Jurnal Komputer Terapan

Perancangan Sistem Informasi Pembayaran Uang Komite Sekolah Berbasis Web

2021-04-20T00:30:01+00:00

The SMK Kinali 1 Vocational School Committee is an organization engaged in the management of school committee money payments consisting of payment of tuition fees and payment of development money which is managed directly by committee treasurers and data processing has not yet used a computerized system so that less time is needed in processing payment data SPP money and development money payments. Based on the existing problems, a web-based information system was built to process data in the SMK Negeri 1 Kinali committee. Information systems designed using the SDLC (System Development Life Cycle) method, PHP programming language and MySQL database.Data Processing Management of the committee's money payment was built an information system with the name of the Web-based School Committee Money Payment Information System at the SMK Kinali 1 State Vocational School in West Pasaman District, with the aim of assisting the committee treasurer in processing committee money payment data. This information system provides convenience in obtaining information, because all data is stored in the db_Komite database so that all data and information are well, so that the system provides quality and valuable information. The school committee's payment information system is very effective and efficient so that the information presented is more valid.

Kompresi Citra Digital Dengan Basis Komponen Warna RGB Menggunakan Metode K-Means Clustering

2021-04-20T00:44:11+00:00

With the development of technology and digital media, the quality of the data used is also getting higher but the size of the data is also getting bigger and requires larger storage media. To overcome the increasing need for data storage, one way that can be used is by compressing data to save space in storage memory. In this study, the k-means clustering method will be used to compress data in the form of a digital image. By grouping the colors of an image and changing the value of the color pixels in the image based on the value of the cluster center of each cluster member. The initial centroid value which is determined at the initial stage of clustering will affect the compression results. In this study, 10 experiments were carried out, with the best image quality results obtained in the 5th experiment with an MSE value of 70.22 and a PSNR value of 29.70. While the compression quality was obtained in the 7th experiment with a compression ratio of 74.5%. The results of the measurement of image quality in the 10th experiment were also obtained with an MSE value of 73.45 and a PSNR value of 29.51, and the lowest compression quality was obtained in the third experiment with a compression yield ratio of 71.3%. The average measurement results obtained an MSE value of 71.47, a PSNR value of 29.62 and a compression ratio of 72.40%.

Prediksi Harga Bitcoin Menggunakan Metode Random Forest

2021-04-20T00:48:13+00:00

During this pandemic, virtual financial transactions increased sharply. Because the storage of assets and forms of buying and selling transformed using digital services. Bitcoin as one of the cryptocurrencies that is currently widely used and in demand by the people of the world, but there is no specialized financial institution responsible for bitcoin buying and selling transactions, requires a bitcoin price prediction system to know the status of the value of bitcoin. Referring to the ever-fluctuating characteristics of bitcoin data, the Random Forest Regression method is used to predict the price of bitcoin. This algorithm is one of the modeling that can produce good performance in terms of prediction. Using Random Forest Regression modeling, MAPE value was obtained by 1.50% with accuracy of 98.50%. That value is the value that produces the best performance among all bitcoin prediction attempts.

Klasifikasi Topik Skripsi Berdasarkan Makna dengan Pendekatan Semantik Web

2021-04-20T01:02:19+00:00

The Semantic web is a technology that can understand contexts as humans do. Many fields can take advantage of the technology in solving the problems it faces, one of which is higher education. This research aims to find out the most popular topic(s) discussed in Bachelor’s theses of the Informatics Engineering Study Program of Universitas Padjadjaran. Many of the Bachelor’s theses have discussed similar topic areas, but with different terminologies. It is difficult to determine whether a topic has been discussed too often and what algorithms are often used in the research. The Study Program can use the results of data processing in curriculum design and evaluation. The steps taken in this research are data collection, entity creation, ontology implementation, creating RDF, and performing SPARQL queries. In creating an entity, several terms with similar meanings were obtained and then made into unique master data. The results can be seen from the ontology's visualization using Protégé that the relationship between entities with the same value can be seen. The query results revealed that 36.15% of the theses is about Information System, and 24.41% involve making applications.

