Claim Missing Document
Check
Articles

Found 39 Documents
Search

Regresi Linear untuk Mengurangi Bias Sistem Penilaian Uraian Singkat Silmi Fauziati; Adhistya Erna Permanasari; Indriana Hidayah; Eko Wahyu Nugroho; Bobby Rian Dewangga
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1199.718 KB) | DOI: 10.22146/jnteti.v10i3.1983

Abstract

This study is aimed to improve the performance of a short essay scoring system. The improvement is executed by integrating a simple linear regression to the output of a combined cosine similarity method (with weighted term frequency using Term Frequency –Inverse Document Frequency (TF-IDF) method) and term-matching mechanism.The linear regression is conducted by taking the short essay score (resulting from the combined cosine similarity and termmatching) as a regressor variable. In order to demonstrate the effectivenessof the proposedscoring system, the performance of the scoring system is measured relative to manual scoring by a lecturer.The results show that prior to linear regression, the scoring system tends to give higher score(biased score) compared to the manual score,which is problematic. The following scoring system with linear regression tackles this problem as the scoring bias is significantly reduced, that is, no tendency to givehigher or less scorecompared to the manual score.That the scoring bias is significantly reduced using a simple approach, linear regression,is expected to contribute in the acceleration of implementingautomatedessay scoring system on online learning technologiessuch as e-learning.
Pengembangan Basis Data Sistem Informasi Manajemen Rumah Sakit Berbasis Linguistic-based Schema Matching Adhistya Erna Permanasari; Hayu Pradnya Satyaprabha; Addin Suwastono; Guntari Titik Mulyani
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 8 No 2: Mei 2019
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (958.789 KB)

Abstract

Prof. Soeparwi veterinary hospital is one of the medical institutions focused on providing medical services for animals. In its daily operations, the flow of informations among various departments has yet to be supported by management information systems (MIS) which enables efficiency of business process and a better management of the data. Previous researches have been conducted to develop MIS, which resulted in three independent MIS for managing registration, medical records, and patient bills. Each MIS is using their own database to store the data, thus causing duplicates of information and inconsistencies, and also increasing complexity in accessing the data. The goal of this research is to re-design the said database into a single database that will be used by various MIS. Three independent databases are merged by applying a technique that uses linguistic information as the basis for the matching–called linguistic-based schema matching. This method’s accuracy is evaluated by calculating precision, recall, and F-measure–which we obtained scores of above 50% for all three indicators. Requirement analysis is performed to further develop the database for supporting further needs of the hospital. The new database system is tested using black-box technique under few test cases to see if its functionality corresponds with the specifications defined. Result of this test proves that the new database could handle valid, invalid, and redundant inputs as expected by a score of 100% success rate.
Analisis Constructivist Multimedia Learning Environment dengan Pendekatan Bayesian Structural Equation Model Eny Sukani Rahayu; Adhistya Erna Permanasari; Dewa Ayu Putu Nadya Hareswary; Inas Ulfah Prisabtini
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 7 No 4: November 2018
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1511.263 KB)

Abstract

Constructivist Multimedia Learning Environment (CMLE) is a learning model where the teacher gives the student an experience that can help them to develop high order thinking skills such as critical thinking, developing solutions, and be creative around their environment. CMLE uses multimedia as their main source of information and as a tool to deliver learning materials. For that purpose, evaluation is needed to assess the effectiveness of the learning model. This evaluation is known as CMLE Survey (CMLES). Data obtained from CMLES needs to be analysed using analytical methods that can show the relationship between each variable and the indicator. Bayesian Structural Equation Model (SEM) is considered as the right approach because of many advantages of Bayesian Approach, such as using prior information to get posterior result and not affected by the number of samples. The seven existing hypotheses are accepted with the following results. RTH has a positive influence on CHL while CHL has a positive effect on COM. RLV has a positive influence on COM. RTH has a positive influence on INQ while INQ has a positive influence on NEG. Nevertheless, CHL gives a negative influence on INQ and RLV gives a negative influence on CHL.
Analisis Penerapan Sistem Informasi Manajemen Rumah Sakit Menggunakan Metode UTAUT dan TTF Novianti Puspitasari; Adhistya Erna Permanasari; Hanung Adi Nugroho
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 2 No 4: November 2013
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (338.009 KB)

