Document grounded conversation (DGC) aims to generate informative responses when talking about a document. It is normally formulated as a sequence-to-sequence (Seq2seq) learning problem, which directly maps source sequences, i.e., the context and background documents, to the target sequence, i.e., the response. These responses are normally used as the final output without further polishing, which may suffer from the global information loss owing to the auto-regression paradigm. To tackle this problem, some researches designed two-pass generation to improve the quality of responses. However, these approaches lack the capability of distinguishing inappropriate words in the first pass, which may maintain the erroneous words while rewrite the correct ones. In this paper, we design a scheduled error correction network (SECN) with multiple generation passes to explicitly locate and rewrite the erroneous words in previous passes. Specifically, a discriminator is employed to distinguish erroneous words which are further revised by a refiner. Moreover, we also apply curriculum learning with reasonable learning schedule to train our model from easy to hard conversations, where the complexity is measured by the number of decoding passes. We conduct comprehensive experiments on a public document grounded conversation dataset, Wizard-of-Wikipedia, and the results demonstrate significant promotions over several strong benchmarks.
{"title":"Learning to Correct Erroneous Words for Document Grounded Conversations","authors":"Junyan Qiu, Haidong Zhang, Yiping Yang","doi":"10.1145/3587828.3587883","DOIUrl":"https://doi.org/10.1145/3587828.3587883","url":null,"abstract":"Document grounded conversation (DGC) aims to generate informative responses when talking about a document. It is normally formulated as a sequence-to-sequence (Seq2seq) learning problem, which directly maps source sequences, i.e., the context and background documents, to the target sequence, i.e., the response. These responses are normally used as the final output without further polishing, which may suffer from the global information loss owing to the auto-regression paradigm. To tackle this problem, some researches designed two-pass generation to improve the quality of responses. However, these approaches lack the capability of distinguishing inappropriate words in the first pass, which may maintain the erroneous words while rewrite the correct ones. In this paper, we design a scheduled error correction network (SECN) with multiple generation passes to explicitly locate and rewrite the erroneous words in previous passes. Specifically, a discriminator is employed to distinguish erroneous words which are further revised by a refiner. Moreover, we also apply curriculum learning with reasonable learning schedule to train our model from easy to hard conversations, where the complexity is measured by the number of decoding passes. We conduct comprehensive experiments on a public document grounded conversation dataset, Wizard-of-Wikipedia, and the results demonstrate significant promotions over several strong benchmarks.","PeriodicalId":340917,"journal":{"name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","volume":"221 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127290184","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 development of artificial intelligence (AI) technologies has led to significant impacts on society. Simultaneously, the ethical issues involved in AI have become increasingly serious, and AI ethics has attracted attention as a topic of active research and discussion. Education in ethics is widely understood to play a crucial role in solving these emerging issues. In this study, we propose a model developed to address some ethical issues of AI based on the case method using network motifs to analyze educational consequences. We evaluated the method in terms of a network analysis of textual data of opinions to understand the changes in participants' perspectives before and after their experience with the case method. The experimental results validated the method we proposed, and the results of the analysis show that the participants’ opinions on the ethics of AI changed to some extent after participating in the case.
