Garuda - Garba Rujukan Digital

Pembuatan Website untuk Rekomendasi Smartphone Bryan Christiansen; Leo Willyanto; Hans Juwiantho
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

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

The era of digitalization is upon mankind. Humans as a social being are heading towards a faster way of exchanging information. With all accessible information known to man is on our fingertip, the use of gadgets is no longer a luxury, but becomes a necessity.The topic for this thesis is creating a website that can give those who need to buy smartphone but do not understand the details of difference of each product. Recommendations that are given to the user are based on their preferences like price or the size of the smartphone. The website converts the criteria of preferences that are inputted by the user into more detailed parameters.The result of this thesis can give users a list of smartphones recommendations. Via the list given, user can have a new perspective and options that are small in size to choose a smartphone that matches user’s criteria of preferences.

Sistem Monitoring Solar Charge Controller Menggunakan Raspberry Pi 3 Secara Mobile Aldo Kris Barlianto; Djoni Haryadi Setiabudi; Resmana Lim
Jurnal Infra Vol 9, No 1 (2021)
Publisher : Jurnal Infra

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

In monitoring the charging of power source using solar panels, it is very important to find out the process of charging resources. Research about monitoring process has been carried out previously, but the monitoring process still depends on other software, and it cannot be done by mobile. In this research, the monitoring of solar charge controller will be carried out where user is no longer depends on additional applications / software and also can be done via PC / smartphone.The solar charge controller itself comes with a factory default software for data monitoring, but the usage of the application is very limited to the wiring system and also the monitoring process cannot be carried out by mobile. This research aims to be able to carry out the monitoring process by mobile using Raspberry Pi, so that users are no longer limited by wiring system and monitoring can be done in application which based on mobile web application, so that users can find out the monitoring process from a website on a desktop and also via smartphone.Through several test that has been held, it can be concluded that monitoring process can be done online using Raspberry Pi and modbus rs485 devices in mobile web application. The power parameters taken by the application are solar voltage, solar current, battery voltage, charge current, and load power. The application is also able to run / monitor several existing devices or more than one device in one application. During testing process, it is using 1 scc device and for other devices using a virtual device. The result of the percentage error from the measurement of the monitoring device is the reading of the solar voltage parameter data has an accuracy rate of 99.26% with an average 0.1 V selection, solar current has an accuracy rate of 95.6% with an average difference of 0.03, and the battery voltage has an accuracy 96.31 with an average difference of 0.18V.

Aplikasi untuk Monitoring Jaringan IoT Menggunakan Algoritma Address Shuffling dengan HMAC Elvan Alandi; Agustinus Noertjahyana; Justinus Andjarwirawan
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

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

With the increasing market of the Internet of Things and Wireless Sensor Network (WSN). Increasing network security on the Internet of Things is important. Internet of Things is used starting from smart homes, smart campuses, smart cities, etc. so securing the Internet of Things network is more important than securing ordinary local networks. In addition, IoT devices have weaknesses in computing capabilities and storing sensitive data. There are four main types of weaknesses in the network, namely address spoofing attacks, false address conflicts, address exhaustion attacks and negative reply attacks.The method used is Address shuffling with HMAC. This method is run by the DHCPv6 server (Dynamic Host Configuration Protocol) as a network coordinator and is monitored by the Android application to secure the Internet of Things network. DHCPv6 server is used on the Internet of Things network because it is faster and easier to control through the server, can be used on large networks and stop and restart commands can be done on the server. Additionally, when a DHCPv6 server has a problem, this will not interrupt other devices on one network.The result of this program is a monitoring application that is able to notify users of attacks and the network is able to minimize four weaknesses in the network. So that later this application can help users to take preventive actions against attacks on the network.

Aplikasi Warehouse Inventory Picking Order pada PT. XYZ Menggunakan Symbiotic Organism Search Algorithm Adelyn Thungriallu; Andreas Handojo; Tanti Octavia
Jurnal Infra Vol 9, No 1 (2021)
Publisher : Jurnal Infra

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

Warehouse Inventory Picking Order is the process of taking or placing goods in the warehouse according to the demand list. This is an important process in a company, for example PT. XYZ, because it involves operational costs and can affect the customer satisfaction. Efficiency is needed, especially in the speed and accuracy of picking up or placing products in the warehouse. If the picking order process is efficient, the operational costs and time required will be more efficient too.Unfortunately, this process is often done manually and becomes inefficient due to long and repetitive processes. To answer this problem, a web-based application was designed to determine the route for picking and placing products to minimize the travel distance by using the Discrete Symbiotic Organism Search Algorithm (SOS Algorithm) for discrete data. The final result is that the routing problem can be solved using SOS Algorithm for discrete data with an average distance reduction rate of 38.49% for 25 data.

