumers. Because with product review videos, consumers can understand more about the product conditions, quality, and testimonials about the products from previous buyers. Researchers raised the topic to discuss and determine the effect of the information quality on product review videos in the short video platform for customer purchase intention. Research questions to be answered are: How can the information quality of product reviews on a short video platform affect customer purchase intention? Researchers use a quantitative method by distributing a questionnaire survey to people who use short video platforms such as TikTok, Instagram Reels, and YouTube Shorts. The survey gained 479 responses and obtained 454 valid data where the respondents have seen product review videos on short video platforms. There are 7 variables that researchers will analyze in this study, namely Information Content Quality (ICQ), Information Utility (IU), Information Expression Quality (IEQ), Perceived Diagnosticity (PD), Information Credibility (IC), Information Adoption (IA), and Purchase Intention (PI). Through this method, we can understand the importance of information quality as the root of information adoption and purchase intentions.
{"title":"The Effect Of Information Quality On Product Reviews In The Short Video Platform For Viewers Purchase Intention","authors":"Jovanka Jeremy Wijaya, M. Setyo, K. William, Y. U. Chandra","doi":"10.1145/3575882.3575957","DOIUrl":"https://doi.org/10.1145/3575882.3575957","url":null,"abstract":"Product review video is one of the genres created by many people on short video platforms such as TikTok, Instagram Reels, and YouTube Shorts. Especially for the business owner to promote their products to influencers so they can sell products better. Product reviews not only give an advantage to influencers and help business owners but also advise consumers. Because with product review videos, consumers can understand more about the product conditions, quality, and testimonials about the products from previous buyers. Researchers raised the topic to discuss and determine the effect of the information quality on product review videos in the short video platform for customer purchase intention. Research questions to be answered are: How can the information quality of product reviews on a short video platform affect customer purchase intention? Researchers use a quantitative method by distributing a questionnaire survey to people who use short video platforms such as TikTok, Instagram Reels, and YouTube Shorts. The survey gained 479 responses and obtained 454 valid data where the respondents have seen product review videos on short video platforms. There are 7 variables that researchers will analyze in this study, namely Information Content Quality (ICQ), Information Utility (IU), Information Expression Quality (IEQ), Perceived Diagnosticity (PD), Information Credibility (IC), Information Adoption (IA), and Purchase Intention (PI). Through this method, we can understand the importance of information quality as the root of information adoption and purchase intentions.","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":"127435383","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}
MeSH stands for Medical Subject Heading. MeSH is a thorough mastery for cataloging books and articles in the biomedical literature. MeSH works as a dictionary that facilitates searching and retrieving information in the biomedical realm. Currently, a human indexer manually indexes articles and books in biomedical literature using the MeSH vocabulary. The problem with using a human indexer is that the indexation process takes a long time and is expensive. Therefore, the indexation developed is automated, which is developed in this study using MeSH vocabulary with predictors based on machine learning and supervised deep learning. The study found that the F1-Score of the deep learning indexation model was superior compared to the machine learning used as the baseline model in predicting the indexation.