{"title":"An Analysis of Opinions on AI Ethics Based on Network Motifs using the Case Method","authors":"Tengfei Shao, Yuya Ieiri, Hitoyoshi Hosoya, Reiko Hishiyama","doi":"10.1145/3587828.3587873","DOIUrl":"https://doi.org/10.1145/3587828.3587873","url":null,"abstract":"The development of artificial intelligence (AI) technologies has led to significant impacts on society. Simultaneously, the ethical issues involved in AI have become increasingly serious, and AI ethics has attracted attention as a topic of active research and discussion. Education in ethics is widely understood to play a crucial role in solving these emerging issues. In this study, we propose a model developed to address some ethical issues of AI based on the case method using network motifs to analyze educational consequences. We evaluated the method in terms of a network analysis of textual data of opinions to understand the changes in participants' perspectives before and after their experience with the case method. The experimental results validated the method we proposed, and the results of the analysis show that the participants’ opinions on the ethics of AI changed to some extent after participating in the case.","PeriodicalId":340917,"journal":{"name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117021638","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}
Individuals and businesses are frequently seen engaging in a fraud scheme, which results in the loss of funds, rights, and assets. This paper aims to provide an empirical analysis and study of a supervised learning technique, decision trees (DT), on a credit card transaction dataset as a benchmark. The proposed approach can be employed to reduce FPs and FNs through supervised machine learning (ML) technique. The fraud detection system also uses historical data to construct a training set and then analyses it to identify fraudulent activity. In this study, suspicious activity is detected using the decision tree classifier. The obtained results showed that FPs and FNs in an online transaction or activity can be reduced to a large extent using DT classification. This method achieved a promising result in terms of performance measures such as precision (99.7%), accuracy (92.25%), recall (81.49%), and F1_score (86.47%) respectively. As a result, the use of ML classifiers can reduce FPs and FNs, increasing customer satisfaction in an online transaction.
{"title":"A Fraud Detection System Using Decision Trees Classification in An Online Transactions","authors":"Y. Qawqzeh, M. Ashraf","doi":"10.1145/3587828.3587860","DOIUrl":"https://doi.org/10.1145/3587828.3587860","url":null,"abstract":"Individuals and businesses are frequently seen engaging in a fraud scheme, which results in the loss of funds, rights, and assets. This paper aims to provide an empirical analysis and study of a supervised learning technique, decision trees (DT), on a credit card transaction dataset as a benchmark. The proposed approach can be employed to reduce FPs and FNs through supervised machine learning (ML) technique. The fraud detection system also uses historical data to construct a training set and then analyses it to identify fraudulent activity. In this study, suspicious activity is detected using the decision tree classifier. The obtained results showed that FPs and FNs in an online transaction or activity can be reduced to a large extent using DT classification. This method achieved a promising result in terms of performance measures such as precision (99.7%), accuracy (92.25%), recall (81.49%), and F1_score (86.47%) respectively. As a result, the use of ML classifiers can reduce FPs and FNs, increasing customer satisfaction in an online transaction.","PeriodicalId":340917,"journal":{"name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117085459","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}
User interface (UI) and user experience (UX) design is an evolving research topic that took up many attentions from researchers especially in software/web design processes. Effective UI/UX design could provide better navigational and accessibility support to access information; intuitive interaction processes to perform several tasks; and good users feedback/responses for its usability acceptance. In this article, we will discuss and overview the fundamental processes of constructing UI/UX design for mobile-based application which focusing on the interactions performed by visually impaired and blind (VIB) users. To meet our purpose, we worked together with the Malaysian Association for the Blind (MAB) to get valuable and useful information as part of the key input in this project. MAB is an association located in Brickfields, Kuala Lumpur that provide facilities and assistance for the People with Disabilities in the category of blindness. The main objective of this collaboration is to establish a strong communication and support between the Universiti Putra Malaysia (UPM) and the MAB in the context of technological support in ICT. We envisage the collaboration to provide better understanding and solutions to any current issues involving VIB users in digital world especially in information technology application and its environments. This article in general emphasizes the overall UI/UX design processes for mobile application prototype development which covered scenario-based activities and tasks among the VIB users. At the end of this article, we will discuss and summarize the best practice of the design steps and processes to provide effective user interface presentation to support better web accessibility and usability acceptance among VIB users.
