Pub Date : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923492
Tao Zhou, Jun Ruan, Kehao Wang
Binocular stereo vision is an essential subject of computer vision research with numerous implications in 3D reconstruction. Binocular stereo vision algorithms, however, are computationally demanding and require a high processing units capability, Some conventional systems cannot meet the requirements of real-time and precision. To solve these issues, we employ a software-hardware co-design approach based on FPGA (Field Programmable Gate Arrays). According to the peculiarities of binocular stereo vision, We separate the system tasks into software and hardware portions that can fully utilize FPGA hardware acceleration and ARM (Advanced RISC Machine) data management. The parallel processing capabilities of FPGAs enable a comprehensive pipeline design synchronized with the same system clock to synchronously run multiple image processing components, considerably enhancing processing performance. This paper propose an improved image processing system that realizes binocular ranging through center point matching, We evaluated the design on the AXU3EG development board. The experimental results show that the system has high real-time performance. The system features a faster image processing rate and less expensive hardware than the conventional stereo matching ranging approach, and the ranging precision may be down to the sub-pixel level.
{"title":"Real-time sub-pixel binocular ranging based on FPGA","authors":"Tao Zhou, Jun Ruan, Kehao Wang","doi":"10.1109/ICACSIS56558.2022.9923492","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923492","url":null,"abstract":"Binocular stereo vision is an essential subject of computer vision research with numerous implications in 3D reconstruction. Binocular stereo vision algorithms, however, are computationally demanding and require a high processing units capability, Some conventional systems cannot meet the requirements of real-time and precision. To solve these issues, we employ a software-hardware co-design approach based on FPGA (Field Programmable Gate Arrays). According to the peculiarities of binocular stereo vision, We separate the system tasks into software and hardware portions that can fully utilize FPGA hardware acceleration and ARM (Advanced RISC Machine) data management. The parallel processing capabilities of FPGAs enable a comprehensive pipeline design synchronized with the same system clock to synchronously run multiple image processing components, considerably enhancing processing performance. This paper propose an improved image processing system that realizes binocular ranging through center point matching, We evaluated the design on the AXU3EG development board. The experimental results show that the system has high real-time performance. The system features a faster image processing rate and less expensive hardware than the conventional stereo matching ranging approach, and the ranging precision may be down to the sub-pixel level.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"729 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125444900","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9922961
Gusti Ngurah Yama Adi Putra, K. Junus, H. Santoso
The use of gamification in an e-learning system has been shown to have a positive impact on motivation and learning achievement. Online collaborative learning that utilizes a gamification system has the potential to increase student engagement in the collaboration process. Unfortunately, current research related to the relationship between gamification elements and the participation of online collaborative learning is still limited. This study aims to design a gamification-based online collaborative learning feature in SoloLearn. This study uses the Mechanics, Dynamics, Aesthetics framework to analyze elements in gamification and user-centered design method to create interface design. This research is guided by theoretical foundations such as the influence factors of student participation in online collaborative learning, aspects of a game, and the interface design principles of Shneiderman's Eight Golden Rules of Interface Design, to produce seven alternative designs. Evaluation of the design was carried out by applying contextual interviews. The results showed that all alternative designs were accepted by the respondents in terms of motivating and helping the learning process in the SoloLearn application. The online survey involving 61 respondents exhibits that the proposed application on SoloLearn is satisfactory. However, some improvements are suggested.
