Pub Date : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970043
Pipit Utami, Rudy Hartanto, I. Soesanti
Increasing the FER accuracy can be done with the Deep-CNN model. However, the model requires a dataset in the training and testing process. Meanwhile, there is still a scarcity of facial expression datasets with expressions in specific contexts for emotion recognition. In general, the existing datasets show common expressions. Therefore, this paper proposes a dataset that includes basic and specific complex emotions in teaching contexts that can be used in the Deep-CNN model. The developed dataset consists of six basic expressions, neutral, and five specific expressions in the teaching context, namely anxiety, enjoyment, hope, hopelessness, and shame. The dataset was obtained from 52 respondents. Dataset development methods consist of needs identification, data collection, data validation, data adjustment, data training and data evaluation. Dataset test performance from testing the four Deep-CNN architectures shows that the multiple emotion classes in the dataset can be classified well. Accuracy using simple CNN is 90%, while the three types of Xception vary with values of 88%, 92% and 93%. Likewise, with accuracy, for precision, recall and f1score from the results of testing datasets with four CNN architectures show good values. The training time on simple CNN took 49.55 minutes and for the three types of Xception it was 47.67 minutes, 32.69 minutes, and 32.56 minutes.
{"title":"The Development of Facial Expressions Dataset for Teaching Context: Preliminary Research","authors":"Pipit Utami, Rudy Hartanto, I. Soesanti","doi":"10.1109/IC2IE56416.2022.9970043","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970043","url":null,"abstract":"Increasing the FER accuracy can be done with the Deep-CNN model. However, the model requires a dataset in the training and testing process. Meanwhile, there is still a scarcity of facial expression datasets with expressions in specific contexts for emotion recognition. In general, the existing datasets show common expressions. Therefore, this paper proposes a dataset that includes basic and specific complex emotions in teaching contexts that can be used in the Deep-CNN model. The developed dataset consists of six basic expressions, neutral, and five specific expressions in the teaching context, namely anxiety, enjoyment, hope, hopelessness, and shame. The dataset was obtained from 52 respondents. Dataset development methods consist of needs identification, data collection, data validation, data adjustment, data training and data evaluation. Dataset test performance from testing the four Deep-CNN architectures shows that the multiple emotion classes in the dataset can be classified well. Accuracy using simple CNN is 90%, while the three types of Xception vary with values of 88%, 92% and 93%. Likewise, with accuracy, for precision, recall and f1score from the results of testing datasets with four CNN architectures show good values. The training time on simple CNN took 49.55 minutes and for the three types of Xception it was 47.67 minutes, 32.69 minutes, and 32.56 minutes.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127728011","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970191
M. R. Ridho, H. Nuha
Phishing site is a website created by internet criminals as closely as possible to resemble a real site to trick internet users by making it look like accessing a site from an official website. In overcoming the many phishing sites that exist in this study, the Extreme Learning Machine (ELM) classification method is used because ELM is one of the algorithms that is often used in classification and regression in machine learning. In this study, the accuracy value obtained from the test which was repeated 10 times was between 82-84% and the time between 5–11 $s$ with the best accuracy of 84.02% with a time of 7.98 $s$, the accuracy results generated from the ELM algorithm are indeed not very good. This large amount occurs because of the overfitting experienced by the formed classification model so that the false positives obtained are quite large. Referring to the dataset itself, the most influential feature or attribute in the labeling of phishing sites is the time domain expires, if the time domain expires has reached 200 days then the site has a phishing site label. In this study, ELM was compared with several other machine learning algorithms such as Support Vector Machine (SVM), Naive Bayes and Decision Tree.
