In Japan, the electric power market has been fully deregulated since April 2016, and many Independent Power Producers have entered the market. Companies participating in the market conduct transactions between market participants to maximize their profits. When companies consider maximization of their profit, it is necessary to optimize the operation of generators in consideration of market transactions.However, it is not easy to consider trading in the market because it contains many complex and uncertain factors. The number of participating companies continues to increase, and research on the operation of generators in consideration of market transactions is an important field. The power market comprises various markets such as the day-ahead and adjustment markets, and various transactions are performed between participants. We discuss the day-ahead market trading. In such a market, electricity prices and demands vary greatly depending on the trends in electricity sell and purchase bidding. It is necessary for business operators to set operational schedules that take fluctuations in electricity prices and demand into account. We consider an optimization model of generator operation considering market transactions and apply stochastic programming to solve the problem. In addition, we demonstrate that scheduling based on the stochastic programming method is better than conventional deterministic planning.
{"title":"Solution methods for unit commitment problem considering market transactions","authors":"Hiroto Ishimori, Ryusei Mikami, Tetsuya Sato, Takayuki Shiina","doi":"10.52731/ijskm.v7.i2.721","DOIUrl":"https://doi.org/10.52731/ijskm.v7.i2.721","url":null,"abstract":"In Japan, the electric power market has been fully deregulated since April 2016, and many Independent Power Producers have entered the market. Companies participating in the market conduct transactions between market participants to maximize their profits. When companies consider maximization of their profit, it is necessary to optimize the operation of generators in consideration of market transactions.However, it is not easy to consider trading in the market because it contains many complex and uncertain factors. The number of participating companies continues to increase, and research on the operation of generators in consideration of market transactions is an important field. The power market comprises various markets such as the day-ahead and adjustment markets, and various transactions are performed between participants. We discuss the day-ahead market trading. In such a market, electricity prices and demands vary greatly depending on the trends in electricity sell and purchase bidding. It is necessary for business operators to set operational schedules that take fluctuations in electricity prices and demand into account. We consider an optimization model of generator operation considering market transactions and apply stochastic programming to solve the problem. In addition, we demonstrate that scheduling based on the stochastic programming method is better than conventional deterministic planning.","PeriodicalId":487422,"journal":{"name":"International journal of service and knowledge management","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135949119","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 rapid development of ICT has ushered in various new approaches to remote Learning. Measures to improve the quality of higher education have been explored by surveying and analyzing the actual situation in other countries and the implementation methods and systems of advanced initiatives. Due to the rapid spread of the COVID-19 pandemic from 2020, teleworking has been implemented in companies and remote learning in universities and other educational institutions to control the spread of infection. For university classes, sessions that would normally be conducted face-to-face are increasingly being conducted remotely, but there are various risks and challenges inherent in this approach. These risks have caused anxiety and dissatisfaction among both students and faculty, and in some cases have prevented the smooth implementation of classes. This paper proposes and evaluates specific countermeasures by conducting a risk assessment of remote learning for universities. Specifically, we conducted risk assessments for two main types of remote learning: on-demand and live-streaming. Then, on the basis of the results, we developed countermeasures such as the enhancement of environmental facilities (for the ondemand type) and privacy-conscious countermeasures (for the live-streaming type). We also clarified the effectiveness of the proposed measures by comparing the risk values before and after their implementation. Finally, we constructed a portfolio of risk countermeasure proposals from the practical viewpoint of operability and developed guidelines for a phased introduction of the system. Our study will contribute to the safe and secure operation of remote learning in the future.
{"title":"Risk Countermeasure Portfolio Management for Remote Learning Based on Lecture Type","authors":"Shigeaki Tanimoto, Teruo Endo, Nao Ohmori, Takashi Hatashima, Atsushi Kanai","doi":"10.52731/ijskm.v7.i2.783","DOIUrl":"https://doi.org/10.52731/ijskm.v7.i2.783","url":null,"abstract":"The rapid development of ICT has ushered in various new approaches to remote Learning. Measures to improve the quality of higher education have been explored by surveying and analyzing the actual situation in other countries and the implementation methods and systems of advanced initiatives. Due to the rapid spread of the COVID-19 pandemic from 2020, teleworking has been implemented in companies and remote learning in universities and other educational institutions to control the spread of infection. For university classes, sessions that would normally be conducted face-to-face are increasingly being conducted remotely, but there are various risks and challenges inherent in this approach. These risks have caused anxiety and dissatisfaction among both students and faculty, and in some cases have prevented the smooth implementation of classes. This paper proposes and evaluates specific countermeasures by conducting a risk assessment of remote learning for universities. Specifically, we conducted risk assessments for two main types of remote learning: on-demand and live-streaming. Then, on the basis of the results, we developed countermeasures such as the enhancement of environmental facilities (for the ondemand type) and privacy-conscious countermeasures (for the live-streaming type). We also clarified the effectiveness of the proposed measures by comparing the risk values before and after their implementation. Finally, we constructed a portfolio of risk countermeasure proposals from the practical viewpoint of operability and developed guidelines for a phased introduction of the system. Our study will contribute to the safe and secure operation of remote learning in the future.","PeriodicalId":487422,"journal":{"name":"International journal of service and knowledge management","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135448054","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 : 2023-01-01DOI: 10.52731/ijskm.v7.i2.807
Shogo Anda, Masato Kikuchi, Tadachika Ozono
When customers purchase a product online, they use reviews to gather information about that product to help them make a purchase decision. Aspect-based Sentiment Analysis is a task that analyzes the review content from various perspectives, including the product itself, its components, and its retail outlets. We focus on comparing the characteristics of each component in a product with those of other products at the time of purchase. We define a task called component-based sentiment analysis (CBSA), which analyzes the review content from the perspective of only each component in the product. The CBSA task consists of opinion target extraction and polarity analysis. We approach that task with a classifier. We describe a semi-automatic category determination method for creating classification labels for CBSA and a data augmentation method to improve its classification performance. In experiments, we show that our category determination method can generate categories that cover 95% of the existing categories on e-commerce sites and that our data augmentation method improves the macro-F1-measure for uncommon opinions by 10%.
