Garuda - Garba Rujukan Digital

Chatbot untuk Website Utama UK Petra dengan Hidden Markov Model dan k-Nearest Neighbor untuk Generate Jawaban Kevin Koesoemo; Alexander Setiawan; Indar Sugiarto
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Petra Christian University has various services for general information about university majors and student admissions, such as social media and WhatsApp. However, these services still limited by number and working time of operators as human. Therefore, with this chatbot, information about PCU can be found anytime. Chatbot Study by S. C. P & Afrianto needs method to match chatbot question with the dataset. This thesis uses two methods, namely kNN (k-Nearest Neighbor) and HMM (Hidden Markov Model) to solve these problem. In this chatbot, it will try to combine and compare these two methods, and see if it can produces answers that can be understood and in accordance with various difficulty questions given. The kNN is used as a classification for questions given to chatbot which approximately match with questions on the chatbot’s knowledge base. HMM is used to assemble answer words from the selected knowledge base. Chatbot’s answers will be tested in terms of validity of the answers by two respondents (Public Relation and Admission staff) also the length of time it takes to produce answers. The results of the chatbot with kNN has an accuracy of 64.44% (45 questions), with average system runtime of 0.08 seconds. While the results of chatbot with kNN-HMM produces random and irregular answers, with average system runtime of 0.12 seconds, cause by HMM which is a probability based method.

Pembuatan Aplikasi Mobile Augmentative and Alternative Communication "BerKata" dengan Menggunakan Text to Speech untuk Membantu Komunikasi Anak Penyandang Autisme Evandruce Filbert; Rolly Intan; Henry Novianus Palit
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Children with autism who lack verbal communication skills often confuse their parents for knowing what their wants are conveniently. It takes extra effort for their parents to understand them, especially with their unclear pronunciations. Their inability to conveniently understand what is kept in their minds may affect their emotions. The children easily experience mood swings, and their parents struggle to identify their children’s needs. All of these struggles can be supported with the Augmentative and Alternative Communication (AAC) with Picture Exchange Communication System (PECS) module. With PECS, children with autism will be able to learn how to converse their needs through image media. Therefore, their parents can easily understand what they want to say. With all the problems, this research presents an AAC mobile application with PECS module called “BerKata”. The result of this research is that “BerKata” may develop children with autism’s speech ability, to decrease their anxiousness and help gaining their confidence, if only their parents consistently use it. Keep in mind to achieve the goal, requires consistency of habituation from children, parents and the people around and not an instant result.

Sistem Informasi Akademik Berbasis Web untuk Mendukung Pembelajaran Jarak Jauh di SD Anak Bangsa Jovan Jeremi; Lily Puspa Dewi; Krisna Wahyudi
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Anak Bangsa Elementary School is a private school located in Surabaya. Schools have many academic administrative processes, such as personnel data collection, assessment, attendance, finance and report cards. At this time, Anak Bangsa doesn’t have a system or database. All administrative processes, data storage and processing are done manually, so errors often occur. In 2019, the Covid-19 outbreak emerged in Indonesia, which caused face-to-face learning process to switch to distance learning. It is undeniable that Anak Bangsa must also change its learning methods and adapt to this situation.Answering these problems, Anak Bangsa School must have an information system to process data that supports distance learning. The system is made based on a website using PHP and Javascript programming languages and mysql database. The features of this system include calculating grades, attendance, finance, online tests, and generating report cards.From the results of the questionnaire, the level of satisfaction with the overall program is 74% good and 26% very good. It can be concluded that this program is able to meet the needs of Anak Bangsa in managing academic data and supporting distance learning process.