{"title":"Comparison of Machine Learning and Deep Learning model for Medical Subject Headings Indexation","authors":"Lukman Heryawan, Arif Bukhori","doi":"10.1145/3575882.3575938","DOIUrl":"https://doi.org/10.1145/3575882.3575938","url":null,"abstract":"MeSH stands for Medical Subject Heading. MeSH is a thorough mastery for cataloging books and articles in the biomedical literature. MeSH works as a dictionary that facilitates searching and retrieving information in the biomedical realm. Currently, a human indexer manually indexes articles and books in biomedical literature using the MeSH vocabulary. The problem with using a human indexer is that the indexation process takes a long time and is expensive. Therefore, the indexation developed is automated, which is developed in this study using MeSH vocabulary with predictors based on machine learning and supervised deep learning. The study found that the F1-Score of the deep learning indexation model was superior compared to the machine learning used as the baseline model in predicting the indexation.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"77 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":"127443319","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. R. Saleh, Y. Kartika, Zaenal Akbar, A. Krisnadhi, W. Fatriasari
Collective data collection has become common in various domains, including biodiversity science. Multiple individuals work on the same biological samples or specimens using various scientific tools to measure different characteristics. Moreover, the measurements are typically regulated by different data collection procedures and protocols. Integrating and guaranteeing the quality of the data has become a significant issue. One solution is to adopt the RDF (Resource Description Framework) data model in combination with a language for validating RDF graphs such as SHACL (Shapes Constraint Language). The RDF data model provides flexibility in accommodating multiple data schemas, while SHACL uses a set of conditions so called shapes, to validate the RDF data graphs. The remaining challenge is an effective method to define SHACL shapes that can be used to validate any given RDF data. This work introduces a semi-automatic database-driven solution to generate SHACL shapes. The solution relies on the database’s internal structure and data items’ values. The solution was applied to a traits database from natural fiber plants in Indonesia, where a high number of individual shapes were successfully generated. Furthermore, a qualitative evaluation indicated the appropriate quality of the shapes. This work contributes to increasing the quality of biodiversity data collections, which has become an essential factor in Big Biodiversity Data processing.
{"title":"On Generating SHACL Shapes from Collective Collection of Plant Trait Data","authors":"D. R. Saleh, Y. Kartika, Zaenal Akbar, A. Krisnadhi, W. Fatriasari","doi":"10.1145/3575882.3575945","DOIUrl":"https://doi.org/10.1145/3575882.3575945","url":null,"abstract":"Collective data collection has become common in various domains, including biodiversity science. Multiple individuals work on the same biological samples or specimens using various scientific tools to measure different characteristics. Moreover, the measurements are typically regulated by different data collection procedures and protocols. Integrating and guaranteeing the quality of the data has become a significant issue. One solution is to adopt the RDF (Resource Description Framework) data model in combination with a language for validating RDF graphs such as SHACL (Shapes Constraint Language). The RDF data model provides flexibility in accommodating multiple data schemas, while SHACL uses a set of conditions so called shapes, to validate the RDF data graphs. The remaining challenge is an effective method to define SHACL shapes that can be used to validate any given RDF data. This work introduces a semi-automatic database-driven solution to generate SHACL shapes. The solution relies on the database’s internal structure and data items’ values. The solution was applied to a traits database from natural fiber plants in Indonesia, where a high number of individual shapes were successfully generated. Furthermore, a qualitative evaluation indicated the appropriate quality of the shapes. This work contributes to increasing the quality of biodiversity data collections, which has become an essential factor in Big Biodiversity Data processing.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"8 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":"125360065","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}
Inna Syafarina, A. Latifah, I. Wahyuni, Rido Dwi Ismanto, Ariani Indrawati, M. Rosyidi, W. Iriana, S. D. A. Kusumaningtyas, A. Imami, E. Yulihastin
Air pollution can intrude on the process of solar radiation reaching the earth’s surface, disrupting the earth’s heat balance. Global warming is one of its consequences. This study aims to analyze the impact of air pollution on solar radiation using Random Forest (RF) and Support Vector Regression (SVR) models. We use six pollutant types to predict the diffuse solar radiation, i.e., PM2.5, PM10, NO2, SO2, CO, and O3. Besides, near-surface temperature and sunshine duration are also expected to influence solar radiation or vice versa. The models are applied in two locations in Jakarta, Kemayoran and Jagakarsa, from January-August 2019. Based on the model performance, RF outperformed compared to the SVR model. RF model found that all variables, pollutants, temperature, and sunshine duration, impact the solar radiation in both locations. While the SVR model showed that the solar radiation in Kemayoran is affected by all variables, excluding O3. Meanwhile, PM2.5, PM10, NO2, temperature, and sunshine duration affect the solar radiation in Jagakarsa. Overall, PM2.5 is one of the top three most influential pollutants.