{"title":"Semi-Automatic Category Estimation and Data Augmentation for Opinion Extraction of Product Components","authors":"Shogo Anda, Masato Kikuchi, Tadachika Ozono","doi":"10.52731/ijskm.v7.i2.807","DOIUrl":"https://doi.org/10.52731/ijskm.v7.i2.807","url":null,"abstract":"When customers purchase a product online, they use reviews to gather information about that product to help them make a purchase decision. Aspect-based Sentiment Analysis is a task that analyzes the review content from various perspectives, including the product itself, its components, and its retail outlets. We focus on comparing the characteristics of each component in a product with those of other products at the time of purchase. We define a task called component-based sentiment analysis (CBSA), which analyzes the review content from the perspective of only each component in the product. The CBSA task consists of opinion target extraction and polarity analysis. We approach that task with a classifier. We describe a semi-automatic category determination method for creating classification labels for CBSA and a data augmentation method to improve its classification performance. In experiments, we show that our category determination method can generate categories that cover 95% of the existing categories on e-commerce sites and that our data augmentation method improves the macro-F1-measure for uncommon opinions by 10%.","PeriodicalId":487422,"journal":{"name":"International journal of service and knowledge management","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135448370","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 vehicle routing problem (VRP) determines a delivery route that minimizes the delivery cost. In this study, we consider the stochastic VRP with uncertainty and consider the variation in customer demand, which may cause a shortage of products during delivery. In this case, delivery vehicles have to return to the depot and replenish the products. We consider a model that minimizes the sum of the additional cost caused by the shortage and the normal delivery cost.
{"title":"Solution Algorithm for Vehicle Routing Problem with Stochastic Demand","authors":"Masahiro Komatsu, Ryota Omori, Tetsuya Sato, Takayuki Shiina","doi":"10.52731/ijskm.v7.i2.710","DOIUrl":"https://doi.org/10.52731/ijskm.v7.i2.710","url":null,"abstract":"The vehicle routing problem (VRP) determines a delivery route that minimizes the delivery cost. In this study, we consider the stochastic VRP with uncertainty and consider the variation in customer demand, which may cause a shortage of products during delivery. In this case, delivery vehicles have to return to the depot and replenish the products. We consider a model that minimizes the sum of the additional cost caused by the shortage and the normal delivery cost.","PeriodicalId":487422,"journal":{"name":"International journal of service and knowledge management","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135949181","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 : 2023-01-01DOI: 10.52731/ijskm.v7.i2.779
Al- Mahmud, Kazutaka Shimada
With the growing prevalence of the Internet, increasingly more people and entities express opinions on online platforms, such as Facebook, Twitter, and Amazon. As it is becoming impossible to detect online opinion trends manually, an automatic approach to detect opinion holders is essential as a means to identify specific concerns regarding a particular topic, product, or problem. Opinion holder detection comprises two steps: the presence of opinion holders in text and identification of opinion holders. The present study examines both steps. Initially, we approach this task as a binary classification problem: INSIDE or OUTSIDE. Then, we consider the identification of opinion holders as a sequence labeling task and prepare an appropriate English-language dataset. Subsequently, we employ three pre-trained models for the opinion holder detection task: BERT, DistilBERT, and contextual string embedding (CSE). For the binary classification task, we employ a logistic regression model on the top layers of the BERT and DistilBERT models. We compare the models’ performance in terms of the F1 score and accuracy. Experimental results show that DistilBERT obtained superior performance, with an F1 score of 0.901 and an accuracy of 0.924. For the opinion holder identification task, we utilize both feature- and fine-tuning-based architectures. Furthermore, we combined CSE and the conditional random field (CRF) with BERT and DistilBERT. For the feature-based architecture, we utilize five models: CSE+CRF, BERT+CRF, (BERT&CSE)+CRF, DistilBERT+CRF, and (DistilBERT&CSE)+CRF. For the fine-tuning-based architecture, we utilize six models: BERT, BERT+CRF, (BERT&CSE)+CRF, DistilBERT, DistilBERT+CRF, and (DistilBERT&CSE)+CRF. All language models are evaluated in terms of F1 score and processing time. The experimental results indicate that both the feature- and fine-tuning-based (DistilBERT&CSE)+CRF models jointly yielded the optimal performance, with an F1 score of 0.9453. However, feature-based CSE+CRF incurred the lowest processing time of 49 s while yielding a comparable F1 score to that obtained by the optimal-performing models.
