Pub Date : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202119
Tinnaphob Angkaprasert, K. Chanchio
This paper investigates the use of ZFS filesystem to improve the checkpointing mechanisms and the backup of the disk image of QEMU-KVM. In the traditional method, QEMU-KVM has to create a new QCOW2 overlay disk image file at every checkpoint operation. After checkpointing many times, the number of overlay disk images can be overwhelming. These overlay disk images have a dependency on one another. Therefore, the traditional method requires high maintenance costs and takes a long time to restore a VM from a checkpoint. In this paper, we introduce a Snapshot Manager to create a checkpoint of a VM, manage ZFS snapshots, and back up the snapshot from one host to another. By using ZFS filesystem, the Snapshot Manager reduces the number of disk images to one. This approach makes it much easier and causes very low overheads to manage VM checkpoints and disk images. In terms of performance, our experimental results show that ZFS takes significantly less restoration time of a VM than the traditional method at the cost of moderately higher backup time.
{"title":"A Backup Mechanism of Virtual Machine Checkpoint Image using ZFS Snapshots","authors":"Tinnaphob Angkaprasert, K. Chanchio","doi":"10.1109/JCSSE58229.2023.10202119","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202119","url":null,"abstract":"This paper investigates the use of ZFS filesystem to improve the checkpointing mechanisms and the backup of the disk image of QEMU-KVM. In the traditional method, QEMU-KVM has to create a new QCOW2 overlay disk image file at every checkpoint operation. After checkpointing many times, the number of overlay disk images can be overwhelming. These overlay disk images have a dependency on one another. Therefore, the traditional method requires high maintenance costs and takes a long time to restore a VM from a checkpoint. In this paper, we introduce a Snapshot Manager to create a checkpoint of a VM, manage ZFS snapshots, and back up the snapshot from one host to another. By using ZFS filesystem, the Snapshot Manager reduces the number of disk images to one. This approach makes it much easier and causes very low overheads to manage VM checkpoints and disk images. In terms of performance, our experimental results show that ZFS takes significantly less restoration time of a VM than the traditional method at the cost of moderately higher backup time.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115073999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10201988
Thanakij Wanavit, Mario Quintana, Samuel Sallee, L. Klieb
Cranioplasty implants are commonly used in the treatment of traumatic brain injuries. 3D-printed titanium has emerged as a suitable material for creating these products. However, their design and manufacturing process involves numerous skilled professionals, including designers, printers, finishers, inspectors, and communication liaisons with surgeons. We have developed a system that automates the design process, streamlines communication, and assists all relevant parties in completing their tasks more efficiently. Our system's backend utilizes deep learning algorithms to automatically read and segment CT scans, subsequently generating implant designs. The initial draft of the design is produced within 5 minutes, a significant improvement from the 5–7 days required by a human technician. The fully serverless backend demands minimal IT maintenance and offers robust resilience and security. The frontend, developed using Swift 5, is compatible with iOS, iPadOS, and macOS platforms. The application ensures a secure and convenient data pipeline with end-to-end encryption, visually appealing rendering, and high speed.
{"title":"Combining AI and Non-AI for a Smooth User Experience","authors":"Thanakij Wanavit, Mario Quintana, Samuel Sallee, L. Klieb","doi":"10.1109/JCSSE58229.2023.10201988","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10201988","url":null,"abstract":"Cranioplasty implants are commonly used in the treatment of traumatic brain injuries. 3D-printed titanium has emerged as a suitable material for creating these products. However, their design and manufacturing process involves numerous skilled professionals, including designers, printers, finishers, inspectors, and communication liaisons with surgeons. We have developed a system that automates the design process, streamlines communication, and assists all relevant parties in completing their tasks more efficiently. Our system's backend utilizes deep learning algorithms to automatically read and segment CT scans, subsequently generating implant designs. The initial draft of the design is produced within 5 minutes, a significant improvement from the 5–7 days required by a human technician. The fully serverless backend demands minimal IT maintenance and offers robust resilience and security. The frontend, developed using Swift 5, is compatible with iOS, iPadOS, and macOS platforms. The application ensures a secure and convenient data pipeline with end-to-end encryption, visually appealing rendering, and high speed.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115090401","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}
In aquaculture, dissolved oxygen (DO) levels affect fish growth and survival. Automated monitoring and prediction of DO is challenging and becomes expensive if unnecessary sensors are used. This study aims to identify the optimal water and environmental parameters for DO prediction. Data from the fishpond station of Rajabhat Rajanagarindra University were pre-processed and used for training using LSTM, GRU, BiLSTM, and BiGRU. The performance of the models was evaluated and contrasted using three error measures. The results showed that GRU gave the best performance compared to the other models. In conclusion, the best parameters for DO prediction are water pH and water temperature.
