Articles
223 Documents
<![CDATA[Implementasi OCR dengan Metode Autoencoder pada Aplikasi Bukutamu berbasis WEB ]]>
<![CDATA[Muhamad Aldi Rizaldi]]>;
<![CDATA[Emil R. Kaburuan]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 8 No. 2 (2022): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (737.978 KB)
|
DOI: 10.35143/jkt.v8i2.5420
<![CDATA[A guestbook is a tool to record the identities of visitors who come to a place or event such as weddings, birthday celebrations, parties etc. Not just recording, the guestbook also functions as evidence and traces to avoid something unwanted. So it is not surprising that in some places it is required to submit an identity card such as a KTP when filling out a guestbook to be allowed to enter the place. KTP itself is an identity card that contains data such as name, place, date of birth etc. The data contained in the KTP can be utilized in the guestbook filling process so that officers only need to take a picture of the KTP and visitor data will be filled in automatically with the help of optical character recognition (OCR). To get a good OCR result, an image with clear words is needed, its position is not tilted and its size is not too small. Therefore, various preprocessing steps are needed before performing the OCR process, one of which is by applying denoise using the Autoencoder which has succeeded in making the image cleaner and the OCR results become more accurate.]]>
<![CDATA[Implementasi Continuous Delivery dengan Zero – Downtime Rolling Update Menggunakan Ansible ]]>
<![CDATA[Kiki Harapan Hutapea]]>;
<![CDATA[Muhammad Arif Fadhly Ridha]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 8 No. 2 (2022): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (326.434 KB)
|
DOI: 10.35143/jkt.v8i2.5429
<![CDATA[Today every organization relies on application to provide services to their customers. In fact, 62% of organizations say application are essential for their business, and a further 36% say application provide a competitive advantage. This makes companies are required to provide innovation quickly in order to give satisfaction and convenience for their customers. To respond these demands, organizations need to deliver application updates more frequently. In the traditional deployment process, each deployment starts with the requirements spesification and ends at production. The weakness of traditional deployment is the slow delivery process, where its done manually and on a step-by-step basis, which can cause points of failure and human errors that resulting in delays or total system shutdowns. Continuous Delivery help organizations speed up the process of delivering applications to customers. One of the software that can build Continuous Delivery with zero-downtime is Ansible. Based on the test, Ansible managed to maintain the service availability with 100% up time rate and able to speed up deployment time by 48%. From load testing, it was found that 1 server was able to handle a load of 2000 users per 5 minutes with 99% success rate.]]>
<![CDATA[Perbandingan Kinerja Ingress Controller Pada Kubernetes Menggunakan Traefik Dan Nginx ]]>
<![CDATA[wisnu ramadhani]]>;
<![CDATA[Muhammad Arif Fadhly Ridha]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 8 No. 2 (2022): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (239.401 KB)
|
DOI: 10.35143/jkt.v8i2.5440
<![CDATA[Pada perkembangan zaman saat ini banyak cara untuk mengekspos sebuah service pada server kubernetes agar dapat digunakan oleh client salah satunya NodePort dan LoadBalancer, tetapi mengekspos menggunakan NodePort dan Loadbalancer client harus tau semua IP Node dan semua IP LoadBalancer yang terespos ke public. Oleh karena itu, ingress hadir untuk memudahkan client mengakses service dengan hanya menggunakan domain ingress. Proyek akhir ini membandingkan latency, throughput, tingkat kecepatan server menyelesaikan request, pemakaian CPU dan pemakaian memori pada saat membuka halaman web, antara kube ingress traefik, kube ingress nginx dan kube tanpa ingress. Diperoleh hasil pengujian latency tertinggi yaitu 356103.5ms oleh Server Kubernetes cluster tanpa ingress (Loadbalancer) dan latency terendah yaitu 5954.1ms oleh Server Kubernetes cluster ingress traefik. Throughput tertinggi yaitu 3268.8 second oleh Server Kubernetes cluster ingress nginx dan Throughput terendah yaitu 11.1 second oleh Server Kubernetes cluster ingress traefik. Dalam pengujian menggunakan Apache Benchmark Server Kubernetes cluster ingress traefik dapat menyelesaikan 100, 300 dan 500 request client lebih dahulu dibandingkan kedua server lainnya. Dalam keadaan busy, pemakaian CPU tertinggi adalah server Kubernetes cluster ingress nginx yaitu 99%, pemakaian memory tertinggi adalah server Kubernetes cluster ingress traefik yaitu 46%]]>
<![CDATA[Aplikasi Metode VIKOR untuk Menentukan Penerimaan Proposal Kegiatan Desa ]]>
<![CDATA[SUKAMTO TO]]>;
<![CDATA[Yanti Andriyani]]>;