Sistem Pakar Diagnosa Kerusakan Pada Gitar Menggunakan Metode Forward Chaining dan Certainty Factor Billy Gracia; Djoni Haryadi Setiabudi; Justinus Andjarwirawan
Jurnal Infra Vol 9, No 1 (2021)
Publisher : Jurnal Infra

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

The guitar is a musical instrument that is in demand by many parties, from beginner to professional musicians. But any musical instrument including the guitar will not be free from damage. There are still many musicians who are confused about the damage they have suffered and do not know what to do with the symptoms they are experiencing. Similar research has been made, namely the application for diagnosing damage to guitars, some using the forward chaining method, some using backward chaining, or dempster-shafers, but in similar studies there is no percentage or level of confidence that can convince users of the diagnostic results, and the user cannot choose how sure to experience the symptoms that occur. Therefore, an expert system is needed to diagnose guitar damage by selecting the symptoms experienced according to the level of confidence, which can detect the damage that occurs and the percentage level of system confidence in the results of the diagnosis to convince the user of the results of the diagnosis..The expert system in diagnosing guitar damage is equipped with Forward Chaining and Certainty Factor methods. The usefulness of Forward Chaining in this diagnostic system is to collect facts or symptoms towards a conclusion, so that users do not need to answer all the questions. By selecting the existing symptoms, a conclusion will be drawn, namely damage. And the use of Certainty Factor in this system is to display the level of system confidence in the results of the diagnosis in the form of a percentage. So that it can convince the user of the diagnostic results.The results of the tests carried out, of the 20 trials by experts, 18 of them have conformity with the results of expert opinion. There are 2 unsuitable trials because the percentage of CF between the probability of damage 1 and 2 is the same, so there is a special case where if the CF percentage of the probability of damage 1 and 2 are the same, then the user can see the solution to the second damage in the Damage Encyclopedia. From the tests carried out, the Expert System with the Forward Chaining and Certainty Factor methods can detect damage to the guitar with an accuracy level of matching the results of the system with expert opinion of 90%.

Perbandingan Character Recognition dan Text Recognition Menggunakan Extended MNIST dan IAM Database dan Tesseract pada Tulisan Tangan Ijazah Made Yoga Mahardika; Kartika Gunadi; Alexander Setiawan
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

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

The problem with handwriting is how a technique can recognize various types of writing in various forms. Different from computer letters that consistent, each human’s handwriting is unique in the form and consistency. These problems can be found in ijazah documents where the data is handwriting.Data location segmentation uses run length smoothing algorithm with dots as segmentation features. Handwritten text recognition (HTR) technique requires data segmented into words. Handwritten character recognition (HCR) technique requires data segmented into characters. HCR uses the LeNet5 model with the EMNIST dataset. HTR uses tesseract tool and convolutional recurrent neural networks with the IAM database.Experiment on 10 samples of scan images, segmentation obtained an average accuracy of 95.6%. The HCR technique failed in the letter segmentation process in cursive handwriting. The best technique is the HTR with tesseract tool managed to get word accuracy above 69% tested on 5 scan samples, 15 data fields.

Perbandingan Analisis Faktor Penentu Penjualan PT. X Menggunakan LASSO Regression dan Gradient Boosted Regression Tree Jessica Athalia; Henry Novianus Palit; Silvia Rostianingsih
Jurnal Infra Vol 9, No 1 (2021)
Publisher : Jurnal Infra

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

Information becomes a crucial asset for an organization. However, employees of PT. X are facing difficulty in analyzing data because it has to be processed one by one. Moreover, analyzing data in an operational database is not recommended as it can interfere with the performance of the operational database. Then, when the Board of Directors want to know the reason behind its sales’ performance, they conclude it based on their mere assumption. This research implemented a data warehouse with the help of ETL tools. Then, sales transactions of PT. X were analyzed to get information about factors that affect company’s revenue. Factor models were formed for brands which sales were not good enough these past few years. Factors which are examined are sales price, stock availability, on time delivery of goods, quantity of returns, month of transaction, and cost price. The analysis was carried with two methods, LASSO regression and Gradient Boosted Regression Tree. These models were measured by Root Mean Squared Error, R-squared, and Variance Inflation Factor to know which model performs better. Result of the research shows LASSO regression and Gradient Boosted Regression Tree succeed in performing feature selection for sales transactions of PT. X. Yet, the factor model from Gradient Boosted Regression Tree gives a better result than LASSO regression. Last, a program was made for the company in the need of future analysis using Gradient Boosted Regression Tree.