Penerapan Microservices dan Amazon Elastic Container Service untuk Mendukung Scalability Antonius Tanuwijaya; Henry Novianus Palit; Agustinus Noertjahyana
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

The technology age under development provides the impact of increasing the number of users in a system may also increase the workload received by the server. This condition is experienced in PT. X, where the server cannot handle the growing workload over time, this makes the server overloaded and slow in response until it gets to the server condition is down and unreachable by the user. This research tried to provide solutions to the problems faced by PT. X by applying a system of microservices and Amazon Elastic Container Service. By applying microservices then all services will be split into independent and can ease the workload of the server. Moreover, with the combination of Amazon ECS then the process of scaling will be more effective only on the service that is experiencing an overload condition so that the process of scaling can adjust the conditions of the workload on the server at that time. The scaling process will allow the system to increase or decrease the number of tasks performed without a lack or excessive use of resources. Based on analysis of the implementation of microservices and the Amazon ECS on the PT. X system, It can be concluded that the scalable microservices system produces a lower average response time with a difference of 805.56% compared to unscalable microservices and 38% compared to monolithic, then the resulting deviation is 902.22% lower than unscalable microservices and 216.87% lower than monolithic, then the resulting throughput is higher by 22018.61 requests/minutes from unscalable microservices and 24524.16 requests/minutes from monolithic. For a maximum concurrent user comparison between a scalable microservices system, an unscalable microservices, and monolithic of 2000:1454:28. In addition, the CPU usage of scalable microservices systems is 20%-21% lower, especially at login, generate access tokens, and get schedules when compared to unscalable microservices systems, due to workload sharing system with replication tasks. Additionally, the use of resources can adjust to workload conditions dynamically and efficiently

Implementasi Pengendalian Inventory Pada PT.X Kevin Joshua Harianto; Yulia Yulia; Rudy Adipranata
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Inventory control is a process to ensure the amount of supply available in a business process. Inventory control can help prevent losses in managing raw materials and also setting up the warehouse system at PT.X. Based on the problems that occur at PT.X, a method that can be systemized with warehouse systems and production results is needed, with the aim of finding the average of sales per day and month which is useful for re-ordering, and also for analyzing so that there is no stockout. Reports for each transaction period can be viewed on the system in accordance with the recording of transaction data. The data used in calculating the Economic Order Quantity and Reorder Point are transactions from 2019 at the warehouse of PT. X.

Klasifikasi dalam Pembuatan Portal Berita Online dengan Menggunakan Metode BERT Jehezkiel Hardwin Tandijaya; Liliana Liliana; Indar Sugiarto
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Internet helps human by making various information from many online news platform accessible. But nowadays, there are a lot of news that can be accessed in different online news platform and needs to be categorized. The news that can be accessed in some of the sources don’t have high credibility about an event, because the publishers use false and misleading information to push their agendas. So in order to check the credibility of an event, it is needed to also read from other sources and not only from 1 source. However, this is not effective because the reader has to look for another news source with different URL address. In this research scraping will be done to retrieve the news that are available in a news platform. After the scraping process is done, the news will be classified to determine the category of the news. The method that will be used is Bidirectional Encoder Representations from Transformers. From the testing of this research, the news can be retrieved and classified. The testing with a pre-trained model indobenchmark /indobert-base-p1 get a very good result where the accuracy reaches 87.548%.

Automatic Playlist Continuation Menggunakan Hybrid Recommender System Martin Andersen Linggajaya; Henry Novianus Palit; Alvin Nathaniel Tjondrowiguno
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

One of the most popular ways to listen to music is using playlists. The playlist feature can be improved by giving track recommendations to be added to certain playlists. To support the development of this recommendation process, ACM and Spotify held the RecSys Challenge 2018 with the task of automatic playlist continuation. This research is a continuation from [6] that placed 3rd in the RecSys Challenge 2018. The method used consists of 2 phases: candidate selection using a hybrid recommender system called LightFM and ranking using XGBoost. The research gap being developed focuses on one of the calculations for co-occurrence features used in the ranking phase. The result of this research shows that co-occurrence of 3 tracks does not improve the performance of the model used. The model by [6] achieved scores of 0.5251, 0.5582, and 1.295 for R-precision, NDCG, and recommended song clicks respectively. Meanwhile, the model produced in this research achieved an R-precision of 0.5241, an NDCG of 0.5579, and recommend song clicks of 1.312.