{"title":"A Comparative Study of LSTM, GRU, BiLSTM and BiGRU to Predict Dissolved Oxygen","authors":"Narongsak Putpuek, Apiradee Putpuek, Apichart Sungthong","doi":"10.1109/JCSSE58229.2023.10202128","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202128","url":null,"abstract":"In aquaculture, dissolved oxygen (DO) levels affect fish growth and survival. Automated monitoring and prediction of DO is challenging and becomes expensive if unnecessary sensors are used. This study aims to identify the optimal water and environmental parameters for DO prediction. Data from the fishpond station of Rajabhat Rajanagarindra University were pre-processed and used for training using LSTM, GRU, BiLSTM, and BiGRU. The performance of the models was evaluated and contrasted using three error measures. The results showed that GRU gave the best performance compared to the other models. In conclusion, the best parameters for DO prediction are water pH and water temperature.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114160334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202108
Pawonrat Khumngoen, S. Sinthupinyo
Sleep is a significant activity that can influence livelihoods. The critical part of sleep is recovery, repairing cells physically, and preparing energy for the beginning of the next living days. Good sleep can refer to strong health and mental health, which is capably measured by sleep quality. Normally, many works used the whole dataset to train models. But we believe that each person has a different sleeping pattern. So, in this paper, we presented a classification of sleep behavior based on a cluster of sleep quality. We first clustered people who have similar sleep patterns using the Principal Component Analysis technique and K-means algorithm. Then, we used Logistic Regression and Random Forest algorithm to classify sleep behavior. We performed models from the analysis with Leave-one-out cross-validation. The results showed that the accuracy given by Random Forest algorithm models in every group was better than Logistic Regression models between 2.1% and 7.6%.
{"title":"Sleep Behavior Classification Based on Clusters of Sleep Quality","authors":"Pawonrat Khumngoen, S. Sinthupinyo","doi":"10.1109/JCSSE58229.2023.10202108","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202108","url":null,"abstract":"Sleep is a significant activity that can influence livelihoods. The critical part of sleep is recovery, repairing cells physically, and preparing energy for the beginning of the next living days. Good sleep can refer to strong health and mental health, which is capably measured by sleep quality. Normally, many works used the whole dataset to train models. But we believe that each person has a different sleeping pattern. So, in this paper, we presented a classification of sleep behavior based on a cluster of sleep quality. We first clustered people who have similar sleep patterns using the Principal Component Analysis technique and K-means algorithm. Then, we used Logistic Regression and Random Forest algorithm to classify sleep behavior. We performed models from the analysis with Leave-one-out cross-validation. The results showed that the accuracy given by Random Forest algorithm models in every group was better than Logistic Regression models between 2.1% and 7.6%.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125131242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202096
Peachyasitt Udomnuchaisup, Aurawan Imsombut, Picha Suwannahitatorn, Thammakorn Saethang
Medication errors threaten patient safety considerably, underscoring the necessity for enhanced detection and prevention techniques. A prevalent classification system in hospitals relies on the standard practice of medication administration known as the Five Rights (5R). This study seeks to develop an NLP-based tool designed to expand 5R error categorization coverage and alleviate the workload of medical professionals. The proposed method focuses on Thai medical text, incorporating Thai and English vocabulary. In this investigation, we developed a supervised learning classification framework using the Universal Sentence Encoder (USE) for sentence embedding, followed by an Artificial Neural Network (ANN) for model training. Additionally, we explored a zero-shot classification model employing pre-trained Large Language Models (PLMs). Our findings reveal that the supervised learning classification model provides the most favorable performance, albeit with the limitation of reliance on labeled datasets, which can be resource intensive. Conversely, the zero-shot classification framework's performance is less optimal. However, future advancements in Thai medical PLMs may improve efficacy and present a viable alternative for medical data analysis without dependence on labeled datasets. This initiative lays the groundwork for potential future applications and advantages within Thailand's medical domain.