{"title":"Impact of Air Pollution on Solar Radiation in Megacity Jakarta","authors":"Inna Syafarina, A. Latifah, I. Wahyuni, Rido Dwi Ismanto, Ariani Indrawati, M. Rosyidi, W. Iriana, S. D. A. Kusumaningtyas, A. Imami, E. Yulihastin","doi":"10.1145/3575882.3575913","DOIUrl":"https://doi.org/10.1145/3575882.3575913","url":null,"abstract":"Air pollution can intrude on the process of solar radiation reaching the earth’s surface, disrupting the earth’s heat balance. Global warming is one of its consequences. This study aims to analyze the impact of air pollution on solar radiation using Random Forest (RF) and Support Vector Regression (SVR) models. We use six pollutant types to predict the diffuse solar radiation, i.e., PM2.5, PM10, NO2, SO2, CO, and O3. Besides, near-surface temperature and sunshine duration are also expected to influence solar radiation or vice versa. The models are applied in two locations in Jakarta, Kemayoran and Jagakarsa, from January-August 2019. Based on the model performance, RF outperformed compared to the SVR model. RF model found that all variables, pollutants, temperature, and sunshine duration, impact the solar radiation in both locations. While the SVR model showed that the solar radiation in Kemayoran is affected by all variables, excluding O3. Meanwhile, PM2.5, PM10, NO2, temperature, and sunshine duration affect the solar radiation in Jagakarsa. Overall, PM2.5 is one of the top three most influential pollutants.","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":"116537036","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}
Edy Maryadi, S. Syahrul, Dea Maulidya, R. Risnandar, E. Prakasa, Dian Andriana
Sign language is a means of communication for The Deaf. Indonesian Sign language or BISINDO is one of the sign languages that is used in Indonesia. For The Deaf with The Deaf sign language is a means of communicating effectively, but not for The Deaf with the hearing. This is partially due to insufficient basic knowledge of The Hearing about how to communicate with The Deaf. A sign language translator needed to help The Deaf communicate with The Hearing. Limited of sign language translator is the reason for this research to develop sign language recognition methods. This research is about the development of methods for recognizing basic sign language alphabet and numbers based on computer vision. Basic sign language alphabet and numbers are demonstrated by arms, so they can be the basis to recognize alphabet and number from them. In this research skeletons graphs are extracted. Features are obtained from angle as direction for each chosen vertex. These features are known as skeletal based. To calculate similarity of the alphabet and numbers based on features, this research uses K-Nearest Neighbor (KNN). The best result of recognize sign language alphabet is 99.70% and to recognize sign language numbers the accuracy is 99.81%.
{"title":"Hand Skeleton Graph Feature for Indonesian Sign Language (BISINDO) Recognition Based on Computer Vision","authors":"Edy Maryadi, S. Syahrul, Dea Maulidya, R. Risnandar, E. Prakasa, Dian Andriana","doi":"10.1145/3575882.3575931","DOIUrl":"https://doi.org/10.1145/3575882.3575931","url":null,"abstract":"Sign language is a means of communication for The Deaf. Indonesian Sign language or BISINDO is one of the sign languages that is used in Indonesia. For The Deaf with The Deaf sign language is a means of communicating effectively, but not for The Deaf with the hearing. This is partially due to insufficient basic knowledge of The Hearing about how to communicate with The Deaf. A sign language translator needed to help The Deaf communicate with The Hearing. Limited of sign language translator is the reason for this research to develop sign language recognition methods. This research is about the development of methods for recognizing basic sign language alphabet and numbers based on computer vision. Basic sign language alphabet and numbers are demonstrated by arms, so they can be the basis to recognize alphabet and number from them. In this research skeletons graphs are extracted. Features are obtained from angle as direction for each chosen vertex. These features are known as skeletal based. To calculate similarity of the alphabet and numbers based on features, this research uses K-Nearest Neighbor (KNN). The best result of recognize sign language alphabet is 99.70% and to recognize sign language numbers the accuracy is 99.81%.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"26 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":"122689649","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}
Rosyidi, W. Winarno, Nurhadi Pramana, Nofriyadi Nurdam, T. Widodo, S. Bismantoko
In the Intelligent Transportation System (ITS) era, several studies related to traffic flow prediction models on the road made it easier to obtain continuous traffic volume data, traffic volume on roads was strongly influenced, one of them by damaged road conditions. This research is related to the development of a traffic flow prediction model due to damaged roads. In developing the traffic flow prediction model for the characteristics of damaged roads (distress raveling type) using the Auto Regressive Integrated Moving Average (ARIMA) and Long Short Term Memory (LSTM) models, these two models are suitable for short-term traffic flow prediction models using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) evaluation methods. The results obtained in the development of this model are quite promising to provide an overview of the traffic flow prediction model for the characteristics of damaged roads (distress raveling type) at the survey location. The evaluation shows that RMSE or MAE values for SARIMA and LSTM are less than 5%.