在电子学习系统中使用游戏化已被证明对动机和学习成绩有积极的影响。利用游戏化系统的在线协作学习有可能提高学生在协作过程中的参与度。不幸的是，目前有关游戏化元素与在线协作学习参与之间关系的研究仍然有限。本研究旨在为solollearn设计一个基于游戏化的在线协作学习功能。本研究使用力学、动力学、美学框架来分析游戏化中的元素和以用户为中心的设计方法来创建界面设计。本研究以学生参与在线协作学习的影响因素、游戏的各个方面、Shneiderman’s Eight Golden Rules of interface design的界面设计原则等理论基础为指导，产生了七种可供选择的设计。通过应用上下文访谈对设计进行评估。结果表明，在solollearn应用程序的激励和帮助学习过程方面，所有备选设计都被受访者接受。这项涉及61名受访者的在线调查显示，solollearn提出的应用程序令人满意。然而，提出了一些改进建议。
{"title":"Gamification-Based Online Collaborative Learning Feature Design on SoloLearn Application with Mechanics-Dynamics-Aesthetics Framework and User-Centered Design Method","authors":"Gusti Ngurah Yama Adi Putra, K. Junus, H. Santoso","doi":"10.1109/ICACSIS56558.2022.9922961","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9922961","url":null,"abstract":"The use of gamification in an e-learning system has been shown to have a positive impact on motivation and learning achievement. Online collaborative learning that utilizes a gamification system has the potential to increase student engagement in the collaboration process. Unfortunately, current research related to the relationship between gamification elements and the participation of online collaborative learning is still limited. This study aims to design a gamification-based online collaborative learning feature in SoloLearn. This study uses the Mechanics, Dynamics, Aesthetics framework to analyze elements in gamification and user-centered design method to create interface design. This research is guided by theoretical foundations such as the influence factors of student participation in online collaborative learning, aspects of a game, and the interface design principles of Shneiderman's Eight Golden Rules of Interface Design, to produce seven alternative designs. Evaluation of the design was carried out by applying contextual interviews. The results showed that all alternative designs were accepted by the respondents in terms of motivating and helping the learning process in the SoloLearn application. The online survey involving 61 respondents exhibits that the proposed application on SoloLearn is satisfactory. However, some improvements are suggested.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128978811","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923493
Hayu Marta Ambarawati, Mahendrawathi Er, Raditvo Prasetianto Wibowo, Agus Imam Sonhaii
Electronic-Based Government System (SPBE) is one of the programs made by the Government of Indonesia to realize clean, effective, transparent, and accountable governance as well as quality and reliable public services. The Surabaya City Office for Population Administration & Civil Registration (COP ACR) must have the SPBE Architecture, especially the Business Process Architecture (BPA). However, until now, the Surabaya COPACR has not had BPA. The absence of BP A potentially causes problems and make the organization unable to assess its readiness to develop architecture in other domains. In this study, the BP A is designed based on its current condition. This is followed by an assessment of the readiness of the Surabaya COP ACR in designing the Data and Information Architecture (DIA). The BP A is developed based on the BPTrends Associates (BPTA) method to find out the value chain, the stakeholders involved, and the business processes being carried out. There are six value chains that are mapped using BPMN and categorized as core processes, support processes, and management processes. The core process value chain has 108 diagrams grouped into Levels 0 to 5. This BP A is used to develop a Conceptual Data Model (CDM), which produces 35 entities and their relationships. The comparison of the data entities in the CDM created with the current data entities yields a ratio of 24:35. Meanwhile, the ratio of the availability of inputs for the preparation of the DIA is 0:4, which indicates that the Surabaya COPACR needs to prepare these inputs before designing the DIA.
