cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota bandar lampung,
Lampung
INDONESIA
Jurnal Komputasi
Published by Universitas Lampung
ISSN : -     EISSN : -     DOI : -
Core Subject : Science,
Computer Science & IT
Lingkup dan fokus jurnal berkaitan dengan tema-tema computer science, information technology, information system, software engineering, data mining, artificial intelligence, networking, multimedia, database, dan operating system
Arjuna Subject : -
Articles 231 Documents
 19   20   21   22   23 
DENOISING CITRA TULISAN TANGAN AKSARA LAMPUNG MENGGUNAKAN CONVOLUTIONAL AUTOENCODER Saniati Saniati; Verdy Haris Munandar; Rikendry Rikendry; Maulana Aziz Assuja
Jurnal Komputasi Vol 9, No 2 (2021)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v9i2.2895

Abstract

The history of a nation or a region is stored in written historical documents using paper, walls, stone, metal, and other media. Efforts to maintain cultural heritage, including these documents, are still being carried out. One of the efforts is to save it in digital form or photos, but it is possible for the obtained images become noisy images. Many factors caused an image to have noise including outdated documents, image results that are influenced by camera lenses, lighting that is not ideal, ect. Noise can affect the information in the image, it is needed to made improvements so that the quality image results can be used for other purposes, both as digital documents and further research such as written recognition. In this research, the Convolutional Autoencoder approach is used to study noise from training data and reconstruct the image into a noise-free image. The noise used in this study will be created using the Gaussian, Salt & Pepper, and Spackle methods on the image of the Lampung script. The hyperparameters on the Convolution Encoder that were tested produced good performance for the model used by achieving low loss of 0.1453 and vall_loss of 0.1504 and also could reduce noise contained in images with various noise types and intensities.
Studi Ekstraksi Fitur Berbasis Vektor Word2Vec pada Pembentukan Fitur Berdimensi Rendah irwan budiman; M Reza Faisal; Dodon Turianto Nugrahadi
Jurnal Komputasi Vol 8, No 1 (2020)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v8i1.2517

Abstract

Klasifikasi teks adalah salah satu metode untuk mengelola dan mencari informasi penting yang terdapat pada format tekstual yang tidak terstruktur. Ekstraksi fitur merupakan proses penting pada klasifikasi teks untuk mengubah format tekstual yang tidak terstruktur menjadi terstruktur sehingga dapat diproses oleh algoritma machine learning untuk mengklasifikasikan ke class yang telah ditentukan. Salah satu teknik ekstraksi fitur yang umum digunakan adalah vector space representation. Teknik ini mudah digunakan tetapi berpotensi menghasilkan data dengan dimensi banyak yang berakibat kepada peningkatan waktu komputasi bahkan tidak dapat diproses karena limitasi perangkat keras. Pada riset ini kami melakukan studi terhadap teknik ekstraksi fitur yang mampu menghasilkan data berdimensi sedikit. Ekstraksi fitur yang digunakan memanfaatkan vektor word2vec untuk mengontrol jumlah fitur yang dihasilkan. Pada riset ini kami membandingkan beberapa model yang dihasilkan sendiri dengan jumlah fitur yang bervariasi dan model yang telah disedikan oleh Google. Hal ini dilakukan untuk mengetahui jumlah fitur yang dapat menghasilkan kinerja klasifikasi terbaik. Hasilnya didapat nilai kinerja tertinggi akurasi yaitu 0.877 dengan jumlah fitur adalah 300 dari model yang dihasilkan sendiri.
PENGEMBANGAN E-RAPORT KURIKULUM 2013 BERBASIS WEB PADA SMA TUNAS MEKAR INDONESIA Ajeng Savitri Puspaningrum; Neneng Neneng; Intan Saputri; Fenty Ariany
Jurnal Komputasi Vol 8, No 2 (2020)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v8i2.2692