<![CDATA[Ibnu Daqiqil Id]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 8 No. 2 (2022): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (377.101 KB)
|
DOI: 10.35143/jkt.v8i2.5443
<![CDATA[The office of the Wali Nagari Simpang has a proposal for village activities. The evaluating proposals is carried out directly in the field and is done manually, so it is possible for errors to occur. For that we need a decision support system using the VIKOR method. The final result of the five proposals submitted with the specified criteria, provides a recommendation that the proposal Jembatan Kp. Batuang - Bukik Putuih is the best proposal and deserves to be funded]]>
<![CDATA[Sistem Deteksi Penggunaan Masker secara Real Time menggunakan Metode Eigenface dan Support Vector Machine ]]>
<![CDATA[Nahya Nur]]>;
<![CDATA[Indra Indra]]>;
<![CDATA[Farid Wajidi]]>;
<![CDATA[Iin Aisyah Khofifah]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 8 No. 2 (2022): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (499.23 KB)
|
DOI: 10.35143/jkt.v8i2.5449
<![CDATA[At the beginning of 2020, Indonesia was shocked by the outbreak of a virus called Covid-19. One of the measures to prevent the spread of the epidemic is to wear a mask. In this research, a real-time mask detection system will be developed using eigenface and support vector machine (SVM). There are three main stages in this research, namely reading the image through the camera, calculating the eigenvalues, and classifying using SVM. The results of the classification consist of two classes, namely masked and unmasked. In general, if the eigenvalues ​​of the testing image are closer to the masked image, the output is masked and vice versa. The results of the research are quite good where the test is carried out through several test scenarios including considering lighting conditions, use of accessories, object distance from the camera, and so on. Most of the results obtained through system testing can distinguish masked and unmasked faces in real time.]]>
<![CDATA[Penerapan Deep Learning Pada Jenis Penyakit Tanaman Kelapa Sawit Menggunakan Algoritma Convolutional Neural Network ]]>
<![CDATA[Wiwin Styorini]]>;
<![CDATA[Wahyu Eka Putra]]>;
<![CDATA[Wahyuni Khabzli]]>;
<![CDATA[Yuli Triyani]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 8 No. 2 (2022): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (328.978 KB)
|
DOI: 10.35143/jkt.v8i2.5522
<![CDATA[The problem of Plant Destruction Organisms (OPT), especially related to disease, has always been an issue in the management of oil palm plantations. Oil palm has diseases caused by pests and others that can affect the growth and fruiting process. For this reasearch, the aims to identify whether or not oil palm plants are healthy through the color of their leaves, so that it will facilitate the performance of farmers. Deep Learning (DL) is a field of science from machine learning by doing deeper learning for many layers. Convolutional Neural Network (CNN) is one of the DL algorithms designed to process data in two-dimensional form such as images. Therefore, in this study, the CNN method will be applied to classify the health of oil palm plants based on the color of the leaves. The data used are 3000 data with test scenarios for training data and testing data are 90%:10%, 80%:20%, 70%:30% and 65%:35%. Based on the 4 test scenarios, the best accuracy obtained is 99.90% for the scenario of 65% of training data and 35% of testing data. While the lowest level of accuracy is 99.50% for the scenario of 90% training data and 10% testing data.]]>
<![CDATA[Aplikasi Penentuan Dosis Kebutuhan Pupuk Nitrogen Berdasarkan BWD Pada Tanaman Padi ]]>
<![CDATA[Yuli Triyani]]>;
<![CDATA[Andika Djojo Kusuma]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 8 No. 2 (2022): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (353.826 KB)
|
DOI: 10.35143/jkt.v8i2.5560
<![CDATA[Nitrogen is one of the nutrients that is needed for vegetative growth of rice, but excessive fertilizer application can damage plants. The balanced application of nitrogen fertilizer to rice plants is a solution to improve the growth of rice plants so that their productivity becomes more optimal. To get the appropriate fertilizer dose, farmers must use the BWD table, but BWD is difficult to obtain, the price is quite expensive, and its use is done manually by comparing the color of the rice leaves with the color of each level in the BWD table. Different perceptions between each use often occur. Therefore, an application for determining the need for nitrogen fertilizer based on BWD was designed for rice plants. This system consists of pre-processing, feature extraction and classification stages. The pre-processing stage is the stage of improving image quality, while the feature extraction stage uses the histogram of s-RGB method to obtain the Mean and Mode values ​​of the color intensity of rice leaves. This system classifies based on the characteristics that have been extracted into 3 classes, namely: 2-3, 3-4, and 4-5 based on the BWD level. Then the system will calculate the dose of nitrogen fertilizer needed based on the input data of GKG and land area. The classification stage uses the K-NN method. Based on the results of training using 210 images and testing 90 images of rice leaves, the best results were obtained using k-NN 3 neighbors with an accuracy of 95.5%, AUC 0.98 and training time 0.8 seconds. So it can be concluded that the classification using k-NN can determine the dose required for rice plants properly.]]>
