Article Per Year (5 Year)
p-Index From 2020 - 2025
2.457
P-Index
This Author published in this journals
All Journal Jurnal Infra
Liliana Liliana
Program Studi Teknik Informatika, Universitas Kristen Petra Surabaya
Computer Science & IT

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 19 Documents
Search

 1   2 
Meningkatkan Kesulitan Serangan Enemy Dengan Menambahkan Influence Map Pada Metode A* Pada Procedural Generated Tower Defense Game Michael Budiono; Liliana Liliana; Hans Juwiantho
Jurnal Infra Vol 10, No 1 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

In tower defense game, if the map dan enemy attack do not change, the strategy that will be used by the player will remain the same, this will make the game having a low replay value and will make the player stop playing the game. The existing tower defense game have used procedural generation to create different levels each time they are played, but there are still shortcoming where the map looks plain and has the same pattern every time it is played, other than that enemy attack using A* have a simple pattern and can’t  search for a profitable path for the enemy so the enemy become easy to defeat and the game become less interesting. To overcome this problem, perlin noise is used in procedural generation so that the map mode does not look plain and does not have the same pattern every time it is played, other than that enemy attack use A* by adding influence map so that enemy attack can be more challenging and interesting to the player.In this thesis, the map was created using perlin noise to determine the terrain of the tile on the map and the location of start and finish will be checked using floyd warshall algorithm to determine if the map need to be remade. For enemy attack, A* is used with the addition of influence map to make the enemy can choose a path that is more profitable for it by avoiding roads blocked by tower and roads that can be attacked by towers.The test results show that after the map is generated repeatedly for 20 times, no map has the same location and distance between start and finish. In addition, it is also found that the implementation of procedural generation and influence map made the game 25.7% more challenging when compared to games that did not use it.
Aplikasi Rekomendasi Resep Menu Meal Plan Berdasarkan TDEE dan Zat Gizi Makro Pengguna Berbasis Web Dengan Pendekatan MCDA Dan EgoSimilar+ Ivana Jovita Handoko; Henry Novianus Palit; Liliana Liliana
Jurnal Infra Vol 10, No 1 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

Public awareness in Indonesia of the importance of a healthy lifestyle is getting higher today. Having a healthy and ideal body is the dream of people in Indonesia. One way to achieve a healthy and ideal body is to control the intake of calories, carbohydrates, protein and fat in the food consumed (TDEE and macronutrients). Everyone has different needs for TDEE and macronutrients. It is difficult to meet macro needs in accordance with the daily calorie TDEE if you do not understand how to arrange a daily food menu. TDEE and macronutrients should not be lacking nor should they be in excess, while the composition of each macro has a different calorific value for each gram unit in each food ingredient.The meal plan menu recommendation system uses EgoSimilar+ and AHPSort which is the MCDA approach, the method used in this study is used to build the "Dahar" application which is the meal plan recommendation application in this study.The results of the application and the methods used in this application are able to provide recommendations for meal plans with a tolerance of 10% calorie difference. From a scale of 1 to a scale of 5 with the meaning of a scale of 5 being the highest value, a user survey was conducted on the application and recommendation system. From the survey results, the average user satisfaction is 4.45 out of 104 respondents with the dominating scale values being scale 4 and scale 5.
Penerapan Segmentasi Warna Menggunakan K-Means Clustering untuk Pemilihan Template dalam Pembuatan Konten Willy Pratama Darmalim; Liliana Liliana; Silvia Rostianingsih
Jurnal Infra Vol 10, No 1 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

The convenience of shopping online has resulted in the development of online business trends making content and publication consistency very important to attract consumers’ attention. Color selection is an important process in content creation. However, not everyone can choose the right colors, create interesting content, and have the time to create content and organize its publication. Li's research uses Generative Adversial Networks to help design’s layout. But these elements are not provided by the application, so user still need to design themselves. To answer this problem, a content maker application was developed.K-Means Clustering is used to get the most dominant color from an image and Euclidean Distance calculates the closest color distance from the user's image with various design templates available. The additional feature of Scheduled Post addresses the problem of limited time for content publication.K-means color segmentation of 20 images with 1 or 2 dominant colors obtains 90% accuracy. Five PCU VCD lecturers rated the accuracy of selected template design color nuances 76%. Making content using thesis application is 56.18% faster than using similar application. Result of content maker design compared to other designs won 1st place with voting score of 46.66%.
Ringkasan Ekstraktif Otomatis pada Berita Berbahasa Indonesia Menggunakan Metode BERT Franky Halim; Liliana Liliana; Kartika Gunadi
Jurnal Infra Vol 10, No 1 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

