Articles
1,196 Documents
<![CDATA[Oil Palm Fruit Ripeness Detection using Deep Learning ]]>
<![CDATA[Ashari, Suci]]>;
<![CDATA[Yanris, Gomal Juni]]>;
<![CDATA[Purnama, Iwan]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i2.11420
<![CDATA[To detect the maturity level of oil palm Fresh Fruit Bunches (FFB) generally seen from the loose fruit that fell to the ground. This method is always used when harvesting swit coconuts. Even though this method is not always valid, because many factors cause the fruit to fall from the bunch. The manual harvesting process can result in the quality of palm oil being not optimal. For this reason, technology is needed that can ensure the maturity level of oil palm FFB. This study aims to detect the maturity of oil palm FFB based on digital images by applying a deep learning algorithm so that the maturity level can be classified into three categories, namely: raw, ripe, and rotten. The deep learning algorithm was chosen because there have been many studies that have proven its high level of accuracy. This research method starts from; preparation of data, designing architectural models and convolutional neural network parameters, testing models, testing images, and analyzing results. From the results of the study, it was found that the convolutional neural network algorithm can be applied to detect the maturity level of oil palm FFB with an accuracy value of 92% for test data, and 76% for model testing.]]>
<![CDATA[Implementation of the RAD Method to Build Catering Application Android-based ]]>
<![CDATA[Tasyabila, Tasyabila]]>;
<![CDATA[Sihombing, Volvo]]>;
<![CDATA[Nasution, Fitri Aini]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i2.11421
<![CDATA[With the rise of culinary businesses that sell food and beverages at this time, business actors must be ready to compete to win and retain their customers so that their business can survive. Ara Catering is one of the culinary business actors in Rantauprapat City which focuses on the food and beverage ordering business. The ordering process applied by Ara Catering is still conventional, where customers come directly to the business location or place an order by telephone. The conventional model turned out to cause problems, including errors in ordering and ordering notes that had piled up. Therefore, a solution must be found to overcome this problem. Based on these problems, this study aims to build an android-based catering ordering application. The method applied in this research is the Rapid Application Development (RAD) method in which the process stages include: requirements planning, user design, and implementation. After the design and implementation have been carried out, the results show that the RAD method can be applied in building an Android-based catering application quickly and effectively. The conclusion drawn from this research is that to build an android-based catering application using the RAD method, the phases of the method must be carried out thoroughly. Hopefully the results of this research can make a positive contribution to Ara Catering in developing its business.]]>
<![CDATA[Development of Corporate Digital Archives in the Industrial Age 4.0 ]]>
<![CDATA[Faujiah, Ria Rizki]]>;
<![CDATA[Yanris, Gomal Juni]]>;
<![CDATA[Pane, Rahmadani]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i2.11422
<![CDATA[CV. Ziefa Karya is a company in Labuhanbatu which is engaged in construction contractors who have experience in working on national projects. CV. Ziefa Karya has used computer applications in daily data processing. However, archive storage and management is still done manually. The current filing system can be said to be still less efficient and effective because the incoming and outgoing mail data is often not in accordance with the actual incoming and outgoing mail data. For that we need a solution to overcome this problem. This study aims to build an information system that can be used to manage digital-based archives in CV. Zief Karya. The information system built is web-based. System development using the waterfall model. This research has produced an archive management information system on CV. Ziefa Karya web-based. The result of this research is a website-based mail filing system on CV. Ziefa Karya which has various uses such as data collection of incoming and outgoing letters, details of incoming and outgoing letters, classification of types of letters, disposition of incoming letters, reports of incoming and outgoing letters, and printing of reports of incoming and outgoing letters, as well as printing disposition sheets. Records management information system on CV. Ziefa Karya is able to provide convenience for admins and users in managing digital-based archives. To build a web-based archive information system on CV. Ziefa Karya, development must be carried out by applying the stages in the Waterfall method.]]>
<![CDATA[Web-based Blood Donor Management Information Sytem using Waterfall Method ]]>
<![CDATA[Andriani, Reza Silvia]]>;
<![CDATA[Irmayani, Deci]]>;
<![CDATA[Ritonga, Ali Akbar]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i2.11423