{"title":"Dataset Construction and Opinion Holder Detection Using Pre-trained Models","authors":"Al- Mahmud, Kazutaka Shimada","doi":"10.52731/ijskm.v7.i2.779","DOIUrl":"https://doi.org/10.52731/ijskm.v7.i2.779","url":null,"abstract":"With the growing prevalence of the Internet, increasingly more people and entities express opinions on online platforms, such as Facebook, Twitter, and Amazon. As it is becoming impossible to detect online opinion trends manually, an automatic approach to detect opinion holders is essential as a means to identify specific concerns regarding a particular topic, product, or problem. Opinion holder detection comprises two steps: the presence of opinion holders in text and identification of opinion holders. The present study examines both steps. Initially, we approach this task as a binary classification problem: INSIDE or OUTSIDE. Then, we consider the identification of opinion holders as a sequence labeling task and prepare an appropriate English-language dataset. Subsequently, we employ three pre-trained models for the opinion holder detection task: BERT, DistilBERT, and contextual string embedding (CSE). For the binary classification task, we employ a logistic regression model on the top layers of the BERT and DistilBERT models. We compare the models’ performance in terms of the F1 score and accuracy. Experimental results show that DistilBERT obtained superior performance, with an F1 score of 0.901 and an accuracy of 0.924. For the opinion holder identification task, we utilize both feature- and fine-tuning-based architectures. Furthermore, we combined CSE and the conditional random field (CRF) with BERT and DistilBERT. For the feature-based architecture, we utilize five models: CSE+CRF, BERT+CRF, (BERT&CSE)+CRF, DistilBERT+CRF, and (DistilBERT&CSE)+CRF. For the fine-tuning-based architecture, we utilize six models: BERT, BERT+CRF, (BERT&CSE)+CRF, DistilBERT, DistilBERT+CRF, and (DistilBERT&CSE)+CRF. All language models are evaluated in terms of F1 score and processing time. The experimental results indicate that both the feature- and fine-tuning-based (DistilBERT&CSE)+CRF models jointly yielded the optimal performance, with an F1 score of 0.9453. However, feature-based CSE+CRF incurred the lowest processing time of 49 s while yielding a comparable F1 score to that obtained by the optimal-performing models.","PeriodicalId":487422,"journal":{"name":"International journal of service and knowledge management","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135498338","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 Japan, telework is attracting renewed attention due to the government-led “work style reform”. The advent of COVID-19 in 2020 has led to the rapid spread of teleworking, and its current state of widespread adoption may be attributed to transient factors as a counter to the spread of COVID-19. A current problem is that dealing with the emergence of risks has been postponed or overlooked because telework was hastily promoted and introduced even though sufficient preparations had not been made. In this work, we conducted a risk assessment from the viewpoints of both companies and employees, identified 28 risk factors, and proposed countermeasures for these factors in order to make teleworking permanently safe and secure in the new normal era. We also proposed the establishment of various systems related to the telework environment and the effective use of cloud computing as measures for both companies and employees. The results of an evaluation of these risk countermeasure proposals using risk values showed that they could reduce risk by approximately 61%. Finally, we constructed a portfolio to identify priorities for the proposed risk measures in terms of practical applicability and to identify the appropriate stepwise introduction of them. The results should contribute to the safe and secure utilization of telework in the new normal era.
{"title":"Risk Management Portfolio for Secure Telework","authors":"Shigeaki Tanimoto, Hiroki Koyama, Yuuna Nakagawa, Teruo Endo, Takashi Hatashima, Atsushi Kanai","doi":"10.52731/ijskm.v7.i2.782","DOIUrl":"https://doi.org/10.52731/ijskm.v7.i2.782","url":null,"abstract":"In Japan, telework is attracting renewed attention due to the government-led “work style reform”. The advent of COVID-19 in 2020 has led to the rapid spread of teleworking, and its current state of widespread adoption may be attributed to transient factors as a counter to the spread of COVID-19. A current problem is that dealing with the emergence of risks has been postponed or overlooked because telework was hastily promoted and introduced even though sufficient preparations had not been made. In this work, we conducted a risk assessment from the viewpoints of both companies and employees, identified 28 risk factors, and proposed countermeasures for these factors in order to make teleworking permanently safe and secure in the new normal era. We also proposed the establishment of various systems related to the telework environment and the effective use of cloud computing as measures for both companies and employees. The results of an evaluation of these risk countermeasure proposals using risk values showed that they could reduce risk by approximately 61%. Finally, we constructed a portfolio to identify priorities for the proposed risk measures in terms of practical applicability and to identify the appropriate stepwise introduction of them. The results should contribute to the safe and secure utilization of telework in the new normal era.","PeriodicalId":487422,"journal":{"name":"International journal of service and knowledge management","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135448057","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：