{"title":"Application of Extreme Learning Machine (ELM) Classification in Detecting Phishing Sites","authors":"M. R. Ridho, H. Nuha","doi":"10.1109/IC2IE56416.2022.9970191","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970191","url":null,"abstract":"Phishing site is a website created by internet criminals as closely as possible to resemble a real site to trick internet users by making it look like accessing a site from an official website. In overcoming the many phishing sites that exist in this study, the Extreme Learning Machine (ELM) classification method is used because ELM is one of the algorithms that is often used in classification and regression in machine learning. In this study, the accuracy value obtained from the test which was repeated 10 times was between 82-84% and the time between 5–11 $s$ with the best accuracy of 84.02% with a time of 7.98 $s$, the accuracy results generated from the ELM algorithm are indeed not very good. This large amount occurs because of the overfitting experienced by the formed classification model so that the false positives obtained are quite large. Referring to the dataset itself, the most influential feature or attribute in the labeling of phishing sites is the time domain expires, if the time domain expires has reached 200 days then the site has a phishing site label. In this study, ELM was compared with several other machine learning algorithms such as Support Vector Machine (SVM), Naive Bayes and Decision Tree.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126835786","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970184
Ivan James G. Gardose, Ryan T. Caballero, Urbano B. Patayon
This study aims to develop an automatic identification model for Corynespora Rubber Disease using a pre-trained Convolutional Neural Network. It explores the effect of using images captured in the natural background and with background elimination when used during training, validation, and testing. In terms of accuracy, the DenseNet, and Inception-V3architectures show an accuracy of 99.8% and 99.2% using the data sets of rubber leaves which is the combination of natural background and background elimination. Unlike Xception architecture with only 99% accuracy using the data sets of natural background. As to precision, the Xception and Inception-V3architectures attain the precision of 100% using the data set of rubber leaves which is the combination of natural background and background elimination. Except for DenseNet architecture with only 99.7% precision. Then for the F1 score, the DenseNet architecture shows an F1 score of 99.8% using the data sets of rubber leaves which is a combination of natural background and background elimination. Then Xception and Inception-V3architectures with an F1 score of 99% and 98.6% using the same data sets of natural background. With the above results, the different models can be used for detecting and identifying Corynespora Rubber Disease.
{"title":"Identification of Corynespora Rubber Disease using Pre-Trained Convolutional Neural Network","authors":"Ivan James G. Gardose, Ryan T. Caballero, Urbano B. Patayon","doi":"10.1109/IC2IE56416.2022.9970184","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970184","url":null,"abstract":"This study aims to develop an automatic identification model for Corynespora Rubber Disease using a pre-trained Convolutional Neural Network. It explores the effect of using images captured in the natural background and with background elimination when used during training, validation, and testing. In terms of accuracy, the DenseNet, and Inception-V3architectures show an accuracy of 99.8% and 99.2% using the data sets of rubber leaves which is the combination of natural background and background elimination. Unlike Xception architecture with only 99% accuracy using the data sets of natural background. As to precision, the Xception and Inception-V3architectures attain the precision of 100% using the data set of rubber leaves which is the combination of natural background and background elimination. Except for DenseNet architecture with only 99.7% precision. Then for the F1 score, the DenseNet architecture shows an F1 score of 99.8% using the data sets of rubber leaves which is a combination of natural background and background elimination. Then Xception and Inception-V3architectures with an F1 score of 99% and 98.6% using the same data sets of natural background. With the above results, the different models can be used for detecting and identifying Corynespora Rubber Disease.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121989952","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970099
Muhammad Dzaky Akbar Aryoputra, A. Agus
Social media is a tool that brands can use to engage and influence consumers and potential customers. This is because social media provides an opportunity for brands to be able to participate and interact with consumers and potential customers while increasing a sense of familiarity and building relationships with consumers and potential customers. One of the social media applications that brands can use to interact and engage with their consumers is Instagram. Especially brands in the fashion industry, where brands in this industry are very dependent on the visual aspect. One of Indonesia's fashion brands with the most followers and interactions on Instagram is @UniqloIndonesia. This study was conducted to determine the factors that can affect the involvement on a brand's social media Instagram, such as brand familiarity and information quality. This study also aims to determine the effect of involvement on a brand's social media Instagram on attitudes towards a brand's social media Instagram and future purchase intentions. The data in this study were processed using Partial Least Squares-Structural Equation Modeling (PLS-SEM). The results of the study show that information quality has an effect on involvement on the brand's social media Instagram. Involvement in brand's social media instagram affects attitudes towards the brand's social media instagram. Attitudes towards Instagram’ s social media brand have a direct effect on future purchase intentions and mediate the relationship between Instagram's involvement in brand's social media and future purchase intentions.