{"title":"UI/UX Fundamental Design for Mobile Application Prototype to Support Web Accessibility and Usability Acceptance: A Scenario-based Design of Mobile Application for Visually Impaired Users","authors":"A. Jantan, Noris Mohd Norowi, Mariam Azwa Yazid","doi":"10.1145/3587828.3587845","DOIUrl":"https://doi.org/10.1145/3587828.3587845","url":null,"abstract":"User interface (UI) and user experience (UX) design is an evolving research topic that took up many attentions from researchers especially in software/web design processes. Effective UI/UX design could provide better navigational and accessibility support to access information; intuitive interaction processes to perform several tasks; and good users feedback/responses for its usability acceptance. In this article, we will discuss and overview the fundamental processes of constructing UI/UX design for mobile-based application which focusing on the interactions performed by visually impaired and blind (VIB) users. To meet our purpose, we worked together with the Malaysian Association for the Blind (MAB) to get valuable and useful information as part of the key input in this project. MAB is an association located in Brickfields, Kuala Lumpur that provide facilities and assistance for the People with Disabilities in the category of blindness. The main objective of this collaboration is to establish a strong communication and support between the Universiti Putra Malaysia (UPM) and the MAB in the context of technological support in ICT. We envisage the collaboration to provide better understanding and solutions to any current issues involving VIB users in digital world especially in information technology application and its environments. This article in general emphasizes the overall UI/UX design processes for mobile application prototype development which covered scenario-based activities and tasks among the VIB users. At the end of this article, we will discuss and summarize the best practice of the design steps and processes to provide effective user interface presentation to support better web accessibility and usability acceptance among VIB users.","PeriodicalId":340917,"journal":{"name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123331336","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}
Theodosie Uwizeyimana, Alexander Ngenzi, Enan M Nyesheja M.
Elderly people face different old-age-related diseases where some of such diseases transform into chronic diseases. However, without assistance, aged persons are helpless. Even informing someone about their health issues is a challenge for them. In developing countries new technologies, including the internet of things, are being used to monitor old adults’ health and activities, thus enabling them to live safely and independently at home as they age. This study aimed at designing and prototyping a system intended to help improve the health of elderly people in Sub-Saharan Africa. This can be achieved by providing a relatively easy way to monitor the health of elderly people remotely and provide vital signs information of elderly people periodically with automatic alerts in case of emergency issues and tracking the location of elderly people. Therefore, architecture for context awareness and IoT- based systems is proposed to improve the health monitoring of elderly people in Africa and thus improve the quality of life of elderly people. The system uses a heartbeat sensor, Temperature sensor, and GPS Module to collect data with Arduino Uno as Microcontroller. The collected data is sent to the cloud using GSM Module. The cloud data is stored, processed, analyzed, and then sends to the caregiver and Doctor. This system will enhance the quality of life for elderly people by enabling them to get real-time health information and medication from any location. Additionally, it will enable healthcare practitioners to remotely monitor them.
{"title":"IoT system to monitor health conditions of elderly","authors":"Theodosie Uwizeyimana, Alexander Ngenzi, Enan M Nyesheja M.","doi":"10.1145/3587828.3587864","DOIUrl":"https://doi.org/10.1145/3587828.3587864","url":null,"abstract":"Elderly people face different old-age-related diseases where some of such diseases transform into chronic diseases. However, without assistance, aged persons are helpless. Even informing someone about their health issues is a challenge for them. In developing countries new technologies, including the internet of things, are being used to monitor old adults’ health and activities, thus enabling them to live safely and independently at home as they age. This study aimed at designing and prototyping a system intended to help improve the health of elderly people in Sub-Saharan Africa. This can be achieved by providing a relatively easy way to monitor the health of elderly people remotely and provide vital signs information of elderly people periodically with automatic alerts in case of emergency issues and tracking the location of elderly people. Therefore, architecture for context awareness and IoT- based systems is proposed to improve the health monitoring of elderly people in Africa and thus improve the quality of life of elderly people. The system uses a heartbeat sensor, Temperature sensor, and GPS Module to collect data with Arduino Uno as Microcontroller. The collected data is sent to the cloud using GSM Module. The cloud data is stored, processed, analyzed, and then sends to the caregiver and Doctor. This system will enhance the quality of life for elderly people by enabling them to get real-time health information and medication from any location. Additionally, it will enable healthcare practitioners to remotely monitor them.","PeriodicalId":340917,"journal":{"name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121504968","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}
Raft is widely known as one of the distributed consensus protocols and is used to build highly available and strongly consistent services. Using Maude, we formally specify the leader election in Raft and conduct model checking to check whether the protocol enjoys the Election Safety Property that at most one leader can be elected in each logical time, which is one of the properties that Raft is expected to guarantee. Our model checking experiments show that the protocol enjoys the property under the condition that we limit the logical time and the number of servers. We also aim to promote understanding of the leader election in Raft.
