Claim Missing Document
Check
Articles

Found 38 Documents
Search

Internship recommendation system using simple additive weighting Santoso, Priyo Aji; Wibawa, Aji Prasetya; Pujianto, Utomo
Bulletin of Social Informatics Theory and Application Vol. 2 No. 1 (2018)
Publisher : Association for Scientific Computing Electrical and Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/businta.v2i1.102

Abstract

Internship is an activity that is compulsory for students of Vocational High School. Great selection of internships and the lack of information about the industry, is the common barriers of apprentice implementation. So find apprenticeship places that fit the needs of students to increase the intensity of the work and the motivation of students is not easy. Apprenticeship recommendation system using a simple additive weighting (SAW) can be used as a solution to assist students in determining the place of internship according to the needs of student. Method SAW can provide recommendations based on the weight of the priority criteria for students and can provide the level of accuracy of calculation of 100%. Evaluation on the behavior of users of the system are also carried out, as many of the implementation of the system failed is caused not due to technical factors but more on users. The results of the evaluation of the Technology Acceptance Model (TAM) approach, the average of user already feel usability and ease of use. While the influence of TAM each variable can give significant effects.
Technology acceptance model of student ability and tendency classification system Dwi Jaelani, Mardian; Prasetya Wibawa, Aji; Pujianto, Utomo
Bulletin of Social Informatics Theory and Application Vol. 2 No. 2 (2018)
Publisher : Association for Scientific Computing Electrical and Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/businta.v2i2.113

Abstract

Skill and competency test (SCT) is part of the Government's intervention in ensuring the quality of education in the Vocational High School (SMK) education unit. The teacher prepares vocational students to face SCT, especially vocational students of class XII. However, the obstacles often encountered by teachers in recommending students to choose competency that are in accordance with students' abilities. Ability Classification System and Student Ability Trends by applying the Learning Vector Quantization (LVQ) algorithm, it can be used as a solution to assist teachers in classifying student abilities and the tendency of students' abilities to be used to select skills competencies during SCT. This study aims to examine the use of the technology acceptance model (TAM) implementation of the classification system. As a result, the average user has felt the usefulness and ease of use of the system. Each TAM variable has a significant effect.
KLASIFIKASI DIALEK BAHASA JAWA MENGGUNAKAN METODE NAIVES BAYES Angeline, Grace; Wibawa, Aji Prasetya; Pujianto, Utomo
Jurnal Mnemonic Vol 5 No 2 (2022): Mnemonic Vol. 5 No. 2
Publisher : Teknik Informatika, Institut Teknologi Nasional malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/mnemonic.v5i2.4748

Abstract

Pulau Jawa merupakan pulau terpadat di Indonesia dan memiliki keragaman dialek yang tinggi. Berdasarkan peta bahasa yang dikeluarkan oleh KEMDIKBUD, Pulau Jawa memiliki 12 dialek utama yang tersebar di Jawa Timur, Jawa Barat dan Jawa Tengah. Dari hasil survei yang telah dilakukan, dialek yang digunakan sebagai dataset hanya dibatasi menjadi 3 dialek terpopuler dari setiap provinsi yaitu Dialek Cirebon, Dialek Tegal dan Dialek Jawa Timur. Penyediaan data dilakukan dengan metode studi literatur yang bersumber dari buku dan dokumen tertulis yang tersedia di internet. Data akan diolah dan dianalisis menggunakan algoritma Multinomial Naives Bayes karena cepat dalam proses perhitungan, sederhana dan memiliki akurasi yang tinggi. Algoritma akan diuji menggunakan K-fold Cross Validation untuk mengetahui performa algoritma Multinomial Naives Bayes dalam melakukan klasifikasi dialek di Pulau Jawa. Metode Synthetic Minority Over-Sampling Technique (SMOTE) juga digunakan dalam penelitian ini untuk mengetahui pengaruh teknik oversampling terhadap performa algoritma. Dari penelitian in dihasilkan performa terbaik dengan akurasi sebesar 96,97%, presisi sebesar 97,53% dan recall sebesar 96,83%.
Mean-Median Smoothing Backpropagation Neural Network to Forecast Unique Visitors Time Series of Electronic Journal Wibawa, Aji Prasetya; Utama, Agung Bella Putra; Lestari, Widya; Saputra, Irzan Tri; Izdihar, Zahra Nabila; Pujianto, Utomo; Haviluddin, Haviluddin; Nafalski, Andrew
Journal of Applied Data Sciences Vol 4, No 3: SEPTEMBER 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i3.97

Abstract

Sessions or unique visitors is the number of visitors from one IP who accessed a journal portal for the first time in a certain period of time. The large number of unique daily average subscriber visits to electronic journal pages indicates that this scientific periodical is in high demand. Hence, the number of unique visitors is an important indicator of the accomplishment of an electronic journal as a measure of the dissemination in accelerating the journal accreditation system. Numerous methods can be used for forecasting, one of which is the backpropagation neural network (BPNN). Data quality is very important in building a good BPNN model, because the success of modeling at BPNN is very dependent on input data. One way that can be carried out to improve data quality is by smoothing the data. In this study, the forecasting method for predicting time series data for unique visitors to electronic journals employed three models, respectively BPNN, BPNN with mean smoothing, and BPNN with median smoothing. Based on the findings, the results of the smallest error were obtained by the BPNN model with a mean smoothing with MSE 0.00129 and RMSE 0.03518 with a learning rate of 0.4 on 1-2-1 architecture which can be used as a forecast for unique visitors of electronic journals.
Reconstructing the Performance Management System of a Legal Entity University (PTN-BH) using the SMART Model: a Strategic Approach to Achieving World-Class University Murdiono, Achmad; Pujianto, Utomo; Raharjo, Swasono; Martha, Jefry Aulia; Murad, Safwan Marwin Abdul
Ekonomi Bisnis Vol 29, No 3 (2024): EKONOMI BISNIS NOVEMBER 2024
Publisher : Departemen Manajemen Fakultas Ekonomi dan Bisnis Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um042v29i3p134-140