{"title":"Analysis the Effect of Involvement on Brand's Social Media Instagram Account of Uniqlo Indonesia (@UniqloIndonesia) on Consumer Purchase Intention","authors":"Muhammad Dzaky Akbar Aryoputra, A. Agus","doi":"10.1109/IC2IE56416.2022.9970099","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970099","url":null,"abstract":"Social media is a tool that brands can use to engage and influence consumers and potential customers. This is because social media provides an opportunity for brands to be able to participate and interact with consumers and potential customers while increasing a sense of familiarity and building relationships with consumers and potential customers. One of the social media applications that brands can use to interact and engage with their consumers is Instagram. Especially brands in the fashion industry, where brands in this industry are very dependent on the visual aspect. One of Indonesia's fashion brands with the most followers and interactions on Instagram is @UniqloIndonesia. This study was conducted to determine the factors that can affect the involvement on a brand's social media Instagram, such as brand familiarity and information quality. This study also aims to determine the effect of involvement on a brand's social media Instagram on attitudes towards a brand's social media Instagram and future purchase intentions. The data in this study were processed using Partial Least Squares-Structural Equation Modeling (PLS-SEM). The results of the study show that information quality has an effect on involvement on the brand's social media Instagram. Involvement in brand's social media instagram affects attitudes towards the brand's social media instagram. Attitudes towards Instagram’ s social media brand have a direct effect on future purchase intentions and mediate the relationship between Instagram's involvement in brand's social media and future purchase intentions.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125036619","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970120
Ubedilah, S. Budiyanto, L. M. Silalahi
The development of communication technology is now very dependent on the internet, not only for information delivery but also for telecommunications (Voice and Data). VoIP (Voice over Internet Protocol) is a communication technology based on IP (Internet Protocol). Data confidentiality using a VPN (Virtual Private Network) can remote access from a private network to another private network over the internet and use protocol tunneling in its security system. The method used in this study is the PPDIOO method (prepare, plan, design, implement, operate, optimize). This method was chosen because it contains the right elements to use in the research. The results of the application of this method will later produce conclusions such as the quality of VoIP using private servers by comparing between GRE tunnel + IPSec and IPIP tunnel on the Internet network. Testing is done between sites with Voice calls. So that quality of service analysis is obtained with delay, jitter, throughput and packet loss parameters. The test results of the Quality of Service of VoIP communication running on intranet networks by utilizing the IPIP tunneling method are better than using the GRE + IPSec tunneling method.
通信技术的发展现在非常依赖互联网，不仅用于信息传递，而且用于电信(语音和数据)。VoIP (Voice over Internet Protocol)是一种基于IP (Internet Protocol)的通信技术。使用VPN(虚拟专用网络)的数据机密性可以通过internet从一个专用网络远程访问到另一个专用网络，并在其安全系统中使用协议隧道。本研究使用的方法是PPDIOO方法(准备、计划、设计、实施、操作、优化)。选择这种方法是因为它包含了在研究中使用的正确元素。通过对Internet上GRE隧道+ IPSec和IPIP隧道的比较，可以得出使用专用服务器的VoIP的质量等结论。测试是在有语音通话的站点之间进行的。利用时延、抖动、吞吐量、丢包等参数进行业务质量分析。在内网运行的VoIP通信中，采用IPIP隧道方式的业务质量测试结果优于GRE + IPSec隧道方式。
{"title":"Analysis QoS VoIP using GRE + IPSec Tunnel and IPIP Based on Session Initiation Protocol","authors":"Ubedilah, S. Budiyanto, L. M. Silalahi","doi":"10.1109/IC2IE56416.2022.9970120","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970120","url":null,"abstract":"The development of communication technology is now very dependent on the internet, not only for information delivery but also for telecommunications (Voice and Data). VoIP (Voice over Internet Protocol) is a communication technology based on IP (Internet Protocol). Data confidentiality using a VPN (Virtual Private Network) can remote access from a private network to another private network over the internet and use protocol tunneling in its security system. The method used in this study is the PPDIOO method (prepare, plan, design, implement, operate, optimize). This method was chosen because it contains the right elements to use in the research. The results of the application of this method will later produce conclusions such as the quality of VoIP using private servers by comparing between GRE tunnel + IPSec and IPIP tunnel on the Internet network. Testing is done between sites with Voice calls. So that quality of service analysis is obtained with delay, jitter, throughput and packet loss parameters. The test results of the Quality of Service of VoIP communication running on intranet networks by utilizing the IPIP tunneling method are better than using the GRE + IPSec tunneling method.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128332199","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}
Internet of Things (IoT) technology has brought a revolution in several ways to a common person's life by making everything smart and intelligent. During the Covid-19 crisis, health workers around the world needed to monitor patients' health and needed to provide sufficient oxygen, when necessary, as Covid-19 was responsible for many respiratory cases. Health workers were at high risk of being contaminated while treating Covid-19 patients. The study of this paper is to propose an IoT-based automatic oxygen flow control in response to the Covid-19 crisis. The proposed approach helped to real-time monitoring of SpO2, heartbeat, oxygen quantity of oxygen cylinder, and control of the flow of oxygen based on SpO2 value. A health worker can monitor a patient's health-related parameters and control the flow of oxygen without any physical contact with it. Also, provides an alarm to the health worker when SpO2 is below the threshold and re-measuring oxygen quantity of oxygen cylinder with the help of our developed android app. Implementation of IoT-based low-cost pulse oximeter and IoT-based pressure gauge helps to monitor and control different health parameters. The IoT-based system may potentially be valuable during the Covid-19 pandemic for accurate oxygen flow distribution and for saving people's lives.