Model Prediksi Kemenangan Tim dalam Game League of Legend Menggunakan Algoritma Decision Tree

2021-04-20T01:09:30+00:00

Online games are growing very rapidly because they are supported by the development of smart phones which are increasingly being used. Online games are in great demand by various groups ranging from children, teenagers to adults who enjoy playing online games. The purpose of this research is to predict the team's victory in the league of legend game by using the decision tree algorithm. In this research, the dataset taken is 50,000 data, divided into 80% training and 20% testing. The results of this research show that the Decision Tree Algorithm has the best performance among other algorithms to predict victory with the results of 96.42% accuracy, 97.74% recall Team 1, 95.06% recall Team 2, 95.31% precision Team 1, 97.62% precision Team 2 and 0.157 RMSE for independent results while for 10 fold cross validation results have 96.24% accuracy, 97.34% recall Team 1, 95.11% recall Team 2, 95.33% precision Team 1, 97.21% precision Team 2, and 0.161 RMSE in detecting wins in the game League of Legend.

Perbandingan Arsitektur LeNet dan AlexNet Pada Metode Convolutional Neural Network Untuk Pengenalan American Sign Language

2021-04-20T07:11:37+00:00

American Sign Language (ASL) is a sign language used to communicate for deaf people. The method used to identify ASL is Convolutional Neural Network (CNN). The architecture used by LeNet and AlexNet. The results of each architecture are then compared. The research was conducted with 2 schemes of the amount of data used, namely the first scheme of 100 data per letter and the second scheme of 1,000 data per letter to test the performance of the two architectures. The research results after being tested with new data, the first scheme for the LeNet architecture produces an overall accuracy of 48.332% and the AlexNet architecture produces an overall accuracy of 32.584%. The second scheme for the LeNet architecture produces an overall accuracy of 92.468% and the AlexNet architecture produces an overall accuracy of 91.618%. Overall comparison can be said that the LeNet architecture is the best architecture in this study.

Analisis Address Resolution Protocol Poisoning Attack Pada Router Wlan Menggunakan Metode Live Forensics

2021-04-21T04:45:50+00:00

Nowdays, the development of technology makes technology a necessity for almost everyone.
Various kinds of jobs can also be connected through a technology called the internet network.
because it’s easy to use, some businesses and agencies are already using wireless local area
network technology, but most of them pay less attention to data communication security on
wireless networks. One type of attack on on Wireless Local Area Network with open access is the
address resolution protocol poisoning. By using it, attackers can find the data frames and modify
or even stop the internet traffic, because the data studied is in the form of volatile data that can
be found only in RAM storage or on network traffic, so the attack in this case can be analyzed by
using the live forensics method. Volatile data is temporary and will only exist when the system is
still on, so that digital evidence information and the behavior of the attacker who carried out the
attack can be identified by using live forensics method. There is detection in this study using the
Intrusion detection system Snort application which will send alerts when the system attacked

Aplikasi Penerjemah Bahasa Isyarat Indonesia menjadi Suara berbasis Android menggunakan Tensorflow

2021-05-06T00:36:46+00:00

Indonesian Sign Language or BISINDO is a two-handed sign language that is used as a liaison in communication. BISINDO is used by people who have limited speech or hearing, but not for other communities. This causes BISINDO users have difficulties in conveying information because only a few people understand BISINDO. Therefore, an application was developed to help communication between BISINDO users and Indonesian in realtime. BISINDO classification is carried out using the Convolutional Neural Network method and the MobilenetV2 architecture using tensorflow. The classification results are used as a model for android which is then used as a sound. Based on model testing, the resulting accuracy rate resulted in 54.8% in the classification of 30 specified languages. Thus, the performance of the model can be said to be not optimal in classifying. Based on the application testers to 30% of respondents, it was found that respondents strongly agreed with this application with an average value of 83.95%.