Abstract

SMA Tunas Mekar Indonesia is one of  Lampung Province schools that uses the 2013 curriculum. The assessment reporting process of student learning skills and achievement by teachers uses report cards that are distributed to parents at the end of each semester. In the managing the report card data process, there are several obstacles, namely the obstruction of grade recapitulation because the subject teacher is late in sending student grades, it takes a long time in managing grades because the processing value data done repeatedly from the attendance recap report then the application of Microsoft Excel and the report books are recapitulated by staff allows data writing errors. The solution developed for this problem is to build a Web-Based E-Report Card Application that will help SMA Tunas Mekar Indonesia by simplifying and accelerating teachers and homeroom teachers in assessing student learning outcomes reports process on inputting student scores. In this application, teachers and homeroom teachers no longer need to send assessment data via email, because the data entered is already integrated with other data. So that it doesn't take a long time to enter student grades, and minimize the damage and loss of report card data. The application built has provided complete information regarding student report card information and helps schools in reporting student grades based on the testing results using ISO 25010 standart with a percentage of success with a total average of 92.82%.
Aplikasi Monitoring Penderita Kardiovaskular dan Obesitas Berbasis Mobile Internet of Things (MIoT) Muhamad Bahrul Ulum; Nizirwan Anwar; Riya Widayanti; Alivia Yulfitri; Hendra Bratanata
Jurnal Komputasi Vol 8, No 2 (2020)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v8i2.2648

Abstract

According to the World Health Organization (WHO), coronary heart disease is the biggest cause of death in Indonesia. In 2016, the death rate from heart disease was 122 people per 100,000 population. This figure is higher than other causes, such as stroke, tuberculosis, and diabetes. The number is increasing every year due to changes in lifestyle of Indonesian people who like to eat high-fat foods and lifestyle factors that affect the risk of cardiovascular disease, including lack of physical activity, smoking, unhealthy diet, and alcohol consumption habits. This study aims to monitor the heart rate of cardiovascular sufferers with the mobile internet of things (MIoT) approach. Using the ESP8266 Wifi module for communication to the database server and heart rate sensor to detect heart rate then convert it to Bit per Minute (BPM). Every patient with cardiovascular disease can be monitored using a sensor connected to a smartphone to record any changes that occur. The research method consists of several stages, namely: Prepare, Plan, Design, Implement, Operate and Optimize (PPDIOO). The results obtained in the form of a aplication heart rate monitoring for patients with cardiovascular for healthcare services.
Pengembangan Sistem Rekruitmen Karyawan Perusahaan Mitra UPT Kewirausahaan Dan Pengembangan Karir Universitas Lampung Destian ade anggi Sukma; Machudor Yusman; Favorisen Lumbanraja; Rico Andrian
Jurnal Komputasi Vol 8, No 1 (2020)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v8i1.2331

Abstract

Recruitment is the process of finding and the best-qualified candidate work in a company or agency. There are various recruitment methods such as via employee recommendations, university collaboration, job vacancy, and jobsfair. In this paper an online company employee recruitment will be made using the black box testing method with the Equivalence Partitioning technique and the Likert scale. The data is taken from company users and job seekers. System displays job vacancies in accordance with the minimum level of education, gender and applicant's GPA. Job seekers fill out the Curriculum Vitae (CV) on the system as a company assessment for acceptance of applicants.The system can also provide announcements for applicants who have successfully passed a company. The system has been tested with black box testing with technique Equivalence Partitioning and get valid results for each test case, and for testing using a Likert scale gets very good results with a value of 87.05%.
Aplikasi Web Pemetaan Wilayah Kelayakan Tanam Jagung Berdasarkan Hasil Panen di Kabupaten Lampung Selatan Agung Tri Prastowo; Dedi Darwis; Nurhuda Budi Pamungkas
Jurnal Komputasi Vol 8, No 1 (2020)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v8i1.2531

Abstract

South Lampung Regency is a district with the capital city of Kalianda which dominates agricultural areas, one of which is corn. With the corn harvest spread in each district in the South Lampung Regency, it will attract investors to invest or invest in corn farming in the South Lampung region. This application was built with the aim of making it easier for the community and potential investors to see the potential of the sub-district corn planting area based on the yield in the form of map visualization to make it easier to find the location of the area to be planted with corn. The result of this application is a web-based system in the form of map visualization to show potential areas for planting corn. Based on the results of tests conducted, this application has a percentage score of 85.96% meaning this application is very good to be implemented.
Penerapan Algoritma C4.5 Untuk Prediksi Churn Rate Pengguna Jasa Telekomunikasi Yohana Tri Utami; Dewi Asiah Shofiana; Yunda Heningtyas
Jurnal Komputasi Vol 8, No 2 (2020)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v8i2.2647