{"title":"Design and Implementation of IoT-Based Automatic Oxygen Flow Control in Response to the Covid-19 Crisis","authors":"Ahmed Lamon, Kanoge Roy, Ahmmad Musha, Md. Galib Hasan, Shamsul Abedin","doi":"10.1109/IC2IE56416.2022.9970199","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970199","url":null,"abstract":"Internet of Things (IoT) technology has brought a revolution in several ways to a common person's life by making everything smart and intelligent. During the Covid-19 crisis, health workers around the world needed to monitor patients' health and needed to provide sufficient oxygen, when necessary, as Covid-19 was responsible for many respiratory cases. Health workers were at high risk of being contaminated while treating Covid-19 patients. The study of this paper is to propose an IoT-based automatic oxygen flow control in response to the Covid-19 crisis. The proposed approach helped to real-time monitoring of SpO2, heartbeat, oxygen quantity of oxygen cylinder, and control of the flow of oxygen based on SpO2 value. A health worker can monitor a patient's health-related parameters and control the flow of oxygen without any physical contact with it. Also, provides an alarm to the health worker when SpO2 is below the threshold and re-measuring oxygen quantity of oxygen cylinder with the help of our developed android app. Implementation of IoT-based low-cost pulse oximeter and IoT-based pressure gauge helps to monitor and control different health parameters. The IoT-based system may potentially be valuable during the Covid-19 pandemic for accurate oxygen flow distribution and for saving people's lives.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129907634","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970096
E. H. Nurkifli, T. Hwang
The fundamental concept in an IWSN-based Healthcare Environment is that doctors' devices can directly access the data from a patient's sensor in real-time. Unfortunately, wireless-based communication between the doctor's device and the patient's sensor is vulnerable to attacks such as impersonation, tracking, DoS, and cloning attacks. Therefore, this article tries to resolve the security problems in an IWSN-based Healthcare Environment by developing a secure authentication protocol using biometric and PUF -based. In addition, the informal use of solid reasoning analysis and formal analysis using the scyther tool proves that our protocol achieves security features and withstanding well-known attacks.
{"title":"A Secure Authentication at Remote Real-Time Data Access in IWSN-Based Healthcare Environment","authors":"E. H. Nurkifli, T. Hwang","doi":"10.1109/IC2IE56416.2022.9970096","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970096","url":null,"abstract":"The fundamental concept in an IWSN-based Healthcare Environment is that doctors' devices can directly access the data from a patient's sensor in real-time. Unfortunately, wireless-based communication between the doctor's device and the patient's sensor is vulnerable to attacks such as impersonation, tracking, DoS, and cloning attacks. Therefore, this article tries to resolve the security problems in an IWSN-based Healthcare Environment by developing a secure authentication protocol using biometric and PUF -based. In addition, the informal use of solid reasoning analysis and formal analysis using the scyther tool proves that our protocol achieves security features and withstanding well-known attacks.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"1230 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134495494","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970169
Defiana Arnaldy, Heru Sukoco, S. N. Neyman, Muladno, K. Seminar
This paper uses a smart system to present a methodical literature review on cattle breeding management. Indonesia is a large country with a veritably large population. Indonesian people like to eat beef; thus the demand for beef in Indonesia always increases. Therefore, Indonesia needs a system to manage livestock data nationally. Sekolah Peternakan Rakyat (SPR) is one of the Bogor Agricultural Institute's programs to strengthen the people's livestock business. In addressing this issue, experimenters proposed using an intelligence system for cattle breeding management in SPR. The method used in this research is a systematic literature review (SLR). The approach used is PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). Hence, this paper analyses the literature to fill the gap by conducting a scoping study to answer three pre-defined research questions. First, search for papers using publish or perish tools with a database of papers used for the last five years (2017 - 2022). Grounded on the search results, the total composition data for all data from the composition database used was 5513 papers, with an aggregate of 3010 papers in the form of journals. In comparison, the number of proceedings amounted to 239 papers. It is known that the content of cattle breeding management using information technology has been extensively carried out. Inquiries are generally carried out outside Indonesia. Although several papers discuss cattle breeding in Indonesia, the discussion is more towards livestock, not information technology.