Sistem Rekomendasi Penerima Zakat Untuk Mustahiq Dengan Metode Simple Additive Weighting (SAW)

2021-04-16T08:47:15+00:00

Zakat in Islam is a cleanser from wealth. Apart from cleansing from wealth, zakat also eases the burden of mustahiq. In Indonesia, which is predominantly Muslim, the problem of zakat is an important matter to maximize its management which will later be useful for overcoming poverty problems. Jami Nurul Hikmah Mosque is a religious and social institution located in Tangerang City. The problem that is often encountered is the method in selecting mustahiq which is still using the manual method so that it often causes problems such as the length of the selection process and the occurrence of miscalculations causing inaccurate mustahiq selection results. In addition, the unavailability of access to information to see mustahiq who have entered the list of zakat recipients has resulted in mustahiq who have received zakat to receive assistance more than once a year. Assessment criteria in determining zakat recipient recommendations for mustahiq include looking at the status of residence, income, employment status, number of dependents, and family vehicle. To solve this problem, a recommendation system was built that could help zakat managers in distributing zakat to zakat recipients. The Simple Additive Weighting (SAW) method is used to calculate the value of the criteria to produce zakat recipient recommendations. With this system, zakat managers can provide recommendations for potential zakat recipients quickly and accurately.

Implementation of Haar Cascade Classifier for Face Detection and Grayscale Image Transformation Using OpenCV

2021-04-16T08:48:10+00:00

Face detection applications on digital images are very necessary in the process of face recognizing. This application is widely used in various disciplines, one of them is computer vision such as biometric recognition systems, search systems, and security systems. Computer vision is a combination of artificial intelligence and machine learning. It can gain informations from image and video by using computer algorithms. Many previous studies have developed face detection applications with various algorithms with certain programming languages. The detection of an object is the most important part in computer vision. Determining an accurate face location is still a challenging task for researchers. The location of the face is the main step in computer vision to find the face part in the input image. Open Source Computer Vision Library (OpenCV) is software that allows open-source library containing supporting object detection that is easily accessed into the Java programming language. Haar cascade classifier is one of the algorithms used for object detection. This algorithm can convert an object quickly by taking the number of images in a square shape on an image. In this study, discussing the application of face detection in digital images using the Haar Cascade Classifier and the transformation of images into gray / grayscale images using the OpenCV library. The results in this study have 100% accuracy in input images that have objects in the frontal position.

The Analysis and Design of School Health Unit Information System

2021-05-25T02:02:04+00:00

The success of education is supported by both academic and non-academic aspects. To achieve this educational goal, schools should have a good partnership with parents regarding both aspects, including student health. But unfortunately, many school considers student health unit which is called Usaha Kesehatan Sekolah (UKS) as a supporting system in their business processes at school, and it gets less attention. Currently, quite a lot of activities at UKS are carried out on a paper-based process, or even rely on the memory of officers, such as permission not to go to school, use of drugs, information on outreach activities, things that happen to the children at school and other activities. Such information may not be well received by parents. Therefore, a system that allows parents and schools to interact online is needed, regarding children's health conditions while in school and otherwise. This system is designed in two platforms, which are web and mobile; and centralized in one database, so that the system remains integrated and can be accessed easily by the school and parents. Thus, this system is expected to improve the quality of communication between schools and parents.

Penerapan Metode System Usability Scale (Sus) Perangkat Lunak Daftar Hadir Di Pondok Pesantren Miftahul Jannah Berbasis Website