{"title":"Business Process Architecture, Data and Information Architecture: a Public Sector Case","authors":"Hayu Marta Ambarawati, Mahendrawathi Er, Raditvo Prasetianto Wibowo, Agus Imam Sonhaii","doi":"10.1109/ICACSIS56558.2022.9923493","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923493","url":null,"abstract":"Electronic-Based Government System (SPBE) is one of the programs made by the Government of Indonesia to realize clean, effective, transparent, and accountable governance as well as quality and reliable public services. The Surabaya City Office for Population Administration & Civil Registration (COP ACR) must have the SPBE Architecture, especially the Business Process Architecture (BPA). However, until now, the Surabaya COPACR has not had BPA. The absence of BP A potentially causes problems and make the organization unable to assess its readiness to develop architecture in other domains. In this study, the BP A is designed based on its current condition. This is followed by an assessment of the readiness of the Surabaya COP ACR in designing the Data and Information Architecture (DIA). The BP A is developed based on the BPTrends Associates (BPTA) method to find out the value chain, the stakeholders involved, and the business processes being carried out. There are six value chains that are mapped using BPMN and categorized as core processes, support processes, and management processes. The core process value chain has 108 diagrams grouped into Levels 0 to 5. This BP A is used to develop a Conceptual Data Model (CDM), which produces 35 entities and their relationships. The comparison of the data entities in the CDM created with the current data entities yields a ratio of 24:35. Meanwhile, the ratio of the availability of inputs for the preparation of the DIA is 0:4, which indicates that the Surabaya COPACR needs to prepare these inputs before designing the DIA.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127707966","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923548
Iustisia Natalia Simbolon, Devi Wahyuni Silitonga, Putri Era Waty Bakara
The Akuntabilitas Kinerja Pemerintah (AKP) Application is a website-based application that functions to collect, manage, measure, report, and store all reports of work in Kemenko Marves. The purpose of developing the AKP application is to centralize the mechanism for reporting work results with the same reporting standards. The AKP application interface to be built uses the User Centered Design (UCD) method. The AKP application interface will then carry out testing to find usability problems in the initial AKP application prototype. The AKP application testing in this study was carried out in two iterations. The first iteration test was carried out using the Cognitive Walkthrough and Heuristic Evaluation methods from the expert's point of view and the Think Aloud method from the end user side. While the second iteration test, only uses the Think Aloud method. After conducting usability testing, a final high-fidelity prototype of the AKP application will be built. Based on the results of the final prototype, usability testing was carried out using the SUS questionnaire to re-measure the usability level of the AKP application prototype. The target score for the usability value that is expected from this research is 80 (Grade Scale B). Before making improvements to the initial design of the AKP application, the SUS score was 79.5 (Grade Scale = C). However, after improvements were made to the AKP application design, the SUS score became 84 (Grade Scale = B). Based on the test results, the usability score increased by 4.5 and has reached the research target.
Akuntabilitas Kinerja Pemerintah (AKP)应用程序是一个基于网站的应用程序，其功能是收集，管理，测量，报告和存储Kemenko Marves的所有工作报告。开发AKP应用程序的目的是用相同的报告标准来集中报告工作结果的机制。要构建的AKP应用程序接口使用以用户为中心的设计(UCD)方法。然后，AKP应用程序接口将进行测试，以发现初始AKP应用程序原型中的可用性问题。本研究的AKP应用测试分两次迭代进行。第一次迭代测试从专家的角度使用认知演练和启发式评估方法，从最终用户的角度使用大声思考方法。而第二次迭代测试，只使用Think Aloud方法。在进行可用性测试后，将构建AKP应用程序的最终高保真原型。基于最终原型的结果，使用SUS问卷进行可用性测试，重新测量AKP应用原型的可用性水平。本研究期望的可用性值目标得分为80分(等级量表B)，在对AKP应用程序的初始设计进行改进之前，SUS得分为79.5分(等级量表= C)，而在对AKP应用程序设计进行改进后，SUS得分为84分(等级量表= B)，根据测试结果，可用性得分提高了4.5分，达到了研究目标。
{"title":"Design and Evaluation of AKP Application","authors":"Iustisia Natalia Simbolon, Devi Wahyuni Silitonga, Putri Era Waty Bakara","doi":"10.1109/ICACSIS56558.2022.9923548","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923548","url":null,"abstract":"The Akuntabilitas Kinerja Pemerintah (AKP) Application is a website-based application that functions to collect, manage, measure, report, and store all reports of work in Kemenko Marves. The purpose of developing the AKP application is to centralize the mechanism for reporting work results with the same reporting standards. The AKP application interface to be built uses the User Centered Design (UCD) method. The AKP application interface will then carry out testing to find usability problems in the initial AKP application prototype. The AKP application testing in this study was carried out in two iterations. The first iteration test was carried out using the Cognitive Walkthrough and Heuristic Evaluation methods from the expert's point of view and the Think Aloud method from the end user side. While the second iteration test, only uses the Think Aloud method. After conducting usability testing, a final high-fidelity prototype of the AKP application will be built. Based on the results of the final prototype, usability testing was carried out using the SUS questionnaire to re-measure the usability level of the AKP application prototype. The target score for the usability value that is expected from this research is 80 (Grade Scale B). Before making improvements to the initial design of the AKP application, the SUS score was 79.5 (Grade Scale = C). However, after improvements were made to the AKP application design, the SUS score became 84 (Grade Scale = B). Based on the test results, the usability score increased by 4.5 and has reached the research target.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127872776","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 : 2022-10-01DOI: 10.1109/icacsis56558.2022.9923483