{"title":"Formal Specification and Model Checking of Raft Leader Election in Maude*","authors":"Takanori Ishibashi, K. Ogata","doi":"10.1145/3587828.3587835","DOIUrl":"https://doi.org/10.1145/3587828.3587835","url":null,"abstract":"Raft is widely known as one of the distributed consensus protocols and is used to build highly available and strongly consistent services. Using Maude, we formally specify the leader election in Raft and conduct model checking to check whether the protocol enjoys the Election Safety Property that at most one leader can be elected in each logical time, which is one of the properties that Raft is expected to guarantee. Our model checking experiments show that the protocol enjoys the property under the condition that we limit the logical time and the number of servers. We also aim to promote understanding of the leader election in Raft.","PeriodicalId":340917,"journal":{"name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115911392","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 use of synthesized images in fields that prioritize visual appearance, particularly the field of art, places a high value on aesthetics, with the system's output images required to adhere to several aesthetic rules. There are two approaches to aesthetic image synthesis with architecture based on GAN. The first strategy is to modify the loss function on the GAN so that, in addition to the loss from the GAN architecture, aesthetic loss and content/semantic loss are also calculated and the total loss is the sum of the three loss calculations. However, the outcomes still fall short of the expected natural image appearance. The second strategy involves modifying the GAN architecture by adding a new layer to the GAN generator and discriminator network, while the loss function calculation remains unchanged. The results of this second approach to image synthesis have not been optimized in terms of producing meaningful images across multiple semantic classes. This study proposes a method for increasing the aesthetic value of the synthesized image by modifying the two approaches and employing the multiple-aesthetic-aware GAN method. The proposed method takes conditional semantic information and conditional aesthetic information into account not only in the GAN architecture, but also in the loss function value calculation. The proposed method is the result of ongoing research and will be evaluated using the Inception Score (IS), the Frechet Inception Distance (FID), and an aesthetic value metric.
{"title":"Aesthetic Image Synthesis Using Multiple-Aesthetic-Aware GAN","authors":"Yaya Setiyadi, J. Santoso, K. Surendro","doi":"10.1145/3587828.3587852","DOIUrl":"https://doi.org/10.1145/3587828.3587852","url":null,"abstract":"The use of synthesized images in fields that prioritize visual appearance, particularly the field of art, places a high value on aesthetics, with the system's output images required to adhere to several aesthetic rules. There are two approaches to aesthetic image synthesis with architecture based on GAN. The first strategy is to modify the loss function on the GAN so that, in addition to the loss from the GAN architecture, aesthetic loss and content/semantic loss are also calculated and the total loss is the sum of the three loss calculations. However, the outcomes still fall short of the expected natural image appearance. The second strategy involves modifying the GAN architecture by adding a new layer to the GAN generator and discriminator network, while the loss function calculation remains unchanged. The results of this second approach to image synthesis have not been optimized in terms of producing meaningful images across multiple semantic classes. This study proposes a method for increasing the aesthetic value of the synthesized image by modifying the two approaches and employing the multiple-aesthetic-aware GAN method. The proposed method takes conditional semantic information and conditional aesthetic information into account not only in the GAN architecture, but also in the loss function value calculation. The proposed method is the result of ongoing research and will be evaluated using the Inception Score (IS), the Frechet Inception Distance (FID), and an aesthetic value metric.","PeriodicalId":340917,"journal":{"name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131031906","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}
