Pub Date : 2023-01-31DOI: 10.24114/cess.v8i1.42432
Mella Geovanie, Ikhwan Ruslianto, Uray Ristian
Aeroponics is a farming method without soil media that works by spraying water and a nutrient solution in the form of a mist on plant roots. The use of the aeroponic method itself requires monitoring and controlling air temperature, air humidity, water temperature, and nutrient levels. Incorrect settings can cause plants to experience drought, root rot, and a lack of nutritional elements, which can cause plant death. Therefore, we need a system that can monitor and control air temperature, air humidity, water temperature, and nutrient content. This research builds an Internet of Things-based system that can assist in providing information regarding the values of air temperature, air humidity, water temperature, and nutrient content displayed on the website application. The system can also perform manual and automatic control functions. In the test results, the sensor value reading system has an accuracy of 98.56% for air temperature, 96.89% for accuracy of air humidity readings, 99.64% for accuracy of water temperature readings, 97.02% for accuracy of nutrient solution readings, and 99.86% for accuracy of water level readings. The test results from observing potato plants for 21 days showed an increase in growth in the highest plant height with an average of 4.36 cm and the lowest plant height growth with an average of 0.96 cm.
{"title":"Aeroponic Media Potato Plant Monitoring and Control System Internet of Things Based","authors":"Mella Geovanie, Ikhwan Ruslianto, Uray Ristian","doi":"10.24114/cess.v8i1.42432","DOIUrl":"https://doi.org/10.24114/cess.v8i1.42432","url":null,"abstract":"Aeroponics is a farming method without soil media that works by spraying water and a nutrient solution in the form of a mist on plant roots. The use of the aeroponic method itself requires monitoring and controlling air temperature, air humidity, water temperature, and nutrient levels. Incorrect settings can cause plants to experience drought, root rot, and a lack of nutritional elements, which can cause plant death. Therefore, we need a system that can monitor and control air temperature, air humidity, water temperature, and nutrient content. This research builds an Internet of Things-based system that can assist in providing information regarding the values of air temperature, air humidity, water temperature, and nutrient content displayed on the website application. The system can also perform manual and automatic control functions. In the test results, the sensor value reading system has an accuracy of 98.56% for air temperature, 96.89% for accuracy of air humidity readings, 99.64% for accuracy of water temperature readings, 97.02% for accuracy of nutrient solution readings, and 99.86% for accuracy of water level readings. The test results from observing potato plants for 21 days showed an increase in growth in the highest plant height with an average of 4.36 cm and the lowest plant height growth with an average of 0.96 cm.","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48941938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-31DOI: 10.24114/cess.v8i1.43002
M. D. Irawan, Harold Situmorang, Rianto Sitanggang, D. Sawitri
Employee mutation is one aspect that greatly affects the performance of employees in a company. However, employee mutations at PT. PLN (Persero) UPDL Tuntungan is still done manually, so determining the employees to be transferred takes quite a long time and the results are not optimal. The research aims to facilitate PT. PLN (Persero) UPDL Benefits in determining employee mutations in order to obtain maximum results. The stages of the research were carried out by collecting data by means of interviews then the data was inputted into the system to be calculated using the COPRAS method which was then stored into the database so that it would produce decisions with the final result ranking by the system by sorting the smallest to the largest values. The results of this study are based on the COPRAS method, namely the alternative of Ahmad Fauzy Hamdani Rahmat being the first alternative with a value of 100%. This is because Ahmad Fauzy Hamdani Rahmat's alternative meets almost all criteria ranging from age, years of service, education, position and status.