Klasifikasi Motif Batik menggunakan metode Deep Convolutional Neural Network dengan Data Augmentation Samuel Febrian Tumewu; Djoni Haryadi Setiabudi; Indar Sugiarto
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

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

Related researches before used Convolutional Neural Network (CNN) VGG to classify batik motif which limited only on geometrical pattern and implemented 2 augmentation consist of scale and rotation. Therefore, this research uses CNN Residual Network (Resnet) with 4 augmentation technique on both geometrical and non geometrical batik pattern.This research use (Resnet) as a main architecture of CNN to identify batik pattern. Batik motives for this research are from geometric category which is ceplok, kawung, lereng, nitik, and parang. And from nongeometri category are semen and lunglungan. Furthermore, the dataset will be applied scale, random erase, rotation, and flip augmentation to increase the quantity and variation of batik dataset.The results show that CNN Resnet with data augmentation on training dataset gives accuracy up to 84,52% on Resnet-18 and 81,90% on Resnet-50. furthermore, rotation augmentation adds 4,06%, random erase augmentation adds 9,38%, scale augmentation adds 6,52%, and flip augmentation adds 8,58% on accuracy

Pengembangan Chrome Extension untuk Mengidentifikasi Phishing Website berdasarkan URL dengan Algoritma Random Forest Kevin Benedict; Agustinus Noertjahyana; Endang Setyati
Jurnal Infra Vol 9, No 1 (2021)
Publisher : Jurnal Infra

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

The ever developing technology makes internet one of the most important part in human’s daily activity. This development is also followed by the increase of phishing activity which is not only in quantity, but also in the variety of techniques. The loss caused by phishing attacks is quite big. There are a lot of applications for preventing phishing attacks, but most of them are still not accurate enough. Several studies show that ensemble learning algorithm has a good capability in detecting phishing website.In this research a chrome extension which uses a Random Forest model to detect phishing websites has been developed. Random Forest is one of the most well-known ensemble learning algorithm. The most important hyperparameters which would be experimented with are n_estimators, min_samples_leaf, min_samples_split, max_features, and max_depth. Features used are Lexical features which are based on references from other researches, and Domain-based features which are the newly proposed ones, comprised of Global Page Rank, Average Daily Time, Sites Linking In, Domain Age, and Registration Period. All features are obtained only from the URL.This research shows that dataset quality is the most impacting factor in making a good model. Hyperparameter tuning is also an important part but is only limited to certain scenario. The newly proposed features could make an improvement to the model’s performance. From several experiments, the usage of Lexical and Domain-based features has successfully achieved the best accuracy of 98.28%.

Smart Trash Untuk Membantu Petugas Kebersihan Menggunakan Arduino Riesky Akbar; Djoni Haryadi Setiabudi; Handry Khoswanto
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

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

Many times, the garbage bins at public places are overloaded even exceeding capacity or overflow which creates unhygienic conditions for people as well as ugliness to that place and leaving bad smell. The full garbage bins are left to pile up and wait until they are taken back by the janitor. To avoid that kind of situation, a smart trash is made for assisting the janitor to monitoring the level content of the garbage bins. Navghane [5] has created a smart trash that can monitoring level of garbage by the web browser. This thesis will create a smart trash system with push notification by a smartphone application that will be easier for janitors pick up the garbage bin just in time.The garbage bin is installed with Arduino WeMos D1 R1 system and proximity sensor E18-D80NK which will show the status of the garbage at the current level. Data obtained from the sensor will be sent with a microcontroller that connected with Wi-Fi to the database. That will be data exchange in real-time between an application on the user’s smartphone with the smart trash device.The result of this thesis is the device can detect and show the garbage level in real-time with percentage and 2D images on the smartphone application, and provide a push notification that appears when the garbage level has full or reached the upper limit. Proximity sensor E18-D80NK is prone to detect dry trash, which is transparent and thin, but can detect dry trash which are solid and not transparent.

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