Abstract

Ministry of Health RI has issued a policy to guide the implementation of health development undertaken by the government and private sector in order to improve the quality of health services at the hospital. This quality improvement is formed by the implementation of Hospital Management Information System (HMIS) in every hospital. The implementation of HMIS is still having problems and obstacles in the level of user acceptance. There are still many operational and managerial things that, makes the implementation of HMIS not properly running.This research study analyses the results of the implementation of HMIS from the user acceptance levels, using the integration model of the Task Technology Fit (TTF) and the Unified Theory of Acceptance and Usage of Technology (UTAUT).
Pengembangan Hypermedia Learning Environment (HLE) untuk Meningkatkan Self-Regulated Learning Berdasarkan Kemampuan Self-Monitoring Intan Sulistyaningrum Sakkinah; Rudy Hartanto; Adhistya Erna Permanasari
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 11 No 2: Mei 2022
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1475.507 KB) | DOI: 10.22146/jnteti.v11i2.3480

Abstract

The use of learning media is currently growing rapidly. Today, many studies use computers as adaptive learning media for students; one example is the hypermedia learning environment (HLE). HLE media was developed to assist students in learning, such as the current situation of the Corona Virus Disease 2019 (COVID-19) pandemic which requires all learning activities to be carried out online. One of those affected fields is the education field, where all learning activities are transferred online, so HLE web-based learning can help students to keep learning from home. HLE is currently being developed to improve students’ abilities in the self-regulated learning (SRL) process. In SRL, there is an important component in it, namely self-monitoring. However, in its development, the developed HLE is not based on self-monitoring. In this study, an adaptive HLE was developed based on students’ self-monitoring abilities. In its development, the HLE system used the agile development method, namely Scrum. The initial data collection for student classification was the self-regulatory inventory (SRI). SRI was used as an instrument to measure students’ self-monitoring ability. The data were then processed to classify students into three classes, namely high, medium, and low. Subsequently, the results of the classification of student abilities were used to develop learning aids in HLE. The development assistance provided was in the form of text and videos that were adjusted to the level of student self-monitoring. From the results of the development, it was found that all HLE functions could run well. The system was tested on twelve students to determine the level of usability by using the system usability scale (SUS). The results were classified as good category, with a score of 72.92. Further research can apply this method to students and measure the effectiveness of the system that has been developed.
Pemanfaatan Metode Smoothing Whittaker-Henderson untuk Meningkatkan Akurasi Neural Network Forecasting Hans Pratyaksa; Adhistya Erna Permanasari; Silmi Fauziati
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 11 No 1: Februari 2022
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1611.559 KB) | DOI: 10.22146/jnteti.v11i1.3489

Abstract

Health institutions need to ensure the availability of drug stocks for patients. There are challenges related to the uncertainty of the amount of drug use for the next period. Uncertainty can be reduced by analysing historical drug data to predict future demand. Time series can contain spikes or fluctuation pattern which spikes can disguise the main information. Hence, it can affect the accuracy of the prediction model. One widely used forecasting method in the time series data is the artificial neural network (ANN) method. The ANN method requires the pre-processing stage of the data before the training process. The pre-processing stage is essential to obtain information or knowledge. This study focused on applying smoothing methods at the pre-processing stage of the ANN method. The application of the smoothing method was expected to improve the quality of ANN learning data that would lead to better predictive accuracy. This research focuses on implementing the smoothing method in data pre-processing step for ANN method. Smoothing methods used in this research were exponential smoothing (ES) and Whittaker-Henderson (WH) smoothing applied to two time series datasets. The refining method used in this study was the WH method, which was tested on two time series datasets of medicine. The results show that the mean square error (MSE) obtained by applying the WH method was lower than the non-smoothing ANN for both datasets. Evaluation results revealed that implementing WH smoothing method in data pre-processing step for ANN (WH+ANN) provided MSE significantly lower than ANN results with a confidence level of 94% for dataset 1 and 85% for the dataset 2.
Study of Undersampling Method: Instance Hardness Threshold with Various Estimators for Hate Speech Classification Naufal Azmi Verdikha; Teguh Bharata Adji; Adhistya Erna Permanasari
IJITEE (International Journal of Information Technology and Electrical Engineering) Vol 2, No 2 (2018): June 2018
Publisher : Department of Electrical Engineering and Information Technology,Faculty of Engineering UGM

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (969.833 KB) | DOI: 10.22146/ijitee.42152