{"title":"ICACSIS Cover","authors":"","doi":"10.1109/icacsis56558.2022.9923483","DOIUrl":"https://doi.org/10.1109/icacsis56558.2022.9923483","url":null,"abstract":"","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127030805","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923498
Jonathan Filbert Liysanto, M. R. Shihab
The impact of COVID-19 in Indonesia has been tremendous. Starting from the announcement of the multi-tiered activity restrictions (PPKM) by the government to the national regulations for the enforcement of the tracking and tracing e-government application, PeduliLindungi, for several regions in Indonesia. Due to the application's significant adoption impact, understanding the integration of its factor and impacts are crucial to gaining a holistic understanding of COVID-19 prevention in Indonesia. This research aims to explore an integrated model consisting of factors affecting and impacts of the adoption of e-government applications in Indonesia, specifically towards PeduliLindungi. This research uses an exploratory research model with constructs adapted from various past research inspired by the Unified theory of acceptance and use of technology (UTAUT) dan Technology Acceptance Model (TAM) research models. The analysis process of this research utilizes the Partial Least Square Structural Equation Modelling (PLS-SEM). This research shows that perceived ease of use, perceived benefits, hedonic motivation, and trust in government prove to predict tracking and tracing e-government adoption. On the other hand, Information transparency, government accessibility, social awareness, dan intention to recommend are proven impacts of tracking and tracing e-government adoption. Theoretically, this research theoretically enriches the e-government research field in Indonesia by exploring PeduliLindungi and providing a baseline for future research. Preictally, this research gives insights and suggestions about the impact of adopting tracking and tracing e-government in Indonesia.
{"title":"Exploring an Integrated Model of Tracking and Tracing Application: Insights from PeduliLindungi in Indonesia","authors":"Jonathan Filbert Liysanto, M. R. Shihab","doi":"10.1109/ICACSIS56558.2022.9923498","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923498","url":null,"abstract":"The impact of COVID-19 in Indonesia has been tremendous. Starting from the announcement of the multi-tiered activity restrictions (PPKM) by the government to the national regulations for the enforcement of the tracking and tracing e-government application, PeduliLindungi, for several regions in Indonesia. Due to the application's significant adoption impact, understanding the integration of its factor and impacts are crucial to gaining a holistic understanding of COVID-19 prevention in Indonesia. This research aims to explore an integrated model consisting of factors affecting and impacts of the adoption of e-government applications in Indonesia, specifically towards PeduliLindungi. This research uses an exploratory research model with constructs adapted from various past research inspired by the Unified theory of acceptance and use of technology (UTAUT) dan Technology Acceptance Model (TAM) research models. The analysis process of this research utilizes the Partial Least Square Structural Equation Modelling (PLS-SEM). This research shows that perceived ease of use, perceived benefits, hedonic motivation, and trust in government prove to predict tracking and tracing e-government adoption. On the other hand, Information transparency, government accessibility, social awareness, dan intention to recommend are proven impacts of tracking and tracing e-government adoption. Theoretically, this research theoretically enriches the e-government research field in Indonesia by exploring PeduliLindungi and providing a baseline for future research. Preictally, this research gives insights and suggestions about the impact of adopting tracking and tracing e-government in Indonesia.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125447926","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923425
Christopher Angelo, Diven Clementius, Kensi Chandrawan, Anderies, Irene Anindaputri Iswanto
In this paper, we explain how website's symmetry, colorfulness and visual complexity weights to user experience as a whole. For this study, 15 random websites with varying levels of user interface attributes were chosen, and 10 people volunteered to be the research subject for this study. The user interface attributes are symmetry, colorfulness, and visual complexity. We use UMUX to measure the user experience of a website numerically and compare it to the user interface attributes score using scatterplots. We found a positive correlation between the symmetric website and the UMUX score and an inverse correlation between Visually complex websites and UMUX scores.