2021-05-27T05:08:10+00:00

The application of technology from time to time develops rapidly, because with the current application of technology it is easier for human work, one of which is by using software, at the Miftahul Jannah Islamic boarding school located in the village of observation, Kec. In the observation of OKU district, in South Sumatra, there has been no application of technology, namely software, one of which is a website-based attendance list software. The purpose of this research is to build a software attendance list at the Miftahul Jannah Islamic boarding school for teachers, students and female students by applying the System Usability Scale (SUS) method. This research method uses observation, interviews, literature study, needs analysis as well as building and implementing attendance list software using the application of the System Usability Scale (SUS) method, where the criteria for implementing the SUS method are if the value is greater than 80.3 then the criteria are very good, while the value from 68 to 80.3 means software with the application criteria is good, the value of 68 application of the SUS method is sufficient, while the value of 51 to 68 with the criteria for applying the SUS method is less, the value is below 51 then the criteria for applying the SUS method is very lacking, As for the results of the application using the method System Usability Scale (SUS), get the results of the respondents for k teachers where the average value of the conversion results obtained was 79.54, while for student respondents showed the average value conversion result using the application of the SUS method the result was 79.33 where the conversion results The application of the SUS method in this study has been accepted in accordance with the criteria for the distribution of the system usability scale (SUS) method.

Rancang Bangun Aplikasi Simulasi 3D Pembelajaran Fisika Berbasis Fisika Berbasis Desktop Sebagai Media Pembelajaran Untuk Siswa Sekolah Menengah Atas (SMA) (Studi Kasus: SMA Negeri 1 Bukit Batu)

2020-11-13T10:51:26+00:00

Elastisitas zat padat, fluida statik, fluida dinamik, dan termodinamika merupakan empat materi yang diajarkan pada pelajaran fisika untuk siswa SMA kelas XI. Berdasarkan hasil wawancara, metode konvensional dengan bantuan media konvensional masih menimbulkan kesulitan dikarenakan keterbatasan informasi, serta kurangnya alat peraga untuk menunjang pembelajaran. Sehingga diperlukannya suatu media pembelajaran baru yang dapat menjelaskan materi fisika secara interaktif dan dipergunakan sebagai alternatif media pembelajaran baru untuk membantu siswa dalam memahami materi. Oleh karena itu, akan dibangun sebuah aplikasi pembelajaran tentang fisika dengan materi elastisitas zat padat, fluida statik, fluida dinamik dan termodinamika berbasis desktop yang akan menampilkan simulasi penerapan dan materi tersebut. Aplikasi ini telah berhasil dibangun dengan fungsionalitas yang berjalan baik serta materi yang tervalidasi untuk membantu siswa dalam memahami materi yang disajikan dengan diperolehnya peningkatan yang lebih unggul dibandingkan media konvensional, yakni 21,33% untuk elastisitas zat padat, 14% untuk fluida statik, 16% untuk fluida dinamik, dan 19% untuk termodinamika. Serta dapat dijadikan alternatif media pembelajaran interaktif untuk guru dalam menyampaikan materi yang disajikan dengan diperolehnya hasil pengujian kepuasan sebesar 89,21% dengan kategori sangat baik serta pengujian usabilitas sebesar 73,20% yang menunjukkan aplikasi telah bersifat acceptable.

Pemodelan CNN Untuk Deteksi Emosi Berbasis Speech Bahasa Indonesia

2021-05-04T01:38:19+00:00

In the interaction between humans and computers, the ability to recognize, interpret, and respond to emotions expressed in speech is needed. Until now, there is very little research for speech emotion recognition (SER) based on Indonesian. This is due to the limited corpus of Indonesian data for SER. In this study, a SER system was created by taking a dataset from an Indonesian TV series. The system is designed with the ability to carry out the process of classification of emotions, namely four classes of emotional labels angry, happy, neutral and sad. For its implementation, the deep learning method is used, which in this case the CNN method is selected. In this system the input is a combination of three features, namely MFCC, fundamental frequency, and RMSE. From the experiments that have been carried out, the best results have been obtained for the Indonesian language SER system using the MFCC input + fundamental frequency, which shows an accuracy rate of 85%. Meanwhile, the lowest accuracy when using the MFCC + RMSE feature is 72%. From this initial study, it is hoped that it will be able to provide an overview for researchers in the SER field, about how to select speech signal features as input in testing and make it easier for the steps to develop their research.