{"title":"Decision Support System for Determining Employee Movements Using the COPRAS Method","authors":"M. D. Irawan, Harold Situmorang, Rianto Sitanggang, D. Sawitri","doi":"10.24114/cess.v8i1.43002","DOIUrl":"https://doi.org/10.24114/cess.v8i1.43002","url":null,"abstract":"Employee mutation is one aspect that greatly affects the performance of employees in a company. However, employee mutations at PT. PLN (Persero) UPDL Tuntungan is still done manually, so determining the employees to be transferred takes quite a long time and the results are not optimal. The research aims to facilitate PT. PLN (Persero) UPDL Benefits in determining employee mutations in order to obtain maximum results. The stages of the research were carried out by collecting data by means of interviews then the data was inputted into the system to be calculated using the COPRAS method which was then stored into the database so that it would produce decisions with the final result ranking by the system by sorting the smallest to the largest values. The results of this study are based on the COPRAS method, namely the alternative of Ahmad Fauzy Hamdani Rahmat being the first alternative with a value of 100%. This is because Ahmad Fauzy Hamdani Rahmat's alternative meets almost all criteria ranging from age, years of service, education, position and status.","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48111368","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}
Abstrak
Irigasi adalah sistem pembendungan sumber air untuk mengairi lahan sawah. Salah satu kegiatan petani yang masih manual adalah memonitoring atau mengawasi persediaan air dengan membuka dan menutup pintu pematang pada kondisi kekurangan atau kelebihan air pada lahan sawah. Tujuan penelitian ini merancang sistem monitoring irigasi sawah menggunakan ESP8266 berbasis Android dengan mode Bot Telegram. Metode penelitian yang digunakan adalah Resech and Development, menggunakan diagram alir sebagai pemecahan masalah, menggunakan diagram blok sebagai pedoman cara kerja sistem alat yang dirancang. Hasil pengujian dimulai dengan mengaktifkan tombol saklar, aktifkan wifi pada smartphone, selanjutnya mengaktifkan aplikasi telegram untuk memberikan perintah dan informasi monitoring seperti ketinggian air yang akan di deteksi oleh sensor ultrasonik dan perintah memasukan air ke lahan sawah sesuai ukuran debit air yang akan masuk terdeteksi melalui sensor flow meter, pompa in dan out akan menyuplai air masuk dan keluar ke lahan sawah saat kondisi lahan kekurangan dan kelebihan batas ketinggian air. Kesimpulan yang diambil dari penelitian sistem monitoring irigasi sawah menggunakan ESP8266 berbasis Android dengan mode dapat membantu petani dalam memonitoring atau mengawasi air irigasi pada lahan sawah dengan pengendalian jarak jauh dan pengujian alat dapat bekerja dengan baik sesuai dengan yang diharapkan.
Kata kunci: Irigasi, ESP8266, Sensor Ultrasonik, Sensor Flow Meter, Bot Telegram
Abstrak& # x0D;& # x0D;灌溉是一种灌溉稻田的水源系统。农民的手工活动之一是通过对稻田缺水或过剩情况的开放和关闭关口来监测供水。这项研究的目的是设计一种基于电报机器人模式的Android监控灌溉系统。使用的研究方法是rech and Development，使用alir图表作为解决问题的方法，使用区块图作为设计工具系统如何工作的指导方针。测试结果首先是激活开关按钮，激活智能手机上的wifi，然后激活telegram应用程序，提供一些命令和监控信息，比如超声波传感器会探测到的水位，并根据流动尺寸将通过流动传感器检测到的水进入稻田，水泵进进出出将为稻田提供水，因为稻田的条件是缺水和过高的水位。利用具有模式的Android监控灌溉系统的研究得出的结论是，利用远程控制和工具测试可以正常工作，帮助农民监控稻田灌溉用水。& # x0D;关键词:超声波传感器,ESP8266灌溉,流米,电报机器人传感器
{"title":"Desain Rancang Bangun Sistem Monitoring Irigasi Sawah Menggunakan ESP8266 Berbasis Android Dengan Mode Bot Telegram","authors":"Syarifuddin Syarifuddin Baco, Sajiah Sajiah, Suradi Suradi, Nurfadila Awalia A., Wulandari Suluwetang","doi":"10.47650/jsce.v4i1.708","DOIUrl":"https://doi.org/10.47650/jsce.v4i1.708","url":null,"abstract":"Abstrak
 
 Irigasi adalah sistem pembendungan sumber air untuk mengairi lahan sawah. Salah satu kegiatan petani yang masih manual adalah memonitoring atau mengawasi persediaan air dengan membuka dan menutup pintu pematang pada kondisi kekurangan atau kelebihan air pada lahan sawah. Tujuan penelitian ini merancang sistem monitoring irigasi sawah menggunakan ESP8266 berbasis Android dengan mode Bot Telegram. Metode penelitian yang digunakan adalah Resech and Development, menggunakan diagram alir sebagai pemecahan masalah, menggunakan diagram blok sebagai pedoman cara kerja sistem alat yang dirancang. Hasil pengujian dimulai dengan mengaktifkan tombol saklar, aktifkan wifi pada smartphone, selanjutnya mengaktifkan aplikasi telegram untuk memberikan perintah dan informasi monitoring seperti ketinggian air yang akan di deteksi oleh sensor ultrasonik dan perintah memasukan air ke lahan sawah sesuai ukuran debit air yang akan masuk terdeteksi melalui sensor flow meter, pompa in dan out akan menyuplai air masuk dan keluar ke lahan sawah saat kondisi lahan kekurangan dan kelebihan batas ketinggian air. Kesimpulan yang diambil dari penelitian sistem monitoring irigasi sawah menggunakan ESP8266 berbasis Android dengan mode dapat membantu petani dalam memonitoring atau mengawasi air irigasi pada lahan sawah dengan pengendalian jarak jauh dan pengujian alat dapat bekerja dengan baik sesuai dengan yang diharapkan.