In this modern era, information has become an important part of everyday life. In getting information several things can be done where one of them is by reading. With the increasing amount of information available on the internet, it is difficult for humans to keep abreast of developments. Online news is also one of the sources of information on the internet with a very large number and various topics. Reading the whole information sometimes also takes a long time. Therefore, it is necessary to make a summary of the available online news to reduce reading time and obtain relevant information. In this research, a summary of the news will be made by selecting important sentences from the news text. The method used in this research is Bidirectional Encoder Representations from Transformers with the addition of a transformer encoder layer.Based on the results of the tests that have been carried out, the pre-trained indolem/indobert-base-uncased model can produce the best F1-Score 57.17 for ROUGE-1, 51.27 for ROUGE-2, and 55.20 for ROUGE-L using abstractive reference and 84.46 for ROUGE-1, 83.21 for ROUGE-2, and 83.40 for ROUGE-L using extractive reference.
Pembuatan Aplikasi Lelang Berbasis Android Lois Fernando Audi; Liliana Liliana; Agustinus Noertjahyana
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

Auction is a process of buying and selling to auction participants, where auction participants will make bids and be sold to bidders at the highest price. Today, conducting an online auction can be done through social media. Based on a survey conducted on CV Toro Developer, people still make auction transactions via Whatsapp. This auction transaction is considered inefficient, where the admin in the Whatsapp group must pay attention to the bid price entered by the auction participant. Therefore, this thesis will make an application so that auction transaction activities can be carried out without admin assistance. This thesis will focus on developing auction applications to facilitate auction transaction activities with chat features, auto bids, deposits, bid features that can be displayed in real-time, and notification features. The test results show that the application can carry out the auction process well from the beginning of creation until the transaction is complete. Also, other features can run well.
Pemodelan Lip Reading Bahasa Indonesia Berbasis Visem Menggunakan VGG16 serta Jaro-Winkler Similarity dan Bigram Henry Wicaksono; Liliana Liliana; Alvin Nathaniel Tjondrowiguno
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

Lip reading is a technique used to understand spoken words through visual representation of lip movements. Lip reading has many uses, such as aids for laryngectomy patients and aids for people with hearing disabilities. A research shows that 2.6% of Indonesia’s population has a hearing disability. Thus, lip reading can be a relevant solution in Indonesia. This study aims to model a viseme-based Indonesian lip reading system. The method used in this research is VGG16 which is used as a classifier and Jaro-Winkler similarity and bigram (JW-bigram) which is used as a decoder. The dataset used consists of 25 Indonesian sentences composed of 50 different words and spoken by 12 speakers. The results showed that the lip reading system made using VGG16 and JW-bigram was more effective in terms of accuracy and speed compared to other methods combinations.
Sistem Mobile Application, Tracking Lokasi dan Estimasi Perjalanan Untuk Aplikasi Shuttle Bus Uk Petra Menggunakan Flutter dan Google Maps Kevin Jonathan; Rolly Intan; Liliana Liliana
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

Petra Christian University (PCU) is a campus that is already growing rapidly becoming one of the popular university in Indonesia with thousands of students from Indonesia and outside Indonesia which is now located in Jalan Siwalankerto, exactly in number 121-131, Surabaya. Petra Christian University planned to launch Shuttle Bus with west Surabaya – Petra Christian University route to facilitate many of the students from west Surabaya to reach Petra Christian University and vice versa. But, this Shuttlebus needs a control system to manage the usage of this shuttle bus by students. This control system is divided in a few big features, which is registration, reservation, identification, tracking, and features related to rating and notification system. The research results showed that after the "Petra Shuttle Bus" application was designed, most of the passengers benefited from being able to make a reservation in advance along with accessing other important features such as viewing bus locations and rating related schedules for service improvement. In addition, the driver also feels benefited because with the current check-in system, this greatly facilitates the driver in the process of checking passengers’attendance who have made the reservations. Please note that this application is far from perfect and requires further improvement according to users’ feedback.
Adaptive Sparse Transformer untuk Meningkatkan ROUGE-1 Score pada Text Summarization Scientific Paper Andrew Firman Saputra; Liliana Liliana; Djoni Haryadi Setiabudi
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