Abstract

A text classification system is needed to address the problem of hate speech in social media. However, texts of hate speech are very hard to find in social media. This will make the distribution of training data to be unbalanced (imbalanced data). Classification with imbalanced data will make a poor performance. There are several methods to solve the problem of classification with imbalanced data. One of them is undersampling with Instance Hardness Threshold (IHT) method. IHT method balances the dataset by eliminating data that are frequently misclassified. To find those data, IHT requires an estimator, which is a classifier. This research aims to compare estimators of IHT method to solve imbalanced data problem in hate speech classification using TF-IDF weighting method. This research uses the class ratio of dataset after undersampling, time of the undersampling process, and Index of Balanced Accuracy (IBA) evaluation to determine the best IHT method. The results of this research show that IHT method using the Logistic Regression (IHT(LR)) has the fastest undersampling process (1.91 s), perfectly balance dataset with the class ratio is 1:1, and has the best of IBA evaluation in all estimation process. This result makes IHT(LR) be the best method to solve the imbalanced data problem in hate speech classification.
Management Information System of the Billing Subsystem: A Prototype Design Farida Setianingsih; Adhistya Erna Permanasari; Warsun Najib
IJITEE (International Journal of Information Technology and Electrical Engineering) Vol 3, No 2 (2019): June 2019
Publisher : Department of Electrical Engineering and Information Technology,Faculty of Engineering UGM

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1290.44 KB) | DOI: 10.22146/ijitee.49424

Abstract

Abstract— Prof. Soeparwi Veterinary Hospital is one of veterinary medical service providers in Yogyakarta ad Central Java areas in which the transaction and the documentation managing process is still done manually. Therefore, Prof. Soeparwi VH needs a management information system that facilitate them in managing process and documentation of transactions, one of which is through billing or billing subsystem. This subsystem was designed using UML and was developed in a form of web-based prototype using PHP and HTML languages as well as CSS with CodeIgniter framework and MySQL for database.  The development of this billing subsystem applied a Rapid Application Development (RAD) model process that focused on the working model and obtained feedback from users to improve the system. Results of this system's development were evaluated with a system feasibility test and functionality test. A system feasibility test was administered by distributing Likert scale questionnaire and analysed them based on a summated rating scale method which showed a result of 85.4%. That result indicates that users strongly agree that the system has met their needs.  The system functionality was tested using a black box method and the result was that the system properly functioned. This billing subsystem could process transaction bills automatically included in the calculation. This system produced bills and reports that could be printed and exported. In addition, data was stored in a database so that it supported paperless documentation.
Design of Web-Based Cashier and Spare Part Warehouse Application Display (Case Study at Surya Motor Shop) Muhammad Esa Permana Putra; Teguh Bharata Adji; Adhistya Erna Permanasari
IJITEE (International Journal of Information Technology and Electrical Engineering) Vol 4, No 2 (2020): June 2020
Publisher : Department of Electrical Engineering and Information Technology,Faculty of Engineering UGM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijitee.53512

Abstract

A cashier and spare parts warehouse application is an information system facilitating financial reporting and items inventory systems. This has become a necessity in almost all fields of large and small-scale businesses in every country. The information system that belongs to Surya Motor Shop does not have a display that can facilitate users in operating the company's financial and transaction systems in accordance with company needs. This information system uses Bootstrap with HTML, CSS, and Javascript programming languages. In this paper, an interactive display was developed, so as to be able to accommodate web users' responses, by developing a prototype using Bootstrap at the Surya Motor Shop. This was carried out to digitize the transaction system, making it easier to report the items inventory and financial reporting of the company. The prototype development was developed using the The Elements of User Experience method, a user-centered design process. After developing the prototype, a test was carried out to determine the quality of the user experience. The test employed the User Experience Questionnaire (UEQ) method. UEQ testing shown that the prototype interface developed had a positive level of user experience. Compared with the benchmarks set by UEQ, the test results were above the mean benchmark, except for the pull factor which was still below the benchmark average.
A Multi Criteria Decision Making to Support Major Selection of Senior High School Adhistya Erna Permanasari; Marsetyo Wisaksono; Sri Suning Kusumawardani
IJITEE (International Journal of Information Technology and Electrical Engineering) Vol 3, No 4 (2019): Desember 2019
Publisher : Department of Electrical Engineering and Information Technology,Faculty of Engineering UGM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijitee.54427

Abstract

Senior high school students need to select a specialization, such as Mathematics and Natural Sciences, Social Sciences, or Language and Culture. This selection process can be improved by using Multi Criteria Decision Making (MCDM) methods. When MCDM methods are implemented, AHP method has accuracy of 61%, whereas AHP-Fuzzy TOPSIS 1 and AHP-Fuzzy TOPSIS 2 have accuracy of 75%. This research implements tests and analyzes new MCDM method, which is Hybrid MCDM Model, in helping aforementioned specialization selection process. There are four basic steps in Hybrid MCDM Model: performing experimental design to obtain attributes' weight and criteria, evaluating MCDM with the three existing methods, performing RSM regression to derive mathematical model, and decision making. This research introduces data normalization to the mathematical model which results in better implementation of Hybrid MCDM Model in the senior high school students' specialization selection process. Hybrid MCDM Model in the senior high school student specialization selection has accuracy of 86%, which includes 11% accuracy improvements compared to other applied MCDM methods.