 
 Kata kunci: Irigasi, ESP8266, Sensor Ultrasonik, Sensor Flow Meter, Bot Telegram","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136356504","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}
Twitter is a social media platform that is quite widely used by the world community, especially people in Indonesia. Twitter is one of the social media that provides information, one of which is the increase in the price of crude oil which was recorded at 105 US dollars per barrel. The increase in fuel prices has a negative impact on society, causing pros and cons. Based on these problems, the authors aim to compare the performance of the artificial neural network and naïve Bayes algorithms to determine the best model for sentiment analysis of fuel price hikes. The data used amounted to 1000 datasets in the form of text documents with labeling using the lexicon and split data 90:10, 80:20, 70:30 and 60:40 as a comparison of precision values. The application of word vectorization utilizes TF-IDF in assigning a weight value to each word. Based on the results of the experiments that have been carried out, it is found that the best algorithm using an artificial neural network is capable of producing an accuracy value of 87% for 1000 data on public opinion sentiment on fuel price hikes. Based on the evaluation results, the model built can categorize public opinion sentiment into positive sentiment, negative sentiment, and neutral sentiment automatically and the polarity of public sentiment tends to be positive towards the issue of the fuel price increase that occurred.
{"title":"Comparison of Machine Learning Algorithms in Analyzing Public Opinion Sentiments Against Fuel Price Increases","authors":"Hanif Wira Saputra, Rahmaddeni Rahmaddeni, Fazri Fazri","doi":"10.24114/cess.v8i1.41911","DOIUrl":"https://doi.org/10.24114/cess.v8i1.41911","url":null,"abstract":"Twitter is a social media platform that is quite widely used by the world community, especially people in Indonesia. Twitter is one of the social media that provides information, one of which is the increase in the price of crude oil which was recorded at 105 US dollars per barrel. The increase in fuel prices has a negative impact on society, causing pros and cons. Based on these problems, the authors aim to compare the performance of the artificial neural network and naïve Bayes algorithms to determine the best model for sentiment analysis of fuel price hikes. The data used amounted to 1000 datasets in the form of text documents with labeling using the lexicon and split data 90:10, 80:20, 70:30 and 60:40 as a comparison of precision values. The application of word vectorization utilizes TF-IDF in assigning a weight value to each word. Based on the results of the experiments that have been carried out, it is found that the best algorithm using an artificial neural network is capable of producing an accuracy value of 87% for 1000 data on public opinion sentiment on fuel price hikes. Based on the evaluation results, the model built can categorize public opinion sentiment into positive sentiment, negative sentiment, and neutral sentiment automatically and the polarity of public sentiment tends to be positive towards the issue of the fuel price increase that occurred.","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134915926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-21DOI: 10.24114/cess.v8i1.40258
Rayco William, Ikhwan Ruslianto, Uray Ristian
Server is a center for providing services and storing data in a computer network. A server is managed by server administrator who has a duty of monitoring security server. While on duty, there are deficiencies in detecting attacks, the slow information about the attacks, and how to handle attacks on the server. In this research, a server security system was created by implementing an Intrusion Prevention System (IPS) based on website and mobile applications. Attack detection focuses on ICMP and TCP port attacks with the latency time when the system responds to an attack is 99,89 ms (very good). The attack handling system was successfully carried out using Iptables against the attacker's IP that detected by the Suricata system through the website and mobile applications, to be given action which is divided into Drop, Reject and Accept. Administrators can quickly take the necessary precautions after receiving an automatic notification when the server is under attack via Telegram with an average speed is 3.41second. The ping attack, port scanning and ping of death (DoS) attacks resulted in an increase in the performance load on the local server with the initial conditions of CPU performance ranging from 10-19%, increasing when a ping attack occurred to 21,6%, memory 41,7%, and disk 19,6%. Port scanning increased by 85,9% CPU, memory 41,9%, and disk 20,3%. Ping of death increased CPU 90,4%, memory 42,9%, and disk 20,8%. Based on the tests that have been done, an excessive increase is found in the ping of death attack which results in server performance increasing to 90,4%, if the attack occurs for a long time then the server condition will be hang (damaged).