本文使用智能系统对牛的养殖管理进行了系统的文献综述。印度尼西亚是一个人口众多的大国。印尼人喜欢吃牛肉;因此，印尼对牛肉的需求一直在增加。因此，印度尼西亚需要一个管理全国牲畜数据的系统。Sekolah Peternakan Rakyat (SPR)是茂物农业研究所加强人民畜牧业的项目之一。为了解决这一问题，实验人员提出了在SPR的牛养殖管理中使用智能系统。本研究采用的方法是系统文献回顾法(SLR)。使用的方法是PRISMA(系统评价和荟萃分析的首选报告项目)。因此，本文通过进行范围研究来回答三个预先定义的研究问题来分析文献以填补空白。首先，使用“发表或消亡”工具，使用过去五年(2017 - 2022)的论文数据库搜索论文。根据检索结果，所使用的论文数据库中所有数据的论文数据总数为5513篇，期刊形式的论文总数为3010篇。相比之下，诉讼的数量为239份。据了解，利用信息技术进行养牛管理的内容已经广泛开展。调查一般在印度尼西亚境外进行。虽然有几篇论文讨论了印度尼西亚的养牛问题，但讨论更多的是针对牲畜，而不是信息技术。
{"title":"Cattle Breeding Management using Smart System: A Systematic Literature Review","authors":"Defiana Arnaldy, Heru Sukoco, S. N. Neyman, Muladno, K. Seminar","doi":"10.1109/IC2IE56416.2022.9970169","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970169","url":null,"abstract":"This paper uses a smart system to present a methodical literature review on cattle breeding management. Indonesia is a large country with a veritably large population. Indonesian people like to eat beef; thus the demand for beef in Indonesia always increases. Therefore, Indonesia needs a system to manage livestock data nationally. Sekolah Peternakan Rakyat (SPR) is one of the Bogor Agricultural Institute's programs to strengthen the people's livestock business. In addressing this issue, experimenters proposed using an intelligence system for cattle breeding management in SPR. The method used in this research is a systematic literature review (SLR). The approach used is PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). Hence, this paper analyses the literature to fill the gap by conducting a scoping study to answer three pre-defined research questions. First, search for papers using publish or perish tools with a database of papers used for the last five years (2017 - 2022). Grounded on the search results, the total composition data for all data from the composition database used was 5513 papers, with an aggregate of 3010 papers in the form of journals. In comparison, the number of proceedings amounted to 239 papers. It is known that the content of cattle breeding management using information technology has been extensively carried out. Inquiries are generally carried out outside Indonesia. Although several papers discuss cattle breeding in Indonesia, the discussion is more towards livestock, not information technology.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"2 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131775277","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970078
Nenny Anggraini, Syarif Hilmi Ramadhani, Luh Kesuma Wardhani, Nashrul Hakiem, I. Shofi, M. T. Rosyadi
This study aimed to develop a mask detection tool with SSDLite MobilenetV3 Small based on Raspberry Pi 4. SSDLite MobilenetV3 Small is a single-stage object detection. The single-stage object detection method is faster than the two-stage detection method. However, it has the disadvantage as the level of accuracy is not as good as the two-stage detection method. In the experiments, we used some methods to compare with SSDLite MobilenetV3, such as: SSDLite MobilenetV3 Large, SSDLite MobilenetV2, SSD MobilenetV2, SSDLite Mobileedets, and SSDMNV2 models. The result is that SSDLite MobilenetV3 is more powerful than other systems for detecting face masks. While the model with the best detection is the SSDLite MobilenetV2 model, the system with the SSDLite MobilenetV3 Small model still detects the use of masks, with a score of 70% accuracy from model accuracy testing in deployment. The limitation is the system with SSDLite MobilenetV3 Small can't detect incorrect masks.
