Claim Missing Document
Check
Articles

Found 9 Documents
Search
Journal : Jurnal Nasional Teknik Elektro dan Teknologi Informasi

Kajian Penggunaan Data Log Mahasiswa untuk Berbagai Permasalahan Analisis Pembelajaran Sri Suning Kusumawardani; Syukron Abu Ishaq Alfarozi
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 9 No 4: November 2020
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1134.372 KB) | DOI: 10.22146/jnteti.v9i4.779

Abstract

An online learning system is a very crucial thing nowadays to prevent the spread of COVID-19 virus. However, this system is very difficult to maintain student motivation and engagement because there is no direct interaction between teacher and student. This study reviewed the use of student log data for the needs of learning analytics to predict student performance or drop-out trends from a course by looking at the student interaction log data with the system and student demographic data using open data, namely the Open University Learning Analytics Dataset (OULAD). From reviews of several research articles that refer to these data, we can see: 1) the common problems, i.e., prediction of drop-out student, prediction of student performance and engagement; 2) the features used during modeling, i.e., demographics and interactions, either summarized daily or weekly with various feature representations; 3) learning analysis methods that use machine learning algorithm, i.e., Decision Tree (DT), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Long Short-Term Memory (LSTM). This paper also discusses the risk mitigation process of students, planning and designing data systems that support learning analytics, and problems that are often encountered during the modeling process.
Tinjauan Pustaka Sistematis: Implementasi Metode Deep Learning pada Prediksi Kinerja Murid Muhammad Haris Diponegoro; Sri Suning Kusumawardani; Indriana Hidayah
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 2: Mei 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 (1346.33 KB) | DOI: 10.22146/jnteti.v10i2.1417

Abstract

The use of machine learning, which is one of the implementations in the field of artificial intelligence, has penetrated into various fields, including education. By using a combination of machine learning techniques, statistics, and databases, educational data mining can be carried out to find out the patterns that exist in a particular dataset. One use of educational data mining is to predict student performance. The results of student performance predictions can be used as an instrument for monitoring and evaluating the learning process so that it can help determine further steps in order to improve the learning process. This study aims to determine the state of the art implementation of deep learning which is part of machine learning in the context of educational data mining, especially regarding student performance predictions. In this study, a systematic literature review is presented to determine the variation of deep learning techniques or algorithms used and their performance. Twenty scientific publications were found and the average performance achieved in making predictions was 89.85%. The majority of the techniques used are Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) with demographic, behavioral, and academic data features.
Aplikasi Pengumpulan Data Survei Memanfaatkan SMS Gateway Andrew B. Osmond; Lukito Edi Nugroho; Sri Suning Kusumawardhani
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 5 No 1: Februari 2016
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (268.13 KB)

Abstract

Application for collecting survey data utilizing SMS technology is used to facilitate the process of survey and data processing. Surveyor can simply send the data via SMS and the results are immediately processed in the server, then displayed via computer browser. This system is proposed because the current survey system is done manually using paper, therefore it is more risky in validity and processing. Operator must entry and process a huge amount of data, then show the result. The web-based application is build to help users operating the system easily. In addition, this application is also made generic, and can be implemented to more diverse survey. This survey data collection application is build using programming language PHP with CodeIgniter framework, javascript, and MySQL database for data storage. This application allows users to conduct surveys and data processing. The application can also minimize various problems that usually arise in manual process with a paper-based survey.
Prototipe Sistem E-Learning dengan Pendekatan Gaya Belajar VARK (Kasus: Politeknik Indramayu) Eka Ismantohadi; Lukito Edi Nugroho; Sri Suning Kusumawardani
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 4 No 3: Agustus 2015
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (430.436 KB)

Abstract

The process of forming knowledge on school or college learning for each student has different characteristics. In the learning process, there are learners with capability to memorize, and then shape it into visual knowledge, while the others can easily recall the information and shape it into aural knowledge and also ability to read/write and to learn practice into kinesthetic ability. Basically, every individual has various learning styles, but they may dominant and has a tendency to a particular learning styleThis study tries to build a prototype of E-learning system to identify the characteristics of students learning styles using Visual, Audio, Read and Kinesthetic (VARK) approach. The results of this identification will also provide recommendations in accordance with the materials needed suitable with the learning styles of each student. This will help students to easily understand the learning materials. This study was constructed in a web-based system using PHP and MySQL.The results indicated that the system can identify the students learning styles by filling out a questionnaire with VARK approach to find out the best learning style suitable to them based on VARK approach. In addition, this system also gives course material recommendations based on the learning styles of VARK approach.
Implementasi pada FPGA atas Soft-Output Viterbi Algorithm (SOVA) untuk Pengawasandian Turbo Daryus Chandra; Budi Setiyanto; Sri Suning Kusumawardani
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 (779.784 KB)