Abstract: Clustering analysis, specifically for extensive image data, is increasingly being applied in various fields such as finance, risk management, prediction, etc., and has been a fascinating subject in many scientific discussions. Deep learning, a widely used approach, and classical methods address complex classification problems stemming from real-world cases. In this study, we took various approaches to classification problems and measured their effectiveness by combining different techniques using the results of different scenarios. Many approaches have been proposed to solve the clustering problem; complex clustering methods such as hierarchical, density-based, centroid-based, and graph theoretical have been submitted. However, when it comes to real-world applications, they exposed significant drawbacks when the dataset introduced immeasurable vagueness, uncertainty, or overlapping samples that made it impossible to predict and classify. Several attempts have been made to improve the clustering method's performance, including joint CNN clustering models. Still, many of them carry the cons of the complicated clustering method, which limits the capability of CNN. The combined CNN clustering method is designed to address the problem with those deterministic CNN clustering models and was evaluated on a dataset we collected from the website designbyhumans.com, with enough features to represent a non-synthetic dataset. This research aims to improve upon the established model by using estimation techniques in determining model parameters and graphing plots to justify those choices and give insights into how the model performs on a non-synthetic dataset like ours. We concluded that the model significantly improved compared with a popular complex clustering method, which has been evaluated by computational time, using different metrics to represent how better separated each cluster was. Based on conducted experiments and the future development of the method, we discussed and addressed some of the drawbacks of this approach.
{"title":"Improvement for Large-Scale Image Data using Fuzzy Rough C-Mean Based Unsupervised CNN Clustering: An Empirical Study on designbyhumans.com","authors":"Anh Tuan Tran, B. Q. Tran, Kien Trung Luong","doi":"10.1145/3587828.3587829","DOIUrl":"https://doi.org/10.1145/3587828.3587829","url":null,"abstract":"Abstract: Clustering analysis, specifically for extensive image data, is increasingly being applied in various fields such as finance, risk management, prediction, etc., and has been a fascinating subject in many scientific discussions. Deep learning, a widely used approach, and classical methods address complex classification problems stemming from real-world cases. In this study, we took various approaches to classification problems and measured their effectiveness by combining different techniques using the results of different scenarios. Many approaches have been proposed to solve the clustering problem; complex clustering methods such as hierarchical, density-based, centroid-based, and graph theoretical have been submitted. However, when it comes to real-world applications, they exposed significant drawbacks when the dataset introduced immeasurable vagueness, uncertainty, or overlapping samples that made it impossible to predict and classify. Several attempts have been made to improve the clustering method's performance, including joint CNN clustering models. Still, many of them carry the cons of the complicated clustering method, which limits the capability of CNN. The combined CNN clustering method is designed to address the problem with those deterministic CNN clustering models and was evaluated on a dataset we collected from the website designbyhumans.com, with enough features to represent a non-synthetic dataset. This research aims to improve upon the established model by using estimation techniques in determining model parameters and graphing plots to justify those choices and give insights into how the model performs on a non-synthetic dataset like ours. We concluded that the model significantly improved compared with a popular complex clustering method, which has been evaluated by computational time, using different metrics to represent how better separated each cluster was. Based on conducted experiments and the future development of the method, we discussed and addressed some of the drawbacks of this approach.","PeriodicalId":340917,"journal":{"name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133289426","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}
Byan Sakura Kireyna Aji, Erna Hikmawati, K. Surendro
Rapid technology innovation has led to unwanted side effects such as global warming and climate change. Recent studies reported that in the present digital age, many industries are utilizing energy-consuming technology in their buildings. Unfortunately, this led to extensive carbon emission that is often unmonitored and not properly managed. This challenge also occurs at the buildings in Bandung Institute of Technology which operates numerous facilities that may contribute to the level of carbon footprint. Accordingly, this research focuses on developing a smart carbon footprint monitoring model for buildings at Bandung Institute of Technology using a design thinking approach to ensure that the result can be adapted to solve the current problems in this organization. The model is expected to bring forth an insight into the carbon level production of each building and its projection in the future so a preventive measure can be considered for Bandung Institute of Technology's emission management.