服务器是计算机网络中提供服务和存储数据的中心。服务器由服务器管理员管理，服务器管理员的职责是监视安全服务器。在执勤时，在检测攻击、攻击信息缓慢、如何处理服务器上的攻击等方面存在不足。在本研究中，通过实施基于网站和移动应用的入侵防御系统(IPS)，构建了一个服务器安全系统。攻击检测主要针对ICMP和TCP端口的攻击，系统响应攻击的延迟时间为99,89 ms(很好)。攻击处理系统使用Iptables对Suricata系统通过网站和移动应用程序检测到的攻击者IP成功执行攻击处理，并给予攻击者Drop、Reject和Accept三种动作。当服务器受到攻击时，通过Telegram收到自动通知后，管理员可以迅速采取必要的预防措施，平均速度为3.41秒。ping攻击、端口扫描和DoS (ping of death)攻击导致本地服务器的性能负载增加，CPU性能初始条件为10-19%，发生ping攻击时，性能负载增加到21.6%，内存41.7%，磁盘19.6%。端口扫描增加了85.9%，CPU、内存和磁盘分别增加了41.9%和20.3%。Ping死亡使CPU增加了904%，内存增加了42.9%，磁盘增加了20.8%。根据已经完成的测试，发现ping of death攻击增加过多，导致服务器性能提高到904%，如果长时间发生攻击，则服务器状态会挂起(损坏)。
{"title":"Implementation of Intrusion Prevention System (IPS) as a Website-Based Server Security System and Mobile Application","authors":"Rayco William, Ikhwan Ruslianto, Uray Ristian","doi":"10.24114/cess.v8i1.40258","DOIUrl":"https://doi.org/10.24114/cess.v8i1.40258","url":null,"abstract":"Server is a center for providing services and storing data in a computer network. A server is managed by server administrator who has a duty of monitoring security server. While on duty, there are deficiencies in detecting attacks, the slow information about the attacks, and how to handle attacks on the server. In this research, a server security system was created by implementing an Intrusion Prevention System (IPS) based on website and mobile applications. Attack detection focuses on ICMP and TCP port attacks with the latency time when the system responds to an attack is 99,89 ms (very good). The attack handling system was successfully carried out using Iptables against the attacker's IP that detected by the Suricata system through the website and mobile applications, to be given action which is divided into Drop, Reject and Accept. Administrators can quickly take the necessary precautions after receiving an automatic notification when the server is under attack via Telegram with an average speed is 3.41second. The ping attack, port scanning and ping of death (DoS) attacks resulted in an increase in the performance load on the local server with the initial conditions of CPU performance ranging from 10-19%, increasing when a ping attack occurred to 21,6%, memory 41,7%, and disk 19,6%. Port scanning increased by 85,9% CPU, memory 41,9%, and disk 20,3%. Ping of death increased CPU 90,4%, memory 42,9%, and disk 20,8%. Based on the tests that have been done, an excessive increase is found in the ping of death attack which results in server performance increasing to 90,4%, if the attack occurs for a long time then the server condition will be hang (damaged).","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48677356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-21DOI: 10.24114/cess.v8i1.40259
Fazar Dawamsyach, Ikhwan Ruslianto, Uray Ristian
Server security is an important thing that must be considered so that the server can work well and serve users. Attacks on servers can threaten server performance and data security in it. According to the National Cyber and Crypto Agency 2020 report, ports 22 and 80 were the top ports with the most attacks. One of the attacks on port 22 is brute force and an attack on port 80 is Distributed Denial of Service (DDoS). To solve this problem, a study was conducted to implement fail2ban IPS (Intrusion Prevention System) to increase server security. The attacks tested focused on brute force attacks on port 22 and DDoS attacks on port 80 using the TCP protocol. The fail2ban system is equipped with a website interface and notifications via telegram. The test results show that DDoS attacks have more impact on CPU performance with the highest increase in CPU being 92%, while brute force attacks have more impact on server memory performance with the highest increase in memory by 100%. The increase in server performance results in slowed server performance. The system managed to prevent DDoS attacks with an average speed of 0.5 seconds while brute force attacks were 6.1 seconds. The system managed to prevent DDoS attacks with a total of 88 attacks and brute force attacks with a total of 864 attacks.