Abstract

There are two kinds of algorithm that widely used for decoding the turbo codes, those are Soft-Output Viterbi Algorithm (SOVA) and Maximum A Posteriori Algorithm (MAP). MAP Algorithm gives a better result on error correcting capability, but the consequence it has higher complexity algorithm, in contrary to SOVA. This paper presented a design for decoding turbo codes using SOVA with Very high-speed integrated circuit Hardware Description Language (VHDL) as the modelling program and the design is implemented on the FPGA. Implementation result shows that SOVA occupies 159 slices or 3% of the available slices in Xilinx Spartan-3E, 105 flip flop (1%), 278 LUT (2%), and 141 IOB (60%) with maximum frequency clock is 43,384 MHz. FPGA implementation of SOVA decoder is able to correct up to six non-burst error symbols from 16 received symbols, but SOVA fails to perform its errorcorrecting capability for three consecutive error symbols. SOVA decoder can be implemented for turbo decoding by combining SOVA decoder with interleaver and deinterleaver.
Analisis Kinerja Reactive Routing Protocol dalam Mobile Ad-Hoc Network (MANET) Menggunakan NS-2 (Network simulator) Olivia Kembuan; Widyawan; Sri Suning Kusumawardani
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 1 No 1: Februari 2012
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (444.236 KB) | DOI: 10.22146/jnteti.v1i1.1

Abstract

Mobile Ad-Hoc Network (MANET) is the type of network that can connect people without depending on fixed infrastructure. Dynamic topology that characterizes this network leads to different routing process compared to wired-network with fixed topology. The two main classes of routing protocols for mobile ad-hoc networks (MANETs) are proactive and reactive (or on-demand). Reactive routing protocols consume less bandwidth compared to proactive routing protocols because they establish the route on demand. This thesis presents the simulation results and performance analysis of reactive routing protocol Dynamic Source Routing (DSR) and Ad Hoc On-demand distance Vector Routing (AODV). The analysis is based on packet delivery ratio, routing overhead, average delay, and averagethroughput by varying the number of nodes and speed of nodes. The simulation is performed using NS2 network simulator. The results show that AODV outperforms DSR in more stress situations, however DSR outperforms AODV in less stressful situations (smaller number of nodes and lower speed of nodes). DSR produces higher delay in all scenarios, therefore this protocol not recommended for MANET with the need for low delay.
Unjuk Kerja Routing Protocol OLSR Pada Wireless Mesh Network Berbasis Standar IEEE 802.11b/g Ari Primaned; Widyawan; Sri Suning Kusumawardani
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 1 No 1: Februari 2012
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (64.503 KB) | DOI: 10.22146/jnteti.v1i1.2

Abstract

WMN merupakan model jaringan komunikasi yang menggabungkan teknologi wireless dan routing ad-hoc yang membentuk sebuah topologi mesh. Optimized Link State Routing Protocol (OLSR) merupakan salah satu routing protocol yang digunakan untuk jaringan ad-hoc agar setiap wireless router yang terhubung dalam jaringan dapat melakukan komunikasi dan menghasilkan jaringan dengan jangkauan yang luas. Tujuan penelitian ini adalah melakukan analisis terhadap kinerja yang dihasilkan oleh testbed WMN dengan menggunakan routing protocol OLSR.Untuk mengetahui kinerja dari WMN, dilakukan pengukuran parameter throughput, latency, jitter, dan packet loss pada tesbed WMN yang dibangun menggunakan lima buah wireless router Linksys WRT54GL dengan firmware OpenWRT Freifunk pada lantai 1 Gedung KPTU Fakultas Teknik, Universitas Gadjah Mada.Hasil analisis pada testbed WMN tersebut adalah sebagai berikut; nilai throughput pada singlehop 988.48 Kbps dan pada multihop 78.952 Kbps, nilai latency berkisar antara 0.5 ms – 7.15 ms, nilai jitter pada singlehop 16.3931 ms dan pada multihop 105.5513 ms, nilai packet loss pada singlehop 2.06 % dan pada multihop 33.3 %.
Evaluasi Keamanan Akses Jaringan Komputer Nirkabel (Kasus : Kantor Pusat Fakultas Teknik Universitas Gadjah Mada) Ida Bagus Verry Hendrawan Manuaba; Risanuri Hidayat; Sri Suning Kusumawardani
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 1 No 1: Februari 2012
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (380.51 KB) | DOI: 10.22146/jnteti.v1i1.3

Abstract

The growth of current wireless networks has increased rapidly. The growth of information technology and telecommunications technology requires interoperability, joint regulation and various solutions to solve the increasingly complex problems, such as computer network security issues on wireless networks. An evaluation is needed to maintain and re-assess the stability of the network to remain adequate. This research resulted a model as a result of evaluation that can be used as a useful recommendations to improve the security of a wireless computer network access which affects the performance on the network at the Headquarters of Engineering Faculty of Gadjah Mada University.
Reduksi Peak to Average Power Ratio (PAPR) Menggunakan Teknik Clipping Muhammad Fitrah Sugita; Risanuri Hidayat; Sri Suning Kusumawardani
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 1 No 1: Februari 2012
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (390.398 KB) | DOI: 10.22146/jnteti.v1i1.9

Abstract

Frequency Division Multiplexing (OFDM) has aweakness that lies at the high power variation. Power variationis stated in peak-to-avarage power ratio (PAPR). PAPR is the ratio between the maximum and average power of OFDM signal at the certain time frame. High PAPR value will result in nonlinear distortion when operating on non linear devices such as high power amplifier (HPA). Therefore, it is necessary to find way to reduce PAPR value. In this paper, we used PAPR reduction simulation using clipping techniques. PAPR reduction is done by clipping of the output signal of IFFT block which has a PAPR value exceeds the clipping level clipping value is determined by the ratio of the test using the clipping ratio is 0.8 and 1.4. Clipping provides complimentary cumulative effect of improving the quality of the distribution function (CCDF) and decreased quality of Bit Error Rate (BER). Finally, the smaller the value of the clipping ratio CCDF quality improvement will be higher and the BER degradation will be even greater.