<![CDATA[PMI Labuhanbatu Regency is one of the central PMI branches where there is a division that handles the blood donation process, namely the Blood Transfusion Unit. UTD PMI Labuhanbatu Regency has the duty to serve blood donation activities and provide blood stock for the Labuhanbatu community in need. As a unit that provides blood donors, UTD PMI Labuhanbatu must always be ready to provide the services needed. One of the concerns is the issue of blood stock availability. If there are many people who need blood, then UTD must be ready to serve. If the amount of blood stock is reduced, then people will find it difficult to get blood. For this reason, the issue of blood availability must always be the main concern of UTD PMI Labuhanbatu. This study aims to build a blood donor information system at the PMI Blood Transfusion Unit in Labuhanbatu Regency. The system built applies a web-based framework. The system development applies the Waterall method which includes the process of needs analysis, design, implementation, testing, and maintenance. After designing, implementing and testing, the results obtained are the system has been successfully developed and all designs are in accordance with what is implemented. The conclusion from this research is that the blood donor information system that has been developed at UTD PMI Labuhanbatu Regency has been able to provide convenience for admins and users in managing donor and blood stock management.]]>
<![CDATA[Comparative analysis of software defined network performance and conventional based on latency parameters ]]>
<![CDATA[Harahap, Raja Pahlevi]]>;
<![CDATA[Irmayani, Deci]]>;
<![CDATA[Muti’ah, Rahma]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i2.11424
<![CDATA[Software Defined Network (SDN) offers convenience in managing network devices by simply setting the software control plane so as to reduce the complexity of network configuration. However, the ease of management offered is not always accompanied by an increase in network performance when compared to conventional network architectures. This study will perform a performance comparison analysis between networks with SDN architecture (OpenFlow) and conventional architecture. The research methods applied are: topology implementation on Mininet, network simulation and data collection, data analysis, and comparative analysis. Network performance testing is carried out based on latency parameters that are simulated in one subnet using the Mininet emulator. From the results of the latency test, it is found that the average latency on the SDN network is 0.119ms, while the average latency on the conventional network is 0.09588ms. Based on these results, it can be concluded that the network topology that has better performance based on latency parameters is a conventional network topology with an average latency value of 0.09588ms.]]>
<![CDATA[Design and Build Expert System Application for Diagnosing Facial Skin Disease based on Android ]]>
<![CDATA[Sarinawati, Sarinawati]]>;
<![CDATA[Yanris, Gomal Juni]]>;
<![CDATA[Muti’ah, Rahma]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i2.11425
<![CDATA[Today, skin health is the main focus for women and men who want healthy, well-groomed and clean facial skin. The use of chemicals and other external materials allows potential disease for facial skin health. Diseases caused on the face are quite diverse from small to medium scale. The problem that often occurs in the community is the lack of knowledge and limited sources of information about facial skin health causing people to tend to let the disease happen. Based on the problems that have been described previously, this expert system was created to help the public understand the symptoms of facial skin diseases experienced and solutions to overcome these diseases. In the development of this expert system using the forward chaining method as the inference engine and the certainty factor method to determine the diagnostic confidence value. In designing this expert system application the user can choose the symptoms of facial skin diseases, then the output produced is the level of confidence, the possibility of the disease experienced and an explanation of the solution for the initial treatment of the facial skin disease. From the test results based on the Black Box, the results obtained 100% functionality runs according to the list of system requirements. In the accuracy test, a very good accuracy value is obtained, which is 100% of the 10 existing sample data.]]>
<![CDATA[A Mobile-based Expert System for Disease Diagnosis Child using Best-First Search Algorithm ]]>
<![CDATA[Hasan, Nurwahyuni]]>;
<![CDATA[Yanris, Gomal Juni]]>;
<![CDATA[Hasibuan, Elysa Rohayani]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i2.11426
<![CDATA[Currently, many parents want their children to be free from disease. Although this cannot be fully expected. Problems that often occur to parents are when their child is sick, lack of knowledge and limited sources of information about the disease that causes parents to leave their children without first aid. In other conditions, in areas that are far from the doctor's practice, the need for information on disease management is very necessary. Based on the problems that have been described previously, this expert system was created to assist parents in understanding the symptoms of skin diseases that occur in children. In the development of this expert system using the Best-First Search (BFS) algorithm as an inference engine. In this expert system application the user can choose the symptoms of the disease in children, then the output produced is the conclusion of the disease. From the test results based on Blackbox, it was found that 100% functionality runs according to the list of system requirements. After this research was completed, it was concluded that to design an expert system in detecting childhood diseases, starting from conducting interviews, followed by system design, the next process was implementing the system, then testing by experts for compatibility with the data that had been obtained.]]>