{"title":"Analysis of the 5Rs in Thailand Medication Error Classification through Natural Language Processing","authors":"Peachyasitt Udomnuchaisup, Aurawan Imsombut, Picha Suwannahitatorn, Thammakorn Saethang","doi":"10.1109/JCSSE58229.2023.10202096","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202096","url":null,"abstract":"Medication errors threaten patient safety considerably, underscoring the necessity for enhanced detection and prevention techniques. A prevalent classification system in hospitals relies on the standard practice of medication administration known as the Five Rights (5R). This study seeks to develop an NLP-based tool designed to expand 5R error categorization coverage and alleviate the workload of medical professionals. The proposed method focuses on Thai medical text, incorporating Thai and English vocabulary. In this investigation, we developed a supervised learning classification framework using the Universal Sentence Encoder (USE) for sentence embedding, followed by an Artificial Neural Network (ANN) for model training. Additionally, we explored a zero-shot classification model employing pre-trained Large Language Models (PLMs). Our findings reveal that the supervised learning classification model provides the most favorable performance, albeit with the limitation of reliance on labeled datasets, which can be resource intensive. Conversely, the zero-shot classification framework's performance is less optimal. However, future advancements in Thai medical PLMs may improve efficacy and present a viable alternative for medical data analysis without dependence on labeled datasets. This initiative lays the groundwork for potential future applications and advantages within Thailand's medical domain.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"27 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126064981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10201972
Sapa Chanyachatchawan, Krich Nasingkun, Patipat Tumsangthong, Porntiwa Chata, M. Buranarach, Monsak Socharoentum
In the current era of extensive data usage across industries, data collection, preservation, utilization, and organization has become more challenging and nuanced because it is necessary to consider critical concerns such as data security, privacy, and legal issues, apart from efficiency issues. As a result, Thai government initiated the idea and effort to implement data governance throughout the government agency. This paper showcases the implementation of data governance in a governmental research organization with highly diverse structured and unstructured data. The implementation follows international standards and the guidelines of the Digital Government Development Agency (DGA). The executives set up the working body, including the Data Governance Council and Data Stewards, responsible for setting up and deploying policies and regulations. Creating awareness and the necessary infrastructure are the main focuses in the first-year phase. The metadata was designed to extend DGA's version and match the organization's unique requirements. A data catalog platform was developed accordingly. We organized activities to boost employee awareness and participation, including advertising and data catalog platform training. By the end of the first year of implementation, every organization unit had registered at least one data record into the data catalog.
{"title":"Design and Implementation of a Data Governance Framework and Platform: A Case Study of a National Research Organization of Thailand","authors":"Sapa Chanyachatchawan, Krich Nasingkun, Patipat Tumsangthong, Porntiwa Chata, M. Buranarach, Monsak Socharoentum","doi":"10.1109/JCSSE58229.2023.10201972","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10201972","url":null,"abstract":"In the current era of extensive data usage across industries, data collection, preservation, utilization, and organization has become more challenging and nuanced because it is necessary to consider critical concerns such as data security, privacy, and legal issues, apart from efficiency issues. As a result, Thai government initiated the idea and effort to implement data governance throughout the government agency. This paper showcases the implementation of data governance in a governmental research organization with highly diverse structured and unstructured data. The implementation follows international standards and the guidelines of the Digital Government Development Agency (DGA). The executives set up the working body, including the Data Governance Council and Data Stewards, responsible for setting up and deploying policies and regulations. Creating awareness and the necessary infrastructure are the main focuses in the first-year phase. The metadata was designed to extend DGA's version and match the organization's unique requirements. A data catalog platform was developed accordingly. We organized activities to boost employee awareness and participation, including advertising and data catalog platform training. By the end of the first year of implementation, every organization unit had registered at least one data record into the data catalog.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129406508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202111
Supornpol Nukrongsin, Chetneti Srisa-An
Data privacy laws such as GDPR in Europe and PDPA in Thailand are both laws to protect personal data. The data center task is also a data service organization that needs to do data publishing services among their stakeholders. The challenging task for the Security Operation Center (SOC) team is to analyze all security risks such as data breaches. Most cases of data breach problems are overlooked cases that occur indirectly by guessing from other prior knowledge. For example, attackers combine our dataset with other data sets to reidentify personal data. This attack is called a re-Identification attack that causes a data breach. To fix the risk, statistical noise control techniques for data anonymization are explored and implemented in this study. A Cell-key perturbation is to fix the attack without modifying an original dataset but return an answer dataset with noise addition per query instead.