{"title":"A Correlational Study Between User Interfaces Attributes to User Experience in a Website","authors":"Christopher Angelo, Diven Clementius, Kensi Chandrawan, Anderies, Irene Anindaputri Iswanto","doi":"10.1109/ICACSIS56558.2022.9923425","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923425","url":null,"abstract":"In this paper, we explain how website's symmetry, colorfulness and visual complexity weights to user experience as a whole. For this study, 15 random websites with varying levels of user interface attributes were chosen, and 10 people volunteered to be the research subject for this study. The user interface attributes are symmetry, colorfulness, and visual complexity. We use UMUX to measure the user experience of a website numerically and compare it to the user interface attributes score using scatterplots. We found a positive correlation between the symmetric website and the UMUX score and an inverse correlation between Visually complex websites and UMUX scores.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121884815","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923512
K. R. Sungkono, Tio Arya Dewa Prakasa, Alfado Rafly Hermawan, Ganendra Aby Bhamakerti, R. Sarno
Medical waste management in a hospital is critical and must be treated properly. Waste management negligence can lead to accumulation of waste, which can trigger new diseases. One of the reasons for the accumulation of waste is insufficient number of resources. Optimization of the number of workers is important, because it will have an impact on the costs incurred and the complete time of the waste treatment. A simulation of medical waste management processes can portray many situations to provide optimal resources. Several existing research utilize Discrete Event Simulation (DES) to simulate waste processes; however, those publications have not determined optimal amount of resources based on cost and time in different rations and identified the effect of difference in the ratio of cost and time to the number of resources. This paper proposes a combination of Discrete Event Simulation (DES) and MOORA to determine amount of resources in different ratio of time and cost. Then, this paper implements two simulations, i.e., a simulation with small amount of incoming waste and a simulation with high amount of incoming waste, to identify the significant between the ratio of cost and time to the number of workers. This study uses a process model of medical waste management of a hospital in East Java to establish the DES. The results of this study indicate that in the case where there is less waste going in, fewer workers will be required than in the case where there is a lot of waste going in. The difference between the balanced ratio and the unbalanced ratio in the case where there is a small amount of incoming waste also does not have a big impact on the resource requirements of workers. In contrast to the case of a lot of incoming waste, the difference in the ratio will be seen significantly in terms of the number of workers needed for each activity.
{"title":"Optimizing Time and Cost Activity based on Discrete Event Simulation with Multi-Objective Optimization Method by Ratio Analysis (MOORA)","authors":"K. R. Sungkono, Tio Arya Dewa Prakasa, Alfado Rafly Hermawan, Ganendra Aby Bhamakerti, R. Sarno","doi":"10.1109/ICACSIS56558.2022.9923512","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923512","url":null,"abstract":"Medical waste management in a hospital is critical and must be treated properly. Waste management negligence can lead to accumulation of waste, which can trigger new diseases. One of the reasons for the accumulation of waste is insufficient number of resources. Optimization of the number of workers is important, because it will have an impact on the costs incurred and the complete time of the waste treatment. A simulation of medical waste management processes can portray many situations to provide optimal resources. Several existing research utilize Discrete Event Simulation (DES) to simulate waste processes; however, those publications have not determined optimal amount of resources based on cost and time in different rations and identified the effect of difference in the ratio of cost and time to the number of resources. This paper proposes a combination of Discrete Event Simulation (DES) and MOORA to determine amount of resources in different ratio of time and cost. Then, this paper implements two simulations, i.e., a simulation with small amount of incoming waste and a simulation with high amount of incoming waste, to identify the significant between the ratio of cost and time to the number of workers. This study uses a process model of medical waste management of a hospital in East Java to establish the DES. The results of this study indicate that in the case where there is less waste going in, fewer workers will be required than in the case where there is a lot of waste going in. The difference between the balanced ratio and the unbalanced ratio in the case where there is a small amount of incoming waste also does not have a big impact on the resource requirements of workers. In contrast to the case of a lot of incoming waste, the difference in the ratio will be seen significantly in terms of the number of workers needed for each activity.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133064981","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923524
H. Pratama, Jeckson Sidabutar
The growth of malware has been significantly high in the last few years. Signature-based and heuristic methods have already been used in malware classification for a long time, but since the growth of polymorphic, both methods have become irrelevant. This problem makes machine learning and deep learning popular to overcome this problem. EfficientNet is one of the transfer learning models, a deep learning subfield. It said that this model could beat the state of the art of deep learning classification in ImageNet. In this paper, the researcher already implemented several EffiicientNet models into two type of Malware BIG 2015 that had been visualized into grayscale and RGB format. From the experiment, we found that EfficientNetB7 implemented into RGB dataset got 99.63% of accuracy, 98.36% of precision, 98.35% of recall, 98.34% of F1-Score, and 98.30% of AUC, with only takes 10 epochs in training process. It could outperformed other pretrained model within a few epochs.