Pemetaan Penyebaran Tingkat Kepatuhan Masyarakat dalam Menggunakan Masker di Pasar Tradisional Kota Surabaya dengan Metode Hot Spot Analysis (Getis-Ord Gi*) Stefanus Benhard; Silvia Rostianingsih; Resmana Lim
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

According to a study conducted to see the level of effectiveness for using masks in case study by [1]), explains that if the use of masks has a positive impact on resulting transmission. Research conducted invloving cloth masks, surgical masks and Filtering Face Piece 2 (FFFP2) masks, with output results that the three types of masks show stable resuts to protect all the time and doesn’t depend on persons activities. At this moment, CoronaVirus Disease 2019 (COVID-19) is one of the disease that causes global pandemic and creates several new clusters, especially traditional market clusters. Traditional market is one of the driving wheels that can pursue society economy. In that case, there needs to be serious attention in taking self care by using protective equipment at least a mask. This mapping of the distribution level people for using masks combines many aspect such as map visualization, website information system and image processing for masks detection. The use of image processing plays an important role in the mapping system, that’s because the processing of manually counting people who are not using masks will take a lot of labor in its implementation. Image processing used is face mask detector and people counter with 82% average accuracy at the implementation process. The hot spot analysis mapping method cannot be used in static data types such as traditional market, because it will gave the same result in the same density of market location from day to day. The most exact method for the data type that compares the values of not using mask to the entire traditional market is Inverse Distance Weighted (IDW) Interpolated Method. Testing results using the new method show that there is a change for highest or lowest not using masks by people at the traditional market. This method only calculates the value and not calculate distance between each market.

Sistem Rekomendasi Games menggunakan Metode Item-based Collaborative Filtering berbasis Website Fernando Febrianto; Justinus Andjarwirawan; Rolly Intan
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Item-based Collaborative Filtering is a method that is usually used for a Recommendation System based on the items that most users choose, because this method can recommend according to the tastes of most users who choose, this method is very effective in time to recommend an item in any form.This study combines Fuzzy Similarity, Item-based Collaborative Filtering, and User-based to produce a recommendation, by calculating the similarity value using Fuzzy Similarity and User-based will make it easier to find the similarity value between users to be processed again using the Item-Based Collaborative Filtering method for recommendations that are suitable for users.The results of this study are 10 Game Recommendations that are in accordance with the implementation of Item-based Collaborative Filtering, Fuzzy Similarity, and User-based which take from the most similar people by calculating the similarity value between users and take the game that is most chosen by users. and the recommendation system works, and from the survey results, it is found that people who try to enter this website do not feel confused about the User Interface, there are also many users who like to play games, and according to the survey, the accuracy rate is quite large.

Sistem Pakar Diagnosa Penyakit Saraf Menggunakan Metode Forward Chaining dan Certainty Factor Lucky Alexandre Lembangan; Kartika Gunadi; Alexander Setiawan
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Neurological diseases are one of the public health problems that requires special policies in an effort to handle it so that complete data are needed regarding cause, developments and outcomes. Neurological diseases consist of various types of nerves. Most people today tend to ignore or less in response to disorders that occur in the nervous system. After all, the neurological system plays a very important role in all human activities, because if the slightest symptom or disturbance is ignored, it can have serious consequence. As technology becomes more sophisticated, therefore in the future this research is expected to help replace the role of a doctor to diagnose early symptoms in the neurological system which will be implemented in a system called an expert system. This neurological disease diagnosis expert system is equipped with Forward channeling and Certainty factor methods. The usefulness of forward chaining in this program is to collect facts that occur to the user so that later they produce conclusions, so that users do not need to answer all the questions. By selecting the existing symptoms, you will get a conclusion that is a neurological disease that is owned by the user. The usefulness of the Certainty factor in this program is to display the level of system confidence in the diagnostic results in the form of a percentage. So that later serves to convince users when using this program. Based on the test results, this program can provide solutions that are suitable for diseases related to the symptoms felt by the user. The results of the calculation of the Certainty factor obtained quite significant results when compared with the results of interviews with experts.

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
-

Contact Email
-

Phone
-

Journal Mail Official
-

Editorial Address
-

Location
Kota surabaya,

Jawa timur

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name -

Contact Email -

Phone -

Journal Mail Official -

Editorial Address -

Location Kota surabaya, Jawa timur INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
-

Contact Email
-

Phone
-

Journal Mail Official
-

Editorial Address
-

Location
Kota surabaya,

Jawa timur

INDONESIA