{"title":"Development of Face Mask Detection using SSDLite MobilenetV3 Small on Raspberry Pi 4","authors":"Nenny Anggraini, Syarif Hilmi Ramadhani, Luh Kesuma Wardhani, Nashrul Hakiem, I. Shofi, M. T. Rosyadi","doi":"10.1109/IC2IE56416.2022.9970078","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970078","url":null,"abstract":"This study aimed to develop a mask detection tool with SSDLite MobilenetV3 Small based on Raspberry Pi 4. SSDLite MobilenetV3 Small is a single-stage object detection. The single-stage object detection method is faster than the two-stage detection method. However, it has the disadvantage as the level of accuracy is not as good as the two-stage detection method. In the experiments, we used some methods to compare with SSDLite MobilenetV3, such as: SSDLite MobilenetV3 Large, SSDLite MobilenetV2, SSD MobilenetV2, SSDLite Mobileedets, and SSDMNV2 models. The result is that SSDLite MobilenetV3 is more powerful than other systems for detecting face masks. While the model with the best detection is the SSDLite MobilenetV2 model, the system with the SSDLite MobilenetV3 Small model still detects the use of masks, with a score of 70% accuracy from model accuracy testing in deployment. The limitation is the system with SSDLite MobilenetV3 Small can't detect incorrect masks.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133281766","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970052
Muhamad Farell Ambiar, A. Aditsania, I. Kurniawan
Malaria is a dangerous endemic disease that infects millions yearly. The Plasmodium falciparum species are responsible for most malaria deaths. Currently, most available antimalarial drugs are less effective due to the increased parasite's resistance to drugs. Hence, novel antimalarial agents with high efficiency to inhibit malaria are urgently needed. Falcipain enzyme is a promising target protein for developing new anti-malaria. However, conventional laboratory testing to design new drugs takes time and is very expensive. Therefore, the quantitative structure-activity relationship (QSAR) can be used to accelerate the drug design process. In this study, we developed a QSAR model using a genetic algorithm-support vector machine (GA-SVM) to predict the pIC50 values of falcipain inhibitors. The GA was utilized as a feature selection method, while SVM with an optimized hyperparameter was used to develop the prediction models. We performed three models with different SVM kernels, i.e., linear, radial basis function (RBF), and polynomial. The model performance was validated using both internal and external data. The validation results show that the RBF model produced the best result, with the $R^{2}$ values of the training and test sets of 0.98 and 0.84, respectively, while $Q^{2}$ of the leave-one-out cross-validation was 0.85.
{"title":"QSAR Study on Falcipain Inhibitors as Anti-malaria using Genetic Algorithm-Support Vector Machine","authors":"Muhamad Farell Ambiar, A. Aditsania, I. Kurniawan","doi":"10.1109/IC2IE56416.2022.9970052","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970052","url":null,"abstract":"Malaria is a dangerous endemic disease that infects millions yearly. The Plasmodium falciparum species are responsible for most malaria deaths. Currently, most available antimalarial drugs are less effective due to the increased parasite's resistance to drugs. Hence, novel antimalarial agents with high efficiency to inhibit malaria are urgently needed. Falcipain enzyme is a promising target protein for developing new anti-malaria. However, conventional laboratory testing to design new drugs takes time and is very expensive. Therefore, the quantitative structure-activity relationship (QSAR) can be used to accelerate the drug design process. In this study, we developed a QSAR model using a genetic algorithm-support vector machine (GA-SVM) to predict the pIC50 values of falcipain inhibitors. The GA was utilized as a feature selection method, while SVM with an optimized hyperparameter was used to develop the prediction models. We performed three models with different SVM kernels, i.e., linear, radial basis function (RBF), and polynomial. The model performance was validated using both internal and external data. The validation results show that the RBF model produced the best result, with the $R^{2}$ values of the training and test sets of 0.98 and 0.84, respectively, while $Q^{2}$ of the leave-one-out cross-validation was 0.85.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132734505","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：