<![CDATA[Komparasi Algoritma Machine Learning Untuk Memprediksi Penyakit Alzheimer ]]>
<![CDATA[Firman Akbar]]>;
<![CDATA[Rahmaddeni]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 8 No. 2 (2022): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (318.371 KB)
|
DOI: 10.35143/jkt.v8i2.5713
<![CDATA[Alzheimer's disease is a degenerative brain disease and the most common cause of dementia. It is characterized by deterioration of memory, language, problem-solving, and other cognitive skills that affect a person's ability to perform everyday activities. This decrease occurs because nerve cells (neurons) in parts of the brain involved in cognitive function are damaged and stop working properly. One way to detect Alzheimer’s is to use models of machine learning algorithms. In this study, the authors' team aimed to compare models of machine learning algorithms to find the one that gives better results in prediction Alzheimer's disease. Machine learning models algorithms in this study were built using Random Forest, Artificial Neural Network, Logistic Regression, Support Vector Machines, and Naive Bayes. The author's team then tested his 373 Alzheimer's disease patient data from Kaggle Open Datasets and showed that the Logistic Regression algorithm model can achieve better with 85,71% accuracy rate.]]>
<![CDATA[Pengembangan dan Penerapan Sistem Informasi Marketplace UMKM ]]>
<![CDATA[Yohana Dewi Lulu Widyasari]]>;
<![CDATA[Abiyyu Taufiq Ramadhan]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 8 No. 2 (2022): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (646.407 KB)
|
DOI: 10.35143/jkt.v8i2.5729
<![CDATA[The Indonesian people in improving their economy form a business or business entity on their own initiative. In many areas, MSMEs use natural resources that have the potential. MSMEs are a means to create new jobs and can be an alternative in reducing the number of unemployed. Currently, the main problem for MSME actors is the existence of obstacles in selling their products widely so that it has an impact on the lack of effectiveness and efficiency of the sales process carried out. Another problem is the lack of information to the public about MSMEs and MSME products that are currently being sold. Based on the problems, an MSME Marketplace information system was built which can be a medium for buying and selling MSME products online. every MSME that has registered on the marketplace can manage their own MSMEs. Marketplace owners can have a system that can record MSMEs. This system was created using the Hypertext Processor (PHP) programming language and MqSQL database. System development is done using the prototyping method in 3 iterations. The results of the prototyping iteration have been implemented well in the system development. The results of black box testing stated that this system was running properly. UAT results in 95% to assess this system has functionality that runs well, and whether users have been able to accept the system.]]>
<![CDATA[Penerapan Standar ISO 55000 Untuk Manajemen Aset Dengan Pendekatan Metode Topsis ]]>
<![CDATA[Salamun Salamun]]>;
<![CDATA[Johan Saka Wikarta]]>;
<![CDATA[Ira Puspitasari]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 8 No. 2 (2022): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (552.045 KB)
|
DOI: 10.35143/jkt.v8i2.5730
<![CDATA[Assets are part of the facilities of a company or institution. Educational institutions, by applying the topsis method, are intended to be able to systematically choose the best alternative from several existing alternatives to be used as a problem-solving method. Abdurrab University has implemented asset management in managing assets at the university but still has not implemented the ISO 55000 standard in its management, where the use of assets is still not in line with the objectives of Abdurrab University. Besides, the asset lifecycle has not been implemented, many assets do not have a long service life. The purpose of this study is to improve asset management at Abdurrab University by implementing an ISO 55000 standard decision support system. The Abdurrab University asset management decision support system is built to the ISO 55000 standard with the topsis method and uses PHP and JavaScript programming languages and MySQL as data storage. The results of this study prove that the asset management system can be implemented to manage assets at Abdurrab University and that this decision support system can be used for asset procurement.]]>