{"title":"Implementation of IPS (Intrusion Prevention System) Fail2ban on Server for DDoS and Brute Force Attacks","authors":"Fazar Dawamsyach, Ikhwan Ruslianto, Uray Ristian","doi":"10.24114/cess.v8i1.40259","DOIUrl":"https://doi.org/10.24114/cess.v8i1.40259","url":null,"abstract":"Server security is an important thing that must be considered so that the server can work well and serve users. Attacks on servers can threaten server performance and data security in it. According to the National Cyber and Crypto Agency 2020 report, ports 22 and 80 were the top ports with the most attacks. One of the attacks on port 22 is brute force and an attack on port 80 is Distributed Denial of Service (DDoS). To solve this problem, a study was conducted to implement fail2ban IPS (Intrusion Prevention System) to increase server security. The attacks tested focused on brute force attacks on port 22 and DDoS attacks on port 80 using the TCP protocol. The fail2ban system is equipped with a website interface and notifications via telegram. The test results show that DDoS attacks have more impact on CPU performance with the highest increase in CPU being 92%, while brute force attacks have more impact on server memory performance with the highest increase in memory by 100%. The increase in server performance results in slowed server performance. The system managed to prevent DDoS attacks with an average speed of 0.5 seconds while brute force attacks were 6.1 seconds. The system managed to prevent DDoS attacks with a total of 88 attacks and brute force attacks with a total of 864 attacks.","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45582682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-16DOI: 10.24114/cess.v8i1.40897
Simeon Yuda Prasetyo
The problem of the spread of COVID-19 (SARS-CoV-2) is spreading fleetly and worldwide. Beforehand discovery and opinion of complaint is veritably important to ensure the right remedy so that it needs to be enforced through various practical approaches. In former studies, complaint discovery through medical imaging has started to appear and get a good delicacy of around 80 to 90 percent using machine learning. In the deep learning era, some trials get better accuracy of 95 percent using the traditional deep learning approach. Now, deep learning has developed more fleetly, especially for image classification. therefore, it's necessary to experiment with a pretrained model approach to medical images. In addition, the fine tuning approach will also be an aspect of the approach that will be carried out in this trial to be compared and to find out its effect, specifically on CT-Scan images of the lungs for the discovery of COVID 19. The results of this experiment showed that the pretrained model approach can get high accuracy. Relatively high accuracy, the smallest testing accuracy in this trial reached 94.78 percent of the Xception without fine tuning phase, this result has beaten the machine learning approach which is didn't reach 90 percent of accuracy. The best experiment testing accuracy get 97.59 percet on the VGG 16 by applying fine tuning. The results of this trial also show that the fine tuning stage (for the top 10th layers) can increase the accuracy of the model.