Abstract

Telecommunication industries are experiencing substantial problems related to the migration of customers due to a large number of competing companies, dynamic circumstances, as well as the presence of many innovative and attractive offerings. The situation has resulted in a high level of customer migration, affecting a decrement toward the company revenue. Regarding that condition, the customer churn is one well-know approach that can help in increasing the company's revenue and reputation. As to predict the reason behind the migration of customer, this study proposed a data mining classification technique by applying the C4.5 algorithm. Patterns generated by the model were implemented using 10-fold cross-validation, resulting in a model with an accuracy rate of 87%, precision 87.5%, and a recall of 97%. Based on the good performance quality of the model, it can be stated that the C4.5 algorithm succeeded to discover several causes from the migration of telecommunication users, in which price holds the top place as the primary reason
ANALISA KOMPUTASI PARALEL MENGURUTKAN DATA DENGAN METODE RADIX DAN SELECTION Favorisen R. Lumbanraja; Aristoteles Aristoteles; Nadila Rizqi Muttaqina
Jurnal Komputasi Vol 8, No 2 (2020)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v8i2.2662

Abstract

Increasing computing power is now achieved by replacing the programming paradigm with parallel programming. Parallel computing is a method of solving problems by dividing the computational load into small parts of the computation sub-process. This study describes the comparative analysis of parallel computations in the Selection Sort and Radix Sort algorithms. The data used are in the form of whole numbers and decimal numbers totaling 100 to 2 million data. The test was carried out with three scenarios, namely using two processors, four processors, and 3 computers connected to each other via a LAN network. The results showed that the parallel Selection Sort algorithm for small data was better than the parallel Radix Sort. On the other hand, parallel Radix Sort is better for millions of data than Selection Sort.
Aplikasi Marketplace Penyewaan untuk Koperasi Menggunakan Laravel Tristiyanto .; Yunda Heningtyas; Hanan Risnawati
Jurnal Komputasi Vol 8, No 1 (2020)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v8i1.2536

Abstract

Cooperatives have purpose to prosper their members. Cooperatives are expected to play an active role in raising their standard of living. A cooperative has several types of business units in order to fulfill the purpose, for example rental business. Rental occurs because of short-term and urgent needs of consumers. Rental business has been promoted online but there are a lot of ordering phases done manually. Cooperative needs a rental marketplace application so cooperative can be more productive. This rental marketplace is a web based application and developed using Extreme Programming method which perceptive to user’s need. Laravel framework with PHP programming language was used to build this application. The  conclusion  of this research is this system is able to facilitate the process of renting goods, providing accurate information about rental goods, and expanding the cooperative business sector.
Metrics Based Feature Selection for Software Defect Prediction Radityo Adi Nugroho; Friska Abadi; M. Reza Faisal; Rudy Herteno; Rahmat Ramadhani
Jurnal Komputasi Vol 8, No 2 (2020)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v8i2.2670

Abstract

Nowadays, software is very influential on various sectors of life, both to solve business needs, as well as personal needs. To have a Software with high quality, testing is needed to avoid software defect. Research on software defects involving Machine Learning is currently being carried out by many researchers. This method contains one important step, which is called feature selection. In this study, researchers conducted a feature selection based on the software metric category to determine the level of accuracy of the prediction of software defects by utilizing 13 (thirteen) datasets from NASA MDP namely CM1, JM1, KC1, KC3, KC4, MC1, MC2, MW1, PC1, PC2, PC3, PC4, and PC5. To classify, the researchers involved 5 (five) classifiers, namely Naive Bayes, Decision Trees, Random Forests, K-Nearest Neighbor, and Support Vector Machines. The research result shows that each attribure on software metric categories has effect on each dataset. Naive Bayes Algorithm and Random Forest Algorithm can give better performance than other algorithm in classifieng software defect with feature selection based on metrics. On the other hand, the best metrics category on each classifier algorithm is metric Misc. From average AUC value, it can be concluded that metrics category which can give best performance is metric LoC, followed by metric Misc. Both categories have achieved highest AUC value in Random Forest classifier.

Page 21 of 24 | Total Record : 231

 19   20   21   22   23 

Filter by Year

2013 2023


Reset
Filter By Issues
All Issue Vol 11, No 1 (2023): Jurnal Komputasi Vol 10, No 1 (2022) Vol 9, No 2 (2021) Vol 9, No 1 (2021): Komputasi Vol 8, No 2 (2020) Vol 8, No 1 (2020) Vol 7, No 2 (2019) Vol 7, No 1 (2019) Vol 6, No 2 (2018) Vol 6, No 1 (2018) Vol 5, No 2 (2017) Vol 5, No 1 (2017) Vol 4, No 2 (2016) Vol 4, No 1 (2016) Vol 4, No 1 (2016) Vol 3, No 2 (2015) Vol 3, No 1 (2015) Vol 2, No 2 (2014) Vol 2, No 1 (2014) Vol 1, No 2 (2013) Vol 1, No 1 (2013) Vol 1, No 1 (2013) More Issue