{"title":"Implementation of Design Thinking in Smart Carbon Footprint Monitoring Model for Buildings: Case Study: Bandung Institute of Technology","authors":"Byan Sakura Kireyna Aji, Erna Hikmawati, K. Surendro","doi":"10.1145/3587828.3587836","DOIUrl":"https://doi.org/10.1145/3587828.3587836","url":null,"abstract":"Rapid technology innovation has led to unwanted side effects such as global warming and climate change. Recent studies reported that in the present digital age, many industries are utilizing energy-consuming technology in their buildings. Unfortunately, this led to extensive carbon emission that is often unmonitored and not properly managed. This challenge also occurs at the buildings in Bandung Institute of Technology which operates numerous facilities that may contribute to the level of carbon footprint. Accordingly, this research focuses on developing a smart carbon footprint monitoring model for buildings at Bandung Institute of Technology using a design thinking approach to ensure that the result can be adapted to solve the current problems in this organization. The model is expected to bring forth an insight into the carbon level production of each building and its projection in the future so a preventive measure can be considered for Bandung Institute of Technology's emission management.","PeriodicalId":340917,"journal":{"name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132104776","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}
Medical records, also known as Electronic Health Records, can be used to analyze medical data which contributes to greater knowledge of information related to disease, disease phase, and early identification of disease. The main problem in medical records is how to determine the features of the selected subset to make predictions on clinical data. The problem of classifying medical record data involves many features. This creates problems in determining which features have a correlation to the predicted results. Feature selection is an appropriate technique for selecting risk factors for disease in medical records. Feature selection requires optimization techniques so that the accuracy value can be increased. Therefore, feature selection using genetic algorithms has the ability to optimize the selected features. The feature selection technique, namely the wrapper, applies a learning algorithm to test the features to be selected. The embedded engineering approach to feature selection makes it possible to apply learning in the selection process. Genetic algorithm-based feature selection method with wrapper-embedded technique is expected to produce an effective feature subset. This technique evaluates features by using combinations in fitness calculations with the aim of assessing the selected features. The development of genetic algorithms by applying fitness value evaluation and elitist aims to maintain the fitness value in the next generation.
{"title":"FEATURE SELECTION METHOD BASED ON GENETIC ALGORITHM WITH WRAPPER-EMBEDDED TECHNIQUE FOR MEDICAL RECORD CLASSIFICATION","authors":"Yuda Syahidin, N. Maulidevi, K. Surendro","doi":"10.1145/3587828.3587856","DOIUrl":"https://doi.org/10.1145/3587828.3587856","url":null,"abstract":"Medical records, also known as Electronic Health Records, can be used to analyze medical data which contributes to greater knowledge of information related to disease, disease phase, and early identification of disease. The main problem in medical records is how to determine the features of the selected subset to make predictions on clinical data. The problem of classifying medical record data involves many features. This creates problems in determining which features have a correlation to the predicted results. Feature selection is an appropriate technique for selecting risk factors for disease in medical records. Feature selection requires optimization techniques so that the accuracy value can be increased. Therefore, feature selection using genetic algorithms has the ability to optimize the selected features. The feature selection technique, namely the wrapper, applies a learning algorithm to test the features to be selected. The embedded engineering approach to feature selection makes it possible to apply learning in the selection process. Genetic algorithm-based feature selection method with wrapper-embedded technique is expected to produce an effective feature subset. This technique evaluates features by using combinations in fitness calculations with the aim of assessing the selected features. The development of genetic algorithms by applying fitness value evaluation and elitist aims to maintain the fitness value in the next generation.","PeriodicalId":340917,"journal":{"name":"Proceedings of the 2023 12th International Conference on Software and Computer Applications","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127632749","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：