COVID-19 (SARS-CoV-2)的传播问题正在全球迅速蔓延。投诉的事先发现和意见对于确保正确的补救措施非常重要，因此需要通过各种切实可行的方法来执行。在以前的研究中，通过医学成像发现投诉已经开始出现，并且使用机器学习获得了80%到90%左右的良好精确度。在深度学习时代，使用传统的深度学习方法，一些试验的准确率达到了95%。现在，深度学习的发展更加迅速，特别是在图像分类方面。因此，有必要对医学图像进行预训练模型方法的实验。此外，微调方法也将是该方法的一个方面，将在本试验中进行比较并找出其效果，特别是对肺部ct扫描图像的影响，以发现COVID - 19。实验结果表明，预训练模型方法可以获得较高的准确率。相对较高的准确率，本次试验中最小的测试准确率达到了exception without fine tuning阶段的94.78%，这一结果击败了没有达到90%准确率的机器学习方法。通过对vgg16进行微调，实验测试精度达到97.59%。试验结果还表明，微调阶段(针对前10层)可以提高模型的精度。
{"title":"SARS-CoV-2 Detection from Lung CT-Scan Images Using Fine Tuning Concept on Deep-CNN Pretrained Model","authors":"Simeon Yuda Prasetyo","doi":"10.24114/cess.v8i1.40897","DOIUrl":"https://doi.org/10.24114/cess.v8i1.40897","url":null,"abstract":"The problem of the spread of COVID-19 (SARS-CoV-2) is spreading fleetly and worldwide. Beforehand discovery and opinion of complaint is veritably important to ensure the right remedy so that it needs to be enforced through various practical approaches. In former studies, complaint discovery through medical imaging has started to appear and get a good delicacy of around 80 to 90 percent using machine learning. In the deep learning era, some trials get better accuracy of 95 percent using the traditional deep learning approach. Now, deep learning has developed more fleetly, especially for image classification. therefore, it's necessary to experiment with a pretrained model approach to medical images. In addition, the fine tuning approach will also be an aspect of the approach that will be carried out in this trial to be compared and to find out its effect, specifically on CT-Scan images of the lungs for the discovery of COVID 19. The results of this experiment showed that the pretrained model approach can get high accuracy. Relatively high accuracy, the smallest testing accuracy in this trial reached 94.78 percent of the Xception without fine tuning phase, this result has beaten the machine learning approach which is didn't reach 90 percent of accuracy. The best experiment testing accuracy get 97.59 percet on the VGG 16 by applying fine tuning. The results of this trial also show that the fine tuning stage (for the top 10th layers) can increase the accuracy of the model.","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43145125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-16DOI: 10.24114/cess.v8i1.41698
Saut Pintubipar Saragih, Mesri Silalahi
Web Based Applications has been implemented to organize bookstore and it is reuired to handle a wider library system, especially in a non-profit organization such as Nyala Aksara community library in Batam City. All library sources especially book collections come from donations from the community or charity, with this situation it is expected for the commitee to be able provide a system to reach more people to donate with easiness. The E-library Web application is expected to be able to provide solutions for the Nyala Aksara organization management. The main problems is the donations systems that have not been systematically organized, and then borrowing and returning system for users. E-library application will be built using web-based programming like HTML PHP, MySQL database and designing method with UML Method. The e-library will provide services for those who want to donate books, this application will also provide a system that is able to manage borrowers and how to process the book returning. The results of this research is producing a solution for the organization called E-libarary which is a web-based library management.
{"title":"Implementation of Digital Libraries in Book Management and Donation in the Nyala Aksara Community","authors":"Saut Pintubipar Saragih, Mesri Silalahi","doi":"10.24114/cess.v8i1.41698","DOIUrl":"https://doi.org/10.24114/cess.v8i1.41698","url":null,"abstract":"Web Based Applications has been implemented to organize bookstore and it is reuired to handle a wider library system, especially in a non-profit organization such as Nyala Aksara community library in Batam City. All library sources especially book collections come from donations from the community or charity, with this situation it is expected for the commitee to be able provide a system to reach more people to donate with easiness. The E-library Web application is expected to be able to provide solutions for the Nyala Aksara organization management. The main problems is the donations systems that have not been systematically organized, and then borrowing and returning system for users. E-library application will be built using web-based programming like HTML PHP, MySQL database and designing method with UML Method. The e-library will provide services for those who want to donate books, this application will also provide a system that is able to manage borrowers and how to process the book returning. The results of this research is producing a solution for the organization called E-libarary which is a web-based library management.","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42041086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-11DOI: 10.24114/cess.v8i1.40707
M. Rizki, Boni Oktaviana Sembiring, Eka Rahayu
The digital era, where all activities can be done using technology. Including about books that can turn printed books into digital books or E-books. Immunization is the process of making a person immune or immune to a disease. The type and schedule of immunizations will determine the health of their toddlers both now and in the future. Parents' ignorance of the type and stage of the immunization schedule is an obstacle for parents. To find out the types and stages of the immunization schedule, parents should read a guide book containing information on immunizations. With immunization books that are still conventional, books become less effective due to carelessness, such as being easily damaged and lost. To prevent and reduce these problems the author wants to design an E-book application or a web-based digital version of a book that can be used as a source of immunization information. In designing this application, the author uses the Object Oriented method, namely Object Oriented Analysis and Design (OOAD) for the system development method and Oriented Programming (OOP) for making the application. With the Immunization E-book Application using the Web-based Object Oriented Method, it is hoped that the general public, especially parents with toddlers, doctors and nurses can find out information about Immunization data quickly anytime and anywhere.