{"title":"Short-Term Road Traffic Flow Prediction Model on Damaged Road Characteristics (Type of Distress Raveling)","authors":"Rosyidi, W. Winarno, Nurhadi Pramana, Nofriyadi Nurdam, T. Widodo, S. Bismantoko","doi":"10.1145/3575882.3575919","DOIUrl":"https://doi.org/10.1145/3575882.3575919","url":null,"abstract":"In the Intelligent Transportation System (ITS) era, several studies related to traffic flow prediction models on the road made it easier to obtain continuous traffic volume data, traffic volume on roads was strongly influenced, one of them by damaged road conditions. This research is related to the development of a traffic flow prediction model due to damaged roads. In developing the traffic flow prediction model for the characteristics of damaged roads (distress raveling type) using the Auto Regressive Integrated Moving Average (ARIMA) and Long Short Term Memory (LSTM) models, these two models are suitable for short-term traffic flow prediction models using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) evaluation methods. The results obtained in the development of this model are quite promising to provide an overview of the traffic flow prediction model for the characteristics of damaged roads (distress raveling type) at the survey location. The evaluation shows that RMSE or MAE values for SARIMA and LSTM are less than 5%.","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":"130540994","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 number of short texts produced daily has increased significantly as a form of social communication commonly used on the internet. Extracting topics from extensive collections of short texts is one of the most challenging tasks in natural language processing, but it has numerous applications in the real world. The purpose of this study is to compare the topic extraction performance of the Latent Dirichlet Allocation (LDA), Non-Negative Matrix Factorization (NMF), and Gibbs Sampling Dirichlet Multinomial Mixture (GSDMM) algorithms from Indonesian short texts. The data was gathered from news articles about electric vehicles published on the online news site (Kompas.com). Regarding topic coherence scores, our results show that LDA outperforms NMF and GSDMM. However, human judgment indicates that the word clusters produced by NMF and GSDMM are easier to conclude.
{"title":"Performance Comparison of Topic Modeling Algorithms on Indonesian Short Texts","authors":"N. Hidayati, Anne Parlina","doi":"10.1145/3575882.3575905","DOIUrl":"https://doi.org/10.1145/3575882.3575905","url":null,"abstract":"The number of short texts produced daily has increased significantly as a form of social communication commonly used on the internet. Extracting topics from extensive collections of short texts is one of the most challenging tasks in natural language processing, but it has numerous applications in the real world. The purpose of this study is to compare the topic extraction performance of the Latent Dirichlet Allocation (LDA), Non-Negative Matrix Factorization (NMF), and Gibbs Sampling Dirichlet Multinomial Mixture (GSDMM) algorithms from Indonesian short texts. The data was gathered from news articles about electric vehicles published on the online news site (Kompas.com). Regarding topic coherence scores, our results show that LDA outperforms NMF and GSDMM. However, human judgment indicates that the word clusters produced by NMF and GSDMM are easier to conclude.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"48 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":"126699026","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}
Wahyu Haris Kusuma Atmaja, Mohammad Isa, Muhammad Aidil Fahmy
Credit appraisal tools has long taken interest of banking and financial industry, since it is their main business to disbursing loan, make profit from loan interest and keeping non-performing loan minimum. Since then, many researchers try to propose alternative data for credit risk analysis. This research proposed a method to profile electricity customer behavior in order to complement traditional credit-risk analysis data. Five parameters are proposed. Those parameters are representing customer behavior in electricity, which is payment order; purchasing power; power (kWh) usage; compliance, and residence occupancy. Based on our Proof of Concept (PoC) with one of State-Owned Bank, this method largely reduces their evaluation time of debtor from days to minutes.