Abstract

The change in status of a Higher Education Institution (PT) to a PTN BH is road going to independence in exploit Resources owned in a way creative and innovative in build Human Resources in Indonesia. In addition, PTNBH is also required own good reputation in ranking national or international. In order to reach objective mentioned, required management institutional apply system management guaranteed performance development sustainable. In addition, the system management developed performance No Again absorption oriented budget, but also optimization budget (efficiency and efficiency). Reconstruction system management performance in study This use SMART approach (Specific, Measurable, Achievable, Relevant, and Time- bound). The approach used in this research This is Research and Development (RnD). Stages study This is (1) stage Study introduction (data collection); (2) stage preparation of grand design; (3) trial stage expert and scale limited; (4) trial and refinement stage scale big. Data is already obtained from results trials will done analysis descriptive For get material as analysis research. Based on model test results obtained results that based on three aspect that is appearance, materials and benefits assessed very well by the work unit leader and capable make it easier time planning in compile plan activities and budget year walk.
Dialect Classification of the Javanese Language Using the K-Nearest Neighbor Filby, Brilliant; Pujianto, Utomo; Hammad, Jehad A. H.; Wibawa, Aji Prasetya
Journal of Information Technology and Cyber Security Vol. 2 No. 2 (2024): July
Publisher : Department of Information Systems and Technology, Faculty of Intelligent Electrical and Informatics Technology, Universitas 17 Agustus 1945 Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30996/jitcs.12213

Abstract

Indonesia is rich in ethnic and cultural diversity, each reflected in its unique linguistic characteristics. One way to preserve the Javanese language is by conducting research on its dialects. This study aims to classify three main dialects in Java Island—East Java, Central Java, and West Java—using text data from online sources. The classification process includes preprocessing (tokenizing, case folding, and word weighting), data balancing with the Synthetic Minority Oversampling Technique (SMOTE), and classification using the K-Nearest Neighbor (K-NN) algorithm. This study highlights the importance of dialect recognition in supporting the preservation of the Javanese language and the development of linguistic technology applications. Testing using 10-fold cross-validation showed the best performance at , with an accuracy of 94.05%, precision of 95.83%, and recall of 94.44%. These findings significantly support computational linguistics research and the preservation of regional languages.
PERBANDINGAN METODE NAÏVE BAYES DAN C4.5 UNTUK MEMPREDIKSI MORTALITAS PADA PETERNAKAN AYAM BROILER Baihaqi, Dimas Imam; Handayani, Anik Nur; Pujianto, Utomo
Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol 10, No 1 (2019): JURNAL SIMETRIS VOLUME 10 NO 1 TAHUN 2019
Publisher : Fakultas Teknik Universitas Muria Kudus

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (185.135 KB) | DOI: 10.24176/simet.v10i1.2846

Abstract

Ayam broiler adalah jenis ternak yang paling cepat untuk dipanen. Namun dalam berternak ayam broiler pasti banyak masalah yang dihadapi contohnya adalah tingkat kematian. Untuk menekan kerugian, para peternak sebaiknya memperhatikan faktor-faktor apa saja yang menyebabkan kematian ayam tersebut. Beberapa penelitian yang meneliti tentang ayam broiler menggunakan metode percobaan dan RAL. Namun masih belum ada yang meneliti mortalitas ayam broiler menggunkan komputasi. Untuk mengetahui metode mana yang lebih baik untuk memprediksi mortalitas pada peternakan ayam broiler dilakukan penelitian perbandingan metode Naïve Bayes dan C4.5. Hasil dari perbandingan akan dievaluasi menggunakan confution matrix. Hasil dari pengujian data menggunakan confution matrix menghasilkan nilai akurasi dari metode C4.5 lebih besar dari pada metode Naïve Bayes. Nilai akurasi dari metode C4.5 adalah 93% dan nilai akurasi dari metode Naïve Bayes adalah 88.66%.
Journal Unique Visitors Forecasting Based on Multivariate Attributes Using CNN Dewandra, Aderyan Reynaldi Fahrezza; Wibawa, Aji Prasetya; Pujianto, Utomo; Utama, Agung Bella Putra; Nafalski, Andrew
International Journal of Artificial Intelligence Research Vol 6, No 2 (2022): Desember 2022
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (379.839 KB) | DOI: 10.29099/ijair.v6i1.274

Abstract

Forecasting is needed in various problems, one of which is forecasting electronic journals unique visitors. Although forecasting cannot produce very accurate predictions, using the proper method can reduce forecasting errors. In this research, forecasting is done using the Deep Learning method, which is often used to process two-dimensional data, namely convolutional neural network (CNN). One-dimensional CNN comes with 1D feature extraction suitable for forecasting 1D time-series problems. This study aims to determine the best architecture and increase the number of hidden layers and neurons on CNN forecasting results. In various architectural scenarios, CNN performance was measured using the root mean squared error (RMSE). Based on the study results, the best results were obtained with an RMSE value of 2.314 using an architecture of 2 hidden layers and 64 neurons in Model 1. Meanwhile, the significant effect of increasing the number of hidden layers on the RMSE value was only found in Model 1 using 64 or 256 neurons.