{"title":"Immunization E-Book Application Using Web-Based Object Oriented Method","authors":"M. Rizki, Boni Oktaviana Sembiring, Eka Rahayu","doi":"10.24114/cess.v8i1.40707","DOIUrl":"https://doi.org/10.24114/cess.v8i1.40707","url":null,"abstract":"The digital era, where all activities can be done using technology. Including about books that can turn printed books into digital books or E-books. Immunization is the process of making a person immune or immune to a disease. The type and schedule of immunizations will determine the health of their toddlers both now and in the future. Parents' ignorance of the type and stage of the immunization schedule is an obstacle for parents. To find out the types and stages of the immunization schedule, parents should read a guide book containing information on immunizations. With immunization books that are still conventional, books become less effective due to carelessness, such as being easily damaged and lost. To prevent and reduce these problems the author wants to design an E-book application or a web-based digital version of a book that can be used as a source of immunization information. In designing this application, the author uses the Object Oriented method, namely Object Oriented Analysis and Design (OOAD) for the system development method and Oriented Programming (OOP) for making the application. With the Immunization E-book Application using the Web-based Object Oriented Method, it is hoped that the general public, especially parents with toddlers, doctors and nurses can find out information about Immunization data quickly anytime and anywhere.","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45606514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-11DOI: 10.24114/cess.v8i1.41209
Marina Wahyuni Paedah, F. Gunawan
COVID-19 has severely impacted the global economy, including ASEAN countries. Various plans and strategies are still needed during the pandemic-to-epidemic transition period to minimize the risk of COVID-19 transmission. The research focuses on the total number of confirmed cases of COVID-19 in Indonesia, Malaysia, the Philippines, and Vietnam, which are among the ASEAN countries with the highest number of cases in Southeast Asia. Those countries have cultural similarities, where gathering with friends and family is an important part of social life. This research evaluates the ability of ARIMA and LSTM to predict COVID-19 cases in each country, using daily data from January 23, 2020 to October 22, 2022. Datasets published by Johns Hopkins University (JHU) and Our World in Data (OWID) are used, which are accessible through Github. Compared to ARIMA with R2 of 0,8883 for Indonesia, 0,8353 for Malaysia, 0.97291 for the Philippines, and -3.105 for Vietnam, LSTM model can predict better in the four sampled ASEAN countries, with an R2 of 0.9996 for Indonesia, 0.9707 for Malaysia, 0.97291 for the Philippines, and 0.9200 for Vietnam.
{"title":"Forecasting COVID-19 Cases in Indonesia, Malaysia, Philippines, and Vietnam Using ARIMA and LSTM","authors":"Marina Wahyuni Paedah, F. Gunawan","doi":"10.24114/cess.v8i1.41209","DOIUrl":"https://doi.org/10.24114/cess.v8i1.41209","url":null,"abstract":"COVID-19 has severely impacted the global economy, including ASEAN countries. Various plans and strategies are still needed during the pandemic-to-epidemic transition period to minimize the risk of COVID-19 transmission. The research focuses on the total number of confirmed cases of COVID-19 in Indonesia, Malaysia, the Philippines, and Vietnam, which are among the ASEAN countries with the highest number of cases in Southeast Asia. Those countries have cultural similarities, where gathering with friends and family is an important part of social life. This research evaluates the ability of ARIMA and LSTM to predict COVID-19 cases in each country, using daily data from January 23, 2020 to October 22, 2022. Datasets published by Johns Hopkins University (JHU) and Our World in Data (OWID) are used, which are accessible through Github. Compared to ARIMA with R2 of 0,8883 for Indonesia, 0,8353 for Malaysia, 0.97291 for the Philippines, and -3.105 for Vietnam, LSTM model can predict better in the four sampled ASEAN countries, with an R2 of 0.9996 for Indonesia, 0.9707 for Malaysia, 0.97291 for the Philippines, and 0.9200 for Vietnam.","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69045670","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：