{"title":"Malware Classification and Visualization Using EfficientNet and B2IMG Algorithm","authors":"H. Pratama, Jeckson Sidabutar","doi":"10.1109/ICACSIS56558.2022.9923524","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923524","url":null,"abstract":"The growth of malware has been significantly high in the last few years. Signature-based and heuristic methods have already been used in malware classification for a long time, but since the growth of polymorphic, both methods have become irrelevant. This problem makes machine learning and deep learning popular to overcome this problem. EfficientNet is one of the transfer learning models, a deep learning subfield. It said that this model could beat the state of the art of deep learning classification in ImageNet. In this paper, the researcher already implemented several EffiicientNet models into two type of Malware BIG 2015 that had been visualized into grayscale and RGB format. From the experiment, we found that EfficientNetB7 implemented into RGB dataset got 99.63% of accuracy, 98.36% of precision, 98.35% of recall, 98.34% of F1-Score, and 98.30% of AUC, with only takes 10 epochs in training process. It could outperformed other pretrained model within a few epochs.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125247453","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 : 2022-10-01DOI: 10.1109/ICACSIS56558.2022.9923521
Galangkangin Gotera, Radityo Eko Prasojo, Y. K. Isal
We develop and benchmark a Singlish pretrained neural language model. To this end, we build a novel 3 GB Singlish freetext dataset collected through various Singaporean websites. Then, we leverage ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to train a transformer-based Singlish language model. ELECTRA is chosen due to its resource-efficiency to better ensure reproducibility. We further build two text classification datasets in Singlish: sentiment analysis and language identification. We use the two datasets to fine-tune our ELECTRA model and benchmark the results against other available pretrained models in English and Singlish. Our experiments show that our Singlish ELECTRA model is competitive against the best open-source models we found despite being pretrained within a significantly less amount of time. We publicly release the benchmarking dataset.
{"title":"Developing a Singlish Neural Language Model using ELECTRA","authors":"Galangkangin Gotera, Radityo Eko Prasojo, Y. K. Isal","doi":"10.1109/ICACSIS56558.2022.9923521","DOIUrl":"https://doi.org/10.1109/ICACSIS56558.2022.9923521","url":null,"abstract":"We develop and benchmark a Singlish pretrained neural language model. To this end, we build a novel 3 GB Singlish freetext dataset collected through various Singaporean websites. Then, we leverage ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to train a transformer-based Singlish language model. ELECTRA is chosen due to its resource-efficiency to better ensure reproducibility. We further build two text classification datasets in Singlish: sentiment analysis and language identification. We use the two datasets to fine-tune our ELECTRA model and benchmark the results against other available pretrained models in English and Singlish. Our experiments show that our Singlish ELECTRA model is competitive against the best open-source models we found despite being pretrained within a significantly less amount of time. We publicly release the benchmarking dataset.","PeriodicalId":165728,"journal":{"name":"2022 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130700763","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：