<![CDATA[Comparative analysis of resampling techniques on Machine Learning algorithm ]]>
<![CDATA[Amelia, Tri Suci]]>;
<![CDATA[Hasibuan, Mila Nirmala Sari]]>;
<![CDATA[Pane, Rahmadani]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i2.11427
<![CDATA[Generally, classification algorithms in the field of data science assume that the classes of training data are equally distributed. However, datasets on real problems often have an unbalanced class distribution. Unbalanced dataset classes make up the majority class and the minority class. In general, minority classes are more attractive and more important to identify. In this case, the correct classification for the minority class sample is more valuable than the majority class. The unbalanced class distribution causes the classification algorithm to have difficulty in classifying minority class samples correctly. If the performance of the algorithm model is good for the majority class sample but bad for the minority class then this imbalance problem is a crucial thing to be addressed. Many solutions are offered for this problem, namely by oversampling techniques in the minority class and/or undersampling techniques in the majority class. In this study, the authors tried various sampling techniques and tested them on various machine learning classification algorithms to find out the combination of resampling techniques and algorithms that have high recall in classifying minority class samples and still considering the majority class classification.]]>
<![CDATA[SVM and Naïve Bayes Algorithm Comparison for User Sentiment Analysis on Twitter ]]>
<![CDATA[Syahputra, Rahmat]]>;
<![CDATA[Yanris, Gomal Juni]]>;
<![CDATA[Irmayani, Deci]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i2.11430
<![CDATA[With the emergence of the Peduli Protect application, which is used by the government to monitor the spread of Covid-19 in Indonesia, it turns out to be reaping the pros and cons of public opinion on Twitter. From this phenomenon, a research was conducted by mapping the sentiment analysis of twitter users towards the Peduli Protect application. This study aims to compare two classification algorithms that are included in the supervised learning category. The two algorithms are Support Vector Machine (SVM) and Naïve Bayes. The two algorithms are implemented in analyzing the sentiment analysis of twitter user reviews on the Peduli Protect application. The dataset used in this research is tweets of twitter users with a total of 4,782 tweets. Then, compared to how much accuracy and processing time required of the two algorithms. The stages of the method in this research are: collecting data from user tweets with a crawling technique, preprocessing text, weighting words using the TF-IDF method, classification using the SVM and Naïve Bayes algorithm, k-fols cross validation test, and drawing conclusions. The results showed that the accuracy of the SMV algorithm with the k-fold test method was 86% and the split 8020 technique resulted in an accuracy of 79%. Meanwhile, the Naïve Bayes algorithm produces an accuracy of 85% with k-fold, and an accuracy of 80% with a split 8020. From these results it can be concluded that both algorithms have the same level of accuracy, only different in processing time, where Naïve Bayes algorithm is faster with time required 0.0094 seconds.]]>
<![CDATA[Applying genetic algorithm for optimization income value ]]>
<![CDATA[Siagian, Ayu Febri]]>;
<![CDATA[Yanris, Gomal Juni]]>;
<![CDATA[Sitorus, Sahat Parulian]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i2.11431
<![CDATA[In this digital era, the use of information technology and internet technology cannot be separated from digital services. Starting from product promotion media, recording customer data, determining the amount of revenue from product sales, and optimizing the value of revenue. Sales of digital service products owned by PT. XYZ needs to be evaluated to find out which products are most in demand by customers from each product offering that has been made. Therefore we need a system to calculate revenue from the number of customers who use the product for further promotion. The object of this research focuses on optimizing the value of income at PT. XYZ of the products they market, the results of the object will be used as an evaluation to determine a new strategy in carrying out promotions for products that are less attractive to customers. The data used in this study is customer data for January 2017-December 2021. The method used in this study uses a genetic algorithm to determine the optimization of the revenue value. For the optimization results, the genetic algorithm went well, because it resulted in a smaller comparison of error values compared to values that were not optimized. The error value in January 2019 with a non-optimized value was 35,498.8 and the optimized value got an error value of 32,364.9. The results of this study are used as a sales evaluation to increase promotions on digital services that are less attractive to customers. In addition, the results of the application of this genetic algorithm method can provide a better solution to increase income in the next period.]]>