{"title":"Cell-key Perturbation Data Privacy Procedure for Security Operations Center Team","authors":"Supornpol Nukrongsin, Chetneti Srisa-An","doi":"10.1109/JCSSE58229.2023.10202111","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202111","url":null,"abstract":"Data privacy laws such as GDPR in Europe and PDPA in Thailand are both laws to protect personal data. The data center task is also a data service organization that needs to do data publishing services among their stakeholders. The challenging task for the Security Operation Center (SOC) team is to analyze all security risks such as data breaches. Most cases of data breach problems are overlooked cases that occur indirectly by guessing from other prior knowledge. For example, attackers combine our dataset with other data sets to reidentify personal data. This attack is called a re-Identification attack that causes a data breach. To fix the risk, statistical noise control techniques for data anonymization are explored and implemented in this study. A Cell-key perturbation is to fix the attack without modifying an original dataset but return an answer dataset with noise addition per query instead.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127035440","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}
This paper studied the identity preserving performance of the speech synthesized model when durations of speech samples in Thai language were varied. In particular, two experiments were designed to investigate such property of the model. The first experiment was set to reflect the identity preserving performance of the identity vector derived from speech synthesized model. The results suggest that better identity vector quality is achieved when the longer duration of a Thai speech signal is used as shorter speech signals result in identity vectors that are more dispersed. The second experiment was set to directly reflect the identity preserving performance of the synthesized voice signal generated from the speech synthesized model in independent speaker recognition systems. The results similarly suggest that a better identity-preserving voice signal is achieved when the longer duration of Thai speech signal is used as shorter speech signals result in synthesized voice signals with larger distances from the real voice signals. Therefore, the trade-off between usability and quality of synthesized voices must be carefully considered when developing applications from such models. In addition, the investigation framework used in this study could be used to evaluate the newly developed identity-preserving speech synthesized models.
{"title":"Effects of Speech Duration on Preserving the Identity of Synthesized Voice","authors":"Papapin Supmee, Klittiya Suwanmalai, Natkrita Hanchoenkul, Napa Sae-Bae, Banphatee Khomkham","doi":"10.1109/JCSSE58229.2023.10202157","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202157","url":null,"abstract":"This paper studied the identity preserving performance of the speech synthesized model when durations of speech samples in Thai language were varied. In particular, two experiments were designed to investigate such property of the model. The first experiment was set to reflect the identity preserving performance of the identity vector derived from speech synthesized model. The results suggest that better identity vector quality is achieved when the longer duration of a Thai speech signal is used as shorter speech signals result in identity vectors that are more dispersed. The second experiment was set to directly reflect the identity preserving performance of the synthesized voice signal generated from the speech synthesized model in independent speaker recognition systems. The results similarly suggest that a better identity-preserving voice signal is achieved when the longer duration of Thai speech signal is used as shorter speech signals result in synthesized voice signals with larger distances from the real voice signals. Therefore, the trade-off between usability and quality of synthesized voices must be carefully considered when developing applications from such models. In addition, the investigation framework used in this study could be used to evaluate the newly developed identity-preserving speech synthesized models.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127168359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10202105
I. Nyoman, Mahayasa Adiputra, Paweena Wanchai
Obtaining a new customer is more expensive than predicting the churn probability of an existing customer. A high-performance model in churn prediction can help a company to reduce the cost of obtaining a new customer. Ensemble machine learning is one of the machine learning techniques that can be used in prediction problems. Many studies have shown ensemble machine learning achieves superior results. The main purpose of this study is to build a framework with several combinations of preprocessing techniques and an ensemble of two machine learning models, XGBoost and random forest. The dataset for this study is from a public dataset platform; the experiment uses two different sectors: telecom and insurance. This study achieved 0.850 F1-score in the telecom sector dataset and the insurance sector achieved 0.947 F1-score and 28 seconds in processing time. Compared with the latest work in the same dataset, our model achieved a greater effectiveness in F1-score performance and efficiency performance in dataset 1, but slower algorithm time in dataset 2.