{"title":"Household Electricity Profile as Alternative Data for Credit Appraisal","authors":"Wahyu Haris Kusuma Atmaja, Mohammad Isa, Muhammad Aidil Fahmy","doi":"10.1145/3575882.3575950","DOIUrl":"https://doi.org/10.1145/3575882.3575950","url":null,"abstract":"Credit appraisal tools has long taken interest of banking and financial industry, since it is their main business to disbursing loan, make profit from loan interest and keeping non-performing loan minimum. Since then, many researchers try to propose alternative data for credit risk analysis. This research proposed a method to profile electricity customer behavior in order to complement traditional credit-risk analysis data. Five parameters are proposed. Those parameters are representing customer behavior in electricity, which is payment order; purchasing power; power (kWh) usage; compliance, and residence occupancy. Based on our Proof of Concept (PoC) with one of State-Owned Bank, this method largely reduces their evaluation time of debtor from days to minutes.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"25 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":"126987079","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}
Bayu Maulana, Mukti Wibowo, Gilang Putra, Josua Geovani Pinem, Umi Chasanah, P. A. Pramesti, Muhamad Supriyadi, Dyah Hidayati, Kristiningrum Kristin, Muhammad Reza Alfin, Aulia Haritsuddin Karisma Muhammad Subekti, Dewi Budiarti, J. Muliadi, A. Nugroho
In order to support research in drug development, there is a need to classify fungi based on their genus. The first step in this research is to perform image segmentation on various fungi images. This study compares three segmentation methods with image datasets of microorganisms of fungi species from three genera: Aspergillus, Trichoderma, and Cladosporium. Otsu thresholding, adaptive thresholding, and k-means clustering are the three segmentation methods used. The comparison is evaluated using Dice and Jaccard similarity. The evaluation result shows that the adaptive thresholding method obtained the highest value with an average Jaccard score of 0.6102 and a Dice score of 0.7321. The Otsu thresholding method obtained an average Jaccard and Dice score of 0.3738 and 0.4625. Meanwhile, the k-means clustering method got an average Jaccard and Dice score of 0.2524 and 0.3272.
{"title":"Image Segmentation for Aspergillus, Cladosporium, and Trichoderma Fungus","authors":"Bayu Maulana, Mukti Wibowo, Gilang Putra, Josua Geovani Pinem, Umi Chasanah, P. A. Pramesti, Muhamad Supriyadi, Dyah Hidayati, Kristiningrum Kristin, Muhammad Reza Alfin, Aulia Haritsuddin Karisma Muhammad Subekti, Dewi Budiarti, J. Muliadi, A. Nugroho","doi":"10.1145/3575882.3575904","DOIUrl":"https://doi.org/10.1145/3575882.3575904","url":null,"abstract":"In order to support research in drug development, there is a need to classify fungi based on their genus. The first step in this research is to perform image segmentation on various fungi images. This study compares three segmentation methods with image datasets of microorganisms of fungi species from three genera: Aspergillus, Trichoderma, and Cladosporium. Otsu thresholding, adaptive thresholding, and k-means clustering are the three segmentation methods used. The comparison is evaluated using Dice and Jaccard similarity. The evaluation result shows that the adaptive thresholding method obtained the highest value with an average Jaccard score of 0.6102 and a Dice score of 0.7321. The Otsu thresholding method obtained an average Jaccard and Dice score of 0.3738 and 0.4625. Meanwhile, the k-means clustering method got an average Jaccard and Dice score of 0.2524 and 0.3272.","PeriodicalId":367340,"journal":{"name":"Proceedings of the 2022 International Conference on Computer, Control, Informatics and Its Applications","volume":"142 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":"116175474","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：