Technology advancement and internet causes lots of information that can be accessed at any time. Journal article is one of such many information that’s available that requires time to read thereof in need of automatic summary. Automatic Text Summarization (ATS) basically a process of making a new text that’s smaller than the original text without removing the meanings from the entire input text. The process of making automatic text summarization can be done in extractive and abstractive way. A summary that was made by an extractive method only able to generate a summary with a word that’s included in the original text, whereas summary that was made by an abstractive method can generate a summary that include word that does not exist in the original text. In the previous research in abstractive summarization is found is not optimal thereof need an improvement. The method used in this research is an abstractive summarization with Adaptive Sparse Transformer. Things that will be done in this research are scraping dataset arxiv machine learning, making the dataset, processing the data and trials on hyperparameter configuration in the model to see ROUGE-1 precision performance. The dataset used is Arxiv Scientific Paper dataset and Arxiv Scientific Paper+Machine Learning dataset. The results of this research showed that the method used capable to compete with state of the art methods with average R-1 precision score of 39.4 for Arxiv Scientific Paper+MachineLearning and 42.5 for Arxiv Scientific Paper.
Penyuaraan Pesan Teks Media Sosial Pada Perangkat Mobile Menggunakan Text To Speech Michael Alexander Rustan; Anita Nathania Purbowo; Liliana Liliana
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

The use of smartphones as a communication tool will increase along with the increase of smartphone users. Based on the data obtained, in early 2021 there are around 167 million smartphone users in Indonesia. The use of smartphone as a communication tool to send messages in its use can also start to annoy people when they are doing activities that require concentration, for example, such as driving. In 2017, there were about 15,341 cases of accidents in America caused by drivers using smartphone. To overcome this problem, the text to speech feature will be used to voicing the incoming messages so smartphone users do not need to open their smartphone to find out the sender and the contents of the message. The results of the tests that carried out on the usage on text to speech feature showed that the system can voiced the incoming messages well. For messages that have abbreviated words, the text to speech feature cannot voiced them properly. As for the tests carried out on the feature to detect the message, the system can detect some message data such as the package name of the application, the sender's name, and also the message content properly. For messages received through group chat, the detection results from the line application, and the whatsapp application have problems, so there are obstacles in the process of voicing group chat messages on the line application and whatsapp applications.
Klasifikasi Benda Organik dan Anorganik Dengan Metode YOLOv3 dan ResNet50 Kevin Reynaldi Tanjung; Liliana Liliana; Hans Juwiantho
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

There are still many Indonesian people throw waste in the wrong place. One of the reasons is that there are still many Indonesian people who still find it difficult to sort organic and inorganic objects. Therefore, the introduction of organic and inorganic objects is very important and we need something that can help in sorting organic and inorganic objects. By knowing the difference between organic and inorganic objects, people can sort out organic and inorganic waste. The methods used are You Only Look Once to get waste objects from an images or videos. The detected object will be cut and the results will be processed by the Convolutional Neural Network with the ResNet50 architectural model for classification. In the YOLOv3 and ResNet50 training process, adjustments are made to find parameters to get best accuracy This research will classify objects on waste objects in images or videos. The Mean Average Precision obtained by YOLOv3 is 45% and the average loss is 91%. For ResNet50 there is rule of thumb where when using input size 416x416 and the lower the number of learning rates can increase accuracy. When combined, ResNet50 is able to increase the accuracy of the detected object types by YOLOv3.
Co-Authors Agustinus Noertjahyana Alvin Nathaniel Tjondrowiguno Andre Gunawan Andrew Firman Saputra Anita Nathania Purbowo Djoni Haryadi Setiabudi Franky Halim Gerry Steven Gregorius Nicholas Goenawan Hans Juwiantho Henry Novianus Palit Henry Wicaksono Ivana Jovita Handoko Kartika Gunadi Kevin Jonathan Kevin Reynaldi Tanjung Lois Fernando Audi Marcel Slamet Sugianto Michael Alexander Rustan Michael Budiono Michelle Christiana Chandra Regan Reinaldo Kalendesang Rolly Intan Silvia Rostianingsih Stephen Cornelius Hertanto Tomy Widjaja William Sean Wiyogo Willy Pratama Darmalim Yoshua Refo