{"title":"Customer Churn Prediction Using Weight Average Ensemble Machine Learning Model","authors":"I. Nyoman, Mahayasa Adiputra, Paweena Wanchai","doi":"10.1109/JCSSE58229.2023.10202105","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10202105","url":null,"abstract":"Obtaining a new customer is more expensive than predicting the churn probability of an existing customer. A high-performance model in churn prediction can help a company to reduce the cost of obtaining a new customer. Ensemble machine learning is one of the machine learning techniques that can be used in prediction problems. Many studies have shown ensemble machine learning achieves superior results. The main purpose of this study is to build a framework with several combinations of preprocessing techniques and an ensemble of two machine learning models, XGBoost and random forest. The dataset for this study is from a public dataset platform; the experiment uses two different sectors: telecom and insurance. This study achieved 0.850 F1-score in the telecom sector dataset and the insurance sector achieved 0.947 F1-score and 28 seconds in processing time. Compared with the latest work in the same dataset, our model achieved a greater effectiveness in F1-score performance and efficiency performance in dataset 1, but slower algorithm time in dataset 2.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128168087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-28DOI: 10.1109/JCSSE58229.2023.10201962
Varanya Somaudon, Pathapee Sakuldee, T. Kerdcharoen
Northern Thailand is home to several Arabica coffee-growing regions, including Mae-kampong, Teentok, Mae-lord, and Monngo Valleys, whose coffees are featured throughout this study. These coffees have distinct aromas and flavors due to their varied cultivation locations, which are influenced by unique climatic conditions. The purpose of this paper is to comprehend the aroma of coffees brought from various locations and roasted under the same conditions. Our lab-made electronic nose (e-nose) was used to digitalize and analyze the smell of coffee. In order to monitor the coffee scent throughout roasting and assess how similar the aromas of coffee samples taken from various locations are to one another, principal component analysis and hierarchical cluster analysis were used. It was found that our e-nose system is an effective tool for determining the geo-location of the coffee origin as well as for quality control of coffee production.
{"title":"Development of a novel quality control indicator for coffee roasting based on the digitalization of smell by a portable electronic nose","authors":"Varanya Somaudon, Pathapee Sakuldee, T. Kerdcharoen","doi":"10.1109/JCSSE58229.2023.10201962","DOIUrl":"https://doi.org/10.1109/JCSSE58229.2023.10201962","url":null,"abstract":"Northern Thailand is home to several Arabica coffee-growing regions, including Mae-kampong, Teentok, Mae-lord, and Monngo Valleys, whose coffees are featured throughout this study. These coffees have distinct aromas and flavors due to their varied cultivation locations, which are influenced by unique climatic conditions. The purpose of this paper is to comprehend the aroma of coffees brought from various locations and roasted under the same conditions. Our lab-made electronic nose (e-nose) was used to digitalize and analyze the smell of coffee. In order to monitor the coffee scent throughout roasting and assess how similar the aromas of coffee samples taken from various locations are to one another, principal component analysis and hierarchical cluster analysis were used. It was found that our e-nose system is an effective tool for determining the geo-location of the coffee origin as well as for quality control of coffee production.","PeriodicalId":298838,"journal